tp1_RegressionData_modelpipeline.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyPk+Ca+9iDYsORjyL791D3l",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/hyonnys/tp1/blob/main/tp1_RegressionData_modelpipeline.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Part 0. Data Loading**"
      ],
      "metadata": {
        "id": "EPAUpaJM-pdf"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install category_encoders"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xNN58v4O_Yvl",
        "outputId": "6cdbfcfc-fd6c-4744-dc69-d33d1f2e6eb2"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting category_encoders\n",
            "  Downloading category_encoders-2.6.1-py2.py3-none-any.whl (81 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.9/81.9 kB\u001b[0m \u001b[31m1.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy>=1.14.0 in /usr/local/lib/python3.10/dist-packages (from category_encoders) (1.22.4)\n",
            "Requirement already satisfied: scikit-learn>=0.20.0 in /usr/local/lib/python3.10/dist-packages (from category_encoders) (1.2.2)\n",
            "Requirement already satisfied: scipy>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from category_encoders) (1.10.1)\n",
            "Requirement already satisfied: statsmodels>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from category_encoders) (0.13.5)\n",
            "Requirement already satisfied: pandas>=1.0.5 in /usr/local/lib/python3.10/dist-packages (from category_encoders) (1.5.3)\n",
            "Requirement already satisfied: patsy>=0.5.1 in /usr/local/lib/python3.10/dist-packages (from category_encoders) (0.5.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.0.5->category_encoders) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.0.5->category_encoders) (2022.7.1)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from patsy>=0.5.1->category_encoders) (1.16.0)\n",
            "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.20.0->category_encoders) (1.3.1)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.20.0->category_encoders) (3.2.0)\n",
            "Requirement already satisfied: packaging>=21.3 in /usr/local/lib/python3.10/dist-packages (from statsmodels>=0.9.0->category_encoders) (23.1)\n",
            "Installing collected packages: category_encoders\n",
            "Successfully installed category_encoders-2.6.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "id": "8Rt5pU6CYcCv"
      },
      "outputs": [],
      "source": [
        "import os\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "from category_encoders import OrdinalEncoder, OneHotEncoder\n",
        "from sklearn.preprocessing import StandardScaler, MinMaxScaler\n",
        "from sklearn.model_selection import train_test_split, GridSearchCV, KFold, cross_val_score, RandomizedSearchCV\n",
        "from sklearn.pipeline import make_pipeline\n",
        "from sklearn.preprocessing import PolynomialFeatures\n",
        "from sklearn.linear_model import LinearRegression, Ridge, Lasso\n",
        "from sklearn.tree import DecisionTreeRegressor\n",
        "from sklearn.ensemble import RandomForestRegressor, AdaBoostRegressor, GradientBoostingRegressor\n",
        "from sklearn.neighbors import KNeighborsRegressor\n",
        "from sklearn.svm import SVR\n",
        "from xgboost.sklearn import XGBRegressor\n",
        "from sklearn.gaussian_process import GaussianProcessRegressor\n",
        "from sklearn.gaussian_process.kernels import DotProduct, ConstantKernel\n",
        "from sklearn.metrics import r2_score as r2, mean_squared_error as mse, mean_absolute_error as mae\n",
        "import datetime as dt\n",
        "from tqdm import tqdm\n",
        "import time"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rZWdsd-bYtqa",
        "outputId": "7a0f0481-bf39-4d55-ac50-a91aaa52e86e"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "abalone = pd.read_csv('/content/drive/MyDrive/regression_data.csv')\n",
        "abalone.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "U0rqu7S_Yvkn",
        "outputId": "756a3474-ef29-47fe-b12c-2f8d71e3c065"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  Sex  Length  Diameter  Height  Whole weight  Shucked weight  Viscera weight  \\\n",
              "0   M   0.455     0.365   0.095        0.5140          0.2245          0.1010   \n",
              "1   M   0.350     0.265   0.090        0.2255          0.0995          0.0485   \n",
              "2   F   0.530     0.420   0.135        0.6770          0.2565          0.1415   \n",
              "3   M   0.440     0.365   0.125        0.5160          0.2155          0.1140   \n",
              "4   I   0.330     0.255   0.080        0.2050          0.0895          0.0395   \n",
              "\n",
              "   Shell weight  Rings  \n",
              "0         0.150     15  \n",
              "1         0.070      7  \n",
              "2         0.210      9  \n",
              "3         0.155     10  \n",
              "4         0.055      7  "
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-92a926ae-08b1-4e12-9dbd-d4c47476dc31\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sex</th>\n",
              "      <th>Length</th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Whole weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Rings</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>M</td>\n",
              "      <td>0.455</td>\n",
              "      <td>0.365</td>\n",
              "      <td>0.095</td>\n",
              "      <td>0.5140</td>\n",
              "      <td>0.2245</td>\n",
              "      <td>0.1010</td>\n",
              "      <td>0.150</td>\n",
              "      <td>15</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>M</td>\n",
              "      <td>0.350</td>\n",
              "      <td>0.265</td>\n",
              "      <td>0.090</td>\n",
              "      <td>0.2255</td>\n",
              "      <td>0.0995</td>\n",
              "      <td>0.0485</td>\n",
              "      <td>0.070</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>F</td>\n",
              "      <td>0.530</td>\n",
              "      <td>0.420</td>\n",
              "      <td>0.135</td>\n",
              "      <td>0.6770</td>\n",
              "      <td>0.2565</td>\n",
              "      <td>0.1415</td>\n",
              "      <td>0.210</td>\n",
              "      <td>9</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>M</td>\n",
              "      <td>0.440</td>\n",
              "      <td>0.365</td>\n",
              "      <td>0.125</td>\n",
              "      <td>0.5160</td>\n",
              "      <td>0.2155</td>\n",
              "      <td>0.1140</td>\n",
              "      <td>0.155</td>\n",
              "      <td>10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I</td>\n",
              "      <td>0.330</td>\n",
              "      <td>0.255</td>\n",
              "      <td>0.080</td>\n",
              "      <td>0.2050</td>\n",
              "      <td>0.0895</td>\n",
              "      <td>0.0395</td>\n",
              "      <td>0.055</td>\n",
              "      <td>7</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-92a926ae-08b1-4e12-9dbd-d4c47476dc31')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-f8e2c240-3c33-4da2-b600-4cfbaface4ed\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-f8e2c240-3c33-4da2-b600-4cfbaface4ed')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-f8e2c240-3c33-4da2-b600-4cfbaface4ed button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-92a926ae-08b1-4e12-9dbd-d4c47476dc31 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-92a926ae-08b1-4e12-9dbd-d4c47476dc31');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "abalone.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ATqdV-30aPjh",
        "outputId": "a430ab66-073c-4d4d-a707-e004e9e48978"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 4177 entries, 0 to 4176\n",
            "Data columns (total 9 columns):\n",
            " #   Column          Non-Null Count  Dtype  \n",
            "---  ------          --------------  -----  \n",
            " 0   Sex             4177 non-null   object \n",
            " 1   Length          4177 non-null   float64\n",
            " 2   Diameter        4177 non-null   float64\n",
            " 3   Height          4177 non-null   float64\n",
            " 4   Whole weight    4177 non-null   float64\n",
            " 5   Shucked weight  4177 non-null   float64\n",
            " 6   Viscera weight  4177 non-null   float64\n",
            " 7   Shell weight    4177 non-null   float64\n",
            " 8   Rings           4177 non-null   int64  \n",
            "dtypes: float64(7), int64(1), object(1)\n",
            "memory usage: 293.8+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "abalone.describe()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 300
        },
        "id": "fKwTFYupaSoD",
        "outputId": "277ce6cf-bb07-49d5-ef34-3fbfbf8d4e4d"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            Length     Diameter       Height  Whole weight  Shucked weight  \\\n",
              "count  4177.000000  4177.000000  4177.000000   4177.000000     4177.000000   \n",
              "mean      0.523992     0.407881     0.139516      0.828742        0.359367   \n",
              "std       0.120093     0.099240     0.041827      0.490389        0.221963   \n",
              "min       0.075000     0.055000     0.000000      0.002000        0.001000   \n",
              "25%       0.450000     0.350000     0.115000      0.441500        0.186000   \n",
              "50%       0.545000     0.425000     0.140000      0.799500        0.336000   \n",
              "75%       0.615000     0.480000     0.165000      1.153000        0.502000   \n",
              "max       0.815000     0.650000     1.130000      2.825500        1.488000   \n",
              "\n",
              "       Viscera weight  Shell weight        Rings  \n",
              "count     4177.000000   4177.000000  4177.000000  \n",
              "mean         0.180594      0.238831     9.933684  \n",
              "std          0.109614      0.139203     3.224169  \n",
              "min          0.000500      0.001500     1.000000  \n",
              "25%          0.093500      0.130000     8.000000  \n",
              "50%          0.171000      0.234000     9.000000  \n",
              "75%          0.253000      0.329000    11.000000  \n",
              "max          0.760000      1.005000    29.000000  "
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-a29a31f4-c588-4699-95fa-512e88da22e7\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Length</th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Whole weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Rings</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "      <td>4177.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>0.523992</td>\n",
              "      <td>0.407881</td>\n",
              "      <td>0.139516</td>\n",
              "      <td>0.828742</td>\n",
              "      <td>0.359367</td>\n",
              "      <td>0.180594</td>\n",
              "      <td>0.238831</td>\n",
              "      <td>9.933684</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>0.120093</td>\n",
              "      <td>0.099240</td>\n",
              "      <td>0.041827</td>\n",
              "      <td>0.490389</td>\n",
              "      <td>0.221963</td>\n",
              "      <td>0.109614</td>\n",
              "      <td>0.139203</td>\n",
              "      <td>3.224169</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>0.075000</td>\n",
              "      <td>0.055000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.002000</td>\n",
              "      <td>0.001000</td>\n",
              "      <td>0.000500</td>\n",
              "      <td>0.001500</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>0.450000</td>\n",
              "      <td>0.350000</td>\n",
              "      <td>0.115000</td>\n",
              "      <td>0.441500</td>\n",
              "      <td>0.186000</td>\n",
              "      <td>0.093500</td>\n",
              "      <td>0.130000</td>\n",
              "      <td>8.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>0.545000</td>\n",
              "      <td>0.425000</td>\n",
              "      <td>0.140000</td>\n",
              "      <td>0.799500</td>\n",
              "      <td>0.336000</td>\n",
              "      <td>0.171000</td>\n",
              "      <td>0.234000</td>\n",
              "      <td>9.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>0.615000</td>\n",
              "      <td>0.480000</td>\n",
              "      <td>0.165000</td>\n",
              "      <td>1.153000</td>\n",
              "      <td>0.502000</td>\n",
              "      <td>0.253000</td>\n",
              "      <td>0.329000</td>\n",
              "      <td>11.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>0.815000</td>\n",
              "      <td>0.650000</td>\n",
              "      <td>1.130000</td>\n",
              "      <td>2.825500</td>\n",
              "      <td>1.488000</td>\n",
              "      <td>0.760000</td>\n",
              "      <td>1.005000</td>\n",
              "      <td>29.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a29a31f4-c588-4699-95fa-512e88da22e7')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-7b3e623f-a717-48ba-b350-30efa22abbdc\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-7b3e623f-a717-48ba-b350-30efa22abbdc')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-7b3e623f-a717-48ba-b350-30efa22abbdc button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-a29a31f4-c588-4699-95fa-512e88da22e7 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-a29a31f4-c588-4699-95fa-512e88da22e7');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Part 1. Data Engineering**<br>\n",
        "- Outlier Drop :  `Height (> 0.4)`"
      ],
      "metadata": {
        "id": "nCse43q4Q7Qv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# data engineering\n",
        "# height outlier 확인\n",
        "outlier_height = abalone[abalone['Height'] > 0.4]\n",
        "outlier_height"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 112
        },
        "id": "DOfGlNE2YzLH",
        "outputId": "7fd0a2da-cdc9-4d31-8e46-9702d90e841c"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Sex  Length  Diameter  Height  Whole weight  Shucked weight  \\\n",
              "1417   M   0.705     0.565   0.515         2.210          1.1075   \n",
              "2051   F   0.455     0.355   1.130         0.594          0.3320   \n",
              "\n",
              "      Viscera weight  Shell weight  Rings  \n",
              "1417          0.4865        0.5120     10  \n",
              "2051          0.1160        0.1335      8  "
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-744ffedd-6b7b-47bb-96ce-c03417642776\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sex</th>\n",
              "      <th>Length</th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Whole weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Rings</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1417</th>\n",
              "      <td>M</td>\n",
              "      <td>0.705</td>\n",
              "      <td>0.565</td>\n",
              "      <td>0.515</td>\n",
              "      <td>2.210</td>\n",
              "      <td>1.1075</td>\n",
              "      <td>0.4865</td>\n",
              "      <td>0.5120</td>\n",
              "      <td>10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2051</th>\n",
              "      <td>F</td>\n",
              "      <td>0.455</td>\n",
              "      <td>0.355</td>\n",
              "      <td>1.130</td>\n",
              "      <td>0.594</td>\n",
              "      <td>0.3320</td>\n",
              "      <td>0.1160</td>\n",
              "      <td>0.1335</td>\n",
              "      <td>8</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-744ffedd-6b7b-47bb-96ce-c03417642776')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-42b2da55-17d9-4a0a-b240-2186f9e0bf41\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-42b2da55-17d9-4a0a-b240-2186f9e0bf41')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-42b2da55-17d9-4a0a-b240-2186f9e0bf41 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-744ffedd-6b7b-47bb-96ce-c03417642776 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-744ffedd-6b7b-47bb-96ce-c03417642776');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Height outlier 데이터 제거 및 결과 확인\n",
        "abalone.drop(outlier_height.index, inplace=True)\n",
        "abalone[abalone['Height']>0.4]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49
        },
        "id": "7ztzfayfaivm",
        "outputId": "954001f6-dcf4-45c8-8779-10e7ffcc8ee8"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Empty DataFrame\n",
              "Columns: [Sex, Length, Diameter, Height, Whole weight, Shucked weight, Viscera weight, Shell weight, Rings]\n",
              "Index: []"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-3e2d8d69-92b9-410a-8c06-d6d797f5d425\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sex</th>\n",
              "      <th>Length</th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Whole weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Rings</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3e2d8d69-92b9-410a-8c06-d6d797f5d425')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-69a22551-9985-4b7a-a6a4-5f076e89de74\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-69a22551-9985-4b7a-a6a4-5f076e89de74')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-69a22551-9985-4b7a-a6a4-5f076e89de74 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-3e2d8d69-92b9-410a-8c06-d6d797f5d425 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-3e2d8d69-92b9-410a-8c06-d6d797f5d425');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Part 2. Data Preprocessing**<br>\n",
        "#### 💡 수치형 변수<br>\n",
        "Scale Standardization<br>\n",
        "- MinMaxScaler : 모든 값을 0과 1 사이의 값으로 조정 (이상치 민감)\n",
        "- StandardScaler : 특성의 평균을 0, 표준편차를 1로 조정 (이상치 덜 민감)\n",
        "<br>\n",
        "\n",
        "Normalization <br>\n",
        "- Log 변환 : 다수 값들이 제한된 범위 내에서만 존재하고 특정 값들이 큰 형태의 분포에서 사용됨 (모든 값이 음수가 아니여야 함)\n",
        "<br>\n",
        "\n",
        "#### 💡 범주형 변수<br>\n",
        "- One Hot Encoding\n",
        "  + 각 범주형 특성 값들을 각 값들에 대해 해당하는지/하지 않는지를 1과 0으로 인코딩한다. 차원을 늘릴 수 있다.\n",
        "  + 특성의 정보를 분산시키므로 트리 기반 모델에는 비효율적이다.\n",
        "- Ordinal Encoding\n",
        "  + 특성 값들을 서로 다른 정수 값들로 인코딩함\n",
        "  + 양적 대소 관계를 갖는 것처럼 간주되므로 선형 회귀 모델 보다 트리 기반 모델에서 효율적임.\n",
        "<br>\n"
      ],
      "metadata": {
        "id": "3QUBc1JMaDEg"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **2-1. First Experiment**<br>\n",
        "\n",
        "> ### *Data Preprocessing*<br>\n",
        "- 수치형 변수 : **_Standard Scaling_**\n",
        "- 범주형 변수 `Sex` : **_One Hot Encoding_**\n",
        "\n",
        "<br>\n",
        "\n",
        "> ### *Model Selection*<br>\n",
        "- Linear Regressison\n",
        "- Ridge\n",
        "- RandomForestRegressor\n",
        "- Gradient Boosting Regressor\n",
        "- KNeighbors Regressor\n",
        "- SVM - SVR\n",
        "<br>\n",
        "\n",
        "> ### *Results*<br>\n",
        "-\n",
        "<br>"
      ],
      "metadata": {
        "id": "FBZ8vkcrBh2l"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "**📌 [sklearn.feature_selection.SelectKBest](https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SelectKBest.html?highlight=selectkbest#sklearn.feature_selection.SelectKBest)**"
      ],
      "metadata": {
        "id": "hvxC32U6Evhy"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "abalone1 = abalone.copy()"
      ],
      "metadata": {
        "id": "Oe6YNFZEOOlE"
      },
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 데이터 분리 기능\n",
        "def data_split(df, target, features):\n",
        "  y = df[target]\n",
        "  x= df[features]\n",
        "  x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=42)\n",
        "  print(f'x_train: {x_train.shape}, y_train: {y_train.shape}')\n",
        "  print(f'x_test: {x_test.shape}, y_test: {y_test.shape}')\n",
        "  return x_train, x_test, y_train, y_test"
      ],
      "metadata": {
        "id": "qq0yQBHjPL7_"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "target = 'Rings'\n",
        "features1 = abalone1.columns.difference(['Rings'])\n",
        "x_train, x_test, y_train, y_test = data_split(abalone1, target, features1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gxgX_uBRC1jn",
        "outputId": "00313b75-df42-408d-e9eb-42fa5307aaa1"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "x_train: (3131, 8), y_train: (3131,)\n",
            "x_test: (1044, 8), y_test: (1044,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "numeric_feats = x_train.dtypes[x_train.dtypes != \"object\"].index\n",
        "categoric_feats = x_train.dtypes[x_train.dtypes == \"object\"].index"
      ],
      "metadata": {
        "id": "YmBRzof-sBjB"
      },
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "sscaler = StandardScaler()\n",
        "x_train[numeric_feats] = sscaler.fit_transform(x_train[numeric_feats])\n",
        "# x_val[numeric_feats] = sscaler.transform(x_val[numeric_feats])\n",
        "x_test[numeric_feats] = sscaler.transform(x_test[numeric_feats])"
      ],
      "metadata": {
        "id": "iMbvF2V0smhO"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# scaling 결과 확인\n",
        "# 평균 0에 가까운 수로, 표준편차 1에 가까운 수로 변환되었는지 확인\n",
        "x_train[numeric_feats].describe().T[['mean', 'std']]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 269
        },
        "id": "bwwLAs_luXxA",
        "outputId": "e5166db4-9466-4ac3-d368-4741d1d0c249"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                        mean      std\n",
              "Diameter        1.089302e-16  1.00016\n",
              "Height         -3.631007e-17  1.00016\n",
              "Length         -1.815504e-16  1.00016\n",
              "Shell weight   -6.808139e-17  1.00016\n",
              "Shucked weight -1.860891e-16  1.00016\n",
              "Viscera weight  2.496318e-17  1.00016\n",
              "Whole weight   -3.177131e-17  1.00016"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-b5dd11c6-f5b7-464a-a316-aebbb124459e\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Diameter</th>\n",
              "      <td>1.089302e-16</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Height</th>\n",
              "      <td>-3.631007e-17</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Length</th>\n",
              "      <td>-1.815504e-16</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Shell weight</th>\n",
              "      <td>-6.808139e-17</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Shucked weight</th>\n",
              "      <td>-1.860891e-16</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Viscera weight</th>\n",
              "      <td>2.496318e-17</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Whole weight</th>\n",
              "      <td>-3.177131e-17</td>\n",
              "      <td>1.00016</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b5dd11c6-f5b7-464a-a316-aebbb124459e')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-73436336-ea87-45a6-8cd7-812c1aaeb1da\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-73436336-ea87-45a6-8cd7-812c1aaeb1da')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-73436336-ea87-45a6-8cd7-812c1aaeb1da button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-b5dd11c6-f5b7-464a-a316-aebbb124459e button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-b5dd11c6-f5b7-464a-a316-aebbb124459e');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# OneHotEncoder : categorical feature - Sex\n",
        "ohe = OneHotEncoder()\n",
        "x_train_ohe = ohe.fit_transform(x_train)\n",
        "x_test_ohe = ohe.transform(x_test)\n",
        "\n",
        "# 결과 확인\n",
        "print((x_train_ohe.dtypes == 'object').sum())\n",
        "print((x_test_ohe.dtypes == 'object').sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QrBD34icanEj",
        "outputId": "efebccca-4ed5-4998-b6f5-e416d6296e4b"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0\n",
            "0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# data preprocessing 결과 확인\n",
        "x_train_ohe.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "AalmtP-UACtU",
        "outputId": "1e5906ed-cc42-4382-e0e8-9bb46defb55b"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      Diameter    Height    Length  Sex_1  Sex_2  Sex_3  Shell weight  \\\n",
              "2667  0.414915  0.272779  0.501373      1      0      0     -0.109638   \n",
              "4086  0.414915  0.403271  0.543362      0      1      0     -0.001912   \n",
              "2552 -1.869461 -1.684603 -1.808021      0      0      1     -1.463391   \n",
              "1804  0.617971  0.142287  0.795296      0      1      0      0.116586   \n",
              "247  -1.361822 -1.423619 -1.388131      0      0      1     -1.222803   \n",
              "\n",
              "      Shucked weight  Viscera weight  Whole weight  \n",
              "2667        0.476648        0.195746      0.213957  \n",
              "4086        0.035414        0.291626      0.083463  \n",
              "2552       -1.333311       -1.320068     -1.382547  \n",
              "1804        0.674753        0.821248      0.516742  \n",
              "247        -1.290539       -1.278976     -1.295892  "
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-6582479b-d3cd-44e7-87ba-9d8179db935c\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Length</th>\n",
              "      <th>Sex_1</th>\n",
              "      <th>Sex_2</th>\n",
              "      <th>Sex_3</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Whole weight</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2667</th>\n",
              "      <td>0.414915</td>\n",
              "      <td>0.272779</td>\n",
              "      <td>0.501373</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>-0.109638</td>\n",
              "      <td>0.476648</td>\n",
              "      <td>0.195746</td>\n",
              "      <td>0.213957</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4086</th>\n",
              "      <td>0.414915</td>\n",
              "      <td>0.403271</td>\n",
              "      <td>0.543362</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>-0.001912</td>\n",
              "      <td>0.035414</td>\n",
              "      <td>0.291626</td>\n",
              "      <td>0.083463</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2552</th>\n",
              "      <td>-1.869461</td>\n",
              "      <td>-1.684603</td>\n",
              "      <td>-1.808021</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>-1.463391</td>\n",
              "      <td>-1.333311</td>\n",
              "      <td>-1.320068</td>\n",
              "      <td>-1.382547</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1804</th>\n",
              "      <td>0.617971</td>\n",
              "      <td>0.142287</td>\n",
              "      <td>0.795296</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0.116586</td>\n",
              "      <td>0.674753</td>\n",
              "      <td>0.821248</td>\n",
              "      <td>0.516742</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>247</th>\n",
              "      <td>-1.361822</td>\n",
              "      <td>-1.423619</td>\n",
              "      <td>-1.388131</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>-1.222803</td>\n",
              "      <td>-1.290539</td>\n",
              "      <td>-1.278976</td>\n",
              "      <td>-1.295892</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-6582479b-d3cd-44e7-87ba-9d8179db935c')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-6081d443-6f2e-4fe2-9068-fdf5a78122fe\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-6081d443-6f2e-4fe2-9068-fdf5a78122fe')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-6081d443-6f2e-4fe2-9068-fdf5a78122fe button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-6582479b-d3cd-44e7-87ba-9d8179db935c button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-6582479b-d3cd-44e7-87ba-9d8179db935c');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# OrdinalEncoding\n",
        "le = OrdinalEncoder()\n",
        "x_train_le = le.fit_transform(x_train)\n",
        "x_test_le = le.transform(x_test)\n",
        "\n",
        "# 결과 확인\n",
        "print((x_train_le.dtypes == 'object').sum())\n",
        "print((x_test_le.dtypes == 'object').sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "srFdgp2fJPVO",
        "outputId": "c6547405-fd33-4f93-9f5c-29429fccb09d"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0\n",
            "0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 성능 결과 출력 기능\n",
        "def print_score(model, X_train, y_train, X_test, y_test) :\n",
        "\n",
        "    train_score = np.round(model.score(X_train, y_train) , 3)\n",
        "    val_score = np.round(np.mean(cross_val_score(model, X_train, y_train, scoring='r2', cv=5).round(3)),3)\n",
        "    test_score = np.round(model.score(X_test, y_test),3)\n",
        "    d = {'train':train_score, 'val':val_score, 'test':test_score}\n",
        "    ser = pd.Series(data=d, index=['train', 'val', 'test'])\n",
        "\n",
        "    return train_score, val_score, test_score, ser"
      ],
      "metadata": {
        "id": "e-unDKSbD30s"
      },
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# LinearRegression\n",
        "ols = LinearRegression()\n",
        "ols.fit(x_train_le, y_train)\n",
        "\n",
        "# 성능 비교\n",
        "ols_train, ols_val, ols_test, ols_ser = print_score(ols,x_train_le, y_train, x_test_le, y_test)"
      ],
      "metadata": {
        "id": "I4YVr5ycAUIf"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 성능 확인\n",
        "ols_ser"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6wzo_rsGU7EI",
        "outputId": "7b4317c3-27f5-461d-e1e0-86d255080f43"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "train    0.530\n",
              "val      0.524\n",
              "test     0.565\n",
              "dtype: float64"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Ridge\n",
        "rg = Ridge()\n",
        "rg.fit(x_train_le, y_train)\n",
        "\n",
        "# 성능 비교\n",
        "rg_train, rg_val, rg_test, rg_ser = print_score(rg,x_train_le, y_train, x_test_le, y_test)"
      ],
      "metadata": {
        "id": "hd2XZB3NLVfx"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# RandomForestRegressor_le\n",
        "rf = RandomForestRegressor()\n",
        "rf.fit(x_train_le, y_train)\n",
        "\n",
        "# 성능 비교\n",
        "rf_train, rf_val, rf_test, rf_ser = print_score(rf,x_train_le, y_train, x_test_le, y_test)"
      ],
      "metadata": {
        "id": "6aTkNNeaJbdf"
      },
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# SVM\n",
        "svr = SVR()\n",
        "svr.fit(x_train_le, y_train)\n",
        "\n",
        "#성능 비교\n",
        "svr_train, svr_val, svr_test, svr_ser = print_score(svr,x_train_le, y_train, x_test_le, y_test)"
      ],
      "metadata": {
        "id": "1RnRO9TGItsc"
      },
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# GradientBoostingRegressor\n",
        "gb = GradientBoostingRegressor()\n",
        "gb.fit(x_train_le, y_train)\n",
        "\n",
        "# 성능 비교\n",
        "gb_train, gb_val, gb_test, gb_ser = print_score(gb,x_train_le, y_train, x_test_le, y_test)\n"
      ],
      "metadata": {
        "id": "ruz3aG0AJFPE"
      },
      "execution_count": 24,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# KNeighborsRegressor\n",
        "knn = KNeighborsRegressor(n_neighbors = 4)\n",
        "knn.fit(x_train_le, y_train)\n",
        "\n",
        "# 성능 비교\n",
        "knn_train, knn_val, knn_test, knn_ser = print_score(knn,x_train_le, y_train, x_test_le, y_test)"
      ],
      "metadata": {
        "id": "eC1VvJUUJ36z"
      },
      "execution_count": 25,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "frame = {'ols':ols_ser, 'ridge':rg_ser, 'rf':rf_ser, 'svr':svr_ser, 'gb':gb_ser, 'knn':knn_ser}\n",
        "pd.DataFrame(frame)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "id": "WjxxFAuFVWN7",
        "outputId": "2d3a4d35-d1e0-46e6-e5f4-9a9bcba24f69"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         ols  ridge     rf    svr     gb    knn\n",
              "train  0.530  0.530  0.933  0.544  0.661  0.676\n",
              "val    0.524  0.525  0.530  0.529  0.537  0.438\n",
              "test   0.565  0.565  0.565  0.572  0.573  0.499"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-b58b26f3-ce1b-4e4b-a088-7bca758cf6d3\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>ols</th>\n",
              "      <th>ridge</th>\n",
              "      <th>rf</th>\n",
              "      <th>svr</th>\n",
              "      <th>gb</th>\n",
              "      <th>knn</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>train</th>\n",
              "      <td>0.530</td>\n",
              "      <td>0.530</td>\n",
              "      <td>0.933</td>\n",
              "      <td>0.544</td>\n",
              "      <td>0.661</td>\n",
              "      <td>0.676</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>val</th>\n",
              "      <td>0.524</td>\n",
              "      <td>0.525</td>\n",
              "      <td>0.530</td>\n",
              "      <td>0.529</td>\n",
              "      <td>0.537</td>\n",
              "      <td>0.438</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>test</th>\n",
              "      <td>0.565</td>\n",
              "      <td>0.565</td>\n",
              "      <td>0.565</td>\n",
              "      <td>0.572</td>\n",
              "      <td>0.573</td>\n",
              "      <td>0.499</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b58b26f3-ce1b-4e4b-a088-7bca758cf6d3')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-75ea282e-cccc-4866-bd5d-9672d3c288b1\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-75ea282e-cccc-4866-bd5d-9672d3c288b1')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-75ea282e-cccc-4866-bd5d-9672d3c288b1 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-b58b26f3-ce1b-4e4b-a088-7bca758cf6d3 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-b58b26f3-ce1b-4e4b-a088-7bca758cf6d3');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **2-2. Second Experiment**<br>\n",
        "> ### *Data Preprocessing*<br>\n",
        "- 수치형 변수 : **_MinMax_** Scaling\n",
        "- 범주형 변수 : **_Drop_**\n",
        "<br>\n",
        "\n",
        "> ### *Model Selection*<br>\n",
        "- RandomForestRegressor\n",
        "- Gradient Boosting Regressor\n",
        "- KNeighbors Regressor\n",
        "- SVM - SVR\n",
        "<br>\n",
        "\n",
        "> ### *Results*<br>\n",
        "-\n",
        "<br>"
      ],
      "metadata": {
        "id": "4HgNMBzWKmlW"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "abalone2 = abalone.copy()"
      ],
      "metadata": {
        "id": "iHrraEbBOEtk"
      },
      "execution_count": 27,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "target = 'Rings'\n",
        "features2 = abalone2.columns.difference(['Rings', 'Sex'])\n",
        "x_train2, x_test2, y_train2, y_test2 = data_split(abalone2, target, features2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uX1aLlMYQEIw",
        "outputId": "b4e60bde-b100-4358-d0cf-5d011e591fe0"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "x_train: (3131, 7), y_train: (3131,)\n",
            "x_test: (1044, 7), y_test: (1044,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "mscaler = MinMaxScaler()\n",
        "x_train_mscaled = mscaler.fit_transform(x_train2)\n",
        "x_test_mscaled = mscaler.transform(x_test2)"
      ],
      "metadata": {
        "id": "BR5-opvyQaug"
      },
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# LinearRegression\n",
        "ols.fit(x_train_mscaled, y_train)\n",
        "ols_train, ols_val, ols_test, ols_ser2 = print_score(ols,x_train_mscaled, y_train, x_test_mscaled, y_test)\n",
        "\n",
        "# Ridge\n",
        "rg.fit(x_train_mscaled, y_train)\n",
        "rg_train, rg_val, rg_test, rg_ser2 = print_score(rg,x_train_mscaled, y_train, x_test_mscaled, y_test)\n",
        "\n",
        "\n",
        "# RandomForestRegressor\n",
        "rf.fit(x_train_mscaled, y_train)\n",
        "rf_train, rf_val, rf_test, rf_ser2 = print_score(rf,x_train_mscaled, y_train, x_test_mscaled, y_test)\n",
        "\n",
        "# SVR\n",
        "svr.fit(x_train_mscaled, y_train)\n",
        "svr_train, svr_val, svr_test, svr_ser2 = print_score(svr,x_train_mscaled, y_train, x_test_mscaled, y_test)\n",
        "\n",
        "# GradientBoostingRegressor\n",
        "gb.fit(x_train_mscaled, y_train)\n",
        "gb_train, gb_val, gb_test, gb_ser2 = print_score(gb,x_train_mscaled, y_train, x_test_mscaled, y_test)\n",
        "\n",
        "# KNeighborsRegressor\n",
        "knn.fit(x_train_mscaled, y_train)\n",
        "knn_train, knn_val, knn_test, knn_ser2 = print_score(knn,x_train_mscaled, y_train, x_test_mscaled, y_test)"
      ],
      "metadata": {
        "id": "whJJ6YtGWen1"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# XGBRegressor\n",
        "xgb = XGBRegressor()\n",
        "xgb.fit(x_train_mscaled, y_train)\n",
        "\n",
        "xgb_train, xgb_val, xgb_test, xgb_ser2 = print_score(xgb,x_train_mscaled, y_train, x_test_mscaled, y_test)"
      ],
      "metadata": {
        "id": "1PcsfeW_rh7d"
      },
      "execution_count": 31,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 모델 성능 비교\n",
        "frame2 = {'ols':ols_ser2, 'ridge':rg_ser2, 'rf':rf_ser2, 'svr':svr_ser2,'xgb':xgb_ser2, 'gb':gb_ser2, 'knn':knn_ser2}\n",
        "pd.DataFrame(frame2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "id": "sEktCFo9rrK2",
        "outputId": "47bedf5c-8bf1-47f3-cff9-36e317a8a86c"
      },
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         ols  ridge     rf    svr    xgb     gb    knn\n",
              "train  0.526  0.517  0.935  0.527  0.941  0.651  0.669\n",
              "val    0.521  0.510  0.526  0.514  0.480  0.527  0.437\n",
              "test   0.557  0.546  0.555  0.555  0.493  0.563  0.498"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-63546c07-ffcd-42d7-83ad-2e4b5b2de4ff\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>ols</th>\n",
              "      <th>ridge</th>\n",
              "      <th>rf</th>\n",
              "      <th>svr</th>\n",
              "      <th>xgb</th>\n",
              "      <th>gb</th>\n",
              "      <th>knn</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>train</th>\n",
              "      <td>0.526</td>\n",
              "      <td>0.517</td>\n",
              "      <td>0.935</td>\n",
              "      <td>0.527</td>\n",
              "      <td>0.941</td>\n",
              "      <td>0.651</td>\n",
              "      <td>0.669</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>val</th>\n",
              "      <td>0.521</td>\n",
              "      <td>0.510</td>\n",
              "      <td>0.526</td>\n",
              "      <td>0.514</td>\n",
              "      <td>0.480</td>\n",
              "      <td>0.527</td>\n",
              "      <td>0.437</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>test</th>\n",
              "      <td>0.557</td>\n",
              "      <td>0.546</td>\n",
              "      <td>0.555</td>\n",
              "      <td>0.555</td>\n",
              "      <td>0.493</td>\n",
              "      <td>0.563</td>\n",
              "      <td>0.498</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-63546c07-ffcd-42d7-83ad-2e4b5b2de4ff')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-e3c49135-e6c0-4dce-90f2-7d44f0c821c2\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-e3c49135-e6c0-4dce-90f2-7d44f0c821c2')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-e3c49135-e6c0-4dce-90f2-7d44f0c821c2 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-63546c07-ffcd-42d7-83ad-2e4b5b2de4ff button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-63546c07-ffcd-42d7-83ad-2e4b5b2de4ff');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 32
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **2-3. Third Experiment**<br>\n",
        "> ### *Data Engineering*<br>\n",
        "- Outlier Drop :  `Height (> 0.4)`\n",
        "<br>\n",
        "\n",
        "> ### *Data Preprocessing*<br>\n",
        "- Numerical Features\n",
        "  + **_Log_** Scaling\n",
        "- **_Drop Categorical Feature `Sex`_**\n",
        "<br>\n",
        "\n",
        "> ### *Model Selection*<br>\n",
        "- Polynomial Regressor\n",
        "- RandomForestRegressor\n",
        "- Gradient Boosting Regressor\n",
        "- KNeighbors Regressor\n",
        "- SVM - SVR\n",
        "- Gaussian Process Regressor\n",
        "- XGBRegressor"
      ],
      "metadata": {
        "id": "-dl9k0PoQ8yv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "x_train_log = np.log1p(x_train2)\n",
        "x_test_log = np.log1p(x_test2)"
      ],
      "metadata": {
        "id": "OHpJrN25NVzx"
      },
      "execution_count": 33,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "def PolynomialRegression(degree=2, **kwargs):\n",
        "    return make_pipeline(PolynomialFeatures(degree),\n",
        "                         LinearRegression(**kwargs))\n",
        "\n",
        "poly_ols = PolynomialRegression(degree=2)\n",
        "poly_ols.fit(x_train_log, y_train)\n",
        "\n",
        "poly_train, poly_val, poly_test, poly_ser3 = print_score(poly_ols,x_train_log, y_train, x_test_log, y_test)"
      ],
      "metadata": {
        "id": "GJgUgU9SbLJE"
      },
      "execution_count": 34,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# LinearRegression\n",
        "ols.fit(x_train_log, y_train)\n",
        "ols_train, ols_val, ols_test, ols_ser3 = print_score(ols,x_train_log, y_train, x_test_log, y_test)\n",
        "\n",
        "# Ridge\n",
        "rg.fit(x_train_log, y_train)\n",
        "rg_train, rg_val, rg_test, rg_ser3 = print_score(rg,x_train_log, y_train, x_test_log, y_test)\n",
        "\n",
        "\n",
        "# RandomForestRegressor\n",
        "rf.fit(x_train_log, y_train)\n",
        "rf_train, rf_val, rf_test, rf_ser3 = print_score(rf,x_train_log, y_train, x_test_log, y_test)\n",
        "\n",
        "# SVR\n",
        "svr.fit(x_train_log, y_train)\n",
        "svr_train, svr_val, svr_test, svr_ser3 = print_score(svr,x_train_log, y_train, x_test_log, y_test)\n",
        "\n",
        "# GradientBoostingRegressor\n",
        "gb.fit(x_train_log, y_train)\n",
        "gb_train, gb_val, gb_test, gb_ser3 = print_score(gb,x_train_log, y_train, x_test_log, y_test)\n",
        "\n",
        "# KNeighborsRegressor\n",
        "knn.fit(x_train_log, y_train)\n",
        "knn_train, knn_val, knn_test, knn_ser3 = print_score(knn,x_train_log, y_train, x_test_log, y_test)"
      ],
      "metadata": {
        "id": "a4j60jQ-ORZI"
      },
      "execution_count": 35,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Gaussian Process Regressor\n",
        "gpr = GaussianProcessRegressor()\n",
        "gpr.fit(x_train_log, y_train)\n",
        "\n",
        "gpr_train, gpr_val, gpr_test, gpr_ser3 = print_score(gpr,x_train_log, y_train, x_test_log, y_test)"
      ],
      "metadata": {
        "id": "6cghJEMsdveA"
      },
      "execution_count": 36,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# XGBRegressor\n",
        "xgb = XGBRegressor()\n",
        "xgb.fit(x_train_log, y_train)\n",
        "\n",
        "xgb_train, xgb_val, xgb_test, xgb_ser3 = print_score(xgb,x_train_log, y_train, x_test_log, y_test)"
      ],
      "metadata": {
        "id": "GKrDgX7tiDb2"
      },
      "execution_count": 37,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "frame3 = {'ols':ols_ser3,'poly_ols':poly_ser3, 'ridge':rg_ser3, 'rf':rf_ser3, 'svr':svr_ser3,\\\n",
        "          'xgb':xgb_ser3, 'gb':gb_ser3, 'knn':knn_ser3, 'gpr':gpr_ser3}\n",
        "pd.DataFrame(frame3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "id": "tJiDkcwSdmfN",
        "outputId": "32afba7d-7c99-47b5-902d-a164c59c8234"
      },
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         ols  poly_ols  ridge     rf    svr    xgb     gb    knn    gpr\n",
              "train  0.547     0.577  0.534  0.934  0.530  0.941  0.651  0.688  0.673\n",
              "val    0.542     0.560  0.526  0.519  0.520  0.480  0.529  0.474 -0.204\n",
              "test   0.576     0.598  0.566  0.558  0.568  0.493  0.564  0.542 -6.096"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-c01600f6-218b-4eeb-83f7-d7bb0befbc27\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>ols</th>\n",
              "      <th>poly_ols</th>\n",
              "      <th>ridge</th>\n",
              "      <th>rf</th>\n",
              "      <th>svr</th>\n",
              "      <th>xgb</th>\n",
              "      <th>gb</th>\n",
              "      <th>knn</th>\n",
              "      <th>gpr</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>train</th>\n",
              "      <td>0.547</td>\n",
              "      <td>0.577</td>\n",
              "      <td>0.534</td>\n",
              "      <td>0.934</td>\n",
              "      <td>0.530</td>\n",
              "      <td>0.941</td>\n",
              "      <td>0.651</td>\n",
              "      <td>0.688</td>\n",
              "      <td>0.673</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>val</th>\n",
              "      <td>0.542</td>\n",
              "      <td>0.560</td>\n",
              "      <td>0.526</td>\n",
              "      <td>0.519</td>\n",
              "      <td>0.520</td>\n",
              "      <td>0.480</td>\n",
              "      <td>0.529</td>\n",
              "      <td>0.474</td>\n",
              "      <td>-0.204</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>test</th>\n",
              "      <td>0.576</td>\n",
              "      <td>0.598</td>\n",
              "      <td>0.566</td>\n",
              "      <td>0.558</td>\n",
              "      <td>0.568</td>\n",
              "      <td>0.493</td>\n",
              "      <td>0.564</td>\n",
              "      <td>0.542</td>\n",
              "      <td>-6.096</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c01600f6-218b-4eeb-83f7-d7bb0befbc27')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-bdfdb7ea-2509-4205-ba85-7317962ff44c\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-bdfdb7ea-2509-4205-ba85-7317962ff44c')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-bdfdb7ea-2509-4205-ba85-7317962ff44c button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-c01600f6-218b-4eeb-83f7-d7bb0befbc27 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-c01600f6-218b-4eeb-83f7-d7bb0befbc27');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **2-4.Fourth Experiment**<br>\n",
        "### Data Engineering<br>\n",
        "- Outlier Drop :  `Height (> 0.4)` , `Rings (> 15)`\n",
        "<br>\n",
        "\n",
        "### Data Preprocessing<br>\n",
        "- 수치형 변수 : log 변환\n",
        "- 범주형 변수 : Ordinal Encoding\n",
        "<br>\n",
        "\n",
        "### Results<br>\n",
        "-"
      ],
      "metadata": {
        "id": "y-E_4FtwtDRb"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "abalone3 = abalone.copy()"
      ],
      "metadata": {
        "id": "SVHICLOQtD_Q"
      },
      "execution_count": 39,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "outlier_rings = abalone3[abalone3['Rings']> 15]\n",
        "outlier_rings"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "NX9mukOhtPmV",
        "outputId": "df0f83be-69de-4dc0-9143-5326b5f01259"
      },
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Sex  Length  Diameter  Height  Whole weight  Shucked weight  \\\n",
              "6      F   0.530     0.415   0.150        0.7775          0.2370   \n",
              "7      F   0.545     0.425   0.125        0.7680          0.2940   \n",
              "9      F   0.550     0.440   0.150        0.8945          0.3145   \n",
              "32     M   0.665     0.525   0.165        1.3380          0.5515   \n",
              "33     F   0.680     0.550   0.175        1.7980          0.8150   \n",
              "...   ..     ...       ...     ...           ...             ...   \n",
              "3929   F   0.650     0.515   0.215        1.4980          0.5640   \n",
              "3930   F   0.670     0.535   0.185        1.5970          0.6275   \n",
              "3931   I   0.550     0.440   0.165        0.8605          0.3120   \n",
              "3944   M   0.550     0.440   0.160        0.9910          0.3480   \n",
              "3947   M   0.475     0.365   0.140        0.6175          0.2020   \n",
              "\n",
              "      Viscera weight  Shell weight  Rings  \n",
              "6             0.1415         0.330     20  \n",
              "7             0.1495         0.260     16  \n",
              "9             0.1510         0.320     19  \n",
              "32            0.3575         0.350     18  \n",
              "33            0.3925         0.455     19  \n",
              "...              ...           ...    ...  \n",
              "3929          0.3230         0.425     16  \n",
              "3930          0.3500         0.470     21  \n",
              "3931          0.1690         0.300     17  \n",
              "3944          0.1680         0.375     20  \n",
              "3947          0.1445         0.190     16  \n",
              "\n",
              "[261 rows x 9 columns]"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-e4f1f3fd-f4fa-4b4e-8834-7a054baf15fe\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sex</th>\n",
              "      <th>Length</th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Whole weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Rings</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>F</td>\n",
              "      <td>0.530</td>\n",
              "      <td>0.415</td>\n",
              "      <td>0.150</td>\n",
              "      <td>0.7775</td>\n",
              "      <td>0.2370</td>\n",
              "      <td>0.1415</td>\n",
              "      <td>0.330</td>\n",
              "      <td>20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>F</td>\n",
              "      <td>0.545</td>\n",
              "      <td>0.425</td>\n",
              "      <td>0.125</td>\n",
              "      <td>0.7680</td>\n",
              "      <td>0.2940</td>\n",
              "      <td>0.1495</td>\n",
              "      <td>0.260</td>\n",
              "      <td>16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>F</td>\n",
              "      <td>0.550</td>\n",
              "      <td>0.440</td>\n",
              "      <td>0.150</td>\n",
              "      <td>0.8945</td>\n",
              "      <td>0.3145</td>\n",
              "      <td>0.1510</td>\n",
              "      <td>0.320</td>\n",
              "      <td>19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>32</th>\n",
              "      <td>M</td>\n",
              "      <td>0.665</td>\n",
              "      <td>0.525</td>\n",
              "      <td>0.165</td>\n",
              "      <td>1.3380</td>\n",
              "      <td>0.5515</td>\n",
              "      <td>0.3575</td>\n",
              "      <td>0.350</td>\n",
              "      <td>18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>F</td>\n",
              "      <td>0.680</td>\n",
              "      <td>0.550</td>\n",
              "      <td>0.175</td>\n",
              "      <td>1.7980</td>\n",
              "      <td>0.8150</td>\n",
              "      <td>0.3925</td>\n",
              "      <td>0.455</td>\n",
              "      <td>19</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3929</th>\n",
              "      <td>F</td>\n",
              "      <td>0.650</td>\n",
              "      <td>0.515</td>\n",
              "      <td>0.215</td>\n",
              "      <td>1.4980</td>\n",
              "      <td>0.5640</td>\n",
              "      <td>0.3230</td>\n",
              "      <td>0.425</td>\n",
              "      <td>16</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3930</th>\n",
              "      <td>F</td>\n",
              "      <td>0.670</td>\n",
              "      <td>0.535</td>\n",
              "      <td>0.185</td>\n",
              "      <td>1.5970</td>\n",
              "      <td>0.6275</td>\n",
              "      <td>0.3500</td>\n",
              "      <td>0.470</td>\n",
              "      <td>21</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3931</th>\n",
              "      <td>I</td>\n",
              "      <td>0.550</td>\n",
              "      <td>0.440</td>\n",
              "      <td>0.165</td>\n",
              "      <td>0.8605</td>\n",
              "      <td>0.3120</td>\n",
              "      <td>0.1690</td>\n",
              "      <td>0.300</td>\n",
              "      <td>17</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3944</th>\n",
              "      <td>M</td>\n",
              "      <td>0.550</td>\n",
              "      <td>0.440</td>\n",
              "      <td>0.160</td>\n",
              "      <td>0.9910</td>\n",
              "      <td>0.3480</td>\n",
              "      <td>0.1680</td>\n",
              "      <td>0.375</td>\n",
              "      <td>20</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3947</th>\n",
              "      <td>M</td>\n",
              "      <td>0.475</td>\n",
              "      <td>0.365</td>\n",
              "      <td>0.140</td>\n",
              "      <td>0.6175</td>\n",
              "      <td>0.2020</td>\n",
              "      <td>0.1445</td>\n",
              "      <td>0.190</td>\n",
              "      <td>16</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>261 rows × 9 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e4f1f3fd-f4fa-4b4e-8834-7a054baf15fe')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-eb5e246e-be7f-4122-b907-0c7cd7567436\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-eb5e246e-be7f-4122-b907-0c7cd7567436')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-eb5e246e-be7f-4122-b907-0c7cd7567436 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-e4f1f3fd-f4fa-4b4e-8834-7a054baf15fe button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-e4f1f3fd-f4fa-4b4e-8834-7a054baf15fe');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 40
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "abalone3.drop(outlier_rings.index, inplace=True)\n",
        "abalone3[abalone3['Rings']> 15]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49
        },
        "id": "3udm0DGLuMxs",
        "outputId": "442e37ae-df1f-41d8-ffb3-419b3b5a6500"
      },
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Empty DataFrame\n",
              "Columns: [Sex, Length, Diameter, Height, Whole weight, Shucked weight, Viscera weight, Shell weight, Rings]\n",
              "Index: []"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-df50624a-d6bd-4752-b518-4da1b341773b\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Sex</th>\n",
              "      <th>Length</th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Whole weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Rings</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-df50624a-d6bd-4752-b518-4da1b341773b')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-b3b0f83d-5906-448e-b4f9-37f13a927977\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-b3b0f83d-5906-448e-b4f9-37f13a927977')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-b3b0f83d-5906-448e-b4f9-37f13a927977 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-df50624a-d6bd-4752-b518-4da1b341773b button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-df50624a-d6bd-4752-b518-4da1b341773b');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 41
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 데이터 분리\n",
        "target = 'Rings'\n",
        "features3 = abalone3.columns.difference(['Rings'])\n",
        "x_train3, x_test3, y_train3, y_test3 = data_split(abalone3, target, features3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "koLXKP1EvDrC",
        "outputId": "b7d6fb14-8a83-4e05-85f4-eede4c09b780"
      },
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "x_train: (2935, 8), y_train: (2935,)\n",
            "x_test: (979, 8), y_test: (979,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Log 변환\n",
        "x_train3[numeric_feats] = np.log1p(x_train3[numeric_feats])\n",
        "x_test3[numeric_feats] = np.log1p(x_test3[numeric_feats])"
      ],
      "metadata": {
        "id": "JCXCTE4yuwbn"
      },
      "execution_count": 43,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# OrdinalEncoding\n",
        "le = OrdinalEncoder()\n",
        "x_train3_le = le.fit_transform(x_train3)\n",
        "x_test3_le = le.transform(x_test3)\n",
        "\n",
        "# 결과 확인\n",
        "print((x_train3_le.dtypes == 'object').sum())\n",
        "print((x_test3_le.dtypes == 'object').sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8amJ7Jw4ugol",
        "outputId": "d142c410-87ad-4353-cb30-e19b343137cb"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0\n",
            "0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_train3_le.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "Sbad3i-vv5Zh",
        "outputId": "a0c6e838-7d94-46ec-9d2d-81f077ea59d3"
      },
      "execution_count": 45,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      Diameter    Height    Length  Sex  Shell weight  Shucked weight  \\\n",
              "2848  0.395415  0.148420  0.485508    1      0.298993        0.464363   \n",
              "1773  0.281412  0.131028  0.381855    2      0.189794        0.308954   \n",
              "2054  0.307485  0.104360  0.381855    3      0.114221        0.236257   \n",
              "62    0.343590  0.122218  0.425268    1      0.182322        0.263902   \n",
              "1293  0.336472  0.122218  0.418710    2      0.165514        0.209450   \n",
              "\n",
              "      Viscera weight  Whole weight  \n",
              "2848        0.230318      0.812706  \n",
              "1773        0.142801      0.566166  \n",
              "2054        0.081580      0.402461  \n",
              "62          0.176890      0.528567  \n",
              "1293        0.127953      0.459006  "
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-a7899fc8-a730-427e-b9d5-ffa97fa43979\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Diameter</th>\n",
              "      <th>Height</th>\n",
              "      <th>Length</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Shell weight</th>\n",
              "      <th>Shucked weight</th>\n",
              "      <th>Viscera weight</th>\n",
              "      <th>Whole weight</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>2848</th>\n",
              "      <td>0.395415</td>\n",
              "      <td>0.148420</td>\n",
              "      <td>0.485508</td>\n",
              "      <td>1</td>\n",
              "      <td>0.298993</td>\n",
              "      <td>0.464363</td>\n",
              "      <td>0.230318</td>\n",
              "      <td>0.812706</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1773</th>\n",
              "      <td>0.281412</td>\n",
              "      <td>0.131028</td>\n",
              "      <td>0.381855</td>\n",
              "      <td>2</td>\n",
              "      <td>0.189794</td>\n",
              "      <td>0.308954</td>\n",
              "      <td>0.142801</td>\n",
              "      <td>0.566166</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2054</th>\n",
              "      <td>0.307485</td>\n",
              "      <td>0.104360</td>\n",
              "      <td>0.381855</td>\n",
              "      <td>3</td>\n",
              "      <td>0.114221</td>\n",
              "      <td>0.236257</td>\n",
              "      <td>0.081580</td>\n",
              "      <td>0.402461</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>62</th>\n",
              "      <td>0.343590</td>\n",
              "      <td>0.122218</td>\n",
              "      <td>0.425268</td>\n",
              "      <td>1</td>\n",
              "      <td>0.182322</td>\n",
              "      <td>0.263902</td>\n",
              "      <td>0.176890</td>\n",
              "      <td>0.528567</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1293</th>\n",
              "      <td>0.336472</td>\n",
              "      <td>0.122218</td>\n",
              "      <td>0.418710</td>\n",
              "      <td>2</td>\n",
              "      <td>0.165514</td>\n",
              "      <td>0.209450</td>\n",
              "      <td>0.127953</td>\n",
              "      <td>0.459006</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a7899fc8-a730-427e-b9d5-ffa97fa43979')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-480f3f69-1426-4792-a657-cc1da16a4974\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-480f3f69-1426-4792-a657-cc1da16a4974')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-480f3f69-1426-4792-a657-cc1da16a4974 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-a7899fc8-a730-427e-b9d5-ffa97fa43979 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-a7899fc8-a730-427e-b9d5-ffa97fa43979');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 45
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# LinearRegression\n",
        "ols.fit(x_train3_le, y_train3)\n",
        "ols_train4, ols_val4, ols_test4, ols_ser4 = print_score(ols,x_train3_le, y_train3, x_test3_le, y_test3)\n",
        "\n",
        "# Ridge\n",
        "rg.fit(x_train3_le, y_train3)\n",
        "rg_train4, rg_val4, rg_test4, rg_ser4 = print_score(rg,x_train3_le, y_train3, x_test3_le, y_test3)\n",
        "\n",
        "\n",
        "# RandomForestRegressor\n",
        "rf.fit(x_train3_le, y_train3)\n",
        "rf_train4, rf_val4, rf_test4, rf_ser4 = print_score(rf,x_train3_le, y_train3, x_test3_le, y_test3)\n",
        "\n",
        "# SVR\n",
        "svr.fit(x_train3_le, y_train3)\n",
        "svr_train4, svr_val4, svr_test4, svr_ser4 = print_score(svr,x_train3_le, y_train3, x_test3_le, y_test3)\n",
        "\n",
        "# XGBRegressor\n",
        "xgb = XGBRegressor()\n",
        "xgb.fit(x_train3_le, y_train3)\n",
        "\n",
        "xgb_train4, xgb_val4, xgb_test4, xgb_ser4 = print_score(xgb,x_train3_le, y_train3, x_test3_le, y_test3)"
      ],
      "metadata": {
        "id": "wgJDK4h4v-G4"
      },
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "frame4 = {'ols':ols_ser4,'ridge':rg_ser4, 'rf':rf_ser4, 'svr':svr_ser4,'xgb':xgb_ser4}\n",
        "pd.DataFrame(frame4)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "id": "tiMQKOZNSeCf",
        "outputId": "3b50b76a-b2f1-4637-fa63-70f179f336e7"
      },
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "         ols  ridge     rf    svr    xgb\n",
              "train  0.545  0.535  0.940  0.502  0.947\n",
              "val    0.540  0.529  0.550  0.489  0.503\n",
              "test   0.547  0.536  0.558  0.504  0.511"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-b597d016-dd8b-471f-a1fc-3899a39fdc61\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>ols</th>\n",
              "      <th>ridge</th>\n",
              "      <th>rf</th>\n",
              "      <th>svr</th>\n",
              "      <th>xgb</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>train</th>\n",
              "      <td>0.545</td>\n",
              "      <td>0.535</td>\n",
              "      <td>0.940</td>\n",
              "      <td>0.502</td>\n",
              "      <td>0.947</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>val</th>\n",
              "      <td>0.540</td>\n",
              "      <td>0.529</td>\n",
              "      <td>0.550</td>\n",
              "      <td>0.489</td>\n",
              "      <td>0.503</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>test</th>\n",
              "      <td>0.547</td>\n",
              "      <td>0.536</td>\n",
              "      <td>0.558</td>\n",
              "      <td>0.504</td>\n",
              "      <td>0.511</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b597d016-dd8b-471f-a1fc-3899a39fdc61')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-26bf86a5-9754-4475-8974-4000c59e5e4e\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-26bf86a5-9754-4475-8974-4000c59e5e4e')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-26bf86a5-9754-4475-8974-4000c59e5e4e button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-b597d016-dd8b-471f-a1fc-3899a39fdc61 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-b597d016-dd8b-471f-a1fc-3899a39fdc61');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# **Part 3. Model Tuning**\n",
        "비선형 회귀 모델 (RandomForestRegressor, XGBRegressor) <br>\n",
        "💡 과대적합 발생원인 <br>\n",
        "- 데이터의 양이 충분하지 못할 경우\n",
        "- 분산이 크거나 노이즈가 심한 경우\n",
        "- 모델의 복잡도가 큰 경우 (모델의 학습 가능한 가중치의 개수)\n",
        "- 과도하게 큰 epoch로 학습하는 경우\n",
        "<br>\n",
        "\n",
        "💡 모델 성능 향상 <br>\n",
        "\n",
        "✅ **[Baseline]**<br>\n",
        "[Epoch 10, lr 0.001] <br>\n",
        "[Train Dataset] Loss = 5.863, Accuracy = 0.824 <br>\n",
        "[Test Dataset] Accuracy = 0.827 <br>\n"
      ],
      "metadata": {
        "id": "CQxlobNkSwDi"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **3-1. GridSearchCV**"
      ],
      "metadata": {
        "id": "k9jFmZmfprcv"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "abalone4 = abalone.copy()\n",
        "\n",
        "# 데이터 분리\n",
        "target = 'Rings'\n",
        "features4 = abalone4.columns.difference(['Rings','Sex'])\n",
        "x_train4, x_test4, y_train4, y_test4 = data_split(abalone4, target, features4)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9mkLOeEMrHo5",
        "outputId": "48e34463-9f02-4cca-8821-e1b4d155bf35"
      },
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "x_train: (3131, 7), y_train: (3131,)\n",
            "x_test: (1044, 7), y_test: (1044,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Log 변환\n",
        "x_train4[numeric_feats] = np.log1p(x_train4[numeric_feats])\n",
        "x_test4[numeric_feats] = np.log1p(x_test4[numeric_feats])"
      ],
      "metadata": {
        "id": "3aBeT6_grijv"
      },
      "execution_count": 49,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "rf_grid = make_pipeline(\n",
        "    RandomForestRegressor(\n",
        "        n_estimators=200,\n",
        "        max_depth=2,\n",
        "        random_state = 42\n",
        "    )\n",
        ")\n",
        "print(rf_grid)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RJVs6tTAjBbJ",
        "outputId": "ce6c24a4-8db0-4d6d-cf66-33ef76e28cb0"
      },
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Pipeline(steps=[('randomforestregressor',\n",
            "                 RandomForestRegressor(max_depth=2, n_estimators=200,\n",
            "                                       random_state=42))])\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "rf_params = {'randomforestregressor__n_estimators' : [100, 150, 200], 'randomforestregressor__max_depth': [4, 6, 8, 9, 10, 11, 12]}"
      ],
      "metadata": {
        "id": "qi-AQ_XsxNlA"
      },
      "execution_count": 51,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "rf_gridCV = GridSearchCV(rf_grid, param_grid=rf_params, scoring='r2', cv=5, verbose=3)\n",
        "rf_gridCV.fit(x_train4, y_train4)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "lK61iQanpIQ8",
        "outputId": "155c4ffc-a20f-4d95-86d4-3a341646c49d"
      },
      "execution_count": 52,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 5 folds for each of 21 candidates, totalling 105 fits\n",
            "[CV 1/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=100;, score=0.476 total time=   0.5s\n",
            "[CV 2/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=100;, score=0.473 total time=   0.7s\n",
            "[CV 3/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=100;, score=0.495 total time=   0.7s\n",
            "[CV 4/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=100;, score=0.529 total time=   0.7s\n",
            "[CV 5/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=100;, score=0.461 total time=   0.8s\n",
            "[CV 1/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=150;, score=0.476 total time=   1.5s\n",
            "[CV 2/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=150;, score=0.476 total time=   1.1s\n",
            "[CV 3/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=150;, score=0.496 total time=   0.9s\n",
            "[CV 4/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=150;, score=0.531 total time=   0.9s\n",
            "[CV 5/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=150;, score=0.460 total time=   0.9s\n",
            "[CV 1/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=200;, score=0.476 total time=   1.2s\n",
            "[CV 2/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=200;, score=0.479 total time=   1.3s\n",
            "[CV 3/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=200;, score=0.497 total time=   1.4s\n",
            "[CV 4/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=200;, score=0.531 total time=   1.1s\n",
            "[CV 5/5] END randomforestregressor__max_depth=4, randomforestregressor__n_estimators=200;, score=0.461 total time=   1.2s\n",
            "[CV 1/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=100;, score=0.502 total time=   1.0s\n",
            "[CV 2/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=100;, score=0.507 total time=   3.3s\n",
            "[CV 3/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=100;, score=0.535 total time=   3.3s\n",
            "[CV 4/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=100;, score=0.579 total time=   2.1s\n",
            "[CV 5/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=100;, score=0.486 total time=   1.0s\n",
            "[CV 1/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=150;, score=0.501 total time=   1.6s\n",
            "[CV 2/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=150;, score=0.510 total time=   1.0s\n",
            "[CV 3/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=150;, score=0.535 total time=   0.9s\n",
            "[CV 4/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=150;, score=0.581 total time=   1.6s\n",
            "[CV 5/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=150;, score=0.487 total time=   3.3s\n",
            "[CV 1/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=200;, score=0.502 total time=   4.0s\n",
            "[CV 2/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=200;, score=0.511 total time=   2.2s\n",
            "[CV 3/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=200;, score=0.535 total time=   2.0s\n",
            "[CV 4/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=200;, score=0.580 total time=   1.2s\n",
            "[CV 5/5] END randomforestregressor__max_depth=6, randomforestregressor__n_estimators=200;, score=0.489 total time=   1.2s\n",
            "[CV 1/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=100;, score=0.503 total time=   0.8s\n",
            "[CV 2/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=100;, score=0.517 total time=   1.3s\n",
            "[CV 3/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=100;, score=0.543 total time=   2.5s\n",
            "[CV 4/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=100;, score=0.592 total time=   1.2s\n",
            "[CV 5/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=100;, score=0.492 total time=   1.6s\n",
            "[CV 1/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=150;, score=0.502 total time=   1.5s\n",
            "[CV 2/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=150;, score=0.516 total time=   1.2s\n",
            "[CV 3/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=150;, score=0.543 total time=   1.2s\n",
            "[CV 4/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=150;, score=0.595 total time=   1.2s\n",
            "[CV 5/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=150;, score=0.497 total time=   1.2s\n",
            "[CV 1/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=200;, score=0.505 total time=   1.6s\n",
            "[CV 2/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=200;, score=0.518 total time=   1.6s\n",
            "[CV 3/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=200;, score=0.542 total time=   2.4s\n",
            "[CV 4/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=200;, score=0.595 total time=   2.3s\n",
            "[CV 5/5] END randomforestregressor__max_depth=8, randomforestregressor__n_estimators=200;, score=0.497 total time=   1.5s\n",
            "[CV 1/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=100;, score=0.504 total time=   0.9s\n",
            "[CV 2/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=100;, score=0.519 total time=   0.9s\n",
            "[CV 3/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=100;, score=0.545 total time=   0.9s\n",
            "[CV 4/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=100;, score=0.597 total time=   0.9s\n",
            "[CV 5/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=100;, score=0.488 total time=   0.9s\n",
            "[CV 1/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=150;, score=0.502 total time=   1.3s\n",
            "[CV 2/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=150;, score=0.519 total time=   1.3s\n",
            "[CV 3/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=150;, score=0.546 total time=   1.4s\n",
            "[CV 4/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=150;, score=0.599 total time=   2.0s\n",
            "[CV 5/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=150;, score=0.493 total time=   2.5s\n",
            "[CV 1/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=200;, score=0.504 total time=   2.1s\n",
            "[CV 2/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=200;, score=0.519 total time=   1.7s\n",
            "[CV 3/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=200;, score=0.546 total time=   1.7s\n",
            "[CV 4/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=200;, score=0.599 total time=   1.7s\n",
            "[CV 5/5] END randomforestregressor__max_depth=9, randomforestregressor__n_estimators=200;, score=0.494 total time=   1.7s\n",
            "[CV 1/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=100;, score=0.502 total time=   0.9s\n",
            "[CV 2/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=100;, score=0.521 total time=   1.3s\n",
            "[CV 3/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=100;, score=0.541 total time=   1.4s\n",
            "[CV 4/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=100;, score=0.597 total time=   1.4s\n",
            "[CV 5/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=100;, score=0.489 total time=   1.1s\n",
            "[CV 1/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=150;, score=0.498 total time=   1.4s\n",
            "[CV 2/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=150;, score=0.518 total time=   1.4s\n",
            "[CV 3/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=150;, score=0.542 total time=   1.4s\n",
            "[CV 4/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=150;, score=0.599 total time=   1.4s\n",
            "[CV 5/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=150;, score=0.494 total time=   1.4s\n",
            "[CV 1/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=200;, score=0.501 total time=   1.8s\n",
            "[CV 2/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=200;, score=0.518 total time=   2.4s\n",
            "[CV 3/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=200;, score=0.541 total time=   2.7s\n",
            "[CV 4/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=200;, score=0.599 total time=   1.8s\n",
            "[CV 5/5] END randomforestregressor__max_depth=10, randomforestregressor__n_estimators=200;, score=0.495 total time=   1.8s\n",
            "[CV 1/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=100;, score=0.502 total time=   1.0s\n",
            "[CV 2/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=100;, score=0.515 total time=   1.0s\n",
            "[CV 3/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=100;, score=0.542 total time=   1.0s\n",
            "[CV 4/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=100;, score=0.597 total time=   1.0s\n",
            "[CV 5/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=100;, score=0.482 total time=   1.0s\n",
            "[CV 1/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=150;, score=0.498 total time=   1.6s\n",
            "[CV 2/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=150;, score=0.515 total time=   2.3s\n",
            "[CV 3/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=150;, score=0.542 total time=   2.1s\n",
            "[CV 4/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=150;, score=0.599 total time=   1.5s\n",
            "[CV 5/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=150;, score=0.490 total time=   1.5s\n",
            "[CV 1/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=200;, score=0.500 total time=   2.0s\n",
            "[CV 2/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=200;, score=0.516 total time=   2.0s\n",
            "[CV 3/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=200;, score=0.542 total time=   2.0s\n",
            "[CV 4/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=200;, score=0.599 total time=   2.6s\n",
            "[CV 5/5] END randomforestregressor__max_depth=11, randomforestregressor__n_estimators=200;, score=0.493 total time=   3.1s\n",
            "[CV 1/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=100;, score=0.499 total time=   1.4s\n",
            "[CV 2/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=100;, score=0.517 total time=   1.1s\n",
            "[CV 3/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=100;, score=0.543 total time=   1.1s\n",
            "[CV 4/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=100;, score=0.597 total time=   1.1s\n",
            "[CV 5/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=100;, score=0.481 total time=   1.0s\n",
            "[CV 1/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=150;, score=0.495 total time=   1.6s\n",
            "[CV 2/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=150;, score=0.517 total time=   1.6s\n",
            "[CV 3/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=150;, score=0.544 total time=   2.0s\n",
            "[CV 4/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=150;, score=0.599 total time=   2.3s\n",
            "[CV 5/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=150;, score=0.492 total time=   1.9s\n",
            "[CV 1/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=200;, score=0.499 total time=   2.1s\n",
            "[CV 2/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=200;, score=0.517 total time=   2.1s\n",
            "[CV 3/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=200;, score=0.543 total time=   2.1s\n",
            "[CV 4/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=200;, score=0.599 total time=   2.8s\n",
            "[CV 5/5] END randomforestregressor__max_depth=12, randomforestregressor__n_estimators=200;, score=0.491 total time=   3.4s\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5,\n",
              "             estimator=Pipeline(steps=[('randomforestregressor',\n",
              "                                        RandomForestRegressor(max_depth=2,\n",
              "                                                              n_estimators=200,\n",
              "                                                              random_state=42))]),\n",
              "             param_grid={'randomforestregressor__max_depth': [4, 6, 8, 9, 10,\n",
              "                                                              11, 12],\n",
              "                         'randomforestregressor__n_estimators': [100, 150,\n",
              "                                                                 200]},\n",
              "             scoring='r2', verbose=3)"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5,\n",
              "             estimator=Pipeline(steps=[(&#x27;randomforestregressor&#x27;,\n",
              "                                        RandomForestRegressor(max_depth=2,\n",
              "                                                              n_estimators=200,\n",
              "                                                              random_state=42))]),\n",
              "             param_grid={&#x27;randomforestregressor__max_depth&#x27;: [4, 6, 8, 9, 10,\n",
              "                                                              11, 12],\n",
              "                         &#x27;randomforestregressor__n_estimators&#x27;: [100, 150,\n",
              "                                                                 200]},\n",
              "             scoring=&#x27;r2&#x27;, verbose=3)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5,\n",
              "             estimator=Pipeline(steps=[(&#x27;randomforestregressor&#x27;,\n",
              "                                        RandomForestRegressor(max_depth=2,\n",
              "                                                              n_estimators=200,\n",
              "                                                              random_state=42))]),\n",
              "             param_grid={&#x27;randomforestregressor__max_depth&#x27;: [4, 6, 8, 9, 10,\n",
              "                                                              11, 12],\n",
              "                         &#x27;randomforestregressor__n_estimators&#x27;: [100, 150,\n",
              "                                                                 200]},\n",
              "             scoring=&#x27;r2&#x27;, verbose=3)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;randomforestregressor&#x27;,\n",
              "                 RandomForestRegressor(max_depth=2, n_estimators=200,\n",
              "                                       random_state=42))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(max_depth=2, n_estimators=200, random_state=42)</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(\"최적 하이퍼파라미터: \", rf_gridCV.best_params_)\n",
        "print(\"최적 AUC: \", rf_gridCV.best_score_)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "83YZJJCnp4oI",
        "outputId": "d5f0a602-b781-44a9-8e6a-010252750faa"
      },
      "execution_count": 53,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "최적 하이퍼파라미터:  {'randomforestregressor__max_depth': 9, 'randomforestregressor__n_estimators': 200}\n",
            "최적 AUC:  0.5323714661998805\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pd.DataFrame(rf_gridCV.cv_results_).sort_values(by=\"rank_test_score\").T"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 630
        },
        "id": "T2Fdq8N7v1dv",
        "outputId": "ccf30239-ee3b-4cf8-c9ac-99b2c3030503"
      },
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                                                                          11  \\\n",
              "mean_fit_time                                                                       1.772477   \n",
              "std_fit_time                                                                        0.159026   \n",
              "mean_score_time                                                                     0.024618   \n",
              "std_score_time                                                                      0.002718   \n",
              "param_randomforestregressor__max_depth                                                     9   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 9, 'rando...   \n",
              "split0_test_score                                                                   0.503827   \n",
              "split1_test_score                                                                   0.519458   \n",
              "split2_test_score                                                                   0.545769   \n",
              "split3_test_score                                                                   0.598765   \n",
              "split4_test_score                                                                   0.494039   \n",
              "mean_test_score                                                                     0.532371   \n",
              "std_test_score                                                                      0.037519   \n",
              "rank_test_score                                                                            1   \n",
              "\n",
              "                                                                                          10  \\\n",
              "mean_fit_time                                                                       1.658683   \n",
              "std_fit_time                                                                        0.418747   \n",
              "mean_score_time                                                                     0.038109   \n",
              "std_score_time                                                                       0.03276   \n",
              "param_randomforestregressor__max_depth                                                     9   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 9, 'rando...   \n",
              "split0_test_score                                                                   0.501659   \n",
              "split1_test_score                                                                   0.519227   \n",
              "split2_test_score                                                                   0.545998   \n",
              "split3_test_score                                                                   0.598973   \n",
              "split4_test_score                                                                   0.493196   \n",
              "mean_test_score                                                                     0.531811   \n",
              "std_test_score                                                                      0.038133   \n",
              "rank_test_score                                                                            2   \n",
              "\n",
              "                                                                                          8   \\\n",
              "mean_fit_time                                                                       1.854504   \n",
              "std_fit_time                                                                        0.370921   \n",
              "mean_score_time                                                                     0.023637   \n",
              "std_score_time                                                                      0.003551   \n",
              "param_randomforestregressor__max_depth                                                     8   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 8, 'rando...   \n",
              "split0_test_score                                                                   0.504933   \n",
              "split1_test_score                                                                   0.518234   \n",
              "split2_test_score                                                                   0.542334   \n",
              "split3_test_score                                                                   0.594645   \n",
              "split4_test_score                                                                   0.497436   \n",
              "mean_test_score                                                                     0.531516   \n",
              "std_test_score                                                                      0.035062   \n",
              "rank_test_score                                                                            3   \n",
              "\n",
              "                                                                                          14  \\\n",
              "mean_fit_time                                                                       2.105215   \n",
              "std_fit_time                                                                        0.371806   \n",
              "mean_score_time                                                                     0.026258   \n",
              "std_score_time                                                                      0.002452   \n",
              "param_randomforestregressor__max_depth                                                    10   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 10, 'rand...   \n",
              "split0_test_score                                                                   0.501086   \n",
              "split1_test_score                                                                   0.517636   \n",
              "split2_test_score                                                                   0.541099   \n",
              "split3_test_score                                                                   0.599367   \n",
              "split4_test_score                                                                   0.495432   \n",
              "mean_test_score                                                                     0.530924   \n",
              "std_test_score                                                                      0.037721   \n",
              "rank_test_score                                                                            4   \n",
              "\n",
              "                                                                                          7   \\\n",
              "mean_fit_time                                                                       1.216117   \n",
              "std_fit_time                                                                        0.129794   \n",
              "mean_score_time                                                                     0.017733   \n",
              "std_score_time                                                                      0.004068   \n",
              "param_randomforestregressor__max_depth                                                     8   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 8, 'rando...   \n",
              "split0_test_score                                                                    0.50223   \n",
              "split1_test_score                                                                   0.516366   \n",
              "split2_test_score                                                                   0.543438   \n",
              "split3_test_score                                                                   0.594705   \n",
              "split4_test_score                                                                   0.497197   \n",
              "mean_test_score                                                                     0.530787   \n",
              "std_test_score                                                                       0.03577   \n",
              "rank_test_score                                                                            5   \n",
              "\n",
              "                                                                                          9   \\\n",
              "mean_fit_time                                                                       0.859069   \n",
              "std_fit_time                                                                        0.007547   \n",
              "mean_score_time                                                                     0.013081   \n",
              "std_score_time                                                                      0.000783   \n",
              "param_randomforestregressor__max_depth                                                     9   \n",
              "param_randomforestregressor__n_estimators                                                100   \n",
              "params                                     {'randomforestregressor__max_depth': 9, 'rando...   \n",
              "split0_test_score                                                                   0.503754   \n",
              "split1_test_score                                                                   0.518964   \n",
              "split2_test_score                                                                   0.545264   \n",
              "split3_test_score                                                                   0.597236   \n",
              "split4_test_score                                                                    0.48789   \n",
              "mean_test_score                                                                     0.530621   \n",
              "std_test_score                                                                      0.038303   \n",
              "rank_test_score                                                                            6   \n",
              "\n",
              "                                                                                          13  \\\n",
              "mean_fit_time                                                                       1.353473   \n",
              "std_fit_time                                                                         0.01831   \n",
              "mean_score_time                                                                      0.01916   \n",
              "std_score_time                                                                      0.000155   \n",
              "param_randomforestregressor__max_depth                                                    10   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 10, 'rand...   \n",
              "split0_test_score                                                                   0.498078   \n",
              "split1_test_score                                                                   0.517995   \n",
              "split2_test_score                                                                   0.542413   \n",
              "split3_test_score                                                                   0.599075   \n",
              "split4_test_score                                                                   0.494372   \n",
              "mean_test_score                                                                     0.530386   \n",
              "std_test_score                                                                      0.038359   \n",
              "rank_test_score                                                                            7   \n",
              "\n",
              "                                                                                          17  \\\n",
              "mean_fit_time                                                                        2.27442   \n",
              "std_fit_time                                                                        0.395051   \n",
              "mean_score_time                                                                     0.047736   \n",
              "std_score_time                                                                      0.037188   \n",
              "param_randomforestregressor__max_depth                                                    11   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 11, 'rand...   \n",
              "split0_test_score                                                                   0.500195   \n",
              "split1_test_score                                                                   0.516487   \n",
              "split2_test_score                                                                   0.541791   \n",
              "split3_test_score                                                                   0.599145   \n",
              "split4_test_score                                                                   0.492754   \n",
              "mean_test_score                                                                     0.530074   \n",
              "std_test_score                                                                      0.038414   \n",
              "rank_test_score                                                                            8   \n",
              "\n",
              "                                                                                          12  \\\n",
              "mean_fit_time                                                                       1.194477   \n",
              "std_fit_time                                                                        0.178535   \n",
              "mean_score_time                                                                     0.017094   \n",
              "std_score_time                                                                      0.001733   \n",
              "param_randomforestregressor__max_depth                                                    10   \n",
              "param_randomforestregressor__n_estimators                                                100   \n",
              "params                                     {'randomforestregressor__max_depth': 10, 'rand...   \n",
              "split0_test_score                                                                   0.502286   \n",
              "split1_test_score                                                                   0.520543   \n",
              "split2_test_score                                                                   0.541169   \n",
              "split3_test_score                                                                    0.59726   \n",
              "split4_test_score                                                                   0.488742   \n",
              "mean_test_score                                                                         0.53   \n",
              "std_test_score                                                                      0.037969   \n",
              "rank_test_score                                                                            9   \n",
              "\n",
              "                                                                                          20  \\\n",
              "mean_fit_time                                                                       2.478599   \n",
              "std_fit_time                                                                        0.514289   \n",
              "mean_score_time                                                                     0.033911   \n",
              "std_score_time                                                                      0.008052   \n",
              "param_randomforestregressor__max_depth                                                    12   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 12, 'rand...   \n",
              "split0_test_score                                                                   0.498929   \n",
              "split1_test_score                                                                   0.516931   \n",
              "split2_test_score                                                                   0.543165   \n",
              "split3_test_score                                                                   0.598985   \n",
              "split4_test_score                                                                   0.491382   \n",
              "mean_test_score                                                                     0.529878   \n",
              "std_test_score                                                                      0.038884   \n",
              "rank_test_score                                                                           10   \n",
              "\n",
              "                                           ...  \\\n",
              "mean_fit_time                              ...   \n",
              "std_fit_time                               ...   \n",
              "mean_score_time                            ...   \n",
              "std_score_time                             ...   \n",
              "param_randomforestregressor__max_depth     ...   \n",
              "param_randomforestregressor__n_estimators  ...   \n",
              "params                                     ...   \n",
              "split0_test_score                          ...   \n",
              "split1_test_score                          ...   \n",
              "split2_test_score                          ...   \n",
              "split3_test_score                          ...   \n",
              "split4_test_score                          ...   \n",
              "mean_test_score                            ...   \n",
              "std_test_score                             ...   \n",
              "rank_test_score                            ...   \n",
              "\n",
              "                                                                                          19  \\\n",
              "mean_fit_time                                                                       1.855846   \n",
              "std_fit_time                                                                        0.266437   \n",
              "mean_score_time                                                                     0.023645   \n",
              "std_score_time                                                                      0.003467   \n",
              "param_randomforestregressor__max_depth                                                    12   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 12, 'rand...   \n",
              "split0_test_score                                                                   0.495426   \n",
              "split1_test_score                                                                   0.516912   \n",
              "split2_test_score                                                                   0.544028   \n",
              "split3_test_score                                                                   0.598711   \n",
              "split4_test_score                                                                   0.491744   \n",
              "mean_test_score                                                                     0.529364   \n",
              "std_test_score                                                                       0.03936   \n",
              "rank_test_score                                                                           12   \n",
              "\n",
              "                                                                                          16  \\\n",
              "mean_fit_time                                                                       1.767274   \n",
              "std_fit_time                                                                        0.333239   \n",
              "mean_score_time                                                                     0.024275   \n",
              "std_score_time                                                                      0.003911   \n",
              "param_randomforestregressor__max_depth                                                    11   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 11, 'rand...   \n",
              "split0_test_score                                                                   0.498455   \n",
              "split1_test_score                                                                   0.515104   \n",
              "split2_test_score                                                                   0.542293   \n",
              "split3_test_score                                                                   0.599372   \n",
              "split4_test_score                                                                   0.490114   \n",
              "mean_test_score                                                                     0.529068   \n",
              "std_test_score                                                                      0.039414   \n",
              "rank_test_score                                                                           13   \n",
              "\n",
              "                                                                                          15  \\\n",
              "mean_fit_time                                                                       0.988791   \n",
              "std_fit_time                                                                        0.020911   \n",
              "mean_score_time                                                                     0.015792   \n",
              "std_score_time                                                                      0.002331   \n",
              "param_randomforestregressor__max_depth                                                    11   \n",
              "param_randomforestregressor__n_estimators                                                100   \n",
              "params                                     {'randomforestregressor__max_depth': 11, 'rand...   \n",
              "split0_test_score                                                                   0.502124   \n",
              "split1_test_score                                                                   0.515076   \n",
              "split2_test_score                                                                   0.541841   \n",
              "split3_test_score                                                                    0.59732   \n",
              "split4_test_score                                                                   0.482485   \n",
              "mean_test_score                                                                     0.527769   \n",
              "std_test_score                                                                      0.039761   \n",
              "rank_test_score                                                                           14   \n",
              "\n",
              "                                                                                          18  \\\n",
              "mean_fit_time                                                                       1.104476   \n",
              "std_fit_time                                                                        0.120326   \n",
              "mean_score_time                                                                     0.014441   \n",
              "std_score_time                                                                      0.000317   \n",
              "param_randomforestregressor__max_depth                                                    12   \n",
              "param_randomforestregressor__n_estimators                                                100   \n",
              "params                                     {'randomforestregressor__max_depth': 12, 'rand...   \n",
              "split0_test_score                                                                   0.499392   \n",
              "split1_test_score                                                                   0.516747   \n",
              "split2_test_score                                                                   0.542933   \n",
              "split3_test_score                                                                    0.59722   \n",
              "split4_test_score                                                                   0.481244   \n",
              "mean_test_score                                                                     0.527507   \n",
              "std_test_score                                                                      0.040359   \n",
              "rank_test_score                                                                           15   \n",
              "\n",
              "                                                                                          5   \\\n",
              "mean_fit_time                                                                       2.097273   \n",
              "std_fit_time                                                                        0.998673   \n",
              "mean_score_time                                                                     0.025906   \n",
              "std_score_time                                                                      0.009403   \n",
              "param_randomforestregressor__max_depth                                                     6   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 6, 'rando...   \n",
              "split0_test_score                                                                   0.501961   \n",
              "split1_test_score                                                                   0.511494   \n",
              "split2_test_score                                                                   0.534704   \n",
              "split3_test_score                                                                   0.579641   \n",
              "split4_test_score                                                                   0.488873   \n",
              "mean_test_score                                                                     0.523334   \n",
              "std_test_score                                                                      0.031888   \n",
              "rank_test_score                                                                           16   \n",
              "\n",
              "                                                                                          4   \\\n",
              "mean_fit_time                                                                       1.652839   \n",
              "std_fit_time                                                                        0.849754   \n",
              "mean_score_time                                                                     0.022352   \n",
              "std_score_time                                                                      0.011631   \n",
              "param_randomforestregressor__max_depth                                                     6   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 6, 'rando...   \n",
              "split0_test_score                                                                   0.500941   \n",
              "split1_test_score                                                                   0.509771   \n",
              "split2_test_score                                                                   0.535001   \n",
              "split3_test_score                                                                   0.580584   \n",
              "split4_test_score                                                                   0.487162   \n",
              "mean_test_score                                                                     0.522692   \n",
              "std_test_score                                                                       0.03288   \n",
              "rank_test_score                                                                           17   \n",
              "\n",
              "                                                                                          3   \\\n",
              "mean_fit_time                                                                       2.129223   \n",
              "std_fit_time                                                                         1.02114   \n",
              "mean_score_time                                                                     0.026858   \n",
              "std_score_time                                                                      0.010739   \n",
              "param_randomforestregressor__max_depth                                                     6   \n",
              "param_randomforestregressor__n_estimators                                                100   \n",
              "params                                     {'randomforestregressor__max_depth': 6, 'rando...   \n",
              "split0_test_score                                                                   0.502273   \n",
              "split1_test_score                                                                    0.50739   \n",
              "split2_test_score                                                                   0.535406   \n",
              "split3_test_score                                                                   0.578856   \n",
              "split4_test_score                                                                   0.485658   \n",
              "mean_test_score                                                                     0.521917   \n",
              "std_test_score                                                                      0.032667   \n",
              "rank_test_score                                                                           18   \n",
              "\n",
              "                                                                                          2   \\\n",
              "mean_fit_time                                                                        1.24624   \n",
              "std_fit_time                                                                        0.095623   \n",
              "mean_score_time                                                                     0.022541   \n",
              "std_score_time                                                                      0.006599   \n",
              "param_randomforestregressor__max_depth                                                     4   \n",
              "param_randomforestregressor__n_estimators                                                200   \n",
              "params                                     {'randomforestregressor__max_depth': 4, 'rando...   \n",
              "split0_test_score                                                                    0.47632   \n",
              "split1_test_score                                                                   0.478511   \n",
              "split2_test_score                                                                    0.49701   \n",
              "split3_test_score                                                                   0.531361   \n",
              "split4_test_score                                                                   0.460973   \n",
              "mean_test_score                                                                     0.488835   \n",
              "std_test_score                                                                      0.024145   \n",
              "rank_test_score                                                                           19   \n",
              "\n",
              "                                                                                          1   \\\n",
              "mean_fit_time                                                                       1.039717   \n",
              "std_fit_time                                                                        0.240667   \n",
              "mean_score_time                                                                     0.017179   \n",
              "std_score_time                                                                      0.004388   \n",
              "param_randomforestregressor__max_depth                                                     4   \n",
              "param_randomforestregressor__n_estimators                                                150   \n",
              "params                                     {'randomforestregressor__max_depth': 4, 'rando...   \n",
              "split0_test_score                                                                   0.476139   \n",
              "split1_test_score                                                                   0.475863   \n",
              "split2_test_score                                                                    0.49564   \n",
              "split3_test_score                                                                   0.530864   \n",
              "split4_test_score                                                                   0.460133   \n",
              "mean_test_score                                                                     0.487728   \n",
              "std_test_score                                                                      0.024331   \n",
              "rank_test_score                                                                           20   \n",
              "\n",
              "                                                                                          0   \n",
              "mean_fit_time                                                                       0.648036  \n",
              "std_fit_time                                                                         0.09924  \n",
              "mean_score_time                                                                     0.015521  \n",
              "std_score_time                                                                      0.008501  \n",
              "param_randomforestregressor__max_depth                                                     4  \n",
              "param_randomforestregressor__n_estimators                                                100  \n",
              "params                                     {'randomforestregressor__max_depth': 4, 'rando...  \n",
              "split0_test_score                                                                   0.476145  \n",
              "split1_test_score                                                                   0.473095  \n",
              "split2_test_score                                                                   0.494724  \n",
              "split3_test_score                                                                   0.529482  \n",
              "split4_test_score                                                                    0.46122  \n",
              "mean_test_score                                                                     0.486933  \n",
              "std_test_score                                                                      0.023833  \n",
              "rank_test_score                                                                           21  \n",
              "\n",
              "[15 rows x 21 columns]"
            ],
            "text/html": [
              "\n",
              "\n",
              "  <div id=\"df-df103e3b-3082-431b-ac7d-34e38f295aac\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>11</th>\n",
              "      <th>10</th>\n",
              "      <th>8</th>\n",
              "      <th>14</th>\n",
              "      <th>7</th>\n",
              "      <th>9</th>\n",
              "      <th>13</th>\n",
              "      <th>17</th>\n",
              "      <th>12</th>\n",
              "      <th>20</th>\n",
              "      <th>...</th>\n",
              "      <th>19</th>\n",
              "      <th>16</th>\n",
              "      <th>15</th>\n",
              "      <th>18</th>\n",
              "      <th>5</th>\n",
              "      <th>4</th>\n",
              "      <th>3</th>\n",
              "      <th>2</th>\n",
              "      <th>1</th>\n",
              "      <th>0</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>mean_fit_time</th>\n",
              "      <td>1.772477</td>\n",
              "      <td>1.658683</td>\n",
              "      <td>1.854504</td>\n",
              "      <td>2.105215</td>\n",
              "      <td>1.216117</td>\n",
              "      <td>0.859069</td>\n",
              "      <td>1.353473</td>\n",
              "      <td>2.27442</td>\n",
              "      <td>1.194477</td>\n",
              "      <td>2.478599</td>\n",
              "      <td>...</td>\n",
              "      <td>1.855846</td>\n",
              "      <td>1.767274</td>\n",
              "      <td>0.988791</td>\n",
              "      <td>1.104476</td>\n",
              "      <td>2.097273</td>\n",
              "      <td>1.652839</td>\n",
              "      <td>2.129223</td>\n",
              "      <td>1.24624</td>\n",
              "      <td>1.039717</td>\n",
              "      <td>0.648036</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std_fit_time</th>\n",
              "      <td>0.159026</td>\n",
              "      <td>0.418747</td>\n",
              "      <td>0.370921</td>\n",
              "      <td>0.371806</td>\n",
              "      <td>0.129794</td>\n",
              "      <td>0.007547</td>\n",
              "      <td>0.01831</td>\n",
              "      <td>0.395051</td>\n",
              "      <td>0.178535</td>\n",
              "      <td>0.514289</td>\n",
              "      <td>...</td>\n",
              "      <td>0.266437</td>\n",
              "      <td>0.333239</td>\n",
              "      <td>0.020911</td>\n",
              "      <td>0.120326</td>\n",
              "      <td>0.998673</td>\n",
              "      <td>0.849754</td>\n",
              "      <td>1.02114</td>\n",
              "      <td>0.095623</td>\n",
              "      <td>0.240667</td>\n",
              "      <td>0.09924</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean_score_time</th>\n",
              "      <td>0.024618</td>\n",
              "      <td>0.038109</td>\n",
              "      <td>0.023637</td>\n",
              "      <td>0.026258</td>\n",
              "      <td>0.017733</td>\n",
              "      <td>0.013081</td>\n",
              "      <td>0.01916</td>\n",
              "      <td>0.047736</td>\n",
              "      <td>0.017094</td>\n",
              "      <td>0.033911</td>\n",
              "      <td>...</td>\n",
              "      <td>0.023645</td>\n",
              "      <td>0.024275</td>\n",
              "      <td>0.015792</td>\n",
              "      <td>0.014441</td>\n",
              "      <td>0.025906</td>\n",
              "      <td>0.022352</td>\n",
              "      <td>0.026858</td>\n",
              "      <td>0.022541</td>\n",
              "      <td>0.017179</td>\n",
              "      <td>0.015521</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std_score_time</th>\n",
              "      <td>0.002718</td>\n",
              "      <td>0.03276</td>\n",
              "      <td>0.003551</td>\n",
              "      <td>0.002452</td>\n",
              "      <td>0.004068</td>\n",
              "      <td>0.000783</td>\n",
              "      <td>0.000155</td>\n",
              "      <td>0.037188</td>\n",
              "      <td>0.001733</td>\n",
              "      <td>0.008052</td>\n",
              "      <td>...</td>\n",
              "      <td>0.003467</td>\n",
              "      <td>0.003911</td>\n",
              "      <td>0.002331</td>\n",
              "      <td>0.000317</td>\n",
              "      <td>0.009403</td>\n",
              "      <td>0.011631</td>\n",
              "      <td>0.010739</td>\n",
              "      <td>0.006599</td>\n",
              "      <td>0.004388</td>\n",
              "      <td>0.008501</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>param_randomforestregressor__max_depth</th>\n",
              "      <td>9</td>\n",
              "      <td>9</td>\n",
              "      <td>8</td>\n",
              "      <td>10</td>\n",
              "      <td>8</td>\n",
              "      <td>9</td>\n",
              "      <td>10</td>\n",
              "      <td>11</td>\n",
              "      <td>10</td>\n",
              "      <td>12</td>\n",
              "      <td>...</td>\n",
              "      <td>12</td>\n",
              "      <td>11</td>\n",
              "      <td>11</td>\n",
              "      <td>12</td>\n",
              "      <td>6</td>\n",
              "      <td>6</td>\n",
              "      <td>6</td>\n",
              "      <td>4</td>\n",
              "      <td>4</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>param_randomforestregressor__n_estimators</th>\n",
              "      <td>200</td>\n",
              "      <td>150</td>\n",
              "      <td>200</td>\n",
              "      <td>200</td>\n",
              "      <td>150</td>\n",
              "      <td>100</td>\n",
              "      <td>150</td>\n",
              "      <td>200</td>\n",
              "      <td>100</td>\n",
              "      <td>200</td>\n",
              "      <td>...</td>\n",
              "      <td>150</td>\n",
              "      <td>150</td>\n",
              "      <td>100</td>\n",
              "      <td>100</td>\n",
              "      <td>200</td>\n",
              "      <td>150</td>\n",
              "      <td>100</td>\n",
              "      <td>200</td>\n",
              "      <td>150</td>\n",
              "      <td>100</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>params</th>\n",
              "      <td>{'randomforestregressor__max_depth': 9, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 9, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 8, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 10, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 8, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 9, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 10, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 11, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 10, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 12, 'rand...</td>\n",
              "      <td>...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 12, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 11, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 11, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 12, 'rand...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 6, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 6, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 6, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 4, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 4, 'rando...</td>\n",
              "      <td>{'randomforestregressor__max_depth': 4, 'rando...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>split0_test_score</th>\n",
              "      <td>0.503827</td>\n",
              "      <td>0.501659</td>\n",
              "      <td>0.504933</td>\n",
              "      <td>0.501086</td>\n",
              "      <td>0.50223</td>\n",
              "      <td>0.503754</td>\n",
              "      <td>0.498078</td>\n",
              "      <td>0.500195</td>\n",
              "      <td>0.502286</td>\n",
              "      <td>0.498929</td>\n",
              "      <td>...</td>\n",
              "      <td>0.495426</td>\n",
              "      <td>0.498455</td>\n",
              "      <td>0.502124</td>\n",
              "      <td>0.499392</td>\n",
              "      <td>0.501961</td>\n",
              "      <td>0.500941</td>\n",
              "      <td>0.502273</td>\n",
              "      <td>0.47632</td>\n",
              "      <td>0.476139</td>\n",
              "      <td>0.476145</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>split1_test_score</th>\n",
              "      <td>0.519458</td>\n",
              "      <td>0.519227</td>\n",
              "      <td>0.518234</td>\n",
              "      <td>0.517636</td>\n",
              "      <td>0.516366</td>\n",
              "      <td>0.518964</td>\n",
              "      <td>0.517995</td>\n",
              "      <td>0.516487</td>\n",
              "      <td>0.520543</td>\n",
              "      <td>0.516931</td>\n",
              "      <td>...</td>\n",
              "      <td>0.516912</td>\n",
              "      <td>0.515104</td>\n",
              "      <td>0.515076</td>\n",
              "      <td>0.516747</td>\n",
              "      <td>0.511494</td>\n",
              "      <td>0.509771</td>\n",
              "      <td>0.50739</td>\n",
              "      <td>0.478511</td>\n",
              "      <td>0.475863</td>\n",
              "      <td>0.473095</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>split2_test_score</th>\n",
              "      <td>0.545769</td>\n",
              "      <td>0.545998</td>\n",
              "      <td>0.542334</td>\n",
              "      <td>0.541099</td>\n",
              "      <td>0.543438</td>\n",
              "      <td>0.545264</td>\n",
              "      <td>0.542413</td>\n",
              "      <td>0.541791</td>\n",
              "      <td>0.541169</td>\n",
              "      <td>0.543165</td>\n",
              "      <td>...</td>\n",
              "      <td>0.544028</td>\n",
              "      <td>0.542293</td>\n",
              "      <td>0.541841</td>\n",
              "      <td>0.542933</td>\n",
              "      <td>0.534704</td>\n",
              "      <td>0.535001</td>\n",
              "      <td>0.535406</td>\n",
              "      <td>0.49701</td>\n",
              "      <td>0.49564</td>\n",
              "      <td>0.494724</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>split3_test_score</th>\n",
              "      <td>0.598765</td>\n",
              "      <td>0.598973</td>\n",
              "      <td>0.594645</td>\n",
              "      <td>0.599367</td>\n",
              "      <td>0.594705</td>\n",
              "      <td>0.597236</td>\n",
              "      <td>0.599075</td>\n",
              "      <td>0.599145</td>\n",
              "      <td>0.59726</td>\n",
              "      <td>0.598985</td>\n",
              "      <td>...</td>\n",
              "      <td>0.598711</td>\n",
              "      <td>0.599372</td>\n",
              "      <td>0.59732</td>\n",
              "      <td>0.59722</td>\n",
              "      <td>0.579641</td>\n",
              "      <td>0.580584</td>\n",
              "      <td>0.578856</td>\n",
              "      <td>0.531361</td>\n",
              "      <td>0.530864</td>\n",
              "      <td>0.529482</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>split4_test_score</th>\n",
              "      <td>0.494039</td>\n",
              "      <td>0.493196</td>\n",
              "      <td>0.497436</td>\n",
              "      <td>0.495432</td>\n",
              "      <td>0.497197</td>\n",
              "      <td>0.48789</td>\n",
              "      <td>0.494372</td>\n",
              "      <td>0.492754</td>\n",
              "      <td>0.488742</td>\n",
              "      <td>0.491382</td>\n",
              "      <td>...</td>\n",
              "      <td>0.491744</td>\n",
              "      <td>0.490114</td>\n",
              "      <td>0.482485</td>\n",
              "      <td>0.481244</td>\n",
              "      <td>0.488873</td>\n",
              "      <td>0.487162</td>\n",
              "      <td>0.485658</td>\n",
              "      <td>0.460973</td>\n",
              "      <td>0.460133</td>\n",
              "      <td>0.46122</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean_test_score</th>\n",
              "      <td>0.532371</td>\n",
              "      <td>0.531811</td>\n",
              "      <td>0.531516</td>\n",
              "      <td>0.530924</td>\n",
              "      <td>0.530787</td>\n",
              "      <td>0.530621</td>\n",
              "      <td>0.530386</td>\n",
              "      <td>0.530074</td>\n",
              "      <td>0.53</td>\n",
              "      <td>0.529878</td>\n",
              "      <td>...</td>\n",
              "      <td>0.529364</td>\n",
              "      <td>0.529068</td>\n",
              "      <td>0.527769</td>\n",
              "      <td>0.527507</td>\n",
              "      <td>0.523334</td>\n",
              "      <td>0.522692</td>\n",
              "      <td>0.521917</td>\n",
              "      <td>0.488835</td>\n",
              "      <td>0.487728</td>\n",
              "      <td>0.486933</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std_test_score</th>\n",
              "      <td>0.037519</td>\n",
              "      <td>0.038133</td>\n",
              "      <td>0.035062</td>\n",
              "      <td>0.037721</td>\n",
              "      <td>0.03577</td>\n",
              "      <td>0.038303</td>\n",
              "      <td>0.038359</td>\n",
              "      <td>0.038414</td>\n",
              "      <td>0.037969</td>\n",
              "      <td>0.038884</td>\n",
              "      <td>...</td>\n",
              "      <td>0.03936</td>\n",
              "      <td>0.039414</td>\n",
              "      <td>0.039761</td>\n",
              "      <td>0.040359</td>\n",
              "      <td>0.031888</td>\n",
              "      <td>0.03288</td>\n",
              "      <td>0.032667</td>\n",
              "      <td>0.024145</td>\n",
              "      <td>0.024331</td>\n",
              "      <td>0.023833</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>rank_test_score</th>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>3</td>\n",
              "      <td>4</td>\n",
              "      <td>5</td>\n",
              "      <td>6</td>\n",
              "      <td>7</td>\n",
              "      <td>8</td>\n",
              "      <td>9</td>\n",
              "      <td>10</td>\n",
              "      <td>...</td>\n",
              "      <td>12</td>\n",
              "      <td>13</td>\n",
              "      <td>14</td>\n",
              "      <td>15</td>\n",
              "      <td>16</td>\n",
              "      <td>17</td>\n",
              "      <td>18</td>\n",
              "      <td>19</td>\n",
              "      <td>20</td>\n",
              "      <td>21</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>15 rows × 21 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-df103e3b-3082-431b-ac7d-34e38f295aac')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "\n",
              "\n",
              "\n",
              "    <div id=\"df-42f51907-64af-4f42-8b11-f08469007c83\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-42f51907-64af-4f42-8b11-f08469007c83')\"\n",
              "              title=\"Suggest charts.\"\n",
              "              style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "    </div>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "    background-color: #E8F0FE;\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: #1967D2;\n",
              "    height: 32px;\n",
              "    padding: 0 0 0 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: #E2EBFA;\n",
              "    box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: #174EA6;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "    background-color: #3B4455;\n",
              "    fill: #D2E3FC;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart:hover {\n",
              "    background-color: #434B5C;\n",
              "    box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "    filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "    fill: #FFFFFF;\n",
              "  }\n",
              "</style>\n",
              "\n",
              "    <script>\n",
              "      async function quickchart(key) {\n",
              "        const containerElement = document.querySelector('#' + key);\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      }\n",
              "    </script>\n",
              "\n",
              "      <script>\n",
              "\n",
              "function displayQuickchartButton(domScope) {\n",
              "  let quickchartButtonEl =\n",
              "    domScope.querySelector('#df-42f51907-64af-4f42-8b11-f08469007c83 button.colab-df-quickchart');\n",
              "  quickchartButtonEl.style.display =\n",
              "    google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "}\n",
              "\n",
              "        displayQuickchartButton(document);\n",
              "      </script>\n",
              "      <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-df103e3b-3082-431b-ac7d-34e38f295aac button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-df103e3b-3082-431b-ac7d-34e38f295aac');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 54
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "xgb_grid = XGBRegressor(n_estimators=10000,\n",
        "                        max_depth=5,\n",
        "                        learning_rate=0.01,\n",
        "                        n_jobs=5,\n",
        "                        early_stopping_rounds=30,\n",
        "                        random_state=42)\n",
        "print(xgb_grid)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KTON0YqsxOIv",
        "outputId": "4ce051f4-3c0c-43e1-e1e1-9ee81c9f5159"
      },
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
            "             colsample_bylevel=None, colsample_bynode=None,\n",
            "             colsample_bytree=None, early_stopping_rounds=50,\n",
            "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
            "             gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
            "             interaction_constraints=None, learning_rate=0.01, max_bin=None,\n",
            "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
            "             max_delta_step=None, max_depth=5, max_leaves=None,\n",
            "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
            "             n_estimators=10000, n_jobs=5, num_parallel_tree=None,\n",
            "             predictor=None, random_state=42, ...)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "xgb_params={ 'max_depth':[2, 4, 6, 8,9, 10],'learning_rate':[0.03, 0.05, 0.07]}"
      ],
      "metadata": {
        "id": "6SE8tgoc00qx"
      },
      "execution_count": 58,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "xgb_gridCV = GridSearchCV(xgb_grid, xgb_params, scoring='r2', cv=5, verbose=3)\n",
        "xgb_gridCV.fit(x_train4, y_train4)\n",
        "# Must have at least 1 validation dataset for early stopping."
      ],
      "metadata": {
        "id": "xm-2-6mX0kJf"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(\"최적 하이퍼파라미터: \", xgb_gridCV.best_params_)\n",
        "print(\"최적 AUC: \", xgb_gridCV.best_score_)"
      ],
      "metadata": {
        "id": "2l8W44YP3ypy"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **3-2. Randomized SearchCV**"
      ],
      "metadata": {
        "id": "vkCjlBVR5voE"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "rr_params = {\n",
        "    'n_estimators' : [100, 150, 200],\n",
        "    'max_depth': [4, 6, 8, 9, 10, 11, 12]\n",
        "}"
      ],
      "metadata": {
        "id": "F9koFRsL52_i"
      },
      "execution_count": 67,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "rf_rs = RandomForestRegressor(max_depth=2,\n",
        "                              random_state=42,\n",
        "                              n_jobs=1)"
      ],
      "metadata": {
        "id": "r0-8PyIfVpRb"
      },
      "execution_count": 63,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "rsCV = RandomizedSearchCV(\n",
        "    rf_rs,\n",
        "    rr_params,\n",
        "    scoring='r2',\n",
        "    n_iter=10,\n",
        "    cv=5,\n",
        "    verbose=3,\n",
        "    random_state=42\n",
        ")\n",
        "\n",
        "rsCV.fit(x_train4, y_train4)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "KhoqvwTXV8Z0",
        "outputId": "6f1e667c-5a21-4125-d390-2d1ef96e6791"
      },
      "execution_count": 69,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Fitting 5 folds for each of 10 candidates, totalling 50 fits\n",
            "[CV 1/5] END .....max_depth=4, n_estimators=100;, score=0.476 total time=   1.5s\n",
            "[CV 2/5] END .....max_depth=4, n_estimators=100;, score=0.473 total time=   0.7s\n",
            "[CV 3/5] END .....max_depth=4, n_estimators=100;, score=0.495 total time=   0.7s\n",
            "[CV 4/5] END .....max_depth=4, n_estimators=100;, score=0.529 total time=   0.5s\n",
            "[CV 5/5] END .....max_depth=4, n_estimators=100;, score=0.461 total time=   0.5s\n",
            "[CV 1/5] END ....max_depth=11, n_estimators=200;, score=0.500 total time=   2.0s\n",
            "[CV 2/5] END ....max_depth=11, n_estimators=200;, score=0.516 total time=   2.0s\n",
            "[CV 3/5] END ....max_depth=11, n_estimators=200;, score=0.542 total time=   1.9s\n",
            "[CV 4/5] END ....max_depth=11, n_estimators=200;, score=0.599 total time=   2.1s\n",
            "[CV 5/5] END ....max_depth=11, n_estimators=200;, score=0.493 total time=   2.9s\n",
            "[CV 1/5] END ....max_depth=11, n_estimators=100;, score=0.502 total time=   1.4s\n",
            "[CV 2/5] END ....max_depth=11, n_estimators=100;, score=0.515 total time=   1.0s\n",
            "[CV 3/5] END ....max_depth=11, n_estimators=100;, score=0.542 total time=   1.0s\n",
            "[CV 4/5] END ....max_depth=11, n_estimators=100;, score=0.597 total time=   1.0s\n",
            "[CV 5/5] END ....max_depth=11, n_estimators=100;, score=0.482 total time=   1.1s\n",
            "[CV 1/5] END .....max_depth=4, n_estimators=150;, score=0.476 total time=   0.7s\n",
            "[CV 2/5] END .....max_depth=4, n_estimators=150;, score=0.476 total time=   0.7s\n",
            "[CV 3/5] END .....max_depth=4, n_estimators=150;, score=0.496 total time=   0.7s\n",
            "[CV 4/5] END .....max_depth=4, n_estimators=150;, score=0.531 total time=   0.7s\n",
            "[CV 5/5] END .....max_depth=4, n_estimators=150;, score=0.460 total time=   0.7s\n",
            "[CV 1/5] END .....max_depth=8, n_estimators=200;, score=0.505 total time=   1.6s\n",
            "[CV 2/5] END .....max_depth=8, n_estimators=200;, score=0.518 total time=   2.0s\n",
            "[CV 3/5] END .....max_depth=8, n_estimators=200;, score=0.542 total time=   2.3s\n",
            "[CV 4/5] END .....max_depth=8, n_estimators=200;, score=0.595 total time=   1.8s\n",
            "[CV 5/5] END .....max_depth=8, n_estimators=200;, score=0.497 total time=   1.5s\n",
            "[CV 1/5] END .....max_depth=6, n_estimators=200;, score=0.502 total time=   1.3s\n",
            "[CV 2/5] END .....max_depth=6, n_estimators=200;, score=0.511 total time=   1.3s\n",
            "[CV 3/5] END .....max_depth=6, n_estimators=200;, score=0.535 total time=   1.3s\n",
            "[CV 4/5] END .....max_depth=6, n_estimators=200;, score=0.580 total time=   1.5s\n",
            "[CV 5/5] END .....max_depth=6, n_estimators=200;, score=0.489 total time=   1.9s\n",
            "[CV 1/5] END .....max_depth=9, n_estimators=200;, score=0.504 total time=   2.7s\n",
            "[CV 2/5] END .....max_depth=9, n_estimators=200;, score=0.519 total time=   2.7s\n",
            "[CV 3/5] END .....max_depth=9, n_estimators=200;, score=0.546 total time=   2.0s\n",
            "[CV 4/5] END .....max_depth=9, n_estimators=200;, score=0.599 total time=   1.7s\n",
            "[CV 5/5] END .....max_depth=9, n_estimators=200;, score=0.494 total time=   1.7s\n",
            "[CV 1/5] END .....max_depth=6, n_estimators=100;, score=0.502 total time=   0.6s\n",
            "[CV 2/5] END .....max_depth=6, n_estimators=100;, score=0.507 total time=   0.6s\n",
            "[CV 3/5] END .....max_depth=6, n_estimators=100;, score=0.535 total time=   0.6s\n",
            "[CV 4/5] END .....max_depth=6, n_estimators=100;, score=0.579 total time=   0.6s\n",
            "[CV 5/5] END .....max_depth=6, n_estimators=100;, score=0.486 total time=   0.6s\n",
            "[CV 1/5] END ....max_depth=12, n_estimators=100;, score=0.499 total time=   1.0s\n",
            "[CV 2/5] END ....max_depth=12, n_estimators=100;, score=0.517 total time=   1.1s\n",
            "[CV 3/5] END ....max_depth=12, n_estimators=100;, score=0.543 total time=   1.5s\n",
            "[CV 4/5] END ....max_depth=12, n_estimators=100;, score=0.597 total time=   1.6s\n",
            "[CV 5/5] END ....max_depth=12, n_estimators=100;, score=0.481 total time=   1.5s\n",
            "[CV 1/5] END ....max_depth=11, n_estimators=150;, score=0.498 total time=   1.5s\n",
            "[CV 2/5] END ....max_depth=11, n_estimators=150;, score=0.515 total time=   1.5s\n",
            "[CV 3/5] END ....max_depth=11, n_estimators=150;, score=0.542 total time=   1.5s\n",
            "[CV 4/5] END ....max_depth=11, n_estimators=150;, score=0.599 total time=   1.5s\n",
            "[CV 5/5] END ....max_depth=11, n_estimators=150;, score=0.490 total time=   1.5s\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomizedSearchCV(cv=5,\n",
              "                   estimator=RandomForestRegressor(max_depth=2, n_jobs=1,\n",
              "                                                   random_state=42),\n",
              "                   param_distributions={'max_depth': [4, 6, 8, 9, 10, 11, 12],\n",
              "                                        'n_estimators': [100, 150, 200]},\n",
              "                   random_state=42, scoring='r2', verbose=3)"
            ],
            "text/html": [
              "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomizedSearchCV(cv=5,\n",
              "                   estimator=RandomForestRegressor(max_depth=2, n_jobs=1,\n",
              "                                                   random_state=42),\n",
              "                   param_distributions={&#x27;max_depth&#x27;: [4, 6, 8, 9, 10, 11, 12],\n",
              "                                        &#x27;n_estimators&#x27;: [100, 150, 200]},\n",
              "                   random_state=42, scoring=&#x27;r2&#x27;, verbose=3)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomizedSearchCV</label><div class=\"sk-toggleable__content\"><pre>RandomizedSearchCV(cv=5,\n",
              "                   estimator=RandomForestRegressor(max_depth=2, n_jobs=1,\n",
              "                                                   random_state=42),\n",
              "                   param_distributions={&#x27;max_depth&#x27;: [4, 6, 8, 9, 10, 11, 12],\n",
              "                                        &#x27;n_estimators&#x27;: [100, 150, 200]},\n",
              "                   random_state=42, scoring=&#x27;r2&#x27;, verbose=3)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(max_depth=2, n_jobs=1, random_state=42)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(max_depth=2, n_jobs=1, random_state=42)</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 69
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(\"최적 하이퍼파라미터: \", rsCV.best_params_)\n",
        "print(\"최적 AUC: \", rsCV.best_score_)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "KWUhiBIvWngK",
        "outputId": "df15eb61-510f-4bc5-f142-f9c5c10ebe6b"
      },
      "execution_count": 70,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "최적 하이퍼파라미터:  {'n_estimators': 200, 'max_depth': 9}\n",
            "최적 AUC:  0.5323714661998805\n"
          ]
        }
      ]
    }
  ]
}