Very_simple_titanic_ML_model.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Very simple titanic ML model.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyN5QPA/1Bq6k83h/3cm26m1",
      "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/victoraccete/omdena_streamlit_workshop/blob/main/Very_simple_titanic_ML_model.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DplvHh55Dx4q"
      },
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.model_selection import cross_val_score\n",
        "from joblib import dump, load"
      ],
      "execution_count": 47,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "GcyPzw5bK5b4"
      },
      "source": [
        "# Dataset:\n",
        "Full version: vhttps://www.kaggle.com/c/titanic/data?select=train.csv  \n",
        "Reduced version (the one we're using here): https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/problem12.html\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 419
        },
        "id": "m-p_bSa8JQ9J",
        "outputId": "40ef1a3b-727f-46df-c3b2-9ecd51b11836"
      },
      "source": [
        "titanic = pd.read_csv(\"https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/stuff/titanic.csv\")\n",
        "titanic = titanic.drop(columns=\"Name\")\n",
        "titanic"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>Siblings/Spouses Aboard</th>\n",
              "      <th>Parents/Children Aboard</th>\n",
              "      <th>Fare</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>7.2500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>71.2833</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>7.9250</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>female</td>\n",
              "      <td>35.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>53.1000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>male</td>\n",
              "      <td>35.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>8.0500</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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>882</th>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>male</td>\n",
              "      <td>27.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>13.0000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>883</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>female</td>\n",
              "      <td>19.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>30.0000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>884</th>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>female</td>\n",
              "      <td>7.0</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>23.4500</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>885</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>male</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>30.0000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>886</th>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>male</td>\n",
              "      <td>32.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>7.7500</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>887 rows × 7 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     Survived  Pclass  ... Parents/Children Aboard     Fare\n",
              "0           0       3  ...                       0   7.2500\n",
              "1           1       1  ...                       0  71.2833\n",
              "2           1       3  ...                       0   7.9250\n",
              "3           1       1  ...                       0  53.1000\n",
              "4           0       3  ...                       0   8.0500\n",
              "..        ...     ...  ...                     ...      ...\n",
              "882         0       2  ...                       0  13.0000\n",
              "883         1       1  ...                       0  30.0000\n",
              "884         0       3  ...                       2  23.4500\n",
              "885         1       1  ...                       0  30.0000\n",
              "886         0       3  ...                       0   7.7500\n",
              "\n",
              "[887 rows x 7 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4oGzj8w3NW1W",
        "outputId": "fc551303-5c9e-42da-ebc2-9779326462a4"
      },
      "source": [
        "titanic['Parents/Children Aboard'].unique()"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0, 1, 2, 5, 3, 4, 6])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "vhXuQ59HKhsS",
        "outputId": "cc151923-1899-41a5-d134-ae3227727984"
      },
      "source": [
        "titanic = pd.get_dummies(titanic)\n",
        "titanic.head()"
      ],
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Age</th>\n",
              "      <th>Siblings/Spouses Aboard</th>\n",
              "      <th>Parents/Children Aboard</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Sex_female</th>\n",
              "      <th>Sex_male</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>35.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>53.1000</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>35.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>8.0500</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Survived  Pclass   Age  ...     Fare  Sex_female  Sex_male\n",
              "0         0       3  22.0  ...   7.2500           0         1\n",
              "1         1       1  38.0  ...  71.2833           1         0\n",
              "2         1       3  26.0  ...   7.9250           1         0\n",
              "3         1       1  35.0  ...  53.1000           1         0\n",
              "4         0       3  35.0  ...   8.0500           0         1\n",
              "\n",
              "[5 rows x 8 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "id": "zMNcT_UrNAS6",
        "outputId": "eddd10f5-b3a5-4525-89fc-b94af13522dd"
      },
      "source": [
        "inputs = titanic.iloc[:, 1:]\n",
        "inputs.head()"
      ],
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Pclass</th>\n",
              "      <th>Age</th>\n",
              "      <th>Siblings/Spouses Aboard</th>\n",
              "      <th>Parents/Children Aboard</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Sex_female</th>\n",
              "      <th>Sex_male</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>3</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>35.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>53.1000</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>3</td>\n",
              "      <td>35.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>8.0500</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   Pclass   Age  Siblings/Spouses Aboard  ...     Fare  Sex_female  Sex_male\n",
              "0       3  22.0                        1  ...   7.2500           0         1\n",
              "1       1  38.0                        1  ...  71.2833           1         0\n",
              "2       3  26.0                        0  ...   7.9250           1         0\n",
              "3       1  35.0                        1  ...  53.1000           1         0\n",
              "4       3  35.0                        0  ...   8.0500           0         1\n",
              "\n",
              "[5 rows x 7 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Qm-VUhD1Uvag",
        "outputId": "0424af6a-bb70-41d5-c7d8-4a24ebfc2a98"
      },
      "source": [
        "labels = titanic.iloc[:, 0]\n",
        "labels.head()"
      ],
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    0\n",
              "1    1\n",
              "2    1\n",
              "3    1\n",
              "4    0\n",
              "Name: Survived, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 31
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "soyobFkGU2c9",
        "outputId": "991dca35-d948-4187-fbfa-003b50b0a666"
      },
      "source": [
        "rf_clf = RandomForestClassifier(n_estimators=50)\n",
        "rf_clf.fit(inputs.values, labels.values)\n",
        "scores = cross_val_score(rf_clf, inputs, labels, cv=20)\n",
        "scores"
      ],
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.68888889, 0.82222222, 0.71111111, 0.8       , 0.75555556,\n",
              "       0.73333333, 0.88888889, 0.81818182, 0.93181818, 0.86363636,\n",
              "       0.90909091, 0.77272727, 0.77272727, 0.90909091, 0.77272727,\n",
              "       0.77272727, 0.79545455, 0.84090909, 0.81818182, 0.93181818])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 32
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mOpkafSSXbYi",
        "outputId": "fd9c7b6c-51a9-4657-907f-f357e4d419de"
      },
      "source": [
        "scores.mean()"
      ],
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.8154545454545454"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ORB7_KIuXoEl",
        "outputId": "ec9b55a6-d172-4b7f-aec8-b58d232bfcae"
      },
      "source": [
        "rf_clf.predict(inputs.iloc[1:2, :].values)"
      ],
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sEdTmT4CXvXE",
        "outputId": "d5ed8659-87a3-4b91-8517-93cfc7ffe2f7"
      },
      "source": [
        "dump(rf_clf, 'rf.joblib')"
      ],
      "execution_count": 50,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['rf.joblib']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-hTRAXsrY3ev",
        "outputId": "1e9292fe-dc2f-4831-a11c-7810af661f9b"
      },
      "source": [
        "clf = load('rf.joblib')\n",
        "clf.predict(inputs.iloc[1:2, :].values)"
      ],
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U5dGJXHkZ0Ki"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}