Resampling.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mWARNING: The directory '/home/jovyan/.cache/pip/http' or its parent directory is not owned by the current user and the cache has been disabled. Please check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.\u001b[0m\n",
      "\u001b[33mWARNING: The directory '/home/jovyan/.cache/pip' or its parent directory is not owned by the current user and caching wheels has been disabled. check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.\u001b[0m\n",
      "Requirement already satisfied: numpy==1.19.5 in /opt/conda/lib/python3.7/site-packages (1.19.5)\n"
     ]
    }
   ],
   "source": [
    "!pip install numpy==1.19.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.19.5\n"
     ]
    }
   ],
   "source": [
    "print(np.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "bankData = pd.read_csv(\"https://raw.githubusercontent.com/PacktWorkshops/The-Data-Science-Workshop/master/Chapter13/Dataset/bank-full.csv\",sep=\";\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 45211 entries, 0 to 45210\n",
      "Data columns (total 17 columns):\n",
      "age          45211 non-null int64\n",
      "job          45211 non-null object\n",
      "marital      45211 non-null object\n",
      "education    45211 non-null object\n",
      "default      45211 non-null object\n",
      "balance      45211 non-null int64\n",
      "housing      45211 non-null object\n",
      "loan         45211 non-null object\n",
      "contact      45211 non-null object\n",
      "day          45211 non-null int64\n",
      "month        45211 non-null object\n",
      "duration     45211 non-null int64\n",
      "campaign     45211 non-null int64\n",
      "pdays        45211 non-null int64\n",
      "previous     45211 non-null int64\n",
      "poutcome     45211 non-null object\n",
      "y            45211 non-null object\n",
      "dtypes: int64(7), object(10)\n",
      "memory usage: 5.9+ MB\n"
     ]
    }
   ],
   "source": [
    "bankData.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "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>age</th>\n",
       "      <th>job</th>\n",
       "      <th>marital</th>\n",
       "      <th>education</th>\n",
       "      <th>default</th>\n",
       "      <th>balance</th>\n",
       "      <th>housing</th>\n",
       "      <th>loan</th>\n",
       "      <th>contact</th>\n",
       "      <th>day</th>\n",
       "      <th>month</th>\n",
       "      <th>duration</th>\n",
       "      <th>campaign</th>\n",
       "      <th>pdays</th>\n",
       "      <th>previous</th>\n",
       "      <th>poutcome</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>58</td>\n",
       "      <td>management</td>\n",
       "      <td>married</td>\n",
       "      <td>tertiary</td>\n",
       "      <td>no</td>\n",
       "      <td>2143</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>261</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>44</td>\n",
       "      <td>technician</td>\n",
       "      <td>single</td>\n",
       "      <td>secondary</td>\n",
       "      <td>no</td>\n",
       "      <td>29</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>151</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>33</td>\n",
       "      <td>entrepreneur</td>\n",
       "      <td>married</td>\n",
       "      <td>secondary</td>\n",
       "      <td>no</td>\n",
       "      <td>2</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>76</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>47</td>\n",
       "      <td>blue-collar</td>\n",
       "      <td>married</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>1506</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>92</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>33</td>\n",
       "      <td>unknown</td>\n",
       "      <td>single</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>1</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>198</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age           job  marital  education default  balance housing loan  \\\n",
       "0   58    management  married   tertiary      no     2143     yes   no   \n",
       "1   44    technician   single  secondary      no       29     yes   no   \n",
       "2   33  entrepreneur  married  secondary      no        2     yes  yes   \n",
       "3   47   blue-collar  married    unknown      no     1506     yes   no   \n",
       "4   33       unknown   single    unknown      no        1      no   no   \n",
       "\n",
       "   contact  day month  duration  campaign  pdays  previous poutcome   y  \n",
       "0  unknown    5   may       261         1     -1         0  unknown  no  \n",
       "1  unknown    5   may       151         1     -1         0  unknown  no  \n",
       "2  unknown    5   may        76         1     -1         0  unknown  no  \n",
       "3  unknown    5   may        92         1     -1         0  unknown  no  \n",
       "4  unknown    5   may       198         1     -1         0  unknown  no  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age           int64\n",
       "job          object\n",
       "marital      object\n",
       "education    object\n",
       "default      object\n",
       "balance       int64\n",
       "housing      object\n",
       "loan         object\n",
       "contact      object\n",
       "day           int64\n",
       "month        object\n",
       "duration      int64\n",
       "campaign      int64\n",
       "pdays         int64\n",
       "previous      int64\n",
       "poutcome     object\n",
       "y            object\n",
       "dtype: object"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bankData.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import RobustScaler\n",
    "rob_scaler = RobustScaler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Converting each of the columns to scaled version\n",
    "bankData['ageScaled'] = rob_scaler.fit_transform\\\n",
    "                        (bankData['age'].values.reshape(-1,1))\n",
    "bankData['balScaled'] = rob_scaler.fit_transform\\\n",
    "                        (bankData['balance']\\\n",
    "                         .values.reshape(-1,1))\n",
    "bankData['durScaled'] = rob_scaler.fit_transform\\\n",
    "                        (bankData['duration']\\\n",
    "                         .values.reshape(-1,1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Dropping the original columns\n",
    "bankData.drop(['age','balance','duration'], \\\n",
    "              axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "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>job</th>\n",
       "      <th>marital</th>\n",
       "      <th>education</th>\n",
       "      <th>default</th>\n",
       "      <th>housing</th>\n",
       "      <th>loan</th>\n",
       "      <th>contact</th>\n",
       "      <th>day</th>\n",
       "      <th>month</th>\n",
       "      <th>campaign</th>\n",
       "      <th>pdays</th>\n",
       "      <th>previous</th>\n",
       "      <th>poutcome</th>\n",
       "      <th>y</th>\n",
       "      <th>ageScaled</th>\n",
       "      <th>balScaled</th>\n",
       "      <th>durScaled</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>management</td>\n",
       "      <td>married</td>\n",
       "      <td>tertiary</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>1.266667</td>\n",
       "      <td>1.250000</td>\n",
       "      <td>0.375000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>technician</td>\n",
       "      <td>single</td>\n",
       "      <td>secondary</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>-0.308997</td>\n",
       "      <td>-0.134259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>entrepreneur</td>\n",
       "      <td>married</td>\n",
       "      <td>secondary</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>-0.400000</td>\n",
       "      <td>-0.328909</td>\n",
       "      <td>-0.481481</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>blue-collar</td>\n",
       "      <td>married</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>yes</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>0.533333</td>\n",
       "      <td>0.780236</td>\n",
       "      <td>-0.407407</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>unknown</td>\n",
       "      <td>single</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>no</td>\n",
       "      <td>unknown</td>\n",
       "      <td>5</td>\n",
       "      <td>may</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>unknown</td>\n",
       "      <td>no</td>\n",
       "      <td>-0.400000</td>\n",
       "      <td>-0.329646</td>\n",
       "      <td>0.083333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            job  marital  education default housing loan  contact  day month  \\\n",
       "0    management  married   tertiary      no     yes   no  unknown    5   may   \n",
       "1    technician   single  secondary      no     yes   no  unknown    5   may   \n",
       "2  entrepreneur  married  secondary      no     yes  yes  unknown    5   may   \n",
       "3   blue-collar  married    unknown      no     yes   no  unknown    5   may   \n",
       "4       unknown   single    unknown      no      no   no  unknown    5   may   \n",
       "\n",
       "   campaign  pdays  previous poutcome   y  ageScaled  balScaled  durScaled  \n",
       "0         1     -1         0  unknown  no   1.266667   1.250000   0.375000  \n",
       "1         1     -1         0  unknown  no   0.333333  -0.308997  -0.134259  \n",
       "2         1     -1         0  unknown  no  -0.400000  -0.328909  -0.481481  \n",
       "3         1     -1         0  unknown  no   0.533333   0.780236  -0.407407  \n",
       "4         1     -1         0  unknown  no  -0.400000  -0.329646   0.083333  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "bankCat = pd.get_dummies(bankData[['job','marital','education','default','housing','loan','contact','month','poutcome']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "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>job_admin.</th>\n",
       "      <th>job_blue-collar</th>\n",
       "      <th>job_entrepreneur</th>\n",
       "      <th>job_housemaid</th>\n",
       "      <th>job_management</th>\n",
       "      <th>job_retired</th>\n",
       "      <th>job_self-employed</th>\n",
       "      <th>job_services</th>\n",
       "      <th>job_student</th>\n",
       "      <th>job_technician</th>\n",
       "      <th>...</th>\n",
       "      <th>month_jun</th>\n",
       "      <th>month_mar</th>\n",
       "      <th>month_may</th>\n",
       "      <th>month_nov</th>\n",
       "      <th>month_oct</th>\n",
       "      <th>month_sep</th>\n",
       "      <th>poutcome_failure</th>\n",
       "      <th>poutcome_other</th>\n",
       "      <th>poutcome_success</th>\n",
       "      <th>poutcome_unknown</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 44 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   job_admin.  job_blue-collar  job_entrepreneur  job_housemaid  \\\n",
       "0           0                0                 0              0   \n",
       "1           0                0                 0              0   \n",
       "2           0                0                 1              0   \n",
       "3           0                1                 0              0   \n",
       "4           0                0                 0              0   \n",
       "\n",
       "   job_management  job_retired  job_self-employed  job_services  job_student  \\\n",
       "0               1            0                  0             0            0   \n",
       "1               0            0                  0             0            0   \n",
       "2               0            0                  0             0            0   \n",
       "3               0            0                  0             0            0   \n",
       "4               0            0                  0             0            0   \n",
       "\n",
       "   job_technician  ...  month_jun  month_mar  month_may  month_nov  month_oct  \\\n",
       "0               0  ...          0          0          1          0          0   \n",
       "1               1  ...          0          0          1          0          0   \n",
       "2               0  ...          0          0          1          0          0   \n",
       "3               0  ...          0          0          1          0          0   \n",
       "4               0  ...          0          0          1          0          0   \n",
       "\n",
       "   month_sep  poutcome_failure  poutcome_other  poutcome_success  \\\n",
       "0          0                 0               0                 0   \n",
       "1          0                 0               0                 0   \n",
       "2          0                 0               0                 0   \n",
       "3          0                 0               0                 0   \n",
       "4          0                 0               0                 0   \n",
       "\n",
       "   poutcome_unknown  \n",
       "0                 1  \n",
       "1                 1  \n",
       "2                 1  \n",
       "3                 1  \n",
       "4                 1  \n",
       "\n",
       "[5 rows x 44 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bankCat.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Numeric Rows and cols:  (45211, 7)\n",
      "Categorical Rows & Cols:  (45211, 44)\n"
     ]
    }
   ],
   "source": [
    "bankNum = bankData[['ageScaled','balScaled','day',\\\n",
    "                    'durScaled','campaign','pdays','previous']]\n",
    "print(\"Numeric Rows and cols: \", bankNum.shape)\n",
    "print(\"Categorical Rows & Cols: \", bankCat.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(45211, 51)\n",
      "(45211,)\n"
     ]
    },
    {
     "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>job_admin.</th>\n",
       "      <th>job_blue-collar</th>\n",
       "      <th>job_entrepreneur</th>\n",
       "      <th>job_housemaid</th>\n",
       "      <th>job_management</th>\n",
       "      <th>job_retired</th>\n",
       "      <th>job_self-employed</th>\n",
       "      <th>job_services</th>\n",
       "      <th>job_student</th>\n",
       "      <th>job_technician</th>\n",
       "      <th>...</th>\n",
       "      <th>poutcome_other</th>\n",
       "      <th>poutcome_success</th>\n",
       "      <th>poutcome_unknown</th>\n",
       "      <th>ageScaled</th>\n",
       "      <th>balScaled</th>\n",
       "      <th>day</th>\n",
       "      <th>durScaled</th>\n",
       "      <th>campaign</th>\n",
       "      <th>pdays</th>\n",
       "      <th>previous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.266667</td>\n",
       "      <td>1.250000</td>\n",
       "      <td>5</td>\n",
       "      <td>0.375000</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.333333</td>\n",
       "      <td>-0.308997</td>\n",
       "      <td>5</td>\n",
       "      <td>-0.134259</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.400000</td>\n",
       "      <td>-0.328909</td>\n",
       "      <td>5</td>\n",
       "      <td>-0.481481</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.533333</td>\n",
       "      <td>0.780236</td>\n",
       "      <td>5</td>\n",
       "      <td>-0.407407</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.400000</td>\n",
       "      <td>-0.329646</td>\n",
       "      <td>5</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 51 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   job_admin.  job_blue-collar  job_entrepreneur  job_housemaid  \\\n",
       "0           0                0                 0              0   \n",
       "1           0                0                 0              0   \n",
       "2           0                0                 1              0   \n",
       "3           0                1                 0              0   \n",
       "4           0                0                 0              0   \n",
       "\n",
       "   job_management  job_retired  job_self-employed  job_services  job_student  \\\n",
       "0               1            0                  0             0            0   \n",
       "1               0            0                  0             0            0   \n",
       "2               0            0                  0             0            0   \n",
       "3               0            0                  0             0            0   \n",
       "4               0            0                  0             0            0   \n",
       "\n",
       "   job_technician  ...  poutcome_other  poutcome_success  poutcome_unknown  \\\n",
       "0               0  ...               0                 0                 1   \n",
       "1               1  ...               0                 0                 1   \n",
       "2               0  ...               0                 0                 1   \n",
       "3               0  ...               0                 0                 1   \n",
       "4               0  ...               0                 0                 1   \n",
       "\n",
       "   ageScaled  balScaled  day  durScaled  campaign  pdays  previous  \n",
       "0   1.266667   1.250000    5   0.375000         1     -1         0  \n",
       "1   0.333333  -0.308997    5  -0.134259         1     -1         0  \n",
       "2  -0.400000  -0.328909    5  -0.481481         1     -1         0  \n",
       "3   0.533333   0.780236    5  -0.407407         1     -1         0  \n",
       "4  -0.400000  -0.329646    5   0.083333         1     -1         0  \n",
       "\n",
       "[5 rows x 51 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Merging with the original data frame\n",
    "# Preparing the X variables\n",
    "X = pd.concat([bankCat, bankNum], axis=1)\n",
    "print(X.shape)\n",
    "# Preparing the Y variable\n",
    "Y = bankData['y']\n",
    "print(Y.shape)\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split\\\n",
    "                                   (X, Y, test_size=0.3, \\\n",
    "                                    random_state=123)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='warn', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='warn', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Defining the LogisticRegression function\n",
    "bankModel = LogisticRegression()\n",
    "bankModel.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Logistic regression model prediction on test set: 0.90\n"
     ]
    }
   ],
   "source": [
    "pred = bankModel.predict(X_test)\n",
    "print('Accuracy of Logistic regression model prediction on '\\\n",
    "      'test set: {:.2f}'\\\n",
    "      .format(bankModel.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[11707   291]\n",
      " [ 1060   506]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          no       0.92      0.98      0.95     11998\n",
      "         yes       0.63      0.32      0.43      1566\n",
      "\n",
      "    accuracy                           0.90     13564\n",
      "   macro avg       0.78      0.65      0.69     13564\n",
      "weighted avg       0.88      0.90      0.89     13564\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Confusion Matrix for the model\n",
    "from sklearn.metrics import confusion_matrix\n",
    "confusionMatrix = confusion_matrix(y_test, pred)\n",
    "print(confusionMatrix)\n",
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Percentage of negative class : yes    11.764148\n",
      "Name: y, dtype: float64\n",
      "Percentage of positive class : no    88.235852\n",
      "Name: y, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print('Percentage of negative class :',\\\n",
    "      (y_train[y_train=='yes'].value_counts()\\\n",
    "       /len(y_train) ) * 100)\n",
    "print('Percentage of positive class :',\\\n",
    "      (y_train[y_train=='no'].value_counts()\\\n",
    "       /len(y_train) ) * 100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "### Undersampling Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Let us first join the train_x and train_y for ease of operation\n",
    "\"\"\"\n",
    "trainData = pd.concat([X_train,y_train],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "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>job_admin.</th>\n",
       "      <th>job_blue-collar</th>\n",
       "      <th>job_entrepreneur</th>\n",
       "      <th>job_housemaid</th>\n",
       "      <th>job_management</th>\n",
       "      <th>job_retired</th>\n",
       "      <th>job_self-employed</th>\n",
       "      <th>job_services</th>\n",
       "      <th>job_student</th>\n",
       "      <th>job_technician</th>\n",
       "      <th>...</th>\n",
       "      <th>poutcome_success</th>\n",
       "      <th>poutcome_unknown</th>\n",
       "      <th>ageScaled</th>\n",
       "      <th>balScaled</th>\n",
       "      <th>day</th>\n",
       "      <th>durScaled</th>\n",
       "      <th>campaign</th>\n",
       "      <th>pdays</th>\n",
       "      <th>previous</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>19100</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>-0.162979</td>\n",
       "      <td>5</td>\n",
       "      <td>0.236111</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37958</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.733333</td>\n",
       "      <td>-0.238938</td>\n",
       "      <td>14</td>\n",
       "      <td>0.865741</td>\n",
       "      <td>2</td>\n",
       "      <td>289</td>\n",
       "      <td>19</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12451</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.385693</td>\n",
       "      <td>1</td>\n",
       "      <td>1.347222</td>\n",
       "      <td>3</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18263</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.333333</td>\n",
       "      <td>-0.330383</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.592593</td>\n",
       "      <td>8</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5128</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.466667</td>\n",
       "      <td>-0.142330</td>\n",
       "      <td>21</td>\n",
       "      <td>-0.435185</td>\n",
       "      <td>2</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 52 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       job_admin.  job_blue-collar  job_entrepreneur  job_housemaid  \\\n",
       "19100           1                0                 0              0   \n",
       "37958           1                0                 0              0   \n",
       "12451           0                1                 0              0   \n",
       "18263           0                0                 0              0   \n",
       "5128            0                0                 0              0   \n",
       "\n",
       "       job_management  job_retired  job_self-employed  job_services  \\\n",
       "19100               0            0                  0             0   \n",
       "37958               0            0                  0             0   \n",
       "12451               0            0                  0             0   \n",
       "18263               1            0                  0             0   \n",
       "5128                0            0                  0             1   \n",
       "\n",
       "       job_student  job_technician  ...  poutcome_success  poutcome_unknown  \\\n",
       "19100            0               0  ...                 0                 1   \n",
       "37958            0               0  ...                 0                 0   \n",
       "12451            0               0  ...                 0                 1   \n",
       "18263            0               0  ...                 0                 1   \n",
       "5128             0               0  ...                 0                 1   \n",
       "\n",
       "       ageScaled  balScaled  day  durScaled  campaign  pdays  previous   y  \n",
       "19100   0.800000  -0.162979    5   0.236111         1     -1         0  no  \n",
       "37958   0.733333  -0.238938   14   0.865741         2    289        19  no  \n",
       "12451   0.000000   0.385693    1   1.347222         3     -1         0  no  \n",
       "18263   1.333333  -0.330383   31  -0.592593         8     -1         0  no  \n",
       "5128   -0.466667  -0.142330   21  -0.435185         2     -1         0  no  \n",
       "\n",
       "[5 rows x 52 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trainData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3723\n"
     ]
    }
   ],
   "source": [
    "ind = trainData[trainData['y']=='yes'].index\n",
    "print(len(ind))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3723, 52)\n"
     ]
    }
   ],
   "source": [
    "minData = trainData.loc[ind]\n",
    "print(minData.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "27924\n"
     ]
    }
   ],
   "source": [
    "ind1 = trainData[trainData['y']=='no'].index\n",
    "print(len(ind1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(27924, 52)\n"
     ]
    },
    {
     "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>job_admin.</th>\n",
       "      <th>job_blue-collar</th>\n",
       "      <th>job_entrepreneur</th>\n",
       "      <th>job_housemaid</th>\n",
       "      <th>job_management</th>\n",
       "      <th>job_retired</th>\n",
       "      <th>job_self-employed</th>\n",
       "      <th>job_services</th>\n",
       "      <th>job_student</th>\n",
       "      <th>job_technician</th>\n",
       "      <th>...</th>\n",
       "      <th>poutcome_success</th>\n",
       "      <th>poutcome_unknown</th>\n",
       "      <th>ageScaled</th>\n",
       "      <th>balScaled</th>\n",
       "      <th>day</th>\n",
       "      <th>durScaled</th>\n",
       "      <th>campaign</th>\n",
       "      <th>pdays</th>\n",
       "      <th>previous</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>19100</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.800000</td>\n",
       "      <td>-0.162979</td>\n",
       "      <td>5</td>\n",
       "      <td>0.236111</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37958</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.733333</td>\n",
       "      <td>-0.238938</td>\n",
       "      <td>14</td>\n",
       "      <td>0.865741</td>\n",
       "      <td>2</td>\n",
       "      <td>289</td>\n",
       "      <td>19</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12451</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.385693</td>\n",
       "      <td>1</td>\n",
       "      <td>1.347222</td>\n",
       "      <td>3</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18263</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.333333</td>\n",
       "      <td>-0.330383</td>\n",
       "      <td>31</td>\n",
       "      <td>-0.592593</td>\n",
       "      <td>8</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5128</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.466667</td>\n",
       "      <td>-0.142330</td>\n",
       "      <td>21</td>\n",
       "      <td>-0.435185</td>\n",
       "      <td>2</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 52 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       job_admin.  job_blue-collar  job_entrepreneur  job_housemaid  \\\n",
       "19100           1                0                 0              0   \n",
       "37958           1                0                 0              0   \n",
       "12451           0                1                 0              0   \n",
       "18263           0                0                 0              0   \n",
       "5128            0                0                 0              0   \n",
       "\n",
       "       job_management  job_retired  job_self-employed  job_services  \\\n",
       "19100               0            0                  0             0   \n",
       "37958               0            0                  0             0   \n",
       "12451               0            0                  0             0   \n",
       "18263               1            0                  0             0   \n",
       "5128                0            0                  0             1   \n",
       "\n",
       "       job_student  job_technician  ...  poutcome_success  poutcome_unknown  \\\n",
       "19100            0               0  ...                 0                 1   \n",
       "37958            0               0  ...                 0                 0   \n",
       "12451            0               0  ...                 0                 1   \n",
       "18263            0               0  ...                 0                 1   \n",
       "5128             0               0  ...                 0                 1   \n",
       "\n",
       "       ageScaled  balScaled  day  durScaled  campaign  pdays  previous   y  \n",
       "19100   0.800000  -0.162979    5   0.236111         1     -1         0  no  \n",
       "37958   0.733333  -0.238938   14   0.865741         2    289        19  no  \n",
       "12451   0.000000   0.385693    1   1.347222         3     -1         0  no  \n",
       "18263   1.333333  -0.330383   31  -0.592593         8     -1         0  no  \n",
       "5128   -0.466667  -0.142330   21  -0.435185         2     -1         0  no  \n",
       "\n",
       "[5 rows x 52 columns]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "majData = trainData.loc[ind1]\n",
    "print(majData.shape)\n",
    "majData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "majSample = majData.sample(n=len(ind),random_state = 123) # Extracting out 3,723 Records (the len of ind)\n",
    "\"\"\"\n",
    "Concatenating both data sets and then shuffling the data set\n",
    "\"\"\"\n",
    "balData = pd.concat([minData,majSample],axis = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 3723 entries, 17387 to 9238\n",
      "Data columns (total 52 columns):\n",
      "job_admin.             3723 non-null uint8\n",
      "job_blue-collar        3723 non-null uint8\n",
      "job_entrepreneur       3723 non-null uint8\n",
      "job_housemaid          3723 non-null uint8\n",
      "job_management         3723 non-null uint8\n",
      "job_retired            3723 non-null uint8\n",
      "job_self-employed      3723 non-null uint8\n",
      "job_services           3723 non-null uint8\n",
      "job_student            3723 non-null uint8\n",
      "job_technician         3723 non-null uint8\n",
      "job_unemployed         3723 non-null uint8\n",
      "job_unknown            3723 non-null uint8\n",
      "marital_divorced       3723 non-null uint8\n",
      "marital_married        3723 non-null uint8\n",
      "marital_single         3723 non-null uint8\n",
      "education_primary      3723 non-null uint8\n",
      "education_secondary    3723 non-null uint8\n",
      "education_tertiary     3723 non-null uint8\n",
      "education_unknown      3723 non-null uint8\n",
      "default_no             3723 non-null uint8\n",
      "default_yes            3723 non-null uint8\n",
      "housing_no             3723 non-null uint8\n",
      "housing_yes            3723 non-null uint8\n",
      "loan_no                3723 non-null uint8\n",
      "loan_yes               3723 non-null uint8\n",
      "contact_cellular       3723 non-null uint8\n",
      "contact_telephone      3723 non-null uint8\n",
      "contact_unknown        3723 non-null uint8\n",
      "month_apr              3723 non-null uint8\n",
      "month_aug              3723 non-null uint8\n",
      "month_dec              3723 non-null uint8\n",
      "month_feb              3723 non-null uint8\n",
      "month_jan              3723 non-null uint8\n",
      "month_jul              3723 non-null uint8\n",
      "month_jun              3723 non-null uint8\n",
      "month_mar              3723 non-null uint8\n",
      "month_may              3723 non-null uint8\n",
      "month_nov              3723 non-null uint8\n",
      "month_oct              3723 non-null uint8\n",
      "month_sep              3723 non-null uint8\n",
      "poutcome_failure       3723 non-null uint8\n",
      "poutcome_other         3723 non-null uint8\n",
      "poutcome_success       3723 non-null uint8\n",
      "poutcome_unknown       3723 non-null uint8\n",
      "ageScaled              3723 non-null float64\n",
      "balScaled              3723 non-null float64\n",
      "day                    3723 non-null int64\n",
      "durScaled              3723 non-null float64\n",
      "campaign               3723 non-null int64\n",
      "pdays                  3723 non-null int64\n",
      "previous               3723 non-null int64\n",
      "y                      3723 non-null object\n",
      "dtypes: float64(3), int64(4), object(1), uint8(44)\n",
      "memory usage: 421.7+ KB\n"
     ]
    }
   ],
   "source": [
    "majSample.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "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>job_admin.</th>\n",
       "      <th>job_blue-collar</th>\n",
       "      <th>job_entrepreneur</th>\n",
       "      <th>job_housemaid</th>\n",
       "      <th>job_management</th>\n",
       "      <th>job_retired</th>\n",
       "      <th>job_self-employed</th>\n",
       "      <th>job_services</th>\n",
       "      <th>job_student</th>\n",
       "      <th>job_technician</th>\n",
       "      <th>...</th>\n",
       "      <th>poutcome_success</th>\n",
       "      <th>poutcome_unknown</th>\n",
       "      <th>ageScaled</th>\n",
       "      <th>balScaled</th>\n",
       "      <th>day</th>\n",
       "      <th>durScaled</th>\n",
       "      <th>campaign</th>\n",
       "      <th>pdays</th>\n",
       "      <th>previous</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1920</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>-0.330383</td>\n",
       "      <td>9</td>\n",
       "      <td>0.157407</td>\n",
       "      <td>2</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41709</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.133333</td>\n",
       "      <td>0.115044</td>\n",
       "      <td>7</td>\n",
       "      <td>0.884259</td>\n",
       "      <td>1</td>\n",
       "      <td>495</td>\n",
       "      <td>1</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10329</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.609145</td>\n",
       "      <td>12</td>\n",
       "      <td>2.180556</td>\n",
       "      <td>5</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15390</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.733333</td>\n",
       "      <td>-0.317847</td>\n",
       "      <td>18</td>\n",
       "      <td>0.412037</td>\n",
       "      <td>1</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34406</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.733333</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>5</td>\n",
       "      <td>2.694444</td>\n",
       "      <td>3</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 52 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       job_admin.  job_blue-collar  job_entrepreneur  job_housemaid  \\\n",
       "1920            0                1                 0              0   \n",
       "41709           0                1                 0              0   \n",
       "10329           0                0                 0              0   \n",
       "15390           1                0                 0              0   \n",
       "34406           0                1                 0              0   \n",
       "\n",
       "       job_management  job_retired  job_self-employed  job_services  \\\n",
       "1920                0            0                  0             0   \n",
       "41709               0            0                  0             0   \n",
       "10329               0            0                  1             0   \n",
       "15390               0            0                  0             0   \n",
       "34406               0            0                  0             0   \n",
       "\n",
       "       job_student  job_technician  ...  poutcome_success  poutcome_unknown  \\\n",
       "1920             0               0  ...                 0                 1   \n",
       "41709            0               0  ...                 0                 0   \n",
       "10329            0               0  ...                 0                 1   \n",
       "15390            0               0  ...                 0                 1   \n",
       "34406            0               0  ...                 0                 1   \n",
       "\n",
       "       ageScaled  balScaled  day  durScaled  campaign  pdays  previous    y  \n",
       "1920    0.200000  -0.330383    9   0.157407         2     -1         0   no  \n",
       "41709  -0.133333   0.115044    7   0.884259         1    495         1  yes  \n",
       "10329   0.000000   1.609145   12   2.180556         5     -1         0  yes  \n",
       "15390  -0.733333  -0.317847   18   0.412037         1     -1         0   no  \n",
       "34406   0.733333   4.000000    5   2.694444         3     -1         0  yes  \n",
       "\n",
       "[5 rows x 52 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Shuffling the data set\n",
    "from sklearn.utils import shuffle\n",
    "balData = shuffle(balData)\n",
    "balData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "       job_admin.  job_blue-collar  job_entrepreneur  job_housemaid  \\\n",
      "1920            0                1                 0              0   \n",
      "41709           0                1                 0              0   \n",
      "10329           0                0                 0              0   \n",
      "15390           1                0                 0              0   \n",
      "34406           0                1                 0              0   \n",
      "\n",
      "       job_management  job_retired  job_self-employed  job_services  \\\n",
      "1920                0            0                  0             0   \n",
      "41709               0            0                  0             0   \n",
      "10329               0            0                  1             0   \n",
      "15390               0            0                  0             0   \n",
      "34406               0            0                  0             0   \n",
      "\n",
      "       job_student  job_technician  ...  poutcome_other  poutcome_success  \\\n",
      "1920             0               0  ...               0                 0   \n",
      "41709            0               0  ...               0                 0   \n",
      "10329            0               0  ...               0                 0   \n",
      "15390            0               0  ...               0                 0   \n",
      "34406            0               0  ...               0                 0   \n",
      "\n",
      "       poutcome_unknown  ageScaled  balScaled  day  durScaled  campaign  \\\n",
      "1920                  1   0.200000  -0.330383    9   0.157407         2   \n",
      "41709                 0  -0.133333   0.115044    7   0.884259         1   \n",
      "10329                 1   0.000000   1.609145   12   2.180556         5   \n",
      "15390                 1  -0.733333  -0.317847   18   0.412037         1   \n",
      "34406                 1   0.733333   4.000000    5   2.694444         3   \n",
      "\n",
      "       pdays  previous  \n",
      "1920      -1         0  \n",
      "41709    495         1  \n",
      "10329     -1         0  \n",
      "15390     -1         0  \n",
      "34406     -1         0  \n",
      "\n",
      "[5 rows x 51 columns]\n",
      "1920      no\n",
      "41709    yes\n",
      "10329    yes\n",
      "15390     no\n",
      "34406    yes\n",
      "Name: y, dtype: object\n"
     ]
    }
   ],
   "source": [
    "# Making the new X_train and y_train\n",
    "X_trainNew = balData.iloc[:,0:51]\n",
    "print(X_trainNew.head())\n",
    "y_trainNew = balData['y']\n",
    "print(y_trainNew.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='warn', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='warn', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "bankModel1 = LogisticRegression()\n",
    "bankModel1.fit(X_trainNew, y_trainNew)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Logistic regression model prediction on test set for balanced data set: 0.85\n"
     ]
    }
   ],
   "source": [
    "pred = bankModel1.predict(X_test)\n",
    "print('Accuracy of Logistic regression model prediction on '\\\n",
    "      'test set for balanced data set: {:.2f}'\\\n",
    "      .format(bankModel1.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[10204  1794]\n",
      " [  288  1278]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "          no       0.97      0.85      0.91     11998\n",
      "         yes       0.42      0.82      0.55      1566\n",
      "\n",
      "    accuracy                           0.85     13564\n",
      "   macro avg       0.69      0.83      0.73     13564\n",
      "weighted avg       0.91      0.85      0.87     13564\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "confusionMatrix = confusion_matrix(y_test, pred)\n",
    "print(confusionMatrix)\n",
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "# SMOTE - Synthetic Minority Oversampling TEchnique"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mWARNING: The directory '/home/jovyan/.cache/pip/http' or its parent directory is not owned by the current user and the cache has been disabled. Please check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.\u001b[0m\n",
      "\u001b[33mWARNING: The directory '/home/jovyan/.cache/pip' or its parent directory is not owned by the current user and caching wheels has been disabled. check the permissions and owner of that directory. If executing pip with sudo, you may want sudo's -H flag.\u001b[0m\n",
      "Collecting smote-variants\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/f6/be/15b4db362d53ded5960da7d439455d2efa4d99f85626145c4bb415fde153/smote_variants-0.4.0-py3-none-any.whl (134kB)\n",
      "\u001b[K     |████████████████████████████████| 143kB 14.6MB/s eta 0:00:01\n",
      "\u001b[?25hCollecting mkl (from smote-variants)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/fd/13/1d5966869047ba26f87da6df52447857b486887f7e5d6469a1bb44953639/mkl-2022.1.0-py2.py3-none-manylinux1_x86_64.whl (256.4MB)\n",
      "\u001b[K     |████████████████████████████████| 256.4MB 30.8MB/s eta 0:00:01    |█████████                       | 71.6MB 23.1MB/s eta 0:00:08     |█████████                       | 72.7MB 23.1MB/s eta 0:00:08\n",
      "\u001b[?25hRequirement already satisfied: scipy in /opt/conda/lib/python3.7/site-packages (from smote-variants) (1.4.1)\n",
      "Requirement already satisfied: joblib in /opt/conda/lib/python3.7/site-packages (from smote-variants) (0.13.2)\n",
      "Requirement already satisfied: numpy>=1.13.0 in /opt/conda/lib/python3.7/site-packages (from smote-variants) (1.19.5)\n",
      "Collecting statistics (from smote-variants)\n",
      "  Downloading https://files.pythonhosted.org/packages/bb/3a/ae99a15e65636559d936dd2159d75af1619491e8cb770859fbc8aa62cef6/statistics-1.0.3.5.tar.gz\n",
      "Requirement already satisfied: pandas in /opt/conda/lib/python3.7/site-packages (from smote-variants) (0.25.0)\n",
      "Collecting minisom (from smote-variants)\n",
      "  Downloading https://files.pythonhosted.org/packages/9f/91/e8c00ed159c6a7f05fbbe80444ac42b6648d6f07c112c56ddac0dc681ec6/MiniSom-2.3.0.tar.gz\n",
      "Requirement already satisfied: keras in /opt/conda/lib/python3.7/site-packages (from smote-variants) (2.2.4)\n",
      "Requirement already satisfied: tensorflow in /opt/conda/lib/python3.7/site-packages (from smote-variants) (2.1.0)\n",
      "Requirement already satisfied: scikit-learn in /opt/conda/lib/python3.7/site-packages (from smote-variants) (0.21.3)\n",
      "Collecting tbb==2021.* (from mkl->smote-variants)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/d7/9f/314d2df2b27b73b90175a8b494912a37fbd87cb9e4c2395f5af73fa3e069/tbb-2021.6.0-py2.py3-none-manylinux1_x86_64.whl (4.0MB)\n",
      "\u001b[K     |████████████████████████████████| 4.0MB 13.1MB/s eta 0:00:01\n",
      "\u001b[?25hCollecting intel-openmp==2022.* (from mkl->smote-variants)\n",
      "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/03/d5/c409cc56e323fce807b35b4460ade0b7ec12340cf78a33549d1a73fb939d/intel_openmp-2022.1.0-py2.py3-none-manylinux1_x86_64.whl (10.7MB)\n",
      "\u001b[K     |████████████████████████████████| 10.7MB 23.8MB/s eta 0:00:01\n",
      "\u001b[?25hRequirement already satisfied: docutils>=0.3 in /opt/conda/lib/python3.7/site-packages (from statistics->smote-variants) (0.15.2)\n",
      "Requirement already satisfied: pytz>=2017.2 in /opt/conda/lib/python3.7/site-packages (from pandas->smote-variants) (2019.2)\n",
      "Requirement already satisfied: python-dateutil>=2.6.1 in /opt/conda/lib/python3.7/site-packages (from pandas->smote-variants) (2.8.0)\n",
      "Requirement already satisfied: pyyaml in /opt/conda/lib/python3.7/site-packages (from keras->smote-variants) (5.1.2)\n",
      "Requirement already satisfied: six>=1.9.0 in /opt/conda/lib/python3.7/site-packages (from keras->smote-variants) (1.12.0)\n",
      "Requirement already satisfied: keras-preprocessing>=1.0.5 in /opt/conda/lib/python3.7/site-packages (from keras->smote-variants) (1.1.0)\n",
      "Requirement already satisfied: h5py in /opt/conda/lib/python3.7/site-packages (from keras->smote-variants) (2.9.0)\n",
      "Requirement already satisfied: keras-applications>=1.0.6 in /opt/conda/lib/python3.7/site-packages (from keras->smote-variants) (1.0.8)\n",
      "Requirement already satisfied: google-pasta>=0.1.6 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (0.2.0)\n",
      "Requirement already satisfied: tensorboard<2.2.0,>=2.1.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (2.1.1)\n",
      "Requirement already satisfied: protobuf>=3.8.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (3.9.1)\n",
      "Requirement already satisfied: astor>=0.6.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (0.7.1)\n",
      "Requirement already satisfied: gast==0.2.2 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (0.2.2)\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (3.2.0)\n",
      "Requirement already satisfied: wheel>=0.26; python_version >= \"3\" in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (0.33.4)\n",
      "Requirement already satisfied: termcolor>=1.1.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (1.1.0)\n",
      "Requirement already satisfied: wrapt>=1.11.1 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (1.12.1)\n",
      "Requirement already satisfied: grpcio>=1.8.6 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (1.16.1)\n",
      "Requirement already satisfied: absl-py>=0.7.0 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (0.7.1)\n",
      "Requirement already satisfied: tensorflow-estimator<2.2.0,>=2.1.0rc0 in /opt/conda/lib/python3.7/site-packages (from tensorflow->smote-variants) (2.1.0)\n",
      "Requirement already satisfied: google-auth<2,>=1.6.3 in /opt/conda/lib/python3.7/site-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (1.13.1)\n",
      "Requirement already satisfied: werkzeug>=0.11.15 in /opt/conda/lib/python3.7/site-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (0.15.5)\n",
      "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /opt/conda/lib/python3.7/site-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (0.4.1)\n",
      "Requirement already satisfied: requests<3,>=2.21.0 in /opt/conda/lib/python3.7/site-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (2.22.0)\n",
      "Requirement already satisfied: markdown>=2.6.8 in /opt/conda/lib/python3.7/site-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (3.1.1)\n",
      "Requirement already satisfied: setuptools>=41.0.0 in /opt/conda/lib/python3.7/site-packages (from tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (41.0.1)\n",
      "Requirement already satisfied: pyasn1-modules>=0.2.1 in /opt/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (0.2.8)\n",
      "Requirement already satisfied: cachetools<5.0,>=2.0.0 in /opt/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (4.1.0)\n",
      "Requirement already satisfied: rsa<4.1,>=3.1.4 in /opt/conda/lib/python3.7/site-packages (from google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (4.0)\n",
      "Requirement already satisfied: requests-oauthlib>=0.7.0 in /opt/conda/lib/python3.7/site-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (1.3.0)\n",
      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (1.25.3)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (2019.11.28)\n",
      "Requirement already satisfied: idna<2.9,>=2.5 in /opt/conda/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (2.8)\n",
      "Requirement already satisfied: chardet<3.1.0,>=3.0.2 in /opt/conda/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (3.0.4)\n",
      "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /opt/conda/lib/python3.7/site-packages (from pyasn1-modules>=0.2.1->google-auth<2,>=1.6.3->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (0.4.8)\n",
      "Requirement already satisfied: oauthlib>=3.0.0 in /opt/conda/lib/python3.7/site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.2.0,>=2.1.0->tensorflow->smote-variants) (3.0.1)\n",
      "Building wheels for collected packages: statistics, minisom\n",
      "  Building wheel for statistics (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for statistics: filename=statistics-1.0.3.5-cp37-none-any.whl size=7454 sha256=6fe5e6f2c31062a4c5dfa1e41ed9ffe43e3e58205bd5e76d94c272f4af2d5256\n",
      "  Stored in directory: /home/jovyan/.cache/pip/wheels/75/55/90/73aa7662bfb4565b567618547a275f01372a678ca92ecd64f3\n",
      "  Building wheel for minisom (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for minisom: filename=MiniSom-2.3.0-cp37-none-any.whl size=9020 sha256=636f2e144b686e4bb4eecf6919058cd83418fb0b4964cab67a5bd40973505c30\n",
      "  Stored in directory: /home/jovyan/.cache/pip/wheels/fa/fc/53/1af28011f9ef2252f5dc34944fb445255385a8f110fb9528f5\n",
      "Successfully built statistics minisom\n",
      "Installing collected packages: tbb, intel-openmp, mkl, statistics, minisom, smote-variants\n",
      "Successfully installed intel-openmp-2022.1.0 minisom-2.3.0 mkl-2022.1.0 smote-variants-0.4.0 statistics-1.0.3.5 tbb-2021.6.0\n"
     ]
    }
   ],
   "source": [
    "!pip install smote-variants"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Before OverSampling count of yes: 3723\n",
      "Before OverSampling count of no: 27924 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Shape before oversampling\n",
    "print(\"Before OverSampling count of yes: {}\"\\\n",
    "      .format(sum(y_train=='yes')))\n",
    "print(\"Before OverSampling count of no: {} \\n\"\\\n",
    "      .format(sum(y_train=='no')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [],
   "source": [
    "import smote_variants as sv\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Instantiating the SMOTE class\n",
    "oversampler= sv.SMOTE()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-05-11 18:54:01,290:INFO:SMOTE: Running sampling via ('SMOTE', \"{'proportion': 1.0, 'n_neighbors': 5, 'n_jobs': 1, 'random_state': None}\")\n"
     ]
    }
   ],
   "source": [
    "# Creating new training set\n",
    "X_train_os, y_train_os = oversampler.sample\\\n",
    "                         (np.array(X_train), np.array(y_train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "After OverSampling, the shape of train_X: (55848, 51)\n",
      "After OverSampling, the shape of train_y: (55848,) \n",
      "\n",
      "After OverSampling, counts of label 'Yes': 27924\n",
      "After OverSampling, counts of label 'no': 27924\n"
     ]
    }
   ],
   "source": [
    "# Shape after oversampling\n",
    "print('After OverSampling, the shape of train_X: {}'\\\n",
    "      .format(X_train_os.shape))\n",
    "print('After OverSampling, the shape of train_y: {} \\n'\\\n",
    "      .format(y_train_os.shape))\n",
    "print(\"After OverSampling, counts of label 'Yes': {}\"\\\n",
    "      .format(sum(y_train_os=='yes')))\n",
    "print(\"After OverSampling, counts of label 'no': {}\"\\\n",
    "      .format(sum(y_train_os=='no')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='warn', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='warn', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Training the model with Logistic regression model\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "bankModel2 = LogisticRegression()\n",
    "bankModel2.fit(X_train_os, y_train_os)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred = bankModel2.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Logistic regression model prediction on test set for Smote balanced data set: 0.85\n"
     ]
    }
   ],
   "source": [
    "print('Accuracy of Logistic regression model prediction on '\\\n",
    "      'test set for Smote balanced data set: {:.2f}'\\\n",
    "      .format(bankModel2.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[10268  1730]\n",
      " [  319  1247]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "confusionMatrix = confusion_matrix(y_test, pred)\n",
    "print(confusionMatrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "          no       0.97      0.86      0.91     11998\n",
      "         yes       0.42      0.80      0.55      1566\n",
      "\n",
      "    accuracy                           0.85     13564\n",
      "   macro avg       0.69      0.83      0.73     13564\n",
      "weighted avg       0.91      0.85      0.87     13564\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "# MSMOTE - combo of under and over sampling... might NOT work b/c we are using CPUs and not GPUs..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Before OverSampling count of yes: 3723\n",
      "Before OverSampling count of no: 27924 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Shape before oversampling\n",
    "print(\"Before OverSampling count of yes: {}\"\\\n",
    "      .format(sum(y_train=='yes')))\n",
    "print(\"Before OverSampling count of no: {} \\n\"\\\n",
    "      .format(sum(y_train=='no')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "import smote_variants as sv\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Instantiating the MSMOTE class\n",
    "oversampler= sv.MSMOTE()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-05-11 19:03:19,582:INFO:MSMOTE: Running sampling via ('MSMOTE', \"{'proportion': 1.0, 'n_neighbors': 5, 'n_jobs': 1, 'random_state': None}\")\n"
     ]
    }
   ],
   "source": [
    "# Creating new training set\n",
    "X_train_os, y_train_os = oversampler.sample\\\n",
    "                         (np.array(X_train), np.array(y_train))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "After OverSampling, the shape of train_X: (55848, 51)\n",
      "After OverSampling, the shape of train_y: (55848,) \n",
      "\n",
      "After OverSampling, counts of label 'Yes': 27924\n",
      "After OverSampling, counts of label 'no': 27924\n"
     ]
    }
   ],
   "source": [
    "# Shape after oversampling\n",
    "print('After OverSampling, the shape of train_X: {}'\\\n",
    "      .format(X_train_os.shape))\n",
    "print('After OverSampling, the shape of train_y: {} \\n'\\\n",
    "      .format(y_train_os.shape))\n",
    "print(\"After OverSampling, counts of label 'Yes': {}\"\\\n",
    "      .format(sum(y_train_os=='yes')))\n",
    "print(\"After OverSampling, counts of label 'no': {}\"\\\n",
    "      .format(sum(y_train_os=='no')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.7/site-packages/sklearn/linear_model/logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='warn', n_jobs=None, penalty='l2',\n",
       "                   random_state=None, solver='warn', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Training the model with Logistic regression model\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "# Defining the LogisticRegression function\n",
    "bankModel3 = LogisticRegression()\n",
    "bankModel3.fit(X_train_os, y_train_os)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred = bankModel3.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy of Logistic regression model prediction on test set for MSMOTE balanced data set: 0.85\n"
     ]
    }
   ],
   "source": [
    "print('Accuracy of Logistic regression model prediction on '\\\n",
    "      'test set for MSMOTE balanced data set: {:.2f}'\\\n",
    "      .format(bankModel3.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[10296  1702]\n",
      " [  329  1237]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "confusionMatrix = confusion_matrix(y_test, pred)\n",
    "print(confusionMatrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "          no       0.97      0.86      0.91     11998\n",
      "         yes       0.42      0.79      0.55      1566\n",
      "\n",
      "    accuracy                           0.85     13564\n",
      "   macro avg       0.69      0.82      0.73     13564\n",
      "weighted avg       0.91      0.85      0.87     13564\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}