shoppers_ML_resampling.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Credit Risk Resampling Techniques"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "from collections import Counter"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read the CSV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Administrative</th>\n",
       "      <th>Administrative_Duration</th>\n",
       "      <th>Informational</th>\n",
       "      <th>Informational_Duration</th>\n",
       "      <th>ProductRelated</th>\n",
       "      <th>ProductRelated_Duration</th>\n",
       "      <th>BounceRates</th>\n",
       "      <th>ExitRates</th>\n",
       "      <th>PageValues</th>\n",
       "      <th>SpecialDay</th>\n",
       "      <th>Month</th>\n",
       "      <th>OperatingSystems</th>\n",
       "      <th>Browser</th>\n",
       "      <th>Region</th>\n",
       "      <th>TrafficType</th>\n",
       "      <th>VisitorType</th>\n",
       "      <th>Weekend</th>\n",
       "      <th>Revenue</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.20</td>\n",
       "      <td>0.20</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>64.000000</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.10</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.20</td>\n",
       "      <td>0.20</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2.666667</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.14</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10</td>\n",
       "      <td>627.500000</td>\n",
       "      <td>0.02</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Administrative  Administrative_Duration  Informational  \\\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",
       "   Informational_Duration  ProductRelated  ProductRelated_Duration  \\\n",
       "0                     0.0               1                 0.000000   \n",
       "1                     0.0               2                64.000000   \n",
       "2                     0.0               1                 0.000000   \n",
       "3                     0.0               2                 2.666667   \n",
       "4                     0.0              10               627.500000   \n",
       "\n",
       "   BounceRates  ExitRates  PageValues  SpecialDay Month  OperatingSystems  \\\n",
       "0         0.20       0.20         0.0         0.0   Feb                 1   \n",
       "1         0.00       0.10         0.0         0.0   Feb                 2   \n",
       "2         0.20       0.20         0.0         0.0   Feb                 4   \n",
       "3         0.05       0.14         0.0         0.0   Feb                 3   \n",
       "4         0.02       0.05         0.0         0.0   Feb                 3   \n",
       "\n",
       "   Browser  Region  TrafficType        VisitorType  Weekend  Revenue  \n",
       "0        1       1            1  Returning_Visitor    False    False  \n",
       "1        2       1            2  Returning_Visitor    False    False  \n",
       "2        1       9            3  Returning_Visitor    False    False  \n",
       "3        2       2            4  Returning_Visitor    False    False  \n",
       "4        3       1            4  Returning_Visitor     True    False  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "file_path = \"Resources/online_shoppers_intention.csv\"\n",
    "shoppers_df = pd.read_csv(file_path)\n",
    "shoppers_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Changed Revenue to dtype str\n",
    "shoppers_df['Revenue'] = shoppers_df['Revenue'].astype('str')\n",
    "\n",
    "# Replace True and False in Column Revenue by Sale or No Sale for better readability\n",
    "shoppers_df['Revenue'] = shoppers_df['Revenue'].replace(['True'],'Sale')\n",
    "shoppers_df['Revenue'] = shoppers_df['Revenue'].replace(['False'],'No Sale')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>Administrative</th>\n",
       "      <th>Administrative_Duration</th>\n",
       "      <th>Informational</th>\n",
       "      <th>Informational_Duration</th>\n",
       "      <th>ProductRelated</th>\n",
       "      <th>ProductRelated_Duration</th>\n",
       "      <th>BounceRates</th>\n",
       "      <th>ExitRates</th>\n",
       "      <th>PageValues</th>\n",
       "      <th>SpecialDay</th>\n",
       "      <th>Month</th>\n",
       "      <th>OperatingSystems</th>\n",
       "      <th>Browser</th>\n",
       "      <th>Region</th>\n",
       "      <th>TrafficType</th>\n",
       "      <th>VisitorType</th>\n",
       "      <th>Weekend</th>\n",
       "      <th>Revenue</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>64.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>3</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>2.666667</td>\n",
       "      <td>0.050000</td>\n",
       "      <td>0.140000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10</td>\n",
       "      <td>627.500000</td>\n",
       "      <td>0.020000</td>\n",
       "      <td>0.050000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Feb</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>True</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12325</th>\n",
       "      <td>3</td>\n",
       "      <td>145.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>53</td>\n",
       "      <td>1783.791667</td>\n",
       "      <td>0.007143</td>\n",
       "      <td>0.029031</td>\n",
       "      <td>12.241717</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Dec</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>True</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12326</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5</td>\n",
       "      <td>465.750000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021333</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Nov</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>True</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12327</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6</td>\n",
       "      <td>184.250000</td>\n",
       "      <td>0.083333</td>\n",
       "      <td>0.086667</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Nov</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>True</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12328</th>\n",
       "      <td>4</td>\n",
       "      <td>75.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15</td>\n",
       "      <td>346.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.021053</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Nov</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>Returning_Visitor</td>\n",
       "      <td>False</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12329</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>21.250000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.066667</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Nov</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>New_Visitor</td>\n",
       "      <td>True</td>\n",
       "      <td>No Sale</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>12330 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Administrative  Administrative_Duration  Informational  \\\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",
       "12325               3                    145.0              0   \n",
       "12326               0                      0.0              0   \n",
       "12327               0                      0.0              0   \n",
       "12328               4                     75.0              0   \n",
       "12329               0                      0.0              0   \n",
       "\n",
       "       Informational_Duration  ProductRelated  ProductRelated_Duration  \\\n",
       "0                         0.0               1                 0.000000   \n",
       "1                         0.0               2                64.000000   \n",
       "2                         0.0               1                 0.000000   \n",
       "3                         0.0               2                 2.666667   \n",
       "4                         0.0              10               627.500000   \n",
       "...                       ...             ...                      ...   \n",
       "12325                     0.0              53              1783.791667   \n",
       "12326                     0.0               5               465.750000   \n",
       "12327                     0.0               6               184.250000   \n",
       "12328                     0.0              15               346.000000   \n",
       "12329                     0.0               3                21.250000   \n",
       "\n",
       "       BounceRates  ExitRates  PageValues  SpecialDay Month  OperatingSystems  \\\n",
       "0         0.200000   0.200000    0.000000         0.0   Feb                 1   \n",
       "1         0.000000   0.100000    0.000000         0.0   Feb                 2   \n",
       "2         0.200000   0.200000    0.000000         0.0   Feb                 4   \n",
       "3         0.050000   0.140000    0.000000         0.0   Feb                 3   \n",
       "4         0.020000   0.050000    0.000000         0.0   Feb                 3   \n",
       "...            ...        ...         ...         ...   ...               ...   \n",
       "12325     0.007143   0.029031   12.241717         0.0   Dec                 4   \n",
       "12326     0.000000   0.021333    0.000000         0.0   Nov                 3   \n",
       "12327     0.083333   0.086667    0.000000         0.0   Nov                 3   \n",
       "12328     0.000000   0.021053    0.000000         0.0   Nov                 2   \n",
       "12329     0.000000   0.066667    0.000000         0.0   Nov                 3   \n",
       "\n",
       "       Browser  Region  TrafficType        VisitorType  Weekend  Revenue  \n",
       "0            1       1            1  Returning_Visitor    False  No Sale  \n",
       "1            2       1            2  Returning_Visitor    False  No Sale  \n",
       "2            1       9            3  Returning_Visitor    False  No Sale  \n",
       "3            2       2            4  Returning_Visitor    False  No Sale  \n",
       "4            3       1            4  Returning_Visitor     True  No Sale  \n",
       "...        ...     ...          ...                ...      ...      ...  \n",
       "12325        6       1            1  Returning_Visitor     True  No Sale  \n",
       "12326        2       1            8  Returning_Visitor     True  No Sale  \n",
       "12327        2       1           13  Returning_Visitor     True  No Sale  \n",
       "12328        2       3           11  Returning_Visitor    False  No Sale  \n",
       "12329        2       1            2        New_Visitor     True  No Sale  \n",
       "\n",
       "[12330 rows x 18 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "shoppers_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Split the Data into Training and Testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create our features\n",
    "X = shoppers_df.drop(\"Revenue\", axis=1)\n",
    "X = pd.get_dummies(X)\n",
    "\n",
    "\n",
    "# Create our target\n",
    "target = [\"Revenue\"]\n",
    "\n",
    "y = shoppers_df.loc[:, target].copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>Administrative</th>\n",
       "      <th>Administrative_Duration</th>\n",
       "      <th>Informational</th>\n",
       "      <th>Informational_Duration</th>\n",
       "      <th>ProductRelated</th>\n",
       "      <th>ProductRelated_Duration</th>\n",
       "      <th>BounceRates</th>\n",
       "      <th>ExitRates</th>\n",
       "      <th>PageValues</th>\n",
       "      <th>SpecialDay</th>\n",
       "      <th>...</th>\n",
       "      <th>Month_Jul</th>\n",
       "      <th>Month_June</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>VisitorType_New_Visitor</th>\n",
       "      <th>VisitorType_Other</th>\n",
       "      <th>VisitorType_Returning_Visitor</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "      <td>12330.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2.315166</td>\n",
       "      <td>80.818611</td>\n",
       "      <td>0.503569</td>\n",
       "      <td>34.472398</td>\n",
       "      <td>31.731468</td>\n",
       "      <td>1194.746220</td>\n",
       "      <td>0.022191</td>\n",
       "      <td>0.043073</td>\n",
       "      <td>5.889258</td>\n",
       "      <td>0.061427</td>\n",
       "      <td>...</td>\n",
       "      <td>0.035036</td>\n",
       "      <td>0.023358</td>\n",
       "      <td>0.154663</td>\n",
       "      <td>0.272830</td>\n",
       "      <td>0.243147</td>\n",
       "      <td>0.044526</td>\n",
       "      <td>0.036334</td>\n",
       "      <td>0.137388</td>\n",
       "      <td>0.006894</td>\n",
       "      <td>0.855718</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.321784</td>\n",
       "      <td>176.779107</td>\n",
       "      <td>1.270156</td>\n",
       "      <td>140.749294</td>\n",
       "      <td>44.475503</td>\n",
       "      <td>1913.669288</td>\n",
       "      <td>0.048488</td>\n",
       "      <td>0.048597</td>\n",
       "      <td>18.568437</td>\n",
       "      <td>0.198917</td>\n",
       "      <td>...</td>\n",
       "      <td>0.183880</td>\n",
       "      <td>0.151043</td>\n",
       "      <td>0.361598</td>\n",
       "      <td>0.445432</td>\n",
       "      <td>0.429000</td>\n",
       "      <td>0.206268</td>\n",
       "      <td>0.187128</td>\n",
       "      <td>0.344271</td>\n",
       "      <td>0.082745</td>\n",
       "      <td>0.351390</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>184.137500</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.014286</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>7.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>598.936905</td>\n",
       "      <td>0.003112</td>\n",
       "      <td>0.025156</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>93.256250</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>1464.157214</td>\n",
       "      <td>0.016813</td>\n",
       "      <td>0.050000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>27.000000</td>\n",
       "      <td>3398.750000</td>\n",
       "      <td>24.000000</td>\n",
       "      <td>2549.375000</td>\n",
       "      <td>705.000000</td>\n",
       "      <td>63973.522230</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>0.200000</td>\n",
       "      <td>361.763742</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Administrative  Administrative_Duration  Informational  \\\n",
       "count    12330.000000             12330.000000   12330.000000   \n",
       "mean         2.315166                80.818611       0.503569   \n",
       "std          3.321784               176.779107       1.270156   \n",
       "min          0.000000                 0.000000       0.000000   \n",
       "25%          0.000000                 0.000000       0.000000   \n",
       "50%          1.000000                 7.500000       0.000000   \n",
       "75%          4.000000                93.256250       0.000000   \n",
       "max         27.000000              3398.750000      24.000000   \n",
       "\n",
       "       Informational_Duration  ProductRelated  ProductRelated_Duration  \\\n",
       "count            12330.000000    12330.000000             12330.000000   \n",
       "mean                34.472398       31.731468              1194.746220   \n",
       "std                140.749294       44.475503              1913.669288   \n",
       "min                  0.000000        0.000000                 0.000000   \n",
       "25%                  0.000000        7.000000               184.137500   \n",
       "50%                  0.000000       18.000000               598.936905   \n",
       "75%                  0.000000       38.000000              1464.157214   \n",
       "max               2549.375000      705.000000             63973.522230   \n",
       "\n",
       "        BounceRates     ExitRates    PageValues    SpecialDay  ...  \\\n",
       "count  12330.000000  12330.000000  12330.000000  12330.000000  ...   \n",
       "mean       0.022191      0.043073      5.889258      0.061427  ...   \n",
       "std        0.048488      0.048597     18.568437      0.198917  ...   \n",
       "min        0.000000      0.000000      0.000000      0.000000  ...   \n",
       "25%        0.000000      0.014286      0.000000      0.000000  ...   \n",
       "50%        0.003112      0.025156      0.000000      0.000000  ...   \n",
       "75%        0.016813      0.050000      0.000000      0.000000  ...   \n",
       "max        0.200000      0.200000    361.763742      1.000000  ...   \n",
       "\n",
       "          Month_Jul    Month_June     Month_Mar     Month_May     Month_Nov  \\\n",
       "count  12330.000000  12330.000000  12330.000000  12330.000000  12330.000000   \n",
       "mean       0.035036      0.023358      0.154663      0.272830      0.243147   \n",
       "std        0.183880      0.151043      0.361598      0.445432      0.429000   \n",
       "min        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
       "25%        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
       "50%        0.000000      0.000000      0.000000      0.000000      0.000000   \n",
       "75%        0.000000      0.000000      0.000000      1.000000      0.000000   \n",
       "max        1.000000      1.000000      1.000000      1.000000      1.000000   \n",
       "\n",
       "          Month_Oct     Month_Sep  VisitorType_New_Visitor  VisitorType_Other  \\\n",
       "count  12330.000000  12330.000000             12330.000000       12330.000000   \n",
       "mean       0.044526      0.036334                 0.137388           0.006894   \n",
       "std        0.206268      0.187128                 0.344271           0.082745   \n",
       "min        0.000000      0.000000                 0.000000           0.000000   \n",
       "25%        0.000000      0.000000                 0.000000           0.000000   \n",
       "50%        0.000000      0.000000                 0.000000           0.000000   \n",
       "75%        0.000000      0.000000                 0.000000           0.000000   \n",
       "max        1.000000      1.000000                 1.000000           1.000000   \n",
       "\n",
       "       VisitorType_Returning_Visitor  \n",
       "count                   12330.000000  \n",
       "mean                        0.855718  \n",
       "std                         0.351390  \n",
       "min                         0.000000  \n",
       "25%                         1.000000  \n",
       "50%                         1.000000  \n",
       "75%                         1.000000  \n",
       "max                         1.000000  \n",
       "\n",
       "[8 rows x 27 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "No Sale    10422\n",
       "Sale        1908\n",
       "Name: Revenue, dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check the balance of our target values\n",
    "y['Revenue'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training: Counter({'No Sale': 7786, 'Sale': 1461})\n",
      "Test: Counter({'No Sale': 2636, 'Sale': 447})\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)\n",
    "print(\"Training:\",Counter(y_train['Revenue']))\n",
    "print(\"Test:\",Counter(y_test['Revenue']))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Oversampling\n",
    "\n",
    "In this section, you will compare two oversampling algorithms to determine which algorithm results in the best performance. You will oversample the data using the naive random oversampling algorithm and the SMOTE algorithm. For each algorithm, be sure to complete the folliowing steps:\n",
    "\n",
    "1. View the count of the target classes using `Counter` from the collections library. \n",
    "3. Use the resampled data to train a logistic regression model.\n",
    "3. Calculate the balanced accuracy score from sklearn.metrics.\n",
    "4. Print the confusion matrix from sklearn.metrics.\n",
    "5. Generate a classication report using the `imbalanced_classification_report` from imbalanced-learn.\n",
    "\n",
    "Note: Use a random state of 1 for each sampling algorithm to ensure consistency between tests"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Naive Random Oversampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'No Sale': 7786, 'Sale': 7786})\n"
     ]
    }
   ],
   "source": [
    "# Resample the training data with the RandomOversampler\n",
    "from imblearn.over_sampling import RandomOverSampler\n",
    "ros = RandomOverSampler(random_state=1)\n",
    "X_resampled, y_resampled = ros.fit_resample(X_train, y_train)\n",
    "print(Counter(y_resampled['Revenue']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(random_state=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(random_state=1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression(random_state=1)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the Logistic Regression model using the resampled data\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "model = LogisticRegression(solver='lbfgs', random_state=1)\n",
    "model.fit(X_resampled, y_resampled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8195230893530636"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculate predictions\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "# Calculated the balanced accuracy score\n",
    "from sklearn.metrics import balanced_accuracy_score\n",
    "balanced_accuracy_score(y_test,y_pred)"
   ]
  },
  {
   "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>Predicted No Sale</th>\n",
       "      <th>Predicted Sale</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual No Sale</th>\n",
       "      <td>2345</td>\n",
       "      <td>291</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual Sale</th>\n",
       "      <td>112</td>\n",
       "      <td>335</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Predicted No Sale  Predicted Sale\n",
       "Actual No Sale               2345             291\n",
       "Actual Sale                   112             335"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the confusion matrix\n",
    "from sklearn.metrics import confusion_matrix\n",
    "cmatrix = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "# This will show the confusion matrix as a Pandas Dataframe for better readability\n",
    "cmatrix_df = pd.DataFrame(\n",
    "    cmatrix, index=[\"Actual No Sale\", \"Actual Sale\"], columns=[\"Predicted No Sale\", \"Predicted Sale\"])\n",
    "\n",
    "cmatrix_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   pre       rec       spe        f1       geo       iba       sup\n",
      "\n",
      "    No Sale       0.95      0.89      0.75      0.92      0.82      0.68      2636\n",
      "       Sale       0.54      0.75      0.89      0.62      0.82      0.66       447\n",
      "\n",
      "avg / total       0.89      0.87      0.77      0.88      0.82      0.67      3083\n",
      "\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>precision</th>\n",
       "      <th>recall</th>\n",
       "      <th>f1-score</th>\n",
       "      <th>support</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>No Sale</th>\n",
       "      <td>0.954416</td>\n",
       "      <td>0.889605</td>\n",
       "      <td>0.920872</td>\n",
       "      <td>2636.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weighted avg</th>\n",
       "      <td>0.893626</td>\n",
       "      <td>0.869283</td>\n",
       "      <td>0.877889</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>accuracy</th>\n",
       "      <td>0.869283</td>\n",
       "      <td>0.869283</td>\n",
       "      <td>0.869283</td>\n",
       "      <td>0.869283</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>macro avg</th>\n",
       "      <td>0.744780</td>\n",
       "      <td>0.819523</td>\n",
       "      <td>0.772645</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sale</th>\n",
       "      <td>0.535144</td>\n",
       "      <td>0.749441</td>\n",
       "      <td>0.624418</td>\n",
       "      <td>447.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              precision    recall  f1-score      support\n",
       "No Sale        0.954416  0.889605  0.920872  2636.000000\n",
       "weighted avg   0.893626  0.869283  0.877889  3083.000000\n",
       "accuracy       0.869283  0.869283  0.869283     0.869283\n",
       "macro avg      0.744780  0.819523  0.772645  3083.000000\n",
       "Sale           0.535144  0.749441  0.624418   447.000000"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Print the imbalanced classification report\n",
    "from imblearn.metrics import classification_report_imbalanced\n",
    "print(classification_report_imbalanced(y_test, y_pred))\n",
    "\n",
    "# This will show the classification report as a Pandas Dataframe for better readability\n",
    "# Source: https://stackoverflow.com/questions/39662398/scikit-learn-output-metrics-classification-report-into-csv-tab-delimited-format'''\n",
    "from sklearn import metrics\n",
    "report = metrics.classification_report(y_test, y_pred, output_dict=True)\n",
    "df_classification_report = pd.DataFrame(report).transpose()\n",
    "df_classification_report = df_classification_report.sort_values(by=['f1-score'], ascending=False)\n",
    "\n",
    "df_classification_report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### SMOTE Oversampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'No Sale': 7786, 'Sale': 7786})\n"
     ]
    }
   ],
   "source": [
    "# Resample the training data with SMOTE\n",
    "from imblearn.over_sampling import SMOTE\n",
    "X_resampled, y_resampled = SMOTE(random_state=1, sampling_strategy='auto').fit_resample(X_train, y_train)\n",
    "print(Counter(y_resampled['Revenue']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(random_state=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(random_state=1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression(random_state=1)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the Logistic Regression model using the resampled data\n",
    "model = LogisticRegression(solver='lbfgs', random_state=1)\n",
    "model.fit(X_resampled, y_resampled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculate predictions\n",
    "y_pred = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8086832465976176"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculated the balanced accuracy score\n",
    "balanced_accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2394,  242],\n",
       "       [ 130,  317]], dtype=int64)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the confusion matrix\n",
    "cmatrix2 = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "cmatrix2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "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>Predicted No Sale</th>\n",
       "      <th>Predicted Sale</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual No Sale</th>\n",
       "      <td>2394</td>\n",
       "      <td>242</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual Sale</th>\n",
       "      <td>130</td>\n",
       "      <td>317</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Predicted No Sale  Predicted Sale\n",
       "Actual No Sale               2394             242\n",
       "Actual Sale                   130             317"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This will show the confussion matrix as a Pandas Dataframe for improved readability\n",
    "\n",
    "cmatrix_df2 = pd.DataFrame(cmatrix2, index=[\"Actual No Sale\", \"Actual Sale\"],\n",
    "                                   columns=[\"Predicted No Sale\", \"Predicted Sale\"])\n",
    "\n",
    "cmatrix_df2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   pre       rec       spe        f1       geo       iba       sup\n",
      "\n",
      "    No Sale       0.95      0.91      0.71      0.93      0.80      0.66      2636\n",
      "       Sale       0.57      0.71      0.91      0.63      0.80      0.63       447\n",
      "\n",
      "avg / total       0.89      0.88      0.74      0.88      0.80      0.65      3083\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print the imbalanced classification report\n",
    "print(classification_report_imbalanced(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>precision</th>\n",
       "      <th>recall</th>\n",
       "      <th>f1-score</th>\n",
       "      <th>support</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>No Sale</th>\n",
       "      <td>0.948494</td>\n",
       "      <td>0.908194</td>\n",
       "      <td>0.927907</td>\n",
       "      <td>2636.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weighted avg</th>\n",
       "      <td>0.893194</td>\n",
       "      <td>0.879338</td>\n",
       "      <td>0.884746</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>accuracy</th>\n",
       "      <td>0.879338</td>\n",
       "      <td>0.879338</td>\n",
       "      <td>0.879338</td>\n",
       "      <td>0.879338</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>macro avg</th>\n",
       "      <td>0.757789</td>\n",
       "      <td>0.808683</td>\n",
       "      <td>0.779063</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sale</th>\n",
       "      <td>0.567084</td>\n",
       "      <td>0.709172</td>\n",
       "      <td>0.630219</td>\n",
       "      <td>447.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              precision    recall  f1-score      support\n",
       "No Sale        0.948494  0.908194  0.927907  2636.000000\n",
       "weighted avg   0.893194  0.879338  0.884746  3083.000000\n",
       "accuracy       0.879338  0.879338  0.879338     0.879338\n",
       "macro avg      0.757789  0.808683  0.779063  3083.000000\n",
       "Sale           0.567084  0.709172  0.630219   447.000000"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This will show the classification report as a Pandas Dataframe for better readability\n",
    "# Source: https://stackoverflow.com/questions/39662398/scikit-learn-output-metrics-classification-report-into-csv-tab-delimited-format'''\n",
    "from sklearn import metrics\n",
    "report2 = metrics.classification_report(y_test, y_pred, output_dict=True)\n",
    "df_classification_report2 = pd.DataFrame(report2).transpose()\n",
    "df_classification_report2 = df_classification_report2.sort_values(by=['f1-score'], ascending=False)\n",
    "\n",
    "df_classification_report2\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Undersampling\n",
    "\n",
    "In this section, you will test an undersampling algorithms to determine which algorithm results in the best performance compared to the oversampling algorithms above. You will undersample the data using the Cluster Centroids algorithm and complete the folliowing steps:\n",
    "\n",
    "1. View the count of the target classes using `Counter` from the collections library. \n",
    "3. Use the resampled data to train a logistic regression model.\n",
    "3. Calculate the balanced accuracy score from sklearn.metrics.\n",
    "4. Print the confusion matrix from sklearn.metrics.\n",
    "5. Generate a classication report using the `imbalanced_classification_report` from imbalanced-learn.\n",
    "\n",
    "Note: Use a random state of 1 for each sampling algorithm to ensure consistency between tests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'No Sale': 1461, 'Sale': 1461})\n"
     ]
    }
   ],
   "source": [
    "# Resample the data using the ClusterCentroids resampler\n",
    "# Warning: This is a large dataset, and this step may take some time to complete\n",
    "from imblearn.under_sampling import ClusterCentroids\n",
    "cluster_centroids = ClusterCentroids(random_state=1)\n",
    "X_resampled, y_resampled = cluster_centroids.fit_resample(X_train, y_train)\n",
    "print(Counter(y_resampled[\"Revenue\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(random_state=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(random_state=1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression(random_state=1)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the Logistic Regression model using the resampled data\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "model = LogisticRegression(solver='lbfgs', random_state=1)\n",
    "model.fit(X_resampled, y_resampled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculate predictions\n",
    "y_pred = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5410848923696333"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculated the balanced accuracy score\n",
    "balanced_accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 824, 1812],\n",
       "       [ 103,  344]], dtype=int64)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the confusion matrix\n",
    "cmatrix3 = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "cmatrix3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>Predicted No Sale</th>\n",
       "      <th>Predicted Sale</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual No Sale</th>\n",
       "      <td>824</td>\n",
       "      <td>1812</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual Sale</th>\n",
       "      <td>103</td>\n",
       "      <td>344</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Predicted No Sale  Predicted Sale\n",
       "Actual No Sale                824            1812\n",
       "Actual Sale                   103             344"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This will show the classification report as a Pandas Dataframe for better readability\n",
    "cmatrix3_df = pd.DataFrame(\n",
    "    cmatrix3, index=[\"Actual No Sale\", \"Actual Sale\"], columns=[\"Predicted No Sale\", \"Predicted Sale\"])\n",
    "\n",
    "cmatrix3_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   pre       rec       spe        f1       geo       iba       sup\n",
      "\n",
      "    No Sale       0.89      0.31      0.77      0.46      0.49      0.23      2636\n",
      "       Sale       0.16      0.77      0.31      0.26      0.49      0.25       447\n",
      "\n",
      "avg / total       0.78      0.38      0.70      0.43      0.49      0.23      3083\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print the imbalanced classification report\n",
    "print(classification_report_imbalanced(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>precision</th>\n",
       "      <th>recall</th>\n",
       "      <th>f1-score</th>\n",
       "      <th>support</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>No Sale</th>\n",
       "      <td>0.888889</td>\n",
       "      <td>0.312595</td>\n",
       "      <td>0.462532</td>\n",
       "      <td>2636.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weighted avg</th>\n",
       "      <td>0.783144</td>\n",
       "      <td>0.378852</td>\n",
       "      <td>0.433792</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>accuracy</th>\n",
       "      <td>0.378852</td>\n",
       "      <td>0.378852</td>\n",
       "      <td>0.378852</td>\n",
       "      <td>0.378852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>macro avg</th>\n",
       "      <td>0.524222</td>\n",
       "      <td>0.541085</td>\n",
       "      <td>0.363421</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sale</th>\n",
       "      <td>0.159555</td>\n",
       "      <td>0.769575</td>\n",
       "      <td>0.264310</td>\n",
       "      <td>447.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              precision    recall  f1-score      support\n",
       "No Sale        0.888889  0.312595  0.462532  2636.000000\n",
       "weighted avg   0.783144  0.378852  0.433792  3083.000000\n",
       "accuracy       0.378852  0.378852  0.378852     0.378852\n",
       "macro avg      0.524222  0.541085  0.363421  3083.000000\n",
       "Sale           0.159555  0.769575  0.264310   447.000000"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This will show the classification report as a Pandas Dataframe for better readability\n",
    "# Source: https://stackoverflow.com/questions/39662398/scikit-learn-output-metrics-classification-report-into-csv-tab-delimited-format'''\n",
    "from sklearn import metrics\n",
    "report3 = metrics.classification_report(y_test, y_pred, output_dict=True)\n",
    "df_classification_report3 = pd.DataFrame(report3).transpose()\n",
    "df_classification_report3 = df_classification_report3.sort_values(by=['f1-score'], ascending=False)\n",
    "\n",
    "df_classification_report3\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Combination (Over and Under) Sampling\n",
    "\n",
    "In this section, you will test a combination over- and under-sampling algorithm to determine if the algorithm results in the best performance compared to the other sampling algorithms above. You will resample the data using the SMOTEENN algorithm and complete the folliowing steps:\n",
    "\n",
    "1. View the count of the target classes using `Counter` from the collections library. \n",
    "3. Use the resampled data to train a logistic regression model.\n",
    "3. Calculate the balanced accuracy score from sklearn.metrics.\n",
    "4. Print the confusion matrix from sklearn.metrics.\n",
    "5. Generate a classication report using the `imbalanced_classification_report` from imbalanced-learn.\n",
    "\n",
    "Note: Use a random state of 1 for each sampling algorithm to ensure consistency between tests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Counter({'Sale': 8908, 'No Sale': 7264})\n"
     ]
    }
   ],
   "source": [
    "# Resample the training data with SMOTEENN\n",
    "# Warning: This is a large dataset, and this step may take some time to complete\n",
    "from imblearn.combine import SMOTEENN\n",
    "\n",
    "smoteenn_ = SMOTEENN(random_state=0)\n",
    "X_resampled, y_resampled = smoteenn_.fit_resample(X, y)\n",
    "print(Counter(y_resampled['Revenue']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;background-color: white;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(random_state=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(random_state=1)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression(random_state=1)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the Logistic Regression model using the resampled data\n",
    "model = LogisticRegression(solver='lbfgs', random_state=1)\n",
    "model.fit(X_resampled, y_resampled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculate predictions\n",
    "y_pred = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8302848529906"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculated the balanced accuracy score\n",
    "balanced_accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2272,  364],\n",
       "       [  90,  357]], dtype=int64)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the confusion matrix\n",
    "cmatrix4 = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "cmatrix4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>Predicted No Sale</th>\n",
       "      <th>Predicted Sale</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual No Sale</th>\n",
       "      <td>2272</td>\n",
       "      <td>364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual Sale</th>\n",
       "      <td>90</td>\n",
       "      <td>357</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Predicted No Sale  Predicted Sale\n",
       "Actual No Sale               2272             364\n",
       "Actual Sale                    90             357"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This will show the classification report as a Pandas Dataframe for better readability\n",
    "cmatrix4_df = pd.DataFrame(\n",
    "    cmatrix4, index=[\"Actual No Sale\", \"Actual Sale\"], columns=[\"Predicted No Sale\", \"Predicted Sale\"])\n",
    "\n",
    "cmatrix4_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   pre       rec       spe        f1       geo       iba       sup\n",
      "\n",
      "    No Sale       0.96      0.86      0.80      0.91      0.83      0.69      2636\n",
      "       Sale       0.50      0.80      0.86      0.61      0.83      0.68       447\n",
      "\n",
      "avg / total       0.89      0.85      0.81      0.87      0.83      0.69      3083\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Print the imbalanced classification report\n",
    "print(classification_report_imbalanced(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "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>precision</th>\n",
       "      <th>recall</th>\n",
       "      <th>f1-score</th>\n",
       "      <th>support</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>No Sale</th>\n",
       "      <td>0.961897</td>\n",
       "      <td>0.861912</td>\n",
       "      <td>0.909164</td>\n",
       "      <td>2636.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>weighted avg</th>\n",
       "      <td>0.894223</td>\n",
       "      <td>0.852741</td>\n",
       "      <td>0.865977</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>accuracy</th>\n",
       "      <td>0.852741</td>\n",
       "      <td>0.852741</td>\n",
       "      <td>0.852741</td>\n",
       "      <td>0.852741</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>macro avg</th>\n",
       "      <td>0.728521</td>\n",
       "      <td>0.830285</td>\n",
       "      <td>0.760233</td>\n",
       "      <td>3083.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Sale</th>\n",
       "      <td>0.495146</td>\n",
       "      <td>0.798658</td>\n",
       "      <td>0.611301</td>\n",
       "      <td>447.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              precision    recall  f1-score      support\n",
       "No Sale        0.961897  0.861912  0.909164  2636.000000\n",
       "weighted avg   0.894223  0.852741  0.865977  3083.000000\n",
       "accuracy       0.852741  0.852741  0.852741     0.852741\n",
       "macro avg      0.728521  0.830285  0.760233  3083.000000\n",
       "Sale           0.495146  0.798658  0.611301   447.000000"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This will show the classification report as a Pandas Dataframe for better readability\n",
    "# Source: https://stackoverflow.com/questions/39662398/scikit-learn-output-metrics-classification-report-into-csv-tab-delimited-format'''\n",
    "from sklearn import metrics\n",
    "report4 = metrics.classification_report(y_test, y_pred, output_dict=True)\n",
    "df_classification_report4 = pd.DataFrame(report4).transpose()\n",
    "df_classification_report4 = df_classification_report4.sort_values(by=['f1-score'], ascending=False)\n",
    "\n",
    "df_classification_report4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}