Naive_Bayesian_AdultData.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "ed2c1af9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import packages\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns; sns.set()\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "a73bc249",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import data\n",
    "data = 'adult.csv'\n",
    "\n",
    "df = pd.read_csv(data, header=None) #, sep=',\\s')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "4916856e",
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39</td>\n",
       "      <td>State-gov</td>\n",
       "      <td>77516</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>2174</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50</td>\n",
       "      <td>Self-emp-not-inc</td>\n",
       "      <td>83311</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>38</td>\n",
       "      <td>Private</td>\n",
       "      <td>215646</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Divorced</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>53</td>\n",
       "      <td>Private</td>\n",
       "      <td>234721</td>\n",
       "      <td>11th</td>\n",
       "      <td>7</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>28</td>\n",
       "      <td>Private</td>\n",
       "      <td>338409</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Prof-specialty</td>\n",
       "      <td>Wife</td>\n",
       "      <td>Black</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>Cuba</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   0                  1       2           3   4                    5   \\\n",
       "0  39          State-gov   77516   Bachelors  13        Never-married   \n",
       "1  50   Self-emp-not-inc   83311   Bachelors  13   Married-civ-spouse   \n",
       "2  38            Private  215646     HS-grad   9             Divorced   \n",
       "3  53            Private  234721        11th   7   Married-civ-spouse   \n",
       "4  28            Private  338409   Bachelors  13   Married-civ-spouse   \n",
       "\n",
       "                   6               7       8        9     10  11  12  \\\n",
       "0        Adm-clerical   Not-in-family   White     Male  2174   0  40   \n",
       "1     Exec-managerial         Husband   White     Male     0   0  13   \n",
       "2   Handlers-cleaners   Not-in-family   White     Male     0   0  40   \n",
       "3   Handlers-cleaners         Husband   Black     Male     0   0  40   \n",
       "4      Prof-specialty            Wife   Black   Female     0   0  40   \n",
       "\n",
       "               13      14  \n",
       "0   United-States   <=50K  \n",
       "1   United-States   <=50K  \n",
       "2   United-States   <=50K  \n",
       "3   United-States   <=50K  \n",
       "4            Cuba   <=50K  "
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "ddb81975",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(32561, 15)"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# view dimensions of dataset\n",
    "\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "09c6e455",
   "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>workclass</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>education</th>\n",
       "      <th>education_num</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>capital_gain</th>\n",
       "      <th>capital_loss</th>\n",
       "      <th>hours_per_week</th>\n",
       "      <th>native_country</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39</td>\n",
       "      <td>State-gov</td>\n",
       "      <td>77516</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>2174</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50</td>\n",
       "      <td>Self-emp-not-inc</td>\n",
       "      <td>83311</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>38</td>\n",
       "      <td>Private</td>\n",
       "      <td>215646</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>9</td>\n",
       "      <td>Divorced</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>53</td>\n",
       "      <td>Private</td>\n",
       "      <td>234721</td>\n",
       "      <td>11th</td>\n",
       "      <td>7</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>28</td>\n",
       "      <td>Private</td>\n",
       "      <td>338409</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>13</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Prof-specialty</td>\n",
       "      <td>Wife</td>\n",
       "      <td>Black</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>Cuba</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age          workclass  fnlwgt   education  education_num  \\\n",
       "0   39          State-gov   77516   Bachelors             13   \n",
       "1   50   Self-emp-not-inc   83311   Bachelors             13   \n",
       "2   38            Private  215646     HS-grad              9   \n",
       "3   53            Private  234721        11th              7   \n",
       "4   28            Private  338409   Bachelors             13   \n",
       "\n",
       "        marital_status          occupation    relationship    race      sex  \\\n",
       "0        Never-married        Adm-clerical   Not-in-family   White     Male   \n",
       "1   Married-civ-spouse     Exec-managerial         Husband   White     Male   \n",
       "2             Divorced   Handlers-cleaners   Not-in-family   White     Male   \n",
       "3   Married-civ-spouse   Handlers-cleaners         Husband   Black     Male   \n",
       "4   Married-civ-spouse      Prof-specialty            Wife   Black   Female   \n",
       "\n",
       "   capital_gain  capital_loss  hours_per_week  native_country  income  \n",
       "0          2174             0              40   United-States   <=50K  \n",
       "1             0             0              13   United-States   <=50K  \n",
       "2             0             0              40   United-States   <=50K  \n",
       "3             0             0              40   United-States   <=50K  \n",
       "4             0             0              40            Cuba   <=50K  "
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Give new names to columns\n",
    "col_names = ['age', 'workclass', 'fnlwgt', 'education', 'education_num', 'marital_status', 'occupation', 'relationship',\n",
    "             'race', 'sex', 'capital_gain', 'capital_loss', 'hours_per_week', 'native_country', 'income']\n",
    "\n",
    "df.columns = col_names\n",
    "\n",
    "#df.columns\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "55d446c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 32561 entries, 0 to 32560\n",
      "Data columns (total 15 columns):\n",
      " #   Column          Non-Null Count  Dtype \n",
      "---  ------          --------------  ----- \n",
      " 0   age             32561 non-null  int64 \n",
      " 1   workclass       32561 non-null  object\n",
      " 2   fnlwgt          32561 non-null  int64 \n",
      " 3   education       32561 non-null  object\n",
      " 4   education_num   32561 non-null  int64 \n",
      " 5   marital_status  32561 non-null  object\n",
      " 6   occupation      32561 non-null  object\n",
      " 7   relationship    32561 non-null  object\n",
      " 8   race            32561 non-null  object\n",
      " 9   sex             32561 non-null  object\n",
      " 10  capital_gain    32561 non-null  int64 \n",
      " 11  capital_loss    32561 non-null  int64 \n",
      " 12  hours_per_week  32561 non-null  int64 \n",
      " 13  native_country  32561 non-null  object\n",
      " 14  income          32561 non-null  object\n",
      "dtypes: int64(6), object(9)\n",
      "memory usage: 3.7+ MB\n"
     ]
    }
   ],
   "source": [
    "# sumary of dataset\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "21769009",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "There are 9 categorical variables\n",
      "\n",
      "The categorical variables are :\n",
      "\n",
      " ['workclass', 'education', 'marital_status', 'occupation', 'relationship', 'race', 'sex', 'native_country', 'income']\n"
     ]
    }
   ],
   "source": [
    "# find categorical variables. They are of type object\n",
    "\n",
    "categorical = [var for var in df.columns if df[var].dtype=='O']\n",
    "print('There are {} categorical variables\\n'.format(len(categorical)))\n",
    "print('The categorical variables are :\\n\\n', categorical)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "2508bd5d",
   "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>workclass</th>\n",
       "      <th>education</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>native_country</th>\n",
       "      <th>income</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>State-gov</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Self-emp-not-inc</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Exec-managerial</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Divorced</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Private</td>\n",
       "      <td>11th</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Handlers-cleaners</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Private</td>\n",
       "      <td>Bachelors</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Prof-specialty</td>\n",
       "      <td>Wife</td>\n",
       "      <td>Black</td>\n",
       "      <td>Female</td>\n",
       "      <td>Cuba</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           workclass   education       marital_status          occupation  \\\n",
       "0          State-gov   Bachelors        Never-married        Adm-clerical   \n",
       "1   Self-emp-not-inc   Bachelors   Married-civ-spouse     Exec-managerial   \n",
       "2            Private     HS-grad             Divorced   Handlers-cleaners   \n",
       "3            Private        11th   Married-civ-spouse   Handlers-cleaners   \n",
       "4            Private   Bachelors   Married-civ-spouse      Prof-specialty   \n",
       "\n",
       "     relationship    race      sex  native_country  income  \n",
       "0   Not-in-family   White     Male   United-States   <=50K  \n",
       "1         Husband   White     Male   United-States   <=50K  \n",
       "2   Not-in-family   White     Male   United-States   <=50K  \n",
       "3         Husband   Black     Male   United-States   <=50K  \n",
       "4            Wife   Black   Female            Cuba   <=50K  "
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# view the categorical variables\n",
    "df[categorical].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "3ff3ae4f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "workclass         0\n",
       "education         0\n",
       "marital_status    0\n",
       "occupation        0\n",
       "relationship      0\n",
       "race              0\n",
       "sex               0\n",
       "native_country    0\n",
       "income            0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Explore problems in categorical data.\n",
    "# check missing values in categorical variables\n",
    "\n",
    "df[categorical].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "702b655f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Private             22696\n",
      " Self-emp-not-inc     2541\n",
      " Local-gov            2093\n",
      " ?                    1836\n",
      " State-gov            1298\n",
      " Self-emp-inc         1116\n",
      " Federal-gov           960\n",
      " Without-pay            14\n",
      " Never-worked            7\n",
      "Name: workclass, dtype: int64\n",
      " HS-grad         10501\n",
      " Some-college     7291\n",
      " Bachelors        5355\n",
      " Masters          1723\n",
      " Assoc-voc        1382\n",
      " 11th             1175\n",
      " Assoc-acdm       1067\n",
      " 10th              933\n",
      " 7th-8th           646\n",
      " Prof-school       576\n",
      " 9th               514\n",
      " 12th              433\n",
      " Doctorate         413\n",
      " 5th-6th           333\n",
      " 1st-4th           168\n",
      " Preschool          51\n",
      "Name: education, dtype: int64\n",
      " Married-civ-spouse       14976\n",
      " Never-married            10683\n",
      " Divorced                  4443\n",
      " Separated                 1025\n",
      " Widowed                    993\n",
      " Married-spouse-absent      418\n",
      " Married-AF-spouse           23\n",
      "Name: marital_status, dtype: int64\n",
      " Prof-specialty       4140\n",
      " Craft-repair         4099\n",
      " Exec-managerial      4066\n",
      " Adm-clerical         3770\n",
      " Sales                3650\n",
      " Other-service        3295\n",
      " Machine-op-inspct    2002\n",
      " ?                    1843\n",
      " Transport-moving     1597\n",
      " Handlers-cleaners    1370\n",
      " Farming-fishing       994\n",
      " Tech-support          928\n",
      " Protective-serv       649\n",
      " Priv-house-serv       149\n",
      " Armed-Forces            9\n",
      "Name: occupation, dtype: int64\n",
      " Husband           13193\n",
      " Not-in-family      8305\n",
      " Own-child          5068\n",
      " Unmarried          3446\n",
      " Wife               1568\n",
      " Other-relative      981\n",
      "Name: relationship, dtype: int64\n",
      " White                 27816\n",
      " Black                  3124\n",
      " Asian-Pac-Islander     1039\n",
      " Amer-Indian-Eskimo      311\n",
      " Other                   271\n",
      "Name: race, dtype: int64\n",
      " Male      21790\n",
      " Female    10771\n",
      "Name: sex, dtype: int64\n",
      " United-States                 29170\n",
      " Mexico                          643\n",
      " ?                               583\n",
      " Philippines                     198\n",
      " Germany                         137\n",
      " Canada                          121\n",
      " Puerto-Rico                     114\n",
      " El-Salvador                     106\n",
      " India                           100\n",
      " Cuba                             95\n",
      " England                          90\n",
      " Jamaica                          81\n",
      " South                            80\n",
      " China                            75\n",
      " Italy                            73\n",
      " Dominican-Republic               70\n",
      " Vietnam                          67\n",
      " Guatemala                        64\n",
      " Japan                            62\n",
      " Poland                           60\n",
      " Columbia                         59\n",
      " Taiwan                           51\n",
      " Haiti                            44\n",
      " Iran                             43\n",
      " Portugal                         37\n",
      " Nicaragua                        34\n",
      " Peru                             31\n",
      " France                           29\n",
      " Greece                           29\n",
      " Ecuador                          28\n",
      " Ireland                          24\n",
      " Hong                             20\n",
      " Cambodia                         19\n",
      " Trinadad&Tobago                  19\n",
      " Laos                             18\n",
      " Thailand                         18\n",
      " Yugoslavia                       16\n",
      " Outlying-US(Guam-USVI-etc)       14\n",
      " Honduras                         13\n",
      " Hungary                          13\n",
      " Scotland                         12\n",
      " Holand-Netherlands                1\n",
      "Name: native_country, dtype: int64\n",
      " <=50K    24720\n",
      " >50K      7841\n",
      "Name: income, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "# view frequency counts of values in categorical variables\n",
    "\n",
    "for var in categorical: \n",
    "    \n",
    "    print(df[var].value_counts())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "20cf5c12",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Private             0.697030\n",
      " Self-emp-not-inc    0.078038\n",
      " Local-gov           0.064279\n",
      " ?                   0.056386\n",
      " State-gov           0.039864\n",
      " Self-emp-inc        0.034274\n",
      " Federal-gov         0.029483\n",
      " Without-pay         0.000430\n",
      " Never-worked        0.000215\n",
      "Name: workclass, dtype: float64\n",
      " HS-grad         0.322502\n",
      " Some-college    0.223918\n",
      " Bachelors       0.164461\n",
      " Masters         0.052916\n",
      " Assoc-voc       0.042443\n",
      " 11th            0.036086\n",
      " Assoc-acdm      0.032769\n",
      " 10th            0.028654\n",
      " 7th-8th         0.019840\n",
      " Prof-school     0.017690\n",
      " 9th             0.015786\n",
      " 12th            0.013298\n",
      " Doctorate       0.012684\n",
      " 5th-6th         0.010227\n",
      " 1st-4th         0.005160\n",
      " Preschool       0.001566\n",
      "Name: education, dtype: float64\n",
      " Married-civ-spouse       0.459937\n",
      " Never-married            0.328092\n",
      " Divorced                 0.136452\n",
      " Separated                0.031479\n",
      " Widowed                  0.030497\n",
      " Married-spouse-absent    0.012837\n",
      " Married-AF-spouse        0.000706\n",
      "Name: marital_status, dtype: float64\n",
      " Prof-specialty       0.127146\n",
      " Craft-repair         0.125887\n",
      " Exec-managerial      0.124873\n",
      " Adm-clerical         0.115783\n",
      " Sales                0.112097\n",
      " Other-service        0.101195\n",
      " Machine-op-inspct    0.061485\n",
      " ?                    0.056601\n",
      " Transport-moving     0.049046\n",
      " Handlers-cleaners    0.042075\n",
      " Farming-fishing      0.030527\n",
      " Tech-support         0.028500\n",
      " Protective-serv      0.019932\n",
      " Priv-house-serv      0.004576\n",
      " Armed-Forces         0.000276\n",
      "Name: occupation, dtype: float64\n",
      " Husband           0.405178\n",
      " Not-in-family     0.255060\n",
      " Own-child         0.155646\n",
      " Unmarried         0.105832\n",
      " Wife              0.048156\n",
      " Other-relative    0.030128\n",
      "Name: relationship, dtype: float64\n",
      " White                 0.854274\n",
      " Black                 0.095943\n",
      " Asian-Pac-Islander    0.031909\n",
      " Amer-Indian-Eskimo    0.009551\n",
      " Other                 0.008323\n",
      "Name: race, dtype: float64\n",
      " Male      0.669205\n",
      " Female    0.330795\n",
      "Name: sex, dtype: float64\n",
      " United-States                 0.895857\n",
      " Mexico                        0.019748\n",
      " ?                             0.017905\n",
      " Philippines                   0.006081\n",
      " Germany                       0.004207\n",
      " Canada                        0.003716\n",
      " Puerto-Rico                   0.003501\n",
      " El-Salvador                   0.003255\n",
      " India                         0.003071\n",
      " Cuba                          0.002918\n",
      " England                       0.002764\n",
      " Jamaica                       0.002488\n",
      " South                         0.002457\n",
      " China                         0.002303\n",
      " Italy                         0.002242\n",
      " Dominican-Republic            0.002150\n",
      " Vietnam                       0.002058\n",
      " Guatemala                     0.001966\n",
      " Japan                         0.001904\n",
      " Poland                        0.001843\n",
      " Columbia                      0.001812\n",
      " Taiwan                        0.001566\n",
      " Haiti                         0.001351\n",
      " Iran                          0.001321\n",
      " Portugal                      0.001136\n",
      " Nicaragua                     0.001044\n",
      " Peru                          0.000952\n",
      " France                        0.000891\n",
      " Greece                        0.000891\n",
      " Ecuador                       0.000860\n",
      " Ireland                       0.000737\n",
      " Hong                          0.000614\n",
      " Cambodia                      0.000584\n",
      " Trinadad&Tobago               0.000584\n",
      " Laos                          0.000553\n",
      " Thailand                      0.000553\n",
      " Yugoslavia                    0.000491\n",
      " Outlying-US(Guam-USVI-etc)    0.000430\n",
      " Honduras                      0.000399\n",
      " Hungary                       0.000399\n",
      " Scotland                      0.000369\n",
      " Holand-Netherlands            0.000031\n",
      "Name: native_country, dtype: float64\n",
      " <=50K    0.75919\n",
      " >50K     0.24081\n",
      "Name: income, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "# view frequency distribution of categorical variables\n",
    "\n",
    "for var in categorical: \n",
    "    \n",
    "    print(df[var].value_counts()/np.float64(len(df)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "749dfb1d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([' State-gov', ' Self-emp-not-inc', ' Private', ' Federal-gov',\n",
       "       ' Local-gov', ' ?', ' Self-emp-inc', ' Without-pay',\n",
       "       ' Never-worked'], dtype=object)"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Explore one variable. here Workclass\n",
    "# check labels in workclass variable\n",
    "\n",
    "df.workclass.unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "11920377",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       " Private             22696\n",
       " Self-emp-not-inc     2541\n",
       " Local-gov            2093\n",
       " ?                    1836\n",
       " State-gov            1298\n",
       " Self-emp-inc         1116\n",
       " Federal-gov           960\n",
       " Without-pay            14\n",
       " Never-worked            7\n",
       "Name: workclass, dtype: int64"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check frequency distribution of values in workclass variable\n",
    "\n",
    "df.workclass.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "663db06c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# An unlabeled variable,up to 1836. We will labele it NaN for Not a Number\n",
    "# replace '?' values in workclass variable with `NaN`\n",
    "\n",
    "# df['workclass'].mask(df['workclass'] == ' ?', np.NaN, inplace=True)\n",
    "# df.replace('?', np.NaN, inplace = True)\n",
    "df['workclass'].replace(' ?', np.NaN, inplace = True)\n",
    "# df['occupation'].replace('?', np.NaN, inplace=True)\n",
    "# df['native_country'].replace('?', np.NaN, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "4ac2e7e0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       " Private             22696\n",
       " Self-emp-not-inc     2541\n",
       " Local-gov            2093\n",
       " State-gov            1298\n",
       " Self-emp-inc         1116\n",
       " Federal-gov           960\n",
       " Without-pay            14\n",
       " Never-worked            7\n",
       "Name: workclass, dtype: int64"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# again check the frequency distribution of values in workclass variable\n",
    "\n",
    "df.workclass.value_counts()\n",
    "# df.occupation.value_counts()\n",
    "# df.native_country.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "356d1aad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "workclass         1836\n",
       "education            0\n",
       "marital_status       0\n",
       "occupation           0\n",
       "relationship         0\n",
       "race                 0\n",
       "sex                  0\n",
       "native_country       0\n",
       "income               0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check missing categorical values\n",
    "df[categorical].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "7d0423eb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "workclass  contains  9  labels\n",
      "education  contains  16  labels\n",
      "marital_status  contains  7  labels\n",
      "occupation  contains  15  labels\n",
      "relationship  contains  6  labels\n",
      "race  contains  5  labels\n",
      "sex  contains  2  labels\n",
      "native_country  contains  42  labels\n",
      "income  contains  2  labels\n"
     ]
    }
   ],
   "source": [
    "# check for cardinality in categorical variables\n",
    "\n",
    "for var in categorical:\n",
    "        print(var, ' contains ', len(df[var].unique()), ' labels')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "c0008507",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "There are 6 numerical variables\n",
      "\n",
      "The numerical variables are : ['age', 'fnlwgt', 'education_num', 'capital_gain', 'capital_loss', 'hours_per_week']\n"
     ]
    }
   ],
   "source": [
    "# Explore numerical variables\n",
    "# find numerical variables\n",
    "\n",
    "numerical = [var for var in df.columns if df[var].dtype!='O']\n",
    "\n",
    "print('There are {} numerical variables\\n'.format(len(numerical)))\n",
    "\n",
    "print('The numerical variables are :', numerical)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "31cd0dec",
   "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>fnlwgt</th>\n",
       "      <th>education_num</th>\n",
       "      <th>capital_gain</th>\n",
       "      <th>capital_loss</th>\n",
       "      <th>hours_per_week</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39</td>\n",
       "      <td>77516</td>\n",
       "      <td>13</td>\n",
       "      <td>2174</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50</td>\n",
       "      <td>83311</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>38</td>\n",
       "      <td>215646</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>53</td>\n",
       "      <td>234721</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>28</td>\n",
       "      <td>338409</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  fnlwgt  education_num  capital_gain  capital_loss  hours_per_week\n",
       "0   39   77516             13          2174             0              40\n",
       "1   50   83311             13             0             0              13\n",
       "2   38  215646              9             0             0              40\n",
       "3   53  234721              7             0             0              40\n",
       "4   28  338409             13             0             0              40"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# view the numerical variables\n",
    "\n",
    "df[numerical].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "ae87a9bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age               0\n",
       "fnlwgt            0\n",
       "education_num     0\n",
       "capital_gain      0\n",
       "capital_loss      0\n",
       "hours_per_week    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check missing values in numerical variables\n",
    "\n",
    "df[numerical].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "4027d0d0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Vector and target v ariable\n",
    "X = df.drop(['income'], axis=1)\n",
    "\n",
    "y = df['income']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "94574977",
   "metadata": {},
   "outputs": [],
   "source": [
    "# split X and y into training and testing sets\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "85109c1b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((22792, 14), (9769, 14))"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check the shape of X_train and X_test\n",
    "\n",
    "X_train.shape, X_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "4e88f130",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age                int64\n",
       "workclass         object\n",
       "fnlwgt             int64\n",
       "education         object\n",
       "education_num      int64\n",
       "marital_status    object\n",
       "occupation        object\n",
       "relationship      object\n",
       "race              object\n",
       "sex               object\n",
       "capital_gain       int64\n",
       "capital_loss       int64\n",
       "hours_per_week     int64\n",
       "native_country    object\n",
       "dtype: object"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check data types in X_train\n",
    "\n",
    "X_train.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "c74cfdaf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['workclass',\n",
       " 'education',\n",
       " 'marital_status',\n",
       " 'occupation',\n",
       " 'relationship',\n",
       " 'race',\n",
       " 'sex',\n",
       " 'native_country']"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# display categorical variables\n",
    "\n",
    "categorical = [col for col in X_train.columns if X_train[col].dtypes == 'O']\n",
    "\n",
    "categorical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "8d0639c7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['age',\n",
       " 'fnlwgt',\n",
       " 'education_num',\n",
       " 'capital_gain',\n",
       " 'capital_loss',\n",
       " 'hours_per_week']"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# display numerical variables\n",
    "\n",
    "numerical = [col for col in X_train.columns if X_train[col].dtypes != 'O']\n",
    "\n",
    "numerical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "8f14f9f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "workclass         0.055985\n",
       "education         0.000000\n",
       "marital_status    0.000000\n",
       "occupation        0.000000\n",
       "relationship      0.000000\n",
       "race              0.000000\n",
       "sex               0.000000\n",
       "native_country    0.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print percentage of missing values in the categorical variables in training set\n",
    "\n",
    "X_train[categorical].isnull().mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "9945a8fe",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "workclass 0.055984555984555984\n"
     ]
    }
   ],
   "source": [
    "# print categorical variables with missing data\n",
    "\n",
    "for col in categorical:\n",
    "    if X_train[col].isnull().mean()>0:\n",
    "        print(col, (X_train[col].isnull().mean()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "6bbcb4a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# input missing categorical variables with most frequent value\n",
    "\n",
    "for df2 in [X_train, X_test]:\n",
    "    df2['workclass'].fillna(X_train['workclass'].mode()[0], inplace=True)\n",
    "    df2['occupation'].fillna(X_train['occupation'].mode()[0], inplace=True)\n",
    "    df2['native_country'].fillna(X_train['native_country'].mode()[0], inplace=True)  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "7bc6f118",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "workclass         0\n",
       "education         0\n",
       "marital_status    0\n",
       "occupation        0\n",
       "relationship      0\n",
       "race              0\n",
       "sex               0\n",
       "native_country    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check missing values in categorical variables in X_train\n",
    "\n",
    "X_train[categorical].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "c9df4f19",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "workclass         0\n",
       "education         0\n",
       "marital_status    0\n",
       "occupation        0\n",
       "relationship      0\n",
       "race              0\n",
       "sex               0\n",
       "native_country    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check missing values in categorical variables in X_test\n",
    "\n",
    "X_test[categorical].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "7f68886c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age               0\n",
       "workclass         0\n",
       "fnlwgt            0\n",
       "education         0\n",
       "education_num     0\n",
       "marital_status    0\n",
       "occupation        0\n",
       "relationship      0\n",
       "race              0\n",
       "sex               0\n",
       "capital_gain      0\n",
       "capital_loss      0\n",
       "hours_per_week    0\n",
       "native_country    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check missing values in X_train\n",
    "\n",
    "X_train.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "ffdfa5c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "age               0\n",
       "workclass         0\n",
       "fnlwgt            0\n",
       "education         0\n",
       "education_num     0\n",
       "marital_status    0\n",
       "occupation        0\n",
       "relationship      0\n",
       "race              0\n",
       "sex               0\n",
       "capital_gain      0\n",
       "capital_loss      0\n",
       "hours_per_week    0\n",
       "native_country    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check missing values in X_test\n",
    "\n",
    "X_test.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "12e06f74",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['workclass',\n",
       " 'education',\n",
       " 'marital_status',\n",
       " 'occupation',\n",
       " 'relationship',\n",
       " 'race',\n",
       " 'sex',\n",
       " 'native_country']"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# print categorical variables\n",
    "\n",
    "categorical"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "85ee23de",
   "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>workclass</th>\n",
       "      <th>education</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>occupation</th>\n",
       "      <th>relationship</th>\n",
       "      <th>race</th>\n",
       "      <th>sex</th>\n",
       "      <th>native_country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>32098</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Craft-repair</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25206</th>\n",
       "      <td>State-gov</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Divorced</td>\n",
       "      <td>Adm-clerical</td>\n",
       "      <td>Unmarried</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23491</th>\n",
       "      <td>Private</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Sales</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>United-States</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12367</th>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Craft-repair</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>Guatemala</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7054</th>\n",
       "      <td>Private</td>\n",
       "      <td>7th-8th</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Craft-repair</td>\n",
       "      <td>Not-in-family</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>Germany</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        workclass      education       marital_status     occupation  \\\n",
       "32098     Private        HS-grad   Married-civ-spouse   Craft-repair   \n",
       "25206   State-gov        HS-grad             Divorced   Adm-clerical   \n",
       "23491     Private   Some-college   Married-civ-spouse          Sales   \n",
       "12367     Private        HS-grad        Never-married   Craft-repair   \n",
       "7054      Private        7th-8th        Never-married   Craft-repair   \n",
       "\n",
       "         relationship    race      sex  native_country  \n",
       "32098         Husband   White     Male   United-States  \n",
       "25206       Unmarried   White   Female   United-States  \n",
       "23491         Husband   White     Male   United-States  \n",
       "12367   Not-in-family   White     Male       Guatemala  \n",
       "7054    Not-in-family   White     Male         Germany  "
      ]
     },
     "execution_count": 87,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train[categorical].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "e769586d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting category_encoders\n",
      "  Using cached category_encoders-2.6.3-py2.py3-none-any.whl (81 kB)\n",
      "Requirement already satisfied: statsmodels>=0.9.0 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from category_encoders) (0.13.2)\n",
      "Requirement already satisfied: patsy>=0.5.1 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from category_encoders) (0.5.2)\n",
      "Requirement already satisfied: scikit-learn>=0.20.0 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from category_encoders) (1.0.2)\n",
      "Requirement already satisfied: scipy>=1.0.0 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from category_encoders) (1.7.3)\n",
      "Requirement already satisfied: pandas>=1.0.5 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from category_encoders) (1.4.2)\n",
      "Requirement already satisfied: numpy>=1.14.0 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from category_encoders) (1.22.4)\n",
      "Requirement already satisfied: python-dateutil>=2.8.1 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from pandas>=1.0.5->category_encoders) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from pandas>=1.0.5->category_encoders) (2021.3)\n",
      "Requirement already satisfied: six in c:\\users\\madon\\anaconda3\\lib\\site-packages (from patsy>=0.5.1->category_encoders) (1.16.0)\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from scikit-learn>=0.20.0->category_encoders) (2.2.0)\n",
      "Requirement already satisfied: joblib>=0.11 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from scikit-learn>=0.20.0->category_encoders) (1.1.0)\n",
      "Requirement already satisfied: packaging>=21.3 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from statsmodels>=0.9.0->category_encoders) (21.3)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in c:\\users\\madon\\anaconda3\\lib\\site-packages (from packaging>=21.3->statsmodels>=0.9.0->category_encoders) (3.0.4)\n",
      "Installing collected packages: category-encoders\n",
      "Successfully installed category-encoders-2.6.3\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "pip install category_encoders"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "cf36c503",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import category encoders\n",
    "\n",
    "import category_encoders as ce"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "551e17de",
   "metadata": {},
   "outputs": [],
   "source": [
    "# encode remaining variables with one-hot encoding\n",
    "\n",
    "encoder = ce.OneHotEncoder(cols=['workclass', 'education', 'marital_status', 'occupation', 'relationship', \n",
    "                                 'race', 'sex', 'native_country'])\n",
    "\n",
    "X_train = encoder.fit_transform(X_train)\n",
    "\n",
    "X_test = encoder.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "id": "1dcf391d",
   "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>workclass_1</th>\n",
       "      <th>workclass_2</th>\n",
       "      <th>workclass_3</th>\n",
       "      <th>workclass_4</th>\n",
       "      <th>workclass_5</th>\n",
       "      <th>workclass_6</th>\n",
       "      <th>workclass_7</th>\n",
       "      <th>workclass_8</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>...</th>\n",
       "      <th>native_country_33</th>\n",
       "      <th>native_country_34</th>\n",
       "      <th>native_country_35</th>\n",
       "      <th>native_country_36</th>\n",
       "      <th>native_country_37</th>\n",
       "      <th>native_country_38</th>\n",
       "      <th>native_country_39</th>\n",
       "      <th>native_country_40</th>\n",
       "      <th>native_country_41</th>\n",
       "      <th>native_country_42</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>32098</th>\n",
       "      <td>45</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>170871</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25206</th>\n",
       "      <td>47</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>108890</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23491</th>\n",
       "      <td>48</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>187505</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12367</th>\n",
       "      <td>29</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>145592</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7054</th>\n",
       "      <td>23</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>203003</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 107 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  workclass_1  workclass_2  workclass_3  workclass_4  workclass_5  \\\n",
       "32098   45            1            0            0            0            0   \n",
       "25206   47            0            1            0            0            0   \n",
       "23491   48            1            0            0            0            0   \n",
       "12367   29            1            0            0            0            0   \n",
       "7054    23            1            0            0            0            0   \n",
       "\n",
       "       workclass_6  workclass_7  workclass_8  fnlwgt  ...  native_country_33  \\\n",
       "32098            0            0            0  170871  ...                  0   \n",
       "25206            0            0            0  108890  ...                  0   \n",
       "23491            0            0            0  187505  ...                  0   \n",
       "12367            0            0            0  145592  ...                  0   \n",
       "7054             0            0            0  203003  ...                  0   \n",
       "\n",
       "       native_country_34  native_country_35  native_country_36  \\\n",
       "32098                  0                  0                  0   \n",
       "25206                  0                  0                  0   \n",
       "23491                  0                  0                  0   \n",
       "12367                  0                  0                  0   \n",
       "7054                   0                  0                  0   \n",
       "\n",
       "       native_country_37  native_country_38  native_country_39  \\\n",
       "32098                  0                  0                  0   \n",
       "25206                  0                  0                  0   \n",
       "23491                  0                  0                  0   \n",
       "12367                  0                  0                  0   \n",
       "7054                   0                  0                  0   \n",
       "\n",
       "       native_country_40  native_country_41  native_country_42  \n",
       "32098                  0                  0                  0  \n",
       "25206                  0                  0                  0  \n",
       "23491                  0                  0                  0  \n",
       "12367                  0                  0                  0  \n",
       "7054                   0                  0                  0  \n",
       "\n",
       "[5 rows x 107 columns]"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "id": "999401fd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(22792, 107)"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "id": "40b60a5a",
   "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>workclass_1</th>\n",
       "      <th>workclass_2</th>\n",
       "      <th>workclass_3</th>\n",
       "      <th>workclass_4</th>\n",
       "      <th>workclass_5</th>\n",
       "      <th>workclass_6</th>\n",
       "      <th>workclass_7</th>\n",
       "      <th>workclass_8</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>...</th>\n",
       "      <th>native_country_33</th>\n",
       "      <th>native_country_34</th>\n",
       "      <th>native_country_35</th>\n",
       "      <th>native_country_36</th>\n",
       "      <th>native_country_37</th>\n",
       "      <th>native_country_38</th>\n",
       "      <th>native_country_39</th>\n",
       "      <th>native_country_40</th>\n",
       "      <th>native_country_41</th>\n",
       "      <th>native_country_42</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>22278</th>\n",
       "      <td>27</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>177119</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8950</th>\n",
       "      <td>27</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>216481</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7838</th>\n",
       "      <td>25</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>256263</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16505</th>\n",
       "      <td>46</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>147640</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19140</th>\n",
       "      <td>45</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>172822</td>\n",
       "      <td>...</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>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 107 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       age  workclass_1  workclass_2  workclass_3  workclass_4  workclass_5  \\\n",
       "22278   27            1            0            0            0            0   \n",
       "8950    27            1            0            0            0            0   \n",
       "7838    25            1            0            0            0            0   \n",
       "16505   46            1            0            0            0            0   \n",
       "19140   45            1            0            0            0            0   \n",
       "\n",
       "       workclass_6  workclass_7  workclass_8  fnlwgt  ...  native_country_33  \\\n",
       "22278            0            0            0  177119  ...                  0   \n",
       "8950             0            0            0  216481  ...                  0   \n",
       "7838             0            0            0  256263  ...                  0   \n",
       "16505            0            0            0  147640  ...                  0   \n",
       "19140            0            0            0  172822  ...                  0   \n",
       "\n",
       "       native_country_34  native_country_35  native_country_36  \\\n",
       "22278                  0                  0                  0   \n",
       "8950                   0                  0                  0   \n",
       "7838                   0                  0                  0   \n",
       "16505                  0                  0                  0   \n",
       "19140                  0                  0                  0   \n",
       "\n",
       "       native_country_37  native_country_38  native_country_39  \\\n",
       "22278                  0                  0                  0   \n",
       "8950                   0                  0                  0   \n",
       "7838                   0                  0                  0   \n",
       "16505                  0                  0                  0   \n",
       "19140                  0                  0                  0   \n",
       "\n",
       "       native_country_40  native_country_41  native_country_42  \n",
       "22278                  0                  0                  0  \n",
       "8950                   0                  0                  0  \n",
       "7838                   0                  0                  0  \n",
       "16505                  0                  0                  0  \n",
       "19140                  0                  0                  0  \n",
       "\n",
       "[5 rows x 107 columns]"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "id": "5244bd04",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(9769, 107)"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "id": "a23b6eef",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Feature scaling\n",
    "\n",
    "cols = X_train.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "id": "58a6cc1f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import RobustScaler\n",
    "\n",
    "scaler = RobustScaler()\n",
    "\n",
    "X_train = scaler.fit_transform(X_train)\n",
    "\n",
    "X_test = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "id": "7bc750c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = pd.DataFrame(X_train, columns=[cols])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "id": "01b72872",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test = pd.DataFrame(X_test, columns=[cols])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "id": "ae0a06f4",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>workclass_1</th>\n",
       "      <th>workclass_2</th>\n",
       "      <th>workclass_3</th>\n",
       "      <th>workclass_4</th>\n",
       "      <th>workclass_5</th>\n",
       "      <th>workclass_6</th>\n",
       "      <th>workclass_7</th>\n",
       "      <th>workclass_8</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>...</th>\n",
       "      <th>native_country_33</th>\n",
       "      <th>native_country_34</th>\n",
       "      <th>native_country_35</th>\n",
       "      <th>native_country_36</th>\n",
       "      <th>native_country_37</th>\n",
       "      <th>native_country_38</th>\n",
       "      <th>native_country_39</th>\n",
       "      <th>native_country_40</th>\n",
       "      <th>native_country_41</th>\n",
       "      <th>native_country_42</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.40</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.058906</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.50</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.578076</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.55</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.080425</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.40</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.270650</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.70</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.210240</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 107 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    age workclass_1 workclass_2 workclass_3 workclass_4 workclass_5  \\\n",
       "0  0.40         0.0         0.0         0.0         0.0         0.0   \n",
       "1  0.50        -1.0         1.0         0.0         0.0         0.0   \n",
       "2  0.55         0.0         0.0         0.0         0.0         0.0   \n",
       "3 -0.40         0.0         0.0         0.0         0.0         0.0   \n",
       "4 -0.70         0.0         0.0         0.0         0.0         0.0   \n",
       "\n",
       "  workclass_6 workclass_7 workclass_8    fnlwgt  ... native_country_33  \\\n",
       "0         0.0         0.0         0.0 -0.058906  ...               0.0   \n",
       "1         0.0         0.0         0.0 -0.578076  ...               0.0   \n",
       "2         0.0         0.0         0.0  0.080425  ...               0.0   \n",
       "3         0.0         0.0         0.0 -0.270650  ...               0.0   \n",
       "4         0.0         0.0         0.0  0.210240  ...               0.0   \n",
       "\n",
       "  native_country_34 native_country_35 native_country_36 native_country_37  \\\n",
       "0               0.0               0.0               0.0               0.0   \n",
       "1               0.0               0.0               0.0               0.0   \n",
       "2               0.0               0.0               0.0               0.0   \n",
       "3               0.0               0.0               0.0               0.0   \n",
       "4               0.0               0.0               0.0               0.0   \n",
       "\n",
       "  native_country_38 native_country_39 native_country_40 native_country_41  \\\n",
       "0               0.0               0.0               0.0               0.0   \n",
       "1               0.0               0.0               0.0               0.0   \n",
       "2               0.0               0.0               0.0               0.0   \n",
       "3               0.0               0.0               0.0               0.0   \n",
       "4               0.0               0.0               0.0               0.0   \n",
       "\n",
       "  native_country_42  \n",
       "0               0.0  \n",
       "1               0.0  \n",
       "2               0.0  \n",
       "3               0.0  \n",
       "4               0.0  \n",
       "\n",
       "[5 rows x 107 columns]"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "id": "893cde3c",
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>workclass_1</th>\n",
       "      <th>workclass_2</th>\n",
       "      <th>workclass_3</th>\n",
       "      <th>workclass_4</th>\n",
       "      <th>workclass_5</th>\n",
       "      <th>workclass_6</th>\n",
       "      <th>workclass_7</th>\n",
       "      <th>workclass_8</th>\n",
       "      <th>fnlwgt</th>\n",
       "      <th>...</th>\n",
       "      <th>native_country_33</th>\n",
       "      <th>native_country_34</th>\n",
       "      <th>native_country_35</th>\n",
       "      <th>native_country_36</th>\n",
       "      <th>native_country_37</th>\n",
       "      <th>native_country_38</th>\n",
       "      <th>native_country_39</th>\n",
       "      <th>native_country_40</th>\n",
       "      <th>native_country_41</th>\n",
       "      <th>native_country_42</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.006571</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.50</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.323136</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.60</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.656361</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.45</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.253496</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.40</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.042564</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 107 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    age workclass_1 workclass_2 workclass_3 workclass_4 workclass_5  \\\n",
       "0 -0.50         0.0         0.0         0.0         0.0         0.0   \n",
       "1 -0.50         0.0         0.0         0.0         0.0         0.0   \n",
       "2 -0.60         0.0         0.0         0.0         0.0         0.0   \n",
       "3  0.45         0.0         0.0         0.0         0.0         0.0   \n",
       "4  0.40         0.0         0.0         0.0         0.0         0.0   \n",
       "\n",
       "  workclass_6 workclass_7 workclass_8    fnlwgt  ... native_country_33  \\\n",
       "0         0.0         0.0         0.0 -0.006571  ...               0.0   \n",
       "1         0.0         0.0         0.0  0.323136  ...               0.0   \n",
       "2         0.0         0.0         0.0  0.656361  ...               0.0   \n",
       "3         0.0         0.0         0.0 -0.253496  ...               0.0   \n",
       "4         0.0         0.0         0.0 -0.042564  ...               0.0   \n",
       "\n",
       "  native_country_34 native_country_35 native_country_36 native_country_37  \\\n",
       "0               0.0               0.0               0.0               0.0   \n",
       "1               0.0               0.0               0.0               0.0   \n",
       "2               0.0               0.0               0.0               0.0   \n",
       "3               0.0               0.0               0.0               0.0   \n",
       "4               0.0               0.0               0.0               0.0   \n",
       "\n",
       "  native_country_38 native_country_39 native_country_40 native_country_41  \\\n",
       "0               0.0               0.0               0.0               0.0   \n",
       "1               0.0               0.0               0.0               0.0   \n",
       "2               0.0               0.0               0.0               0.0   \n",
       "3               0.0               0.0               0.0               0.0   \n",
       "4               0.0               0.0               0.0               0.0   \n",
       "\n",
       "  native_country_42  \n",
       "0               0.0  \n",
       "1               0.0  \n",
       "2               0.0  \n",
       "3               0.0  \n",
       "4               0.0  \n",
       "\n",
       "[5 rows x 107 columns]"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "id": "d4af6dd2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\madon\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:1688: FutureWarning: Feature names only support names that are all strings. Got feature names with dtypes: ['tuple']. An error will be raised in 1.2.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GaussianNB()"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# train a Gaussian Naive Bayes classifier on the training set\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "\n",
    "\n",
    "# instantiate the model\n",
    "gnb = GaussianNB()\n",
    "\n",
    "\n",
    "# fit the model\n",
    "gnb.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "id": "c162b8a2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\madon\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:1688: FutureWarning: Feature names only support names that are all strings. Got feature names with dtypes: ['tuple']. An error will be raised in 1.2.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([' <=50K', ' <=50K', ' >50K', ..., ' >50K', ' <=50K', ' <=50K'],\n",
       "      dtype='<U6')"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Predict from the model\n",
    "y_pred = gnb.predict(X_test)\n",
    "\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "id": "133ecfff",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model accuracy score: 0.8027\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "print('Model accuracy score: {0:0.4f}'. format(accuracy_score(y_test, y_pred)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "8b9d2527",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\madon\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:1688: FutureWarning: Feature names only support names that are all strings. Got feature names with dtypes: ['tuple']. An error will be raised in 1.2.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([' >50K', ' <=50K', ' >50K', ..., ' <=50K', ' >50K', ' <=50K'],\n",
       "      dtype='<U6')"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred_train = gnb.predict(X_train)\n",
    "\n",
    "y_pred_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "bb530cf6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training-set accuracy score: 0.8036\n"
     ]
    }
   ],
   "source": [
    "print('Training-set accuracy score: {0:0.4f}'. format(accuracy_score(y_train, y_pred_train)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "7e67c468",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training set score: 0.8036\n",
      "Test set score: 0.8027\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\madon\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:1688: FutureWarning: Feature names only support names that are all strings. Got feature names with dtypes: ['tuple']. An error will be raised in 1.2.\n",
      "  warnings.warn(\n",
      "C:\\Users\\madon\\anaconda3\\lib\\site-packages\\sklearn\\utils\\validation.py:1688: FutureWarning: Feature names only support names that are all strings. Got feature names with dtypes: ['tuple']. An error will be raised in 1.2.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "print('Training set score: {:.4f}'.format(gnb.score(X_train, y_train)))\n",
    "\n",
    "print('Test set score: {:.4f}'.format(gnb.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "7761a4dc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       " <=50K    7407\n",
       " >50K     2362\n",
       "Name: income, dtype: int64"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# check class distribution in test set\n",
    "\n",
    "y_test.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "49e91c72",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion matrix\n",
      "\n",
      " [[5936 1471]\n",
      " [ 456 1906]]\n",
      "\n",
      "True Positives(TP) =  5936\n",
      "\n",
      "True Negatives(TN) =  1906\n",
      "\n",
      "False Positives(FP) =  1471\n",
      "\n",
      "False Negatives(FN) =  456\n"
     ]
    }
   ],
   "source": [
    "# Print the Confusion Matrix and slice it into four pieces\n",
    "\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "print('Confusion matrix\\n\\n', cm)\n",
    "\n",
    "print('\\nTrue Positives(TP) = ', cm[0,0])\n",
    "\n",
    "print('\\nTrue Negatives(TN) = ', cm[1,1])\n",
    "\n",
    "print('\\nFalse Positives(FP) = ', cm[0,1])\n",
    "\n",
    "print('\\nFalse Negatives(FN) = ', cm[1,0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "id": "7bea27f4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# visualize confusion matrix with seaborn heatmap\n",
    "\n",
    "cm_matrix = pd.DataFrame(data=cm, columns=['Actual Positive:1', 'Actual Negative:0'], \n",
    "                                 index=['Predict Positive:1', 'Predict Negative:0'])\n",
    "\n",
    "sns.heatmap(cm_matrix, annot=True, fmt='d', cmap='YlGnBu')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "id": "37432c82",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "       <=50K       0.93      0.80      0.86      7407\n",
      "        >50K       0.56      0.81      0.66      2362\n",
      "\n",
      "    accuracy                           0.80      9769\n",
      "   macro avg       0.75      0.80      0.76      9769\n",
      "weighted avg       0.84      0.80      0.81      9769\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "id": "d6b5e12d",
   "metadata": {},
   "outputs": [],
   "source": [
    "TP = cm[0,0]\n",
    "TN = cm[1,1]\n",
    "FP = cm[0,1]\n",
    "FN = cm[1,0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "id": "8944907f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification accuracy : 0.8027\n"
     ]
    }
   ],
   "source": [
    "# print classification accuracy\n",
    "\n",
    "classification_accuracy = (TP + TN) / float(TP + TN + FP + FN)\n",
    "\n",
    "print('Classification accuracy : {0:0.4f}'.format(classification_accuracy))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "c4600ae8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classification error : 0.1973\n"
     ]
    }
   ],
   "source": [
    "# print classification error\n",
    "\n",
    "classification_error = (FP + FN) / float(TP + TN + FP + FN)\n",
    "\n",
    "print('Classification error : {0:0.4f}'.format(classification_error))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "id": "50d9277d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Precision : 0.8014\n"
     ]
    }
   ],
   "source": [
    "# print precision score\n",
    "\n",
    "precision = TP / float(TP + FP)\n",
    "\n",
    "\n",
    "print('Precision : {0:0.4f}'.format(precision))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "id": "fe8ea227",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Recall or Sensitivity : 0.9287\n"
     ]
    }
   ],
   "source": [
    "recall = TP / float(TP + FN)\n",
    "\n",
    "print('Recall or Sensitivity : {0:0.4f}'.format(recall))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "id": "8ce6b00d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "True Positive Rate : 0.9287\n"
     ]
    }
   ],
   "source": [
    "true_positive_rate = TP / float(TP + FN)\n",
    "\n",
    "\n",
    "print('True Positive Rate : {0:0.4f}'.format(true_positive_rate))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "3878b7ea",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "False Positive Rate : 0.4356\n"
     ]
    }
   ],
   "source": [
    "false_positive_rate = FP / float(FP + TN)\n",
    "\n",
    "\n",
    "print('False Positive Rate : {0:0.4f}'.format(false_positive_rate))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "9f13abd7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Specificity : 0.5553\n"
     ]
    }
   ],
   "source": [
    "specificity = TN / (TN + FP)\n",
    "\n",
    "print('Specificity : {0:0.4f}'.format(specificity))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bb2d43f6",
   "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": 5
}