neural_network.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "import plotly.express as px\n",
    "plt.style.use(['science','ieee', 'no-latex']) # set the style of the plots\n",
    "\n",
    "from util import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train shape: (32561, 13)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</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>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>native-country</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39</td>\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>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>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>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>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>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>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>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>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>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  education      marital-status         occupation  \\\n",
       "0   39         State-gov  Bachelors       Never-married       Adm-clerical   \n",
       "1   50  Self-emp-not-inc  Bachelors  Married-civ-spouse    Exec-managerial   \n",
       "2   38           Private    HS-grad            Divorced  Handlers-cleaners   \n",
       "3   53           Private       11th  Married-civ-spouse  Handlers-cleaners   \n",
       "4   28           Private  Bachelors  Married-civ-spouse     Prof-specialty   \n",
       "\n",
       "    relationship   race     sex  capital-gain  capital-loss  hours-per-week  \\\n",
       "0  Not-in-family  White    Male          2174             0              40   \n",
       "1        Husband  White    Male             0             0              13   \n",
       "2  Not-in-family  White    Male             0             0              40   \n",
       "3        Husband  Black    Male             0             0              40   \n",
       "4           Wife  Black  Female             0             0              40   \n",
       "\n",
       "  native-country target  \n",
       "0  United-States  <=50K  \n",
       "1  United-States  <=50K  \n",
       "2  United-States  <=50K  \n",
       "3  United-States  <=50K  \n",
       "4           Cuba  <=50K  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test shape: (16281, 13)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</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>capital-gain</th>\n",
       "      <th>capital-loss</th>\n",
       "      <th>hours-per-week</th>\n",
       "      <th>native-country</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>25</td>\n",
       "      <td>Private</td>\n",
       "      <td>11th</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Own-child</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>1</th>\n",
       "      <td>38</td>\n",
       "      <td>Private</td>\n",
       "      <td>HS-grad</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Farming-fishing</td>\n",
       "      <td>Husband</td>\n",
       "      <td>White</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28</td>\n",
       "      <td>Local-gov</td>\n",
       "      <td>Assoc-acdm</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Protective-serv</td>\n",
       "      <td>Husband</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>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>Private</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>Married-civ-spouse</td>\n",
       "      <td>Machine-op-inspct</td>\n",
       "      <td>Husband</td>\n",
       "      <td>Black</td>\n",
       "      <td>Male</td>\n",
       "      <td>7688</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&gt;50K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Some-college</td>\n",
       "      <td>Never-married</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Own-child</td>\n",
       "      <td>White</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>United-States</td>\n",
       "      <td>&lt;=50K</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  workclass     education      marital-status         occupation  \\\n",
       "0   25    Private          11th       Never-married  Machine-op-inspct   \n",
       "1   38    Private       HS-grad  Married-civ-spouse    Farming-fishing   \n",
       "2   28  Local-gov    Assoc-acdm  Married-civ-spouse    Protective-serv   \n",
       "3   44    Private  Some-college  Married-civ-spouse  Machine-op-inspct   \n",
       "4   18        NaN  Some-college       Never-married                NaN   \n",
       "\n",
       "  relationship   race     sex  capital-gain  capital-loss  hours-per-week  \\\n",
       "0    Own-child  Black    Male             0             0              40   \n",
       "1      Husband  White    Male             0             0              50   \n",
       "2      Husband  White    Male             0             0              40   \n",
       "3      Husband  Black    Male          7688             0              40   \n",
       "4    Own-child  White  Female             0             0              30   \n",
       "\n",
       "  native-country target  \n",
       "0  United-States  <=50K  \n",
       "1  United-States  <=50K  \n",
       "2  United-States   >50K  \n",
       "3  United-States   >50K  \n",
       "4  United-States  <=50K  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "adult = pd.read_parquet('data/formatted_data.parquet')\n",
    "adult.drop(columns=['fnlwgt', 'education-num'], inplace=True) # dropping these columns\n",
    "train = adult[adult['set'] == 'train'].drop(columns=['set'])\n",
    "test = adult[adult['set'] == 'test'].drop(columns=['set'])\n",
    "print(f'Train shape: {train.shape}')\n",
    "display(train.head())\n",
    "print(f'Test shape: {test.shape}')\n",
    "display(test.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "def runMLPClassifier(XTrainTrans, YTrain, max_iter):\n",
    "    clf = GridSearchCV(\n",
    "        estimator =  MLPClassifier(max_iter=max_iter, random_state=0),\n",
    "        param_grid = {\n",
    "            'hidden_layer_sizes': [(64, 32, 16), (100,)],\n",
    "            'activation': ['relu'],\n",
    "            'solver': ['adam'],\n",
    "            'alpha': [0.0001, 0.05],\n",
    "            'learning_rate': ['adaptive'],\n",
    "        },\n",
    "        scoring=['accuracy', 'precision', 'recall', 'f1', 'roc_auc'],\n",
    "        refit='roc_auc',\n",
    "        cv=4,\n",
    "        n_jobs=-1\n",
    "    )\n",
    "    return clf.fit(XTrainTrans, YTrain)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Starting 3 categories\n",
      "Starting Search for 3 categories\n",
      "Starting 5 categories\n",
      "Starting Search for 5 categories\n",
      "Starting 10 categories\n",
      "Starting Search for 10 categories\n",
      "Starting 20 categories\n",
      "Starting Search for 20 categories\n",
      "Starting 42 categories\n",
      "Starting Search for 42 categories\n"
     ]
    }
   ],
   "source": [
    "# collect data\n",
    "# 30 iterations 0f 4-fold cross validation for each number of maximum values per categorical feature\n",
    "\n",
    "results = []\n",
    "\n",
    "for numCat in [3, 5, 10, 20, 42]:\n",
    "    print(f'Starting {numCat} categories')\n",
    "    train_ = dfCategoryLimit(train, numCat) # limit the number values per category\n",
    "    XTrain, YTrain, XTest, YTest = XYSplit(train_, test) # split into X and Y\n",
    "    XTrain, YTrain = donwSampleLabels(XTrain, YTrain) # downsample the labels\n",
    "\n",
    "    preprocessor = getPreprocessor().fit(XTrain) # fit the preprocessor\n",
    "    XTrainTrans = preprocessor.transform(XTrain) # transform the training data\n",
    "    XTestTrans = preprocessor.transform(XTest) # transform the test data\n",
    "\n",
    "    nDims = XTrainTrans.shape[1] # get the number of dimensions\n",
    "    print(f'Starting Search for {numCat} categories')\n",
    "    search = runMLPClassifier(XTrainTrans, YTrain, max_iter=300) # run the logistic regression search\n",
    "    testMetrics = getMetrics(search, XTestTrans, YTest) # get the test metrics\n",
    "    cvResults = search.cv_results_ # get the cross validation results\n",
    "    results.append((numCat, nDims, testMetrics, cvResults, search)) # collect the results\n",
    "pd.DataFrame(results, columns=['numCat', 'nDims', 'testMetrics', 'cvResults', 'searchObj']).to_pickle('data/MLP_results.pkl')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.12 ('base')",
   "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"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "4f3567101b31d35f97cf2856951ebbba1e09a3f852422478e736adda2bb3beee"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}