{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e316b5fe",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import sys\n",
    "\n",
    "sys.path.append(os.path.join(os.path.abspath(\"..\"), \"code\"))\n",
    "\n",
    "import IPython\n",
    "import matplotlib.pyplot as plt\n",
    "import mglearn\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from IPython.display import HTML, display\n",
    "from plotting_functions import *\n",
    "from sklearn.dummy import DummyClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import average_precision_score, classification_report, f1_score, precision_recall_curve, roc_auc_score, roc_curve, ConfusionMatrixDisplay, PrecisionRecallDisplay, RocCurveDisplay\n",
    "from sklearn.model_selection import cross_val_score, cross_validate, train_test_split\n",
    "from sklearn.pipeline import Pipeline, make_pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from utils import *\n",
    "\n",
    "%matplotlib inline\n",
    "pd.set_option(\"display.max_colwidth\", 200)\n",
    "\n",
    "from IPython.display import Image"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f009286",
   "metadata": {},
   "source": [
    "# Exploring classification metrics"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d6e53c3",
   "metadata": {},
   "source": [
    "### Dataset for demonstration \n",
    "\n",
    "Let's classify fraudulent and non-fraudulent transactions using Kaggle's [Credit Card Fraud Detection](https://www.kaggle.com/mlg-ulb/creditcardfraud) data set."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "812c9f03",
   "metadata": {},
   "source": [
    "### Loading the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "175ada15",
   "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>Time</th>\n",
       "      <th>V1</th>\n",
       "      <th>V2</th>\n",
       "      <th>V3</th>\n",
       "      <th>V4</th>\n",
       "      <th>V5</th>\n",
       "      <th>V6</th>\n",
       "      <th>V7</th>\n",
       "      <th>V8</th>\n",
       "      <th>V9</th>\n",
       "      <th>...</th>\n",
       "      <th>V21</th>\n",
       "      <th>V22</th>\n",
       "      <th>V23</th>\n",
       "      <th>V24</th>\n",
       "      <th>V25</th>\n",
       "      <th>V26</th>\n",
       "      <th>V27</th>\n",
       "      <th>V28</th>\n",
       "      <th>Amount</th>\n",
       "      <th>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>64454</th>\n",
       "      <td>51150.0</td>\n",
       "      <td>-3.538816</td>\n",
       "      <td>3.481893</td>\n",
       "      <td>-1.827130</td>\n",
       "      <td>-0.573050</td>\n",
       "      <td>2.644106</td>\n",
       "      <td>-0.340988</td>\n",
       "      <td>2.102135</td>\n",
       "      <td>-2.939006</td>\n",
       "      <td>2.578654</td>\n",
       "      <td>...</td>\n",
       "      <td>0.530978</td>\n",
       "      <td>-0.860677</td>\n",
       "      <td>-0.201810</td>\n",
       "      <td>-1.719747</td>\n",
       "      <td>0.729143</td>\n",
       "      <td>-0.547993</td>\n",
       "      <td>-0.023636</td>\n",
       "      <td>-0.454966</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37906</th>\n",
       "      <td>39163.0</td>\n",
       "      <td>-0.363913</td>\n",
       "      <td>0.853399</td>\n",
       "      <td>1.648195</td>\n",
       "      <td>1.118934</td>\n",
       "      <td>0.100882</td>\n",
       "      <td>0.423852</td>\n",
       "      <td>0.472790</td>\n",
       "      <td>-0.972440</td>\n",
       "      <td>0.033833</td>\n",
       "      <td>...</td>\n",
       "      <td>0.687055</td>\n",
       "      <td>-0.094586</td>\n",
       "      <td>0.121531</td>\n",
       "      <td>0.146830</td>\n",
       "      <td>-0.944092</td>\n",
       "      <td>-0.558564</td>\n",
       "      <td>-0.186814</td>\n",
       "      <td>-0.257103</td>\n",
       "      <td>18.49</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>79378</th>\n",
       "      <td>57994.0</td>\n",
       "      <td>1.193021</td>\n",
       "      <td>-0.136714</td>\n",
       "      <td>0.622612</td>\n",
       "      <td>0.780864</td>\n",
       "      <td>-0.823511</td>\n",
       "      <td>-0.706444</td>\n",
       "      <td>-0.206073</td>\n",
       "      <td>-0.016918</td>\n",
       "      <td>0.781531</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.310405</td>\n",
       "      <td>-0.842028</td>\n",
       "      <td>0.085477</td>\n",
       "      <td>0.366005</td>\n",
       "      <td>0.254443</td>\n",
       "      <td>0.290002</td>\n",
       "      <td>-0.036764</td>\n",
       "      <td>0.015039</td>\n",
       "      <td>23.74</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245686</th>\n",
       "      <td>152859.0</td>\n",
       "      <td>1.604032</td>\n",
       "      <td>-0.808208</td>\n",
       "      <td>-1.594982</td>\n",
       "      <td>0.200475</td>\n",
       "      <td>0.502985</td>\n",
       "      <td>0.832370</td>\n",
       "      <td>-0.034071</td>\n",
       "      <td>0.234040</td>\n",
       "      <td>0.550616</td>\n",
       "      <td>...</td>\n",
       "      <td>0.519029</td>\n",
       "      <td>1.429217</td>\n",
       "      <td>-0.139322</td>\n",
       "      <td>-1.293663</td>\n",
       "      <td>0.037785</td>\n",
       "      <td>0.061206</td>\n",
       "      <td>0.005387</td>\n",
       "      <td>-0.057296</td>\n",
       "      <td>156.52</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>60943</th>\n",
       "      <td>49575.0</td>\n",
       "      <td>-2.669614</td>\n",
       "      <td>-2.734385</td>\n",
       "      <td>0.662450</td>\n",
       "      <td>-0.059077</td>\n",
       "      <td>3.346850</td>\n",
       "      <td>-2.549682</td>\n",
       "      <td>-1.430571</td>\n",
       "      <td>-0.118450</td>\n",
       "      <td>0.469383</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.228329</td>\n",
       "      <td>-0.370643</td>\n",
       "      <td>-0.211544</td>\n",
       "      <td>-0.300837</td>\n",
       "      <td>-1.174590</td>\n",
       "      <td>0.573818</td>\n",
       "      <td>0.388023</td>\n",
       "      <td>0.161782</td>\n",
       "      <td>57.50</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 31 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            Time        V1        V2        V3        V4        V5        V6  \\\n",
       "64454    51150.0 -3.538816  3.481893 -1.827130 -0.573050  2.644106 -0.340988   \n",
       "37906    39163.0 -0.363913  0.853399  1.648195  1.118934  0.100882  0.423852   \n",
       "79378    57994.0  1.193021 -0.136714  0.622612  0.780864 -0.823511 -0.706444   \n",
       "245686  152859.0  1.604032 -0.808208 -1.594982  0.200475  0.502985  0.832370   \n",
       "60943    49575.0 -2.669614 -2.734385  0.662450 -0.059077  3.346850 -2.549682   \n",
       "\n",
       "              V7        V8        V9  ...       V21       V22       V23  \\\n",
       "64454   2.102135 -2.939006  2.578654  ...  0.530978 -0.860677 -0.201810   \n",
       "37906   0.472790 -0.972440  0.033833  ...  0.687055 -0.094586  0.121531   \n",
       "79378  -0.206073 -0.016918  0.781531  ... -0.310405 -0.842028  0.085477   \n",
       "245686 -0.034071  0.234040  0.550616  ...  0.519029  1.429217 -0.139322   \n",
       "60943  -1.430571 -0.118450  0.469383  ... -0.228329 -0.370643 -0.211544   \n",
       "\n",
       "             V24       V25       V26       V27       V28  Amount  Class  \n",
       "64454  -1.719747  0.729143 -0.547993 -0.023636 -0.454966    1.00      0  \n",
       "37906   0.146830 -0.944092 -0.558564 -0.186814 -0.257103   18.49      0  \n",
       "79378   0.366005  0.254443  0.290002 -0.036764  0.015039   23.74      0  \n",
       "245686 -1.293663  0.037785  0.061206  0.005387 -0.057296  156.52      0  \n",
       "60943  -0.300837 -1.174590  0.573818  0.388023  0.161782   57.50      0  \n",
       "\n",
       "[5 rows x 31 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_df = pd.read_csv(\"../data/creditcard.csv\", encoding=\"latin-1\")\n",
    "train_df, test_df = train_test_split(cc_df, test_size=0.3, random_state=111)\n",
    "train_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "01f5308c",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_big, y_train_big = train_df.drop(columns=[\"Class\", \"Time\"]), train_df[\"Class\"]\n",
    "X_test, y_test = test_df.drop(columns=[\"Class\", \"Time\"]), test_df[\"Class\"]\n",
    "X_train, X_valid, y_train, y_valid = train_test_split(\n",
    "    X_train_big, y_train_big, test_size=0.7, random_state=123\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "56208d5e",
   "metadata": {},
   "source": [
    "## Comparing PR curves\n",
    "\n",
    "Let's create PR curves for SVC and Logisitic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "f6c34625",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;, LogisticRegression(max_iter=500))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;, LogisticRegression(max_iter=500))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(max_iter=500)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('standardscaler', StandardScaler()),\n",
       "                ('logisticregression', LogisticRegression(max_iter=500))])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe_lr = make_pipeline(StandardScaler(), LogisticRegression(max_iter=500))\n",
    "pipe_lr.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a6a76afb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()), (&#x27;svc&#x27;, SVC())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()), (&#x27;svc&#x27;, SVC())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC()</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('standardscaler', StandardScaler()), ('svc', SVC())])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe_svc = make_pipeline(StandardScaler(), SVC())\n",
    "pipe_svc.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "01e1b2c5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[9.99807444e-01, 1.92556242e-04],\n",
       "       [9.99537296e-01, 4.62703836e-04],\n",
       "       [9.99678149e-01, 3.21851032e-04],\n",
       "       ...,\n",
       "       [9.99907898e-01, 9.21018764e-05],\n",
       "       [9.99882185e-01, 1.17814723e-04],\n",
       "       [9.99845434e-01, 1.54565766e-04]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe_lr.predict_proba(X_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "677529c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "precision_lr, recall_lr, thresholds_lr = precision_recall_curve(\n",
    "    y_valid, pipe_lr.predict_proba(X_valid)[:, 1]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "5a9b43b1-38f9-495f-b2ec-755c02d51d3d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5.43344135e-10, 8.87215534e-10, 1.13373820e-09, ...,\n",
       "       9.99999990e-01, 9.99999996e-01, 1.00000000e+00])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "thresholds_lr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f8824998",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([-1.12247976, -1.15220481, -1.05407669, ..., -1.18444729,\n",
       "       -1.06337006, -1.05482241])"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe_svc.decision_function(X_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "05d83c6c",
   "metadata": {},
   "outputs": [],
   "source": [
    "precision_svc, recall_svc, thresholds_svc = precision_recall_curve(\n",
    "    y_valid, pipe_svc.decision_function(X_valid)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "42af91e5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(precision_svc, recall_svc, label=\"SVC\")\n",
    "plt.plot(precision_lr, recall_lr, label=\"Logistic regression\")\n",
    "plt.xlabel(\"Precision\")\n",
    "plt.ylabel(\"Recall\")\n",
    "plt.legend(loc=\"best\");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "092e25ca",
   "metadata": {},
   "source": [
    "### Let's look at the F1 scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "9ddff655",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.6463104325699746 0.553314121037464\n"
     ]
    }
   ],
   "source": [
    "lr_f1 = f1_score(y_valid, pipe_lr.predict(X_valid))\n",
    "svc_f1 = f1_score(y_valid, pipe_svc.predict(X_valid))\n",
    "\n",
    "print(lr_f1, svc_f1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10ff6bbd",
   "metadata": {},
   "source": [
    "### What about the average precision score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "d14f4c58",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.698147830641323 0.7629107575877127\n"
     ]
    }
   ],
   "source": [
    "lr_ap = average_precision_score(y_valid, pipe_lr.predict_proba(X_valid)[:, 1])\n",
    "svc_ap = average_precision_score(y_valid, pipe_svc.decision_function(X_valid))\n",
    "\n",
    "print(lr_ap, svc_ap)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3d2c0dea",
   "metadata": {},
   "source": [
    "## Comparing ROC curves"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8ab105de",
   "metadata": {},
   "source": [
    "Let's look at the ROC curve for Logistic Regression first"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "c825ea26",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x124c45bd0>"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "RocCurveDisplay.from_estimator(pipe_lr, X_valid, y_valid, name=\"Logistic Regression\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "886bcbb1",
   "metadata": {},
   "source": [
    "But what if we want to plot more than one classifier? Let's look at the [documentation](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.RocCurveDisplay.html#sklearn.metrics.RocCurveDisplay.from_estimator)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "c224dfc8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x125924ed0>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure()\n",
    "ax = fig.add_subplot(1, 1, 1)\n",
    "RocCurveDisplay.from_estimator(pipe_lr, X_valid, y_valid, ax=ax, name=\"Logistic Regression\")\n",
    "RocCurveDisplay.from_estimator(pipe_svc, X_valid, y_valid, ax=ax, name=\"SVC\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "117fe572",
   "metadata": {},
   "source": [
    "## Comparing class_weight\n",
    "\n",
    "Let's explore how the `class_weight` argument impacts performance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "d2f957b4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;, LogisticRegression(max_iter=500))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;, LogisticRegression(max_iter=500))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(max_iter=500)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('standardscaler', StandardScaler()),\n",
       "                ('logisticregression', LogisticRegression(max_iter=500))])"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Standard LogisticRegression\n",
    "pipe_lr_std = make_pipeline(StandardScaler(), LogisticRegression(max_iter=500))\n",
    "pipe_lr_std.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "0aba837c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-4 {color: black;}#sk-container-id-4 pre{padding: 0;}#sk-container-id-4 div.sk-toggleable {background-color: white;}#sk-container-id-4 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-4 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-4 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-4 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-4 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-4 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-4 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-4 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-4 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-4 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-4 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-4 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-4 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-4 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-4 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-4 div.sk-item {position: relative;z-index: 1;}#sk-container-id-4 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-4 div.sk-item::before, #sk-container-id-4 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-4 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-4 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-4 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-4 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-4 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-4 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-4 div.sk-label-container {text-align: center;}#sk-container-id-4 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-4 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-4\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;,\n",
       "                 LogisticRegression(class_weight={0: 1, 1: 10}, max_iter=500))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-10\" type=\"checkbox\" ><label for=\"sk-estimator-id-10\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;,\n",
       "                 LogisticRegression(class_weight={0: 1, 1: 10}, max_iter=500))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-11\" type=\"checkbox\" ><label for=\"sk-estimator-id-11\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-12\" type=\"checkbox\" ><label for=\"sk-estimator-id-12\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(class_weight={0: 1, 1: 10}, max_iter=500)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('standardscaler', StandardScaler()),\n",
       "                ('logisticregression',\n",
       "                 LogisticRegression(class_weight={0: 1, 1: 10}, max_iter=500))])"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Giving a weight of 1 to the non-fraud and 10 to fraud examples\n",
    "pipe_lr_upw = make_pipeline(StandardScaler(), LogisticRegression(max_iter=500, class_weight={0:1, 1:10}))\n",
    "pipe_lr_upw.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "68febcd2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-5 {color: black;}#sk-container-id-5 pre{padding: 0;}#sk-container-id-5 div.sk-toggleable {background-color: white;}#sk-container-id-5 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-5 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-5 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-5 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-5 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-5 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-5 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-5 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-5 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-5 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-5 div.sk-item {position: relative;z-index: 1;}#sk-container-id-5 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-5 div.sk-item::before, #sk-container-id-5 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-5 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-5 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-5 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-5 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-5 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-5 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-5 div.sk-label-container {text-align: center;}#sk-container-id-5 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-5 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;,\n",
       "                 LogisticRegression(class_weight=&#x27;balanced&#x27;, max_iter=500))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-13\" type=\"checkbox\" ><label for=\"sk-estimator-id-13\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;standardscaler&#x27;, StandardScaler()),\n",
       "                (&#x27;logisticregression&#x27;,\n",
       "                 LogisticRegression(class_weight=&#x27;balanced&#x27;, max_iter=500))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-14\" type=\"checkbox\" ><label for=\"sk-estimator-id-14\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-15\" type=\"checkbox\" ><label for=\"sk-estimator-id-15\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(class_weight=&#x27;balanced&#x27;, max_iter=500)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('standardscaler', StandardScaler()),\n",
       "                ('logisticregression',\n",
       "                 LogisticRegression(class_weight='balanced', max_iter=500))])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Balanced weights\n",
    "pipe_lr_balanced = make_pipeline(StandardScaler(), LogisticRegression(max_iter=500, class_weight=\"balanced\"))\n",
    "pipe_lr_balanced.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4deef9b1",
   "metadata": {},
   "source": [
    "First let's look at the precision-recall curves"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "7c88aff8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x1260725d0>"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure()\n",
    "ax = fig.add_subplot(1, 1, 1)\n",
    "PrecisionRecallDisplay.from_estimator(pipe_lr_std, X_valid, y_valid, ax=ax, name=\"Std\")\n",
    "PrecisionRecallDisplay.from_estimator(pipe_lr_upw, X_valid, y_valid, ax=ax, name=\"Upweight\")\n",
    "PrecisionRecallDisplay.from_estimator(pipe_lr_balanced, X_valid, y_valid, ax=ax, name=\"Balanced\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7c38fa0",
   "metadata": {},
   "source": [
    "Now let's consider the ROC curves"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "6443fb78",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x1260716d0>"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure()\n",
    "ax = fig.add_subplot(1, 1, 1)\n",
    "RocCurveDisplay.from_estimator(pipe_lr_std, X_valid, y_valid, ax=ax, name=\"Std\")\n",
    "RocCurveDisplay.from_estimator(pipe_lr_upw, X_valid, y_valid, ax=ax, name=\"Upweight\")\n",
    "RocCurveDisplay.from_estimator(pipe_lr_balanced, X_valid, y_valid, ax=ax, name=\"Balanced\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9cc1ac51",
   "metadata": {},
   "source": [
    "# ML fairness activity"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ea84d6ef",
   "metadata": {},
   "source": [
    "AI/ML systems can give the illusion of objectivity as they are derived from seemingly unbiased data & algorithm. However, human are inherently biased and AI/ML systems, if not carefully evaluated, can even further amplify the existing inequities and systemic bias in our society.  \n",
    "\n",
    "How do we make sure our AI/ML systems are *fair*? Which metrics can we use to quatify 'fairness' in AI/ML systems?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "302b6c52",
   "metadata": {},
   "source": [
    "### Dataset for demonstration \n",
    "\n",
    "Let's examine this on [the adult census data set](https://www.kaggle.com/uciml/adult-census-income). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ba0ebaed",
   "metadata": {},
   "outputs": [],
   "source": [
    "census_df = pd.read_csv(\"../data/adult.csv\")\n",
    "census_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7079efcf",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df, test_df = train_test_split(census_df, test_size=0.4, random_state=42)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d5989357",
   "metadata": {},
   "source": [
    "### Data cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e703aa2b",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df_nan = train_df.replace(\"?\", np.nan)\n",
    "test_df_nan = test_df.replace(\"?\", np.nan)\n",
    "train_df_nan.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6861d205",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df_nan.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b2c44140",
   "metadata": {},
   "outputs": [],
   "source": [
    "numeric_features = [\n",
    "    \"age\",\n",
    "    \"capital.gain\",\n",
    "    \"capital.loss\",\n",
    "    \"hours.per.week\",\n",
    "]\n",
    "\n",
    "categorical_features = [\n",
    "    \"workclass\",\n",
    "    \"marital.status\",\n",
    "    \"occupation\",\n",
    "    \"relationship\",\n",
    "    \"race\",\n",
    "    \"native.country\",\n",
    "]\n",
    "\n",
    "ordinal_features = [\"education\"]\n",
    "binary_features = [\n",
    "    \"sex\"\n",
    "]  # Not binary in general but in this particular dataset it seems to have only two possible values\n",
    "drop_features = [\"education.num\", \"fnlwgt\"]\n",
    "target = \"income\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e18c8fa8",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_df[\"education\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "49fb5903",
   "metadata": {},
   "outputs": [],
   "source": [
    "education_levels = [\n",
    "    \"Preschool\",\n",
    "    \"1st-4th\",\n",
    "    \"5th-6th\",\n",
    "    \"7th-8th\",\n",
    "    \"9th\",\n",
    "    \"10th\",\n",
    "    \"11th\",\n",
    "    \"12th\",\n",
    "    \"HS-grad\",\n",
    "    \"Prof-school\",\n",
    "    \"Assoc-voc\",\n",
    "    \"Assoc-acdm\",\n",
    "    \"Some-college\",\n",
    "    \"Bachelors\",\n",
    "    \"Masters\",\n",
    "    \"Doctorate\",\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "62a80052",
   "metadata": {},
   "outputs": [],
   "source": [
    "assert set(education_levels) == set(train_df[\"education\"].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f3a5c474",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = train_df_nan.drop(columns=[target])\n",
    "y_train = train_df_nan[target]\n",
    "\n",
    "X_test = test_df_nan.drop(columns=[target])\n",
    "y_test = test_df_nan[target]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c4905455",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.compose import ColumnTransformer, make_column_transformer\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder, StandardScaler\n",
    "\n",
    "numeric_transformer = make_pipeline(StandardScaler())\n",
    "\n",
    "ordinal_transformer = OrdinalEncoder(categories=[education_levels], dtype=int)\n",
    "\n",
    "categorical_transformer = make_pipeline(\n",
    "    SimpleImputer(strategy=\"constant\", fill_value=\"missing\"),\n",
    "    OneHotEncoder(handle_unknown=\"ignore\", sparse=False),\n",
    ")\n",
    "\n",
    "binary_transformer = make_pipeline(\n",
    "    SimpleImputer(strategy=\"constant\", fill_value=\"missing\"),\n",
    "    OneHotEncoder(drop=\"if_binary\", dtype=int),\n",
    ")\n",
    "\n",
    "preprocessor = make_column_transformer(\n",
    "    (numeric_transformer, numeric_features),\n",
    "    (ordinal_transformer, ordinal_features),\n",
    "    (binary_transformer, binary_features),\n",
    "    (categorical_transformer, categorical_features),\n",
    "    (\"drop\", drop_features),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ef3066fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train.value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "972c818d",
   "metadata": {},
   "source": [
    "Let's build our classification pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0ca55924",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipe_lr = "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2721814c",
   "metadata": {},
   "source": [
    "And look at the confustion matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a71c2aba",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "5017ab07",
   "metadata": {},
   "source": [
    "Let's examine confusion matrix separately for the two genders we have in the data. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ab82934b",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_enc = preprocessor.fit_transform(X_train)\n",
    "preprocessor.named_transformers_[\"pipeline-2\"][\"onehotencoder\"].get_feature_names_out()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7223de3b",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c8d17b24",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_female = X_test.query(\"sex=='Female'\")  # X where sex is female\n",
    "X_male = X_test.query(\"sex=='Male'\")  # X where sex is male\n",
    "\n",
    "y_female = y_test[X_female.index]  # y where sex is female\n",
    "y_male = y_test[X_male.index]  # y where sex is male"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c407bb57",
   "metadata": {},
   "source": [
    "**Get predictions for `X_female` and `y_male` with `pipe_lr`**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6301e4a9",
   "metadata": {},
   "outputs": [],
   "source": [
    "female_preds = pipe_lr.predict(X_female)\n",
    "male_preds = pipe_lr.predict(X_male)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6be5cc0c",
   "metadata": {},
   "source": [
    "Let's examine the accuracy and confusion matrix for female class.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aea0fbc0",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(classification_report(y_female, female_preds))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0ae317d9",
   "metadata": {},
   "outputs": [],
   "source": [
    "ConfusionMatrixDisplay.from_estimator(pipe_lr, X_female, y_female, normalize=\"true\");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3dc7c209",
   "metadata": {},
   "source": [
    "Let's examine the accuracy and confusion matrix for male class.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ea34829c",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(classification_report(y_male, male_preds))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ae7c39e9",
   "metadata": {},
   "outputs": [],
   "source": [
    "ConfusionMatrixDisplay.from_estimator(pipe_lr, X_male, y_male, normalize=\"true\");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a746017d",
   "metadata": {},
   "source": [
    "### ❓❓ Questions for group discussion\n",
    "\n",
    "Let's assume that a company is using this classifier for loan approval with a simple rule that if the income is >=50K, approve the loan else reject the loan. \n",
    "\n",
    "In your group, discuss the questions below and write the main points from your discussion in this [Google document](https://docs.google.com/document/d/1nsOsdO-zRwvWWwM4-6h2t7eHgIhW8FCy3ebxoT7p0HY/edit?usp=sharing). \n",
    "\n",
    "1. Which group has a higher accuracy?\n",
    "2. Which group has a higher precision for class >50K? What about recall for class >50K?\n",
    "3. Will both groups have more or less the same proportion of people with approved loans? \n",
    "4. If a male and a female have both a certain level of income, will they have the same chance of getting the loan?\n",
    "5. Banks want to avoid approving unqualified applications (false positives) because default loan could have detrimental effects for them. Compare the false positive rates for the two groups.    \n",
    "6. Overall, do you think this income classifier will fairly treat both groups? What will be the consequences of using this classifier in loan approval application? \n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b43b6fa7",
   "metadata": {},
   "source": [
    "**Time permitting**\n",
    "1. Do you think the effect will still exist if the sex feature is removed from the model (but you still have it available separately to do the two confusion matrices)? \n",
    "2. Are there any other groups in this dataset worth examining for biases? "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:cpsc330]",
   "language": "python",
   "name": "conda-env-cpsc330-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}