chore: add fairness use-case example

5 - synthetic-data-applications/fairness/Fairness.ipynb

@@ -0,0 +1,218 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "diverse-creek",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import generic packages\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.linear_model import SGDClassifier \n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "import seaborn as sns\n",
+    "from sklearn.metrics import confusion_matrix, roc_auc_score, accuracy_score\n",
+    "import matplotlib.pyplot as plt\n",
+    "import fairlens as fl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "hollywood-system",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import ydata modules\n",
+    "from ydata.synthesizers.regular.model import BaseModel, RegularSynthesizer\n",
+    "from ydata.metadata import Metadata\n",
+    "from ydata.dataset.dataset import Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "intensive-bunch",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# load loans data (available at kaggle https://www.kaggle.com/code/ajaymanwani/loan-approval-prediction/data)\n",
+    "data = pd.read_csv('~/Downloads/loans.csv').fillna(0)\n",
+    "data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "sunset-province",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check that the data in unbalanced for Married status\n",
+    "sns.countplot(x='Married',data=data, palette = 'Set2')   "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "great-effects",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# convert categorical to numerical\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "for c in data.columns:\n",
+    "    if data[c].dtype =='O':\n",
+    "        le = LabelEncoder()\n",
+    "        data[c] = le.fit_transform(data[c].astype(str)).astype('int')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "steady-petersburg",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# train a synthetizer\n",
+    "synthetizer = RegularSynthesizer()\n",
+    "original = Dataset(data)\n",
+    "metadata = Metadata()\n",
+    "synthetizer.fit(original)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "consistent-nursery",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#generate new data\n",
+    "synth = synthetizer.sample(n_samples=900)\n",
+    "s = synth.to_pandas()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "featured-seventh",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#create a balanced dataset\n",
+    "data_balanced = pd.concat([data,s[s.Married==1]],axis=0)\n",
+    "data_balanced.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "stock-schema",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check that new data is balanced\n",
+    "sns.countplot(x='Married',data=data_balanced, palette = 'Set2')   "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "economic-lunch",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create training a test data\n",
+    "xtrainf = []\n",
+    "ytrainf = []\n",
+    "xtrain, xtest, ytrain, ytest = train_test_split(data.drop(columns='Loan_Status'), data['Loan_Status'], test_size=.2, random_state = 100)\n",
+    "xtrainf.append(xtrain)\n",
+    "ytrainf.append(ytrain)\n",
+    "\n",
+    "xtrain, _, ytrain, _ = train_test_split(data_balanced.drop(columns='Loan_Status'), data_balanced['Loan_Status'], test_size=.2, random_state = 100)\n",
+    "ii = [i for i in xtrain.index if i not in xtest.index]\n",
+    "xtrainf.append(xtrain.loc[ii])\n",
+    "ytrainf.append(ytrain.loc[ii])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "portable-courage",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# check accuracy of models trained in both data sets\n",
+    "models = [RandomForestClassifier(),DecisionTreeClassifier(), AdaBoostClassifier()]\n",
+    "married = [1,2]\n",
+    "improvement = {}\n",
+    "\n",
+    "for m in models:\n",
+    "    improvement[m] = {}\n",
+    "    for i in range(0,2):\n",
+    "        m.fit(xtrainf[i],ytrainf[i])\n",
+    "        p = m.predict(xtest)\n",
+    "\n",
+    "        improvement[m][i] = np.round(accuracy_score(p,ytest),2)\n",
+    "        print('Overall Accuracy %f'% (improvement[m][i]))\n",
+    "\n",
+    "        for g in married:\n",
+    "            p = m.predict(xtest[xtest.Married==g])\n",
+    "            print('model %s  accuracy, married_status %s is_augmented %i =  %f'% (m, g , i , \n",
+    "                        np.round(accuracy_score(p,ytest[xtest.Married==g]),2)))\n",
+    "    print ('Relative improvement ', np.round(100*(improvement[m][1]/improvement[m][0] - 1),2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fabulous-wells",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "impossible-kitty",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "talented-anxiety",
+   "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
+}