Fairlearn exemple 2.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Démonstration FairLearn"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img src=\"https://fairlearn.github.io/_static/images/header-image.png\" width=\"400\">"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "> https://fairlearn.github.io/"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Fairlearn package has two components:\n",
    "\n",
    "- A dashboard for assessing which groups are negatively impacted by a model, and for comparing multiple models in terms of various fairness and accuracy metrics.\n",
    "- Algorithms for mitigating unfairness in a variety of AI tasks and along a variety of fairness definitions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'3.6.9 |Anaconda, Inc.| (default, Jul 30 2019, 19:07:31) \\n[GCC 7.3.0]'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import sys\n",
    "sys.version"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2020-07-08 08:25:31.084447\n"
     ]
    }
   ],
   "source": [
    "import datetime\n",
    "now = datetime.datetime.now()\n",
    "print(now)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install azureml-contrib-fairness"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install fairlearn==0.4.6"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from fairlearn.widget import FairlearnDashboard\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
    "import pandas as pd\n",
    "import shap\n",
    "\n",
    "# Load the census dataset\n",
    "X_raw, Y = shap.datasets.adult()\n",
    "X_raw[\"Race\"].value_counts().to_dict()\n",
    "\n",
    "\n",
    "# (Optional) Separate the \"sex\" and \"race\" sensitive features out and drop them from the main data prior to training your model\n",
    "A = X_raw[['Sex','Race']]\n",
    "X = X_raw.drop(labels=['Sex', 'Race'],axis = 1)\n",
    "X = pd.get_dummies(X)\n",
    "\n",
    "sc = StandardScaler()\n",
    "X_scaled = sc.fit_transform(X)\n",
    "X_scaled = pd.DataFrame(X_scaled, columns=X.columns)\n",
    "\n",
    "# Perform some standard data preprocessing steps to convert the data into a format suitable for the ML algorithms\n",
    "le = LabelEncoder()\n",
    "Y = le.fit_transform(Y)\n",
    "\n",
    "# Split data into train and test\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, Y_train, Y_test, A_train, A_test = train_test_split(X_scaled, \n",
    "                                                    Y, \n",
    "                                                    A,\n",
    "                                                    test_size = 0.2,\n",
    "                                                    random_state=0,\n",
    "                                                    stratify=Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(solver='liblinear')"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Work around indexing issue\n",
    "X_train = X_train.reset_index(drop=True)\n",
    "A_train = A_train.reset_index(drop=True)\n",
    "X_test = X_test.reset_index(drop=True)\n",
    "A_test = A_test.reset_index(drop=True)\n",
    "\n",
    "# Improve labels\n",
    "A_test.Sex.loc[(A_test['Sex'] == 0)] = 'female'\n",
    "A_test.Sex.loc[(A_test['Sex'] == 1)] = 'male'\n",
    "\n",
    "A_test.Race.loc[(A_test['Race'] == 0)] = 'Amer-Indian-Eskimo'\n",
    "A_test.Race.loc[(A_test['Race'] == 1)] = 'Asian-Pac-Islander'\n",
    "A_test.Race.loc[(A_test['Race'] == 2)] = 'Black'\n",
    "A_test.Race.loc[(A_test['Race'] == 3)] = 'Other'\n",
    "A_test.Race.loc[(A_test['Race'] == 4)] = 'White'\n",
    "\n",
    "# Train a classification model\n",
    "lr_predictor = LogisticRegression(solver='liblinear', fit_intercept=True)\n",
    "lr_predictor.fit(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "27ee0f452d694e078979bc0580c87e62",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "FairlearnWidget(value={'true_y': [0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<fairlearn.widget._fairlearn_dashboard.FairlearnDashboard at 0x7fb98b77e278>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# (Optional) View this model in Fairlearn's fairness dashboard, and see the disparities which appear:\n",
    "from fairlearn.widget import FairlearnDashboard\n",
    "FairlearnDashboard(sensitive_features=A_test, \n",
    "                   sensitive_feature_names=['Sex', 'Race'],\n",
    "                   y_true=Y_test,\n",
    "                   y_pred={\"lr_model\": lr_predictor.predict(X_test)})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.6 - AzureML",
   "language": "python",
   "name": "python3-azureml"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}