{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Using ML anonymization on one-hot encoded data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this tutorial we will show how to anonymize models using the ML anonymization module, specifically when the input data is already one-hot encoded. \n",
    "\n",
    "This will be demonstarted using the Adult dataset (original dataset can be found here: https://archive.ics.uci.edu/ml/datasets/adult). "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[['State-gov' 'Never-married' 'Adm-clerical' ... 'White' 'Male'\n",
      "  'UnitedStates']\n",
      " ['Self-emp-not-inc' 'Married-civ-spouse' 'Exec-managerial' ... 'White'\n",
      "  'Male' 'UnitedStates']\n",
      " ['Private' 'Divorced' 'Handlers-cleaners' ... 'White' 'Male'\n",
      "  'UnitedStates']\n",
      " ...\n",
      " ['Private' 'Never-married' 'Sales' ... 'White' 'Female' 'UnitedStates']\n",
      " ['Private' 'Never-married' 'Craft-repair' ... 'White' 'Male'\n",
      "  'UnitedStates']\n",
      " ['Private' 'Never-married' 'Handlers-cleaners' ... 'White' 'Male'\n",
      "  'UnitedStates']]\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "\n",
    "import os\n",
    "import sys\n",
    "sys.path.insert(0, os.path.abspath('..'))\n",
    "from apt.utils.dataset_utils import get_adult_dataset_pd\n",
    "\n",
    "# 'workclass', 'marital-status', 'occupation', 'relationship', 'race', 'sex', 'native-country'\n",
    "categorical_features = [1, 3, 4, 5, 6, 7, 11]\n",
    "\n",
    "# requires a folder called 'datasets' in the current directory\n",
    "(x_train, y_train), (x_test, y_test) = get_adult_dataset_pd()\n",
    "x_train = x_train.to_numpy()[:, [1, 3, 4, 5, 6, 7, 11]]\n",
    "y_train = y_train.to_numpy().astype(int)\n",
    "x_test = x_test.to_numpy()[:, [1, 3, 4, 5, 6, 7, 11]]\n",
    "y_test = y_test.to_numpy().astype(int)\n",
    "\n",
    "# get balanced dataset\n",
    "x_train = x_train[:x_test.shape[0]]\n",
    "y_train = y_train[:y_test.shape[0]]\n",
    "\n",
    "print(x_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Encode data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]\n",
      " ...\n",
      " [0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import OneHotEncoder\n",
    "import scipy\n",
    "\n",
    "preprocessor = OneHotEncoder(handle_unknown=\"ignore\")\n",
    "\n",
    "x_train = preprocessor.fit_transform(x_train)\n",
    "x_test = preprocessor.transform(x_test)\n",
    "if scipy.sparse.issparse(x_train):\n",
    "    x_train = x_train.toarray().astype(int)\n",
    "if scipy.sparse.issparse(x_test):\n",
    "    x_test = x_test.toarray().astype(int)\n",
    "\n",
    "print(x_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train decision tree model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Base model accuracy:  0.8143234445058657\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/abigailt/Library/Python/3.9/lib/python/site-packages/sklearn/utils/deprecation.py:103: FutureWarning: The attribute `n_features_` is deprecated in 1.0 and will be removed in 1.2. Use `n_features_in_` instead.\n",
      "  warnings.warn(msg, category=FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from art.estimators.classification.scikitlearn import ScikitlearnDecisionTreeClassifier\n",
    "\n",
    "model = DecisionTreeClassifier()\n",
    "model.fit(x_train, y_train)\n",
    "\n",
    "art_classifier = ScikitlearnDecisionTreeClassifier(model)\n",
    "\n",
    "print('Base model accuracy: ', model.score(x_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Anonymize data\n",
    "## k=100\n",
    "\n",
    "The data is anonymized on the quasi-identifiers: age, education-num, capital-gain, hours-per-week and with a privact parameter k=100.\n",
    "\n",
    "This means that each record in the anonymized dataset is identical to 99 others on the quasi-identifier values (i.e., when looking only at those features, the records are indistinguishable)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]\n",
      " ...\n",
      " [0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]\n",
      " [0 0 0 ... 0 1 0]]\n"
     ]
    }
   ],
   "source": [
    "from apt.utils.datasets import ArrayDataset\n",
    "from apt.anonymization import Anonymize\n",
    "\n",
    "x_train_predictions = np.array([np.argmax(arr) for arr in art_classifier.predict(x_train)])\n",
    "\n",
    "# QI = (race, sex)\n",
    "QI = [53, 52, 51, 50, 49, 48, 47]\n",
    "QI_slices = [[47, 48, 49, 50, 51], [52, 53]]\n",
    "anonymizer = Anonymize(100, QI, quasi_identifer_slices=QI_slices)\n",
    "anon = anonymizer.anonymize(ArrayDataset(x_train, x_train_predictions))\n",
    "print(anon)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2711"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# number of distinct rows in original data\n",
    "len(np.unique(x_train, axis=0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2476"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# number of distinct rows in anonymized data\n",
    "len(np.unique(anon, axis=0))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train decision tree model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Anonymized model accuracy:  0.8124808058473066\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/abigailt/Library/Python/3.9/lib/python/site-packages/sklearn/utils/deprecation.py:103: FutureWarning: The attribute `n_features_` is deprecated in 1.0 and will be removed in 1.2. Use `n_features_in_` instead.\n",
      "  warnings.warn(msg, category=FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "anon_model = DecisionTreeClassifier()\n",
    "anon_model.fit(anon, y_train)\n",
    "\n",
    "anon_art_classifier = ScikitlearnDecisionTreeClassifier(anon_model)\n",
    "\n",
    "print('Anonymized model accuracy: ', anon_model.score(x_test, y_test))"
   ]
  }
 ],
 "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}