{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### MACE counterfactual explanation for income prediction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is an example of the Model-Agnostic Counterfactual Explanation (MACE) developed by Yang et al. If using this explainer, please cite our paper \"MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation\". MACE supports black-box models for classification tasks where input features can either be categorical or continuous-valued, and generates diverse counterfactual examples."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# This default renderer is used for sphinx docs only. Please delete this cell in IPython.\n",
    "import plotly.io as pio\n",
    "pio.renderers.default = \"png\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import sklearn\n",
    "import xgboost\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from omnixai.data.tabular import Tabular\n",
    "from omnixai.preprocessing.tabular import TabularTransform\n",
    "from omnixai.explainers.tabular import MACEExplainer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The dataset used in this example is for income prediction (https://archive.ics.uci.edu/ml/datasets/adult). We recommend using `Tabular` to represent a tabular dataset, which can be constructed from a pandas dataframe or a numpy array. To create a `Tabular` instance given a numpy array, one needs to specify the data, the feature names, the categorical feature names (if exists) and the target/label column name (if exists)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      Age         Workclass  fnlwgt   Education Education-Num  \\\n",
      "0      39         State-gov   77516   Bachelors            13   \n",
      "1      50  Self-emp-not-inc   83311   Bachelors            13   \n",
      "2      38           Private  215646     HS-grad             9   \n",
      "3      53           Private  234721        11th             7   \n",
      "4      28           Private  338409   Bachelors            13   \n",
      "...    ..               ...     ...         ...           ...   \n",
      "32556  27           Private  257302  Assoc-acdm            12   \n",
      "32557  40           Private  154374     HS-grad             9   \n",
      "32558  58           Private  151910     HS-grad             9   \n",
      "32559  22           Private  201490     HS-grad             9   \n",
      "32560  52      Self-emp-inc  287927     HS-grad             9   \n",
      "\n",
      "           Marital Status         Occupation   Relationship   Race     Sex  \\\n",
      "0           Never-married       Adm-clerical  Not-in-family  White    Male   \n",
      "1      Married-civ-spouse    Exec-managerial        Husband  White    Male   \n",
      "2                Divorced  Handlers-cleaners  Not-in-family  White    Male   \n",
      "3      Married-civ-spouse  Handlers-cleaners        Husband  Black    Male   \n",
      "4      Married-civ-spouse     Prof-specialty           Wife  Black  Female   \n",
      "...                   ...                ...            ...    ...     ...   \n",
      "32556  Married-civ-spouse       Tech-support           Wife  White  Female   \n",
      "32557  Married-civ-spouse  Machine-op-inspct        Husband  White    Male   \n",
      "32558             Widowed       Adm-clerical      Unmarried  White  Female   \n",
      "32559       Never-married       Adm-clerical      Own-child  White    Male   \n",
      "32560  Married-civ-spouse    Exec-managerial           Wife  White  Female   \n",
      "\n",
      "      Capital Gain Capital Loss Hours per week        Country  label  \n",
      "0             2174            0             40  United-States  <=50K  \n",
      "1                0            0             13  United-States  <=50K  \n",
      "2                0            0             40  United-States  <=50K  \n",
      "3                0            0             40  United-States  <=50K  \n",
      "4                0            0             40           Cuba  <=50K  \n",
      "...            ...          ...            ...            ...    ...  \n",
      "32556            0            0             38  United-States  <=50K  \n",
      "32557            0            0             40  United-States   >50K  \n",
      "32558            0            0             40  United-States  <=50K  \n",
      "32559            0            0             20  United-States  <=50K  \n",
      "32560        15024            0             40  United-States   >50K  \n",
      "\n",
      "[32561 rows x 15 columns]\n"
     ]
    }
   ],
   "source": [
    "feature_names = [\n",
    "    \"Age\", \"Workclass\", \"fnlwgt\", \"Education\",\n",
    "    \"Education-Num\", \"Marital Status\", \"Occupation\",\n",
    "    \"Relationship\", \"Race\", \"Sex\", \"Capital Gain\",\n",
    "    \"Capital Loss\", \"Hours per week\", \"Country\", \"label\"\n",
    "]\n",
    "data = np.genfromtxt(os.path.join('../data', 'adult.data'), delimiter=', ', dtype=str)\n",
    "tabular_data = Tabular(\n",
    "    data,\n",
    "    feature_columns=feature_names,\n",
    "    categorical_columns=[feature_names[i] for i in [1, 3, 5, 6, 7, 8, 9, 13]],\n",
    "    target_column='label'\n",
    ")\n",
    "print(tabular_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "`TabularTransform` is a special transform designed for tabular data. By default, it converts categorical features into one-hot encoding, and keeps continuous-valued features (if one wants to normalize continuous-valued features, set the parameter `cont_transform` in `TabularTransform` to `Standard` or `MinMax`). The `transform` method of `TabularTransform` will transform a `Tabular` instance into a numpy array. If the `Tabular` instance has a target/label column, the last column of the transformed numpy array will be the target/label. \n",
    "\n",
    "If some other transformations that are not supported in the library are necessary, one can simply convert the `Tabular` instance into a pandas dataframe by calling `Tabular.to_pd()` and try different transformations with it.\n",
    "\n",
    "After data preprocessing, we can train a XGBoost classifier for this task (one may try other classifiers). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training data shape: (26048, 108)\n",
      "Test data shape:     (6513, 108)\n",
      "Test accuracy: 0.8668816213726394\n"
     ]
    }
   ],
   "source": [
    "np.random.seed(1)\n",
    "transformer = TabularTransform().fit(tabular_data)\n",
    "class_names = transformer.class_names\n",
    "x = transformer.transform(tabular_data)\n",
    "train, test, labels_train, labels_test = \\\n",
    "    sklearn.model_selection.train_test_split(x[:, :-1], x[:, -1], train_size=0.80)\n",
    "print('Training data shape: {}'.format(train.shape))\n",
    "print('Test data shape:     {}'.format(test.shape))\n",
    "\n",
    "gbtree = xgboost.XGBClassifier(n_estimators=300, max_depth=5)\n",
    "gbtree.fit(train, labels_train)\n",
    "print('Test accuracy: {}'.format(\n",
    "    sklearn.metrics.accuracy_score(labels_test, gbtree.predict(test))))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The prediction function takes a `Tabular` instance as its inputs, and outputs the class probabilities or logits for classification tasks or the estimated values for regression tasks. In this example, we simply call `transformer.transform` to do data preprocessing followed by the prediction function of `gbtree`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict_function=lambda z: gbtree.predict_proba(transformer.transform(z))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To initialize a MACE explainer, we need to set:\n",
    "  \n",
    "  - `training_data`: The data used to initialize a MACE explainer. ``training_data`` can be the training dataset for training the machine learning model. If the training dataset is too large, ``training_data`` can be a subset of it by applying `omnixai.sampler.tabular.Sampler.subsample`.\n",
    "  - `predict_function`: The prediction function corresponding to the model.\n",
    "  - `ignored_features`: The features ignored in generating counterfactual examples, i.e., those features are fixed.\n",
    "  \n",
    "In this example, we set `ignored_features=[\"Sex\", \"Race\", \"Relationship\", \"Capital Loss\"]`, meaning that the generated counterfactual examples don't change the values of these features."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "explainer = MACEExplainer(\n",
    "    training_data=tabular_data,\n",
    "    predict_function=predict_function,\n",
    "    ignored_features=[\"Sex\", \"Race\", \"Relationship\", \"Capital Loss\"]\n",
    ")\n",
    "test_instances = tabular_data.remove_target_column()[0:5]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "MACE generates local explanations, e.g. `explainer.explain` is called given the test instances. `ipython_plot` plots the generated explanations in IPython. Parameter `index` indicates which instance to plot, e.g., `index = 1` means plotting the second instance in `test_instances`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "explanations = explainer.explain(test_instances)\n",
    "explanations.ipython_plot(index=1, class_names=class_names)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}