{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Imputation of missing values with IsoTree\n",
    "\n",
    "This is a short example about imputation of missing values with the package [isotree](https://www.github.com/david-cortes/isotree) (Isolation Forest and variations), which produces imputations by taking the values from observations in the terminal nodes of each tree in which an observation with missing values falls at prediction time, combining the non-missing values of the other observations as a weighted average according to the depth of the node and the number of observations that fall there. This is not related to how the model handles missing values internally, but is rather meant as a faster way of imputing by similarity. Quality is not as good as chained equations, but the method is a lot faster and more scalable. Recommended to use non-random splits when used as an imputer.\n",
    "\n",
    "\n",
    "The example here is copy-pasted from SciKit-Learn's usage guide for their imputer, and just adds a few extra lines that do the job with this package.\n",
    "\n",
    "Original code was taken from this link:\n",
    "\n",
    "[https://scikit-learn.org/stable/auto_examples/impute/plot_iterative_imputer_variants_comparison.html#sphx-glr-auto-examples-impute-plot-iterative-imputer-variants-comparison-py](https://scikit-learn.org/stable/auto_examples/impute/plot_iterative_imputer_variants_comparison.html#sphx-glr-auto-examples-impute-plot-iterative-imputer-variants-comparison-py)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 936x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "%matplotlib inline\n",
    "\n",
    "### As of 2019-11-02, SciKit-Learn's example throws lots of convergence warnings\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "# To use this experimental feature, we need to explicitly ask for it:\n",
    "from sklearn.experimental import enable_iterative_imputer  # noqa\n",
    "from sklearn.datasets import fetch_california_housing\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.impute import IterativeImputer\n",
    "from sklearn.linear_model import BayesianRidge\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.ensemble import ExtraTreesRegressor\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "N_SPLITS = 5\n",
    "\n",
    "rng = np.random.RandomState(0)\n",
    "\n",
    "X_full, y_full = fetch_california_housing(return_X_y=True)\n",
    "# ~2k samples is enough for the purpose of the example.\n",
    "# Remove the following two lines for a slower run with different error bars.\n",
    "X_full = X_full[::10]\n",
    "y_full = y_full[::10]\n",
    "n_samples, n_features = X_full.shape\n",
    "\n",
    "# Estimate the score on the entire dataset, with no missing values\n",
    "br_estimator = BayesianRidge()\n",
    "score_full_data = pd.DataFrame(\n",
    "    cross_val_score(\n",
    "        br_estimator, X_full, y_full, scoring='neg_mean_squared_error',\n",
    "        cv=N_SPLITS\n",
    "    ),\n",
    "    columns=['Full Data']\n",
    ")\n",
    "\n",
    "# Add a single missing value to each row\n",
    "X_missing = X_full.copy()\n",
    "y_missing = y_full\n",
    "missing_samples = np.arange(n_samples)\n",
    "missing_features = rng.choice(n_features, n_samples, replace=True)\n",
    "X_missing[missing_samples, missing_features] = np.nan\n",
    "\n",
    "# Estimate the score after imputation (mean and median strategies)\n",
    "score_simple_imputer = pd.DataFrame()\n",
    "for strategy in ('mean', 'median'):\n",
    "    estimator = make_pipeline(\n",
    "        SimpleImputer(missing_values=np.nan, strategy=strategy),\n",
    "        br_estimator\n",
    "    )\n",
    "    score_simple_imputer[strategy] = cross_val_score(\n",
    "        estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n",
    "        cv=N_SPLITS\n",
    "    )\n",
    "    \n",
    "##### NEW ADDITION HERE #########\n",
    "# This is the piece of code that adds imputations with isotree\n",
    "from isotree import IsolationForest\n",
    "estimator = make_pipeline(\n",
    "        IsolationForest(build_imputer=True, ndim=3, min_imp_obs=1, prob_pick_pooled_gain=1, ntry=15),\n",
    "        br_estimator\n",
    "    )\n",
    "score_simple_imputer[\"isotree\"] = cross_val_score(\n",
    "        estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n",
    "        cv=N_SPLITS\n",
    "    )\n",
    "##### END OF NEW ADDITION #########\n",
    "\n",
    "# Estimate the score after iterative imputation of the missing values\n",
    "# with different estimators\n",
    "estimators = [\n",
    "    BayesianRidge(),\n",
    "    DecisionTreeRegressor(max_features='sqrt', random_state=0),\n",
    "    ExtraTreesRegressor(n_estimators=10, random_state=0),\n",
    "    KNeighborsRegressor(n_neighbors=15)\n",
    "]\n",
    "score_iterative_imputer = pd.DataFrame()\n",
    "for impute_estimator in estimators:\n",
    "    estimator = make_pipeline(\n",
    "        IterativeImputer(random_state=0, estimator=impute_estimator),\n",
    "        br_estimator\n",
    "    )\n",
    "    score_iterative_imputer[impute_estimator.__class__.__name__] = \\\n",
    "        cross_val_score(\n",
    "            estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n",
    "            cv=N_SPLITS\n",
    "        )\n",
    "\n",
    "scores = pd.concat(\n",
    "    [score_full_data, score_simple_imputer, score_iterative_imputer],\n",
    "    keys=['Original', 'SimpleImputer', 'IterativeImputer'], axis=1\n",
    ")\n",
    "\n",
    "# plot boston results\n",
    "fig, ax = plt.subplots(figsize=(13, 6))\n",
    "means = -scores.mean()\n",
    "errors = scores.std()\n",
    "means.plot.barh(xerr=errors, ax=ax)\n",
    "ax.set_title('California Housing Regression with Different Imputation Methods')\n",
    "ax.set_xlabel('MSE (smaller is better)')\n",
    "ax.set_yticks(np.arange(means.shape[0]))\n",
    "ax.set_yticklabels([\" w/ \".join(label) for label in means.index.get_values()])\n",
    "plt.tight_layout(pad=1)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python (OpenBLAS)",
   "language": "python",
   "name": "py3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}