{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.base import clone\n",
    "from sklearn.datasets import load_boston, load_iris\n",
    "from sklearn.ensemble import RandomForestRegressor, RandomForestClassifier\n",
    "from sklearn.model_selection import KFold, StratifiedKFold\n",
    "from sklearn.model_selection import cross_val_predict as skcross_val_predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def cross_val_predict(estimator, X, y, method=\"predict\"):\n",
    "    if estimator._estimator_type == \"regressor\":\n",
    "        cv = KFold()\n",
    "    else:  # estimator._estimator_type == \"classifier\"\n",
    "        cv = StratifiedKFold()\n",
    "    predictions = []\n",
    "    indices = []\n",
    "    for train, test in cv.split(X, y):\n",
    "        est = clone(estimator)\n",
    "        est.fit(X[train], y[train])\n",
    "        predictions.extend(getattr(est, method)(X[test]))\n",
    "        indices.extend(test)\n",
    "    inv_indices = np.empty(len(indices), dtype=np.int)\n",
    "    inv_indices[indices] = np.arange(len(indices))\n",
    "    return np.array(predictions)[inv_indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# regression\n",
    "X, y = load_boston(return_X_y=True)\n",
    "clf = RandomForestRegressor(random_state=0)\n",
    "ans1 = cross_val_predict(clf, X, y)\n",
    "ans2 = skcross_val_predict(clf, X, y)\n",
    "assert np.allclose(ans1, ans2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# classification\n",
    "X, y = load_iris(return_X_y=True)\n",
    "clf = RandomForestClassifier(random_state=0)\n",
    "ans1 = cross_val_predict(clf, X, y)\n",
    "ans2 = skcross_val_predict(clf, X, y)\n",
    "assert np.array_equal(ans1, ans2)\n",
    "ans1 = cross_val_predict(clf, X, y, method=\"predict_proba\")\n",
    "ans2 = skcross_val_predict(clf, X, y, method=\"predict_proba\")\n",
    "assert np.allclose(ans1, ans2)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "dev",
   "language": "python",
   "name": "dev"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}