{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.datasets import load_iris\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier as skRandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def accuracy_score(y_true, y_pred):\n",
    "    return np.mean(y_true == y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "class RandomForestClassifier():\n",
    "    def __init__(self, n_estimators=100, max_depth=None, max_features=\"auto\",\n",
    "                 oob_score=False, random_state=0):\n",
    "        self.n_estimators = n_estimators\n",
    "        self.max_depth = max_depth\n",
    "        self.max_features = max_features\n",
    "        self.oob_score = oob_score\n",
    "        self.random_state = random_state\n",
    "\n",
    "    def fit(self, X, y):\n",
    "        self.n_features_ = X.shape[1]\n",
    "        self.classes_, y_train = np.unique(y, return_inverse=True)\n",
    "        self.n_classes_ = len(self.classes_)\n",
    "        MAX_INT = np.iinfo(np.int32).max\n",
    "        rng = np.random.RandomState(self.random_state)\n",
    "        self.estimators_ = []\n",
    "        for i in range(self.n_estimators):\n",
    "            est = DecisionTreeClassifier(max_depth=self.max_depth,\n",
    "                                         max_features=self.max_features,\n",
    "                                         random_state=rng.randint(MAX_INT))\n",
    "            sample_rng = np.random.RandomState(est.random_state)\n",
    "            sample_indices = sample_rng.randint(0, X.shape[0], X.shape[0])\n",
    "            sample_counts = np.bincount(sample_indices, minlength=X.shape[0])\n",
    "            est.fit(X, y_train, sample_weight=sample_counts)\n",
    "            self.estimators_.append(est)\n",
    "        if self.oob_score:\n",
    "            self._set_oob_score(X, y_train)\n",
    "        return self\n",
    "\n",
    "    def _set_oob_score(self, X, y):\n",
    "        predictions = np.zeros((X.shape[0], self.n_classes_))\n",
    "        for i in range(self.n_estimators):\n",
    "            sample_rng = np.random.RandomState(self.estimators_[i].random_state)\n",
    "            sample_indices = sample_rng.randint(0, X.shape[0], X.shape[0])\n",
    "            mask = np.ones(X.shape[0], dtype=bool)\n",
    "            mask[sample_indices] = False\n",
    "            predictions[mask] += self.estimators_[i].predict_proba(X[mask])\n",
    "        self.oob_decision_function_ = predictions / np.sum(predictions, axis=1)[:, np.newaxis]\n",
    "        self.oob_score_ = accuracy_score(y, np.argmax(predictions, axis=1))            \n",
    "\n",
    "    def predict_proba(self, X):\n",
    "        proba = np.zeros((X.shape[0], self.n_classes_))\n",
    "        for i in range(self.n_estimators):\n",
    "            proba += self.estimators_[i].predict_proba(X)\n",
    "        proba /= self.n_estimators\n",
    "        return proba\n",
    "\n",
    "    def predict(self, X):\n",
    "        proba = self.predict_proba(X)\n",
    "        return self.classes_[np.argmax(proba, axis=1)]\n",
    "\n",
    "    @property\n",
    "    def feature_importances_(self):\n",
    "        all_importances = np.zeros(self.n_features_)\n",
    "        for i in range(self.n_estimators):\n",
    "            all_importances += self.estimators_[i].feature_importances_\n",
    "        all_importances /= self.n_estimators   \n",
    "        return all_importances / np.sum(all_importances)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = load_iris(return_X_y=True)\n",
    "clf1 = RandomForestClassifier(random_state=0, oob_score=True).fit(X, y)\n",
    "clf2 = skRandomForestClassifier(random_state=0, oob_score=True).fit(X, y)\n",
    "pred1 = clf1.predict(X)\n",
    "pred2 = clf2.predict(X)\n",
    "assert np.array_equal(pred1, pred2)\n",
    "prob1 = clf1.predict_proba(X)\n",
    "prob2 = clf2.predict_proba(X)\n",
    "assert np.allclose(prob1, prob2)\n",
    "assert np.allclose(clf1.oob_decision_function_, clf2.oob_decision_function_)\n",
    "assert np.allclose(clf1.oob_score_, clf2.oob_score_)\n",
    "assert np.allclose(clf1.feature_importances_, clf2.feature_importances_)"
   ]
  }
 ],
 "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
}