{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from scipy.spatial.distance import cdist\n",
    "from sklearn.datasets import load_boston\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.neighbors import KNeighborsRegressor as skKNeighborsRegressor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Implementation 1\n",
    "- based on brute force\n",
    "- similar to scikit-learn algorithm='brute', weights='uniform'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class KNeighborsRegressor():\n",
    "    def __init__(self, n_neighbors=5):\n",
    "        self.n_neighbors = n_neighbors\n",
    "\n",
    "    def fit(self, X, y):\n",
    "        self._fit_X = X\n",
    "        self._y = y\n",
    "        return self\n",
    "\n",
    "    def predict(self, X):\n",
    "        dist_mat = cdist(X, self._fit_X)\n",
    "        neigh_ind = np.argsort(dist_mat, axis=1)[:, :self.n_neighbors]\n",
    "        return np.mean(self._y[neigh_ind], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = load_boston(return_X_y=True)\n",
    "X = StandardScaler().fit_transform(X)\n",
    "clf1 = KNeighborsRegressor().fit(X, y)\n",
    "clf2 = skKNeighborsRegressor().fit(X, y)\n",
    "pred1 = clf1.predict(X)\n",
    "pred2 = clf2.predict(X)\n",
    "assert np.allclose(pred1, pred2)"
   ]
  }
 ],
 "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
}