{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.datasets import load_boston\n",
    "from sklearn.model_selection import KFold as skKFold"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class KFold():\n",
    "    def __init__(self, n_splits=5, shuffle=False, random_state=0):\n",
    "        self.n_splits = n_splits\n",
    "        self.shuffle = shuffle\n",
    "        self.random_state = random_state\n",
    "\n",
    "    def _iter_test_indices(self, X, y):\n",
    "        indices = np.arange(X.shape[0])\n",
    "        if self.shuffle:\n",
    "            rng = np.random.RandomState(self.random_state)\n",
    "            rng.shuffle(indices)\n",
    "        fold_sizes = np.full(self.n_splits, X.shape[0] // self.n_splits)\n",
    "        fold_sizes[:X.shape[0] % self.n_splits] += 1\n",
    "        current = 0\n",
    "        for fold_size in fold_sizes:\n",
    "            yield indices[current:current + fold_size]\n",
    "            current += fold_size\n",
    "\n",
    "    def _iter_test_masks(self, X, y):\n",
    "        for test_index in self._iter_test_indices(X, y):\n",
    "            test_mask = np.zeros(X.shape[0], dtype=bool)\n",
    "            test_mask[test_index] = True\n",
    "            yield test_mask\n",
    "\n",
    "    def split(self, X, y):\n",
    "        indices = np.arange(X.shape[0])\n",
    "        for test_index in self._iter_test_masks(X, y):\n",
    "            yield indices[~test_index], indices[test_index]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = load_boston(return_X_y=True)\n",
    "cv1 = KFold(n_splits=5)\n",
    "cv2 = skKFold(n_splits=5)\n",
    "for (train1, test1), (train2, test2) in zip(cv1.split(X, y), cv2.split(X, y)):\n",
    "    assert np.array_equal(train1, train2)\n",
    "    assert np.array_equal(test1, test2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X, y = load_boston(return_X_y=True)\n",
    "cv1 = KFold(n_splits=5, shuffle=True, random_state=0)\n",
    "cv2 = skKFold(n_splits=5, shuffle=True, random_state=0)\n",
    "for (train1, test1), (train2, test2) in zip(cv1.split(X, y), cv2.split(X, y)):\n",
    "    assert np.array_equal(train1, train2)\n",
    "    assert np.array_equal(test1, test2)"
   ]
  }
 ],
 "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
}