{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# k-Nearest Neighbor (kNN) exercise\n",
    "\n",
    "*Complete and hand in this completed worksheet (including its outputs and any supporting code outside of the worksheet) with your assignment submission. For more details see the [assignments page](http://vision.stanford.edu/teaching/cs231n/assignments.html) on the course website.*\n",
    "\n",
    "The kNN classifier consists of two stages:\n",
    "\n",
    "- During training, the classifier takes the training data and simply remembers it\n",
    "- During testing, kNN classifies every test image by comparing to all training images and transfering the labels of the k most similar training examples\n",
    "- The value of k is cross-validated\n",
    "\n",
    "In this exercise you will implement these steps and understand the basic Image Classification pipeline, cross-validation, and gain proficiency in writing efficient, vectorized code."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Run some setup code for this notebook.\n",
    "\n",
    "import random\n",
    "import numpy as np\n",
    "from cs231n.data_utils import load_CIFAR10\n",
    "import matplotlib.pyplot as plt\n",
    "from tqdm import tqdm_notebook as tqdm\n",
    "\n",
    "from __future__ import print_function\n",
    "\n",
    "# This is a bit of magic to make matplotlib figures appear inline in the notebook\n",
    "# rather than in a new window.\n",
    "%matplotlib inline\n",
    "plt.rcParams['figure.figsize'] = (20.0, 16.0) # set default size of plots\n",
    "plt.rcParams['image.interpolation'] = 'nearest'\n",
    "plt.rcParams['image.cmap'] = 'gray'\n",
    "\n",
    "# Some more magic so that the notebook will reload external python modules;\n",
    "# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython\n",
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training data shape:  (50000, 32, 32, 3)\n",
      "Training labels shape:  (50000,)\n",
      "Test data shape:  (10000, 32, 32, 3)\n",
      "Test labels shape:  (10000,)\n"
     ]
    }
   ],
   "source": [
    "# Load the raw CIFAR-10 data.\n",
    "cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'\n",
    "\n",
    "# Cleaning up variables to prevent loading data multiple times (which may cause memory issue)\n",
    "try:\n",
    "   del X_train, y_train\n",
    "   del X_test, y_test\n",
    "   print('Clear previously loaded data.')\n",
    "except:\n",
    "   pass\n",
    "\n",
    "X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)\n",
    "\n",
    "# As a sanity check, we print out the size of the training and test data.\n",
    "print('Training data shape: ', X_train.shape)\n",
    "print('Training labels shape: ', y_train.shape)\n",
    "print('Test data shape: ', X_test.shape)\n",
    "print('Test labels shape: ', y_test.shape)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 70 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualize some examples from the dataset.\n",
    "# We show a few examples of training images from each class.\n",
    "classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']\n",
    "num_classes = len(classes)\n",
    "samples_per_class = 7\n",
    "for y, cls in enumerate(classes):\n",
    "    idxs = np.flatnonzero(y_train == y)\n",
    "    idxs = np.random.choice(idxs, samples_per_class, replace=False)\n",
    "    for i, idx in enumerate(idxs):\n",
    "        plt_idx = i * num_classes + y + 1\n",
    "        plt.subplot(samples_per_class, num_classes, plt_idx)\n",
    "        plt.imshow(X_train[idx].astype('uint8'))\n",
    "        plt.axis('off')\n",
    "        if i == 0:\n",
    "            plt.title(cls)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Subsample the data for more efficient code execution in this exercise\n",
    "num_training = 5000\n",
    "mask = list(range(num_training))\n",
    "X_train = X_train[mask]\n",
    "y_train = y_train[mask]\n",
    "\n",
    "num_test = 500\n",
    "mask = list(range(num_test))\n",
    "X_test = X_test[mask]\n",
    "y_test = y_test[mask]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(5000, 3072) (500, 3072)\n"
     ]
    }
   ],
   "source": [
    "# Reshape the image data into rows\n",
    "X_train = np.reshape(X_train, (X_train.shape[0], -1))\n",
    "X_test = np.reshape(X_test, (X_test.shape[0], -1))\n",
    "print(X_train.shape, X_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from cs231n.classifiers import KNearestNeighbor\n",
    "\n",
    "# Create a kNN classifier instance. \n",
    "# Remember that training a kNN classifier is a noop: \n",
    "# the Classifier simply remembers the data and does no further processing \n",
    "classifier = KNearestNeighbor()\n",
    "classifier.train(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We would now like to classify the test data with the kNN classifier. Recall that we can break down this process into two steps: \n",
    "\n",
    "1. First we must compute the distances between all test examples and all train examples. \n",
    "2. Given these distances, for each test example we find the k nearest examples and have them vote for the label\n",
    "\n",
    "Lets begin with computing the distance matrix between all training and test examples. For example, if there are **Ntr** training examples and **Nte** test examples, this stage should result in a **Nte x Ntr** matrix where each element (i,j) is the distance between the i-th test and j-th train example.\n",
    "\n",
    "First, open `cs231n/classifiers/k_nearest_neighbor.py` and implement the function `compute_distances_two_loops` that uses a (very inefficient) double loop over all pairs of (test, train) examples and computes the distance matrix one element at a time."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "93adce2783fa4af6a6b380128947ee58",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=500), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-ca518ab5a8fc>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;31m# Test your implementation:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mdists\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mclassifier\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompute_distances_two_loops\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdists\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/Workspace/cs231n Assignments/assignment1/cs231n/classifiers/k_nearest_neighbor.py\u001b[0m in \u001b[0;36mcompute_distances_two_loops\u001b[0;34m(self, X)\u001b[0m\n\u001b[1;32m     74\u001b[0m         \u001b[0;31m#####################################################################\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     75\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 76\u001b[0;31m         \u001b[0mdists\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mj\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinalg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mj\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mord\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     77\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     78\u001b[0m         \u001b[0;31m#####################################################################\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/lib/python3.7/site-packages/numpy/linalg/linalg.py\u001b[0m in \u001b[0;36mnorm\u001b[0;34m(x, ord, axis, keepdims)\u001b[0m\n\u001b[1;32m   2357\u001b[0m                 \u001b[0msqnorm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreal\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreal\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mdot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimag\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mimag\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2358\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2359\u001b[0;31m                 \u001b[0msqnorm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2360\u001b[0m             \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msqrt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msqnorm\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2361\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mkeepdims\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "# Open cs231n/classifiers/k_nearest_neighbor.py and implement\n",
    "# compute_distances_two_loops.\n",
    "\n",
    "# Test your implementation:\n",
    "dists = classifier.compute_distances_two_loops(X_test)\n",
    "print(dists.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# We can visualize the distance matrix: each row is a single test example and\n",
    "# its distances to training examples\n",
    "plt.imshow(dists, interpolation='none')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Inline Question #1:** Notice the structured patterns in the distance matrix, where some rows or columns are visible brighter. (Note that with the default color scheme black indicates low distances while white indicates high distances.)\n",
    "\n",
    "- What in the data is the cause behind the distinctly bright rows? Test samples that is very similar to all train examples.\n",
    "- What causes the columns? Train samples that are very similar to all test examples."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Your Answer**: *fill this in.*\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ff60f0b0a35f4f08aa6a7d1d4a6888ac",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Got 283 / 1000 correct => accuracy: 0.283000\n"
     ]
    }
   ],
   "source": [
    "# Now implement the function predict_labels and run the code below:\n",
    "# We use k = 1 (which is Nearest Neighbor).\n",
    "y_test_pred = classifier.predict_labels(dists, k=1)\n",
    "\n",
    "# Compute and print the fraction of correctly predicted examples\n",
    "num_correct = np.sum(y_test_pred == y_test)\n",
    "accuracy = float(num_correct) / num_test\n",
    "print('Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You should expect to see approximately `27%` accuracy. Now lets try out a larger `k`, say `k = 5`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'dists' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-21-6882bf1206c4>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0my_test_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mclassifier\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict_labels\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdists\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m13\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mnum_correct\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_test_pred\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0maccuracy\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfloat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnum_correct\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m/\u001b[0m \u001b[0mnum_test\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Got %d / %d correct => accuracy: %f'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mnum_correct\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnum_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccuracy\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'dists' is not defined"
     ]
    }
   ],
   "source": [
    "y_test_pred = classifier.predict_labels(dists, k=13)\n",
    "num_correct = np.sum(y_test_pred == y_test)\n",
    "accuracy = float(num_correct) / num_test\n",
    "print('Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You should expect to see a slightly better performance than with `k = 1`."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Inline Question 2**\n",
    "We can also other distance metrics such as L1 distance.\n",
    "The performance of a Nearest Neighbor classifier that uses L1 distance will not change if (Select all that apply.):\n",
    "1. The data is preprocessed by subtracting the mean.\n",
    "2. The data is preprocessed by subtracting the mean and dividing by the standard deviation.\n",
    "3. The coordinate axes for the data are rotated.\n",
    "4. None of the above.\n",
    "\n",
    "*Your Answer*: 1\n",
    "\n",
    "*Your explanation*:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5b70792c5e8c47c59607a0b497fe6e12",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Difference was: 0.000000\n",
      "Good! The distance matrices are the same\n"
     ]
    }
   ],
   "source": [
    "# Now lets speed up distance matrix computation by using partial vectorization\n",
    "# with one loop. Implement the function compute_distances_one_loop and run the\n",
    "# code below:\n",
    "dists_one = classifier.compute_distances_one_loop(X_test)\n",
    "\n",
    "# To ensure that our vectorized implementation is correct, we make sure that it\n",
    "# agrees with the naive implementation. There are many ways to decide whether\n",
    "# two matrices are similar; one of the simplest is the Frobenius norm. In case\n",
    "# you haven't seen it before, the Frobenius norm of two matrices is the square\n",
    "# root of the squared sum of differences of all elements; in other words, reshape\n",
    "# the matrices into vectors and compute the Euclidean distance between them.\n",
    "difference = np.linalg.norm(dists - dists_one, ord='fro')\n",
    "print('Difference was: %f' % (difference, ))\n",
    "if difference < 0.001:\n",
    "    print('Good! The distance matrices are the same')\n",
    "else:\n",
    "    print('Uh-oh! The distance matrices are different')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'dists' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-20-b1a03c2e0947>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;31m# check that the distance matrix agrees with the one we computed before:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0mdifference\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlinalg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnorm\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdists\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mdists_two\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mord\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'fro'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      7\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Difference was: %f'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mdifference\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdifference\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0;36m0.001\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'dists' is not defined"
     ]
    }
   ],
   "source": [
    "# Now implement the fully vectorized version inside compute_distances_no_loops\n",
    "# and run the code\n",
    "dists_two = classifier.compute_distances_no_loops(X_test)\n",
    "\n",
    "# check that the distance matrix agrees with the one we computed before:\n",
    "difference = np.linalg.norm(dists - dists_two, ord='fro')\n",
    "print('Difference was: %f' % (difference, ))\n",
    "if difference < 0.001:\n",
    "    print('Good! The distance matrices are the same')\n",
    "else:\n",
    "    print('Uh-oh! The distance matrices are different')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "No loop version took 0.838690 seconds\n"
     ]
    }
   ],
   "source": [
    "# Let's compare how fast the implementations are\n",
    "def time_function(f, *args):\n",
    "    \"\"\"\n",
    "    Call a function f with args and return the time (in seconds) that it took to execute.\n",
    "    \"\"\"\n",
    "    import time\n",
    "    tic = time.time()\n",
    "    f(*args)\n",
    "    toc = time.time()\n",
    "    return toc - tic\n",
    "\n",
    "two_loop_time = time_function(classifier.compute_distances_two_loops, X_test)\n",
    "print('Two loop version took %f seconds' % two_loop_time)\n",
    "\n",
    "one_loop_time = time_function(classifier.compute_distances_one_loop, X_test)\n",
    "print('One loop version took %f seconds' % one_loop_time)\n",
    "\n",
    "no_loop_time = time_function(classifier.compute_distances_no_loops, X_test)\n",
    "print('No loop version took %f seconds' % no_loop_time)\n",
    "\n",
    "# you should see significantly faster performance with the fully vectorized implementation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Cross-validation\n",
    "\n",
    "We have implemented the k-Nearest Neighbor classifier but we set the value k = 5 arbitrarily. We will now determine the best value of this hyperparameter with cross-validation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2cde7accb4be4f7ab080a66baafac873",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=10), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b0ea7280428949fbae0de36bdbe1de22",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0460601da82d41ceaba8354e6c75151e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "78794322b1fd4ad2b34cca16fe11cbbf",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "37651d8a6ebe4befbcf1cddb88154f95",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3e2ead00776141799a4fd0cff3f28c90",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bba553b5cd6c4045a1dea617d98ded1c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d2c631f030984735ace4fe3d97c678fb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "789d6f12db7f4d8aa27fdfefbda677be",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3b9b2f1b9afa4d96b978c5aa37b0fdaa",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4e210d3dd53845abb50985b85410114d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ae070031ebb04d9084a556c8293e757d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6934d6ca7bbd4cbfa1808274b64a1dfd",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bc2c4cc013e74fca970e44470583b8bd",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "41e302d79d914951bfa4b7d31b154be3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "70bc887c58774e02808c15fd7d6c1d5d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1c4c8115888a4d16bb1347ea55397356",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bc36754c76b64249ac39ed5c7d2c08ff",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8fa8e869bf0c40c39898b14c36648895",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "27115bfcf5c340cdb542faf8442edb0e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a910a69ca1454100a993a4b328f52459",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "eec6344c50f84c6e8c2f76b67eaa3353",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "13a8969ce42b4f5fa723aebfcdf858ba",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9a546dd23d0446efbd0d4c096bcf7e20",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2c87e1b9c3404534ab0e9169386e3bc2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1335f924c9a7416ab3d320d0f3a96f73",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f67aacd132be484aacd0021497e17e5e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "8489aed6e7f04e5db38377fcd4926f0c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "72f98ec41bb9497fb76c7eb2694bc5e8",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ac0baf0f24254760af43d3ef62a71135",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e8aebadb0bc24ee4ad3c3a1d55ca2698",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "06a40383d099474ebea6b3a7d45e59b2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cb10432c71094aaeb2dca85ab6e35095",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "00fef5da80c14bef8e9f325b4a4ebb8c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ef5da8dc14e446b8bd26aab48d2fc9c7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "02b1876c6ca545248045a7b48790c09c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ee18c7d368d24aa68562d4c0d1b47866",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "386e9ebe487f43aab316df352ee79298",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "37f5dcaa546b45c791d2b154e60bd40f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "16f3ff326aae4ff6b51a543e14d7f1b5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f9af90bf26a74076b7085c3dd626c192",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bb12acb3a1154765b4134684d129969d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b40b05ec8a9b4613bf16e8af44a2a7e2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0187885feb6848dd97012b9b5f8d4008",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b3dba433097c4e4cbb0aa2d633537a56",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "2f938d139f284166bcd7d965684ebb62",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=5), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5e1208ddf93745d6b91fb98a7ec6623b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5f2b49900a834983b83b7ea2c21f6d96",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5a28cedd67b84936941c5527972ec185",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "dd2cb8238a924e668e67f0894886b8f5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "cf767998dc484cefa3723444e57e5f36",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1000), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "k = 1, accuracy = 0.263000\n",
      "k = 1, accuracy = 0.257000\n",
      "k = 1, accuracy = 0.264000\n",
      "k = 1, accuracy = 0.278000\n",
      "k = 1, accuracy = 0.266000\n",
      "k = 3, accuracy = 0.239000\n",
      "k = 3, accuracy = 0.249000\n",
      "k = 3, accuracy = 0.240000\n",
      "k = 3, accuracy = 0.266000\n",
      "k = 3, accuracy = 0.254000\n",
      "k = 5, accuracy = 0.248000\n",
      "k = 5, accuracy = 0.266000\n",
      "k = 5, accuracy = 0.280000\n",
      "k = 5, accuracy = 0.292000\n",
      "k = 5, accuracy = 0.280000\n",
      "k = 8, accuracy = 0.262000\n",
      "k = 8, accuracy = 0.282000\n",
      "k = 8, accuracy = 0.273000\n",
      "k = 8, accuracy = 0.290000\n",
      "k = 8, accuracy = 0.273000\n",
      "k = 10, accuracy = 0.265000\n",
      "k = 10, accuracy = 0.296000\n",
      "k = 10, accuracy = 0.276000\n",
      "k = 10, accuracy = 0.284000\n",
      "k = 10, accuracy = 0.280000\n",
      "k = 12, accuracy = 0.260000\n",
      "k = 12, accuracy = 0.295000\n",
      "k = 12, accuracy = 0.279000\n",
      "k = 12, accuracy = 0.283000\n",
      "k = 12, accuracy = 0.280000\n",
      "k = 15, accuracy = 0.252000\n",
      "k = 15, accuracy = 0.289000\n",
      "k = 15, accuracy = 0.278000\n",
      "k = 15, accuracy = 0.282000\n",
      "k = 15, accuracy = 0.274000\n",
      "k = 20, accuracy = 0.270000\n",
      "k = 20, accuracy = 0.279000\n",
      "k = 20, accuracy = 0.279000\n",
      "k = 20, accuracy = 0.282000\n",
      "k = 20, accuracy = 0.285000\n",
      "k = 50, accuracy = 0.271000\n",
      "k = 50, accuracy = 0.288000\n",
      "k = 50, accuracy = 0.278000\n",
      "k = 50, accuracy = 0.269000\n",
      "k = 50, accuracy = 0.266000\n",
      "k = 100, accuracy = 0.256000\n",
      "k = 100, accuracy = 0.270000\n",
      "k = 100, accuracy = 0.263000\n",
      "k = 100, accuracy = 0.256000\n",
      "k = 100, accuracy = 0.263000\n"
     ]
    }
   ],
   "source": [
    "num_folds = 5\n",
    "k_choices = [1, 3, 5, 8, 10, 12, 15, 20, 50, 100]\n",
    "\n",
    "X_train_folds = []\n",
    "y_train_folds = []\n",
    "################################################################################\n",
    "# TODO:                                                                        #\n",
    "# Split up the training data into folds. After splitting, X_train_folds and    #\n",
    "# y_train_folds should each be lists of length num_folds, where                #\n",
    "# y_train_folds[i] is the label vector for the points in X_train_folds[i].     #\n",
    "# Hint: Look up the numpy array_split function.                                #\n",
    "################################################################################\n",
    "\n",
    "X_train_folds = np.split(X_train, num_folds)\n",
    "y_train_folds = np.split(y_train, num_folds)\n",
    "\n",
    "################################################################################\n",
    "#                                 END OF YOUR CODE                             #\n",
    "################################################################################\n",
    "\n",
    "# A dictionary holding the accuracies for different values of k that we find\n",
    "# when running cross-validation. After running cross-validation,\n",
    "# k_to_accuracies[k] should be a list of length num_folds giving the different\n",
    "# accuracy values that we found when using that value of k.\n",
    "k_to_accuracies = {}\n",
    "\n",
    "\n",
    "################################################################################\n",
    "# TODO:                                                                        #\n",
    "# Perform k-fold cross validation to find the best value of k. For each        #\n",
    "# possible value of k, run the k-nearest-neighbor algorithm num_folds times,   #\n",
    "# where in each case you use all but one of the folds as training data and the #\n",
    "# last fold as a validation set. Store the accuracies for all fold and all     #\n",
    "# values of k in the k_to_accuracies dictionary.                               #\n",
    "################################################################################\n",
    "\n",
    "for k in tqdm(k_choices):\n",
    "    accuracies = []\n",
    "    for i in tqdm(range(num_folds), leave=False):\n",
    "        X_train_f = np.concatenate(X_train_folds[:i]+X_train_folds[i+1:], axis=0)\n",
    "        X_val_f = X_train_folds[i]\n",
    "        \n",
    "        y_train_f = np.concatenate(y_train_folds[:i]+y_train_folds[i+1:], axis=0)\n",
    "        y_val_f = y_train_folds[i]\n",
    "        \n",
    "        classifier.train(X_train_f, y_train_f)\n",
    "        y_result = classifier.predict(X_val_f, k=k).astype(np.int_)\n",
    "        \n",
    "        acc = (y_result == y_val_f).sum() / len(y_result)\n",
    "        accuracies.append(acc)        \n",
    "    \n",
    "    k_to_accuracies[k] = accuracies\n",
    "\n",
    "################################################################################\n",
    "#                                 END OF YOUR CODE                             #\n",
    "################################################################################\n",
    "\n",
    "# Print out the computed accuracies\n",
    "for k in sorted(k_to_accuracies):\n",
    "    for accuracy in k_to_accuracies[k]:\n",
    "        print('k = %d, accuracy = %f' % (k, accuracy))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot the raw observations\n",
    "for k in k_choices:\n",
    "    accuracies = k_to_accuracies[k]\n",
    "    plt.scatter([k] * len(accuracies), accuracies)\n",
    "\n",
    "# plot the trend line with error bars that correspond to standard deviation\n",
    "accuracies_mean = np.array([np.mean(v) for k,v in sorted(k_to_accuracies.items())])\n",
    "accuracies_std = np.array([np.std(v) for k,v in sorted(k_to_accuracies.items())])\n",
    "plt.errorbar(k_choices, accuracies_mean, yerr=accuracies_std)\n",
    "plt.title('Cross-validation on k')\n",
    "plt.xlabel('k')\n",
    "plt.ylabel('Cross-validation accuracy')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ba81170c7b80457fae17f5f658d98967",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=500), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Got 141 / 500 correct => accuracy: 0.282000\n"
     ]
    }
   ],
   "source": [
    "# Based on the cross-validation results above, choose the best value for k,   \n",
    "# retrain the classifier using all the training data, and test it on the test\n",
    "# data. You should be able to get above 28% accuracy on the test data.\n",
    "best_k = 10\n",
    "\n",
    "classifier = KNearestNeighbor()\n",
    "classifier.train(X_train, y_train)\n",
    "y_test_pred = classifier.predict(X_test, k=best_k)\n",
    "\n",
    "# Compute and display the accuracy\n",
    "num_correct = np.sum(y_test_pred == y_test)\n",
    "accuracy = float(num_correct) / num_test\n",
    "print('Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Inline Question 3**\n",
    "Which of the following statements about $k$-Nearest Neighbor ($k$-NN) are true in a classification setting, and for all $k$? Select all that apply.\n",
    "1. The training error of a 1-NN will always be better than that of 5-NN. Yes (or equal if n=1)\n",
    "2. The test error of a 1-NN will always be better than that of a 5-NN. Not always, but in general\n",
    "3. The decision boundary of the k-NN classifier is linear.\n",
    "4. The time needed to classify a test example with the k-NN classifier grows with the size of the training set.\n",
    "5. None of the above.\n",
    "\n",
    "*Your Answer*:\n",
    "\n",
    "*Your explanation*:"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}