{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "6xoz29ZbhlWk"
   },
   "source": [
    "Author: Aurélien Garivier\n",
    "# Dimension reduction for the MNIST dataset\n",
    "\n",
    "\n",
    "The Mnist dataset provides a (somewhat old but) very classical example of Machine Learning. The goal is simple and useful: recognize hand-written digits. This was an important challenge for the postal companies in the 1980s.  \n",
    "\n",
    "It is available in sklearn (and on the webpage of <a href=\"http://yann.lecun.com/exdb/mnist/\">Yann LeCun</a>, a very famous researcher in Machine Learning in general and neural networks in particular). \n",
    "\n",
    "</p>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "pygIPffThlWm",
    "outputId": "a375cb2f-1adf-46d9-8373-f97bac3dcd8c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "# loading a lot of facilities for numerical computations and graphs\n",
    "%pylab inline \n",
    "pylab.rcParams['figure.figsize'] = (20, 6) # to have larger plot\n",
    "seed(240979) #initialize random number generator\n",
    "\n",
    "# set working directory\n",
    "workingdir = './'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "moFV5JWfhlWq"
   },
   "source": [
    "## 1. Loading the data set\n",
    "\n",
    "### 1.1 Description of the data set\n",
    "The MNIST data contains $n\\_tot=70000$ images of size $dimX\\times dimY=28\\times28$, and their *labels* (a digit between $0$ and $9$). \n",
    "The images are stored as lines of the matrix *X*. \n",
    "Each image can be reshaped as a matrix $im \\in \\mathcal{M}_{dimX, dimY}(\\mathbb{R})$, where $im[i,j]$ is the intensity level of pixel (i,j): 0 means 'white', 255 means 'black'.\n",
    "\n",
    "The labels, stored in *y*, are numbers (here, we cast them to integers) between $0$ and $9$. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 89
    },
    "colab_type": "code",
    "id": "weoZ7FrOhlWr",
    "outputId": "02082a1d-4f9b-4911-ce1d-fa19b8536caa"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded 70000 images of size 28x28\n",
      "Number of classes: 10\n",
      "Classes:\n",
      "['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']\n"
     ]
    }
   ],
   "source": [
    "from sklearn.datasets import fetch_openml\n",
    "X, y = fetch_openml('mnist_784', version=1, return_X_y=True)\n",
    "\n",
    "X = X.values\n",
    "y = y.values\n",
    "\n",
    "# defining general variables for use throuhout the notebook  \n",
    "n_tot, p = shape(X)\n",
    "dimX = int(sqrt(p))\n",
    "dimY = dimX \n",
    "nc = len(unique(y)) # number of classes\n",
    "\n",
    "print(\"Loaded %d images of size %dx%d\"%(n_tot, dimX, dimY))\n",
    "print(\"Number of classes: %d\"%(nc))\n",
    "print(\"Classes:\")\n",
    "print(sorted(unique(y)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Ncg6bV2JhlWt"
   },
   "source": [
    "### 1.2 What does the data look like?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 776
    },
    "colab_type": "code",
    "id": "5XxvcmyghlWt",
    "outputId": "af5c91b3-b863-43c6-9632-2c47245079d3"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1440x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Showing one image \n",
    "figure(figsize = (7,7))\n",
    "ii = random.randint(0, n_tot-1)\n",
    "plt.imshow(reshape(X[ii], [dimX, dimY], order='C'), cmap=\"Greys\", interpolation=\"none\") # or \"nearest\"\n",
    "ax = plt.gca()\n",
    "ax.set_xticks(arange(-0.5, dimX, 1))\n",
    "ax.set_yticks(arange(-0.5, dimY, 1))\n",
    "ax.set_xticklabels(arange(0, dimX+1, 1))\n",
    "ax.set_yticklabels(arange(0, dimY+1, 1))\n",
    "ax.grid(color='r', linestyle='--', linewidth=1)\n",
    "plt.show()\n",
    "\n",
    "# Showing a few images in the dataset with their labels\n",
    "nbRows = 5\n",
    "nbCols = 15\n",
    "I = [[0 for k in range(nbCols)] for j in range(nbRows)]\n",
    "I[0] = [random.randint(0, n_tot-1) for k in range(nbCols)]\n",
    "I[0][0] = ii\n",
    "M = np.concatenate([reshape(X[i], [dimX,dimY], order='C') for i in I[0]], axis=1)\n",
    "\n",
    "for j in range(1, nbRows):\n",
    "    I[j] = [random.randint(0, n_tot-1) for k in range(nbCols)]\n",
    "    M = concatenate([M, np.concatenate([np.reshape(X[i], [dimX, dimY], order='C') for i in I[j]], axis=1)], axis=0)\n",
    "plt.imshow(M, cmap=\"Greys\", interpolation=\"none\")\n",
    "for j in range(nbRows):\n",
    "    for k in range(nbCols):\n",
    "        plt.text(dimX*k+2, dimX*j+5, y[I[j][k]], fontsize=14, color=\"red\")\n",
    "ax = plt.gca()\n",
    "ax.set_xticks(np.arange(-0.5, dimX*nbCols, dimX))\n",
    "ax.set_yticks(np.arange(-0.5, dimY*nbRows, dimY))\n",
    "ax.set_xticklabels([])\n",
    "ax.set_yticklabels([])\n",
    "ax.grid(color='k', linestyle='-', linewidth=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "8G3Fk6kAhlWw"
   },
   "source": [
    "## Nearest-neighbor classifier\n",
    "Distance-based methods consider some notion of *distance* in the feature space, and assume that if to feature vectors are close, then the corresponding targets are likely to be equal.\n",
    "\n",
    "### 7.1 What distance?\n",
    "The first problem, of course, is to provide the feature space with a relevant distance. There are a few default choices, and in particular the Euclidian distance (o $L^2$ distance) in $\\mathbb{R}^p$ :\n",
    "$$d(x,y) = \\sqrt{\\sum_{i=1}^p (x_i-y_i)^2}$$\n",
    "\n",
    "Is this distance really relevant on images? \n",
    "A better alternative would be the *earthmoving distance*, but it is much more costly in computation time and we will see that the $L^2$ distance already performs well.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "LpWC93U5hlWw"
   },
   "source": [
    "If you code it by yourself, the result will be good butthe computation time ridiculously high...\n",
    "\n",
    "The classifiers of scikitlearn are usually well coded, and much more efficient than a few \"quick and dirty\" lines.\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 53
    },
    "colab_type": "code",
    "id": "nhZAupUJhlWx",
    "outputId": "0593d4e3-4b82-4312-f8a7-eb38a7631c7d"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Proportion of misclassified images in testing set: 0.0542\n",
      "elapsed: 1.35652 seconds\n"
     ]
    }
   ],
   "source": [
    "import time\n",
    "\n",
    "n_train = 10000\n",
    "I = random.choice(range(n_tot), n_train, replace=False)\n",
    "trainingX = X[I, :] \n",
    "trainingTarget = y[I]\n",
    "\n",
    "# testing set: we may not use them, except at the end to assert the quality of the classifier\n",
    "mask = np.ones(n_tot, dtype=bool) #np.ones_like(a,dtype=bool)\n",
    "mask[I] = False\n",
    "testingX = X[mask, :]\n",
    "testingTarget = y[mask]\n",
    "\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "k = 7\n",
    "nearestNeighborsClassifier = KNeighborsClassifier(n_neighbors=k) # L2 distance is the default\n",
    "nearestNeighborsClassifier.fit(trainingX, trainingTarget)\n",
    "\n",
    "J = random.choice(range(len(testingTarget)), 5000, replace=False)\n",
    "\n",
    "start_time = time.time()\n",
    "pred = nearestNeighborsClassifier.predict(testingX[J])\n",
    "print(\"Proportion of misclassified images in testing set: %g\" %(mean(pred != testingTarget[J])))\n",
    "print(\"elapsed: %g seconds\"%(time.time()-start_time))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "iOgqpr3khlWz"
   },
   "source": [
    "# Using PCA to reduce dimensionality"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 53
    },
    "colab_type": "code",
    "id": "epsS__4rhlW0",
    "outputId": "0ce978b0-494b-4539-a6c2-24023cd6104f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PCA projection: Proportion of misclassified images in testing set: 0.0622\n",
      "elapsed: 0.710548 seconds\n"
     ]
    }
   ],
   "source": [
    "from sklearn.decomposition import PCA\n",
    "pca = PCA(n_components=15)\n",
    "trainingXred = pca.fit_transform(trainingX)\n",
    "\n",
    "nearestNeighborsClassifierRed = KNeighborsClassifier(n_neighbors=k) # L2 distance is the default\n",
    "nearestNeighborsClassifierRed.fit(trainingXred, trainingTarget)\n",
    "\n",
    "\n",
    "testingXred = pca.transform(testingX)\n",
    "start_time = time.time()\n",
    "predRed = nearestNeighborsClassifierRed.predict(testingXred[J])\n",
    "print(\"PCA projection: Proportion of misclassified images in testing set: %g\" %(mean(predRed != testingTarget[J])))\n",
    "print(\"elapsed: %g seconds\"%(time.time()-start_time))\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "42X8h-6mhlW2"
   },
   "source": [
    "# Using Random Projections to reduce dimensionality\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 53
    },
    "colab_type": "code",
    "id": "NhdgF1U5hlW3",
    "outputId": "0e940d4d-abfd-4064-dfd2-887e7e545013"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Random projection: Proportion of misclassified images in testing set: 0.0974\n",
      "elapsed: 0.897575 seconds\n"
     ]
    }
   ],
   "source": [
    "d = 50\n",
    "W = random.normal(0, 1/sqrt(d), dimX*dimY*d).reshape((d, dimX*dimY))\n",
    "trainingXrproj = [dot(W, x) for x in trainingX]\n",
    "\n",
    "nearestNeighborsClassifierRproj = KNeighborsClassifier(n_neighbors=k) # L2 distance is the default\n",
    "nearestNeighborsClassifierRproj.fit(trainingXrproj, trainingTarget)\n",
    "\n",
    "\n",
    "testingXrproj = np.array([dot(W, x) for x in testingX])\n",
    "start_time = time.time()\n",
    "predRproj = nearestNeighborsClassifierRproj.predict(testingXrproj[J])\n",
    "print(\"Random projection: Proportion of misclassified images in testing set: %g\" %(mean(predRproj != testingTarget[J])))\n",
    "print(\"elapsed: %g seconds\"%(time.time()-start_time))\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "CLbpuDoWhlW5"
   },
   "source": [
    "## Questions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "jR6_Y-UlhlW5"
   },
   "source": [
    "### Q1. Plot the main eigenvectors (as images) and try to interpret them."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "NK2nezchhlW6"
   },
   "source": [
    "### Q2. For both PCA and random projections, plot the estimated classification performance as a function of the dimension $d$ in the projected space. Comment."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "ZoIw9hO_hlW6"
   },
   "source": [
    "### You are given the same time budget required for the prediction of $n_{test}=5000$ examples with the $k$-nearest neighbors computed on $n=10000$ examples above. You must still use the same classifier, but you may use more examples in the training set and use dimensionality reduction. \n",
    "\n",
    "### Q3. Can you improve the prediction performance?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "CfYHph4ThlW7"
   },
   "source": [
    "### Q4. Try to use some non-Gaussian law for the random projection. When do you observe similar results, when not?"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "correction_mnist_dimred.ipynb",
   "provenance": []
  },
  "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}
