StanfordMLPython/ex3/ex3.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h1>Programming Exercise 3: \n",
    "    Multi-class Classification and Neural Networks"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3> Introduction </h3>\n",
    "In this exercise, we will implement one-vs-all logistic regression and neural networks to recognize hand-written digits. \n",
    "\n",
    "<h4>Files included in this exercise:</h4>\n",
    "- ex3data1.mat\n",
    "- ex3weights.mat\n",
    "- neuralnetwork.png"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>1 Multi-class Classification</h3>\n",
    "Here we will use logistic regression and neural networks to recognize handwritten digits (ranging from 0 to 9). To start we will extend our previous implementation of logistic regression to one-vs-all classification, beginning with a visualization of the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [],
   "source": [
    "# used for manipulating directory paths\n",
    "import os\n",
    "\n",
    "# Scientific and vector computation for python\n",
    "import numpy as np\n",
    "\n",
    "# Plotting library\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "# Optimization module in scipy\n",
    "from scipy import optimize\n",
    "\n",
    "# will be used to load MATLAB mat datafile format\n",
    "from scipy.io import loadmat\n",
    "\n",
    "# tells matplotlib to embed plots within the notebook\n",
    "%matplotlib inline\n",
    "\n",
    "import sys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 20x20 Input Images of Digits\n",
    "input_layer_size  = 400\n",
    "\n",
    "# 10 labels, from 1 to 10 (note that we have mapped \"0\" to label 10)\n",
    "num_labels = 10\n",
    "\n",
    "#  training data stored in arrays X, y\n",
    "data = loadmat(os.path.join('Data', 'ex3data1.mat'))\n",
    "X, y = data['X'], data['y'].ravel()\n",
    "\n",
    "# set the zero digit to 0, rather than its mapped 10 in this dataset\n",
    "# This is an artifact due to the fact that this dataset was used in \n",
    "# MATLAB where there is no index 0\n",
    "y[y == 10] = 0\n",
    "\n",
    "m = y.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "def displayData(X, example_width=None, figsize=(10, 10)):\n",
    "    \"\"\"\n",
    "    Displays 2D data stored in X in a nice grid.\n",
    "    \"\"\"\n",
    "    # Compute rows, cols\n",
    "    if X.ndim == 2:\n",
    "        m, n = X.shape\n",
    "    elif X.ndim == 1:\n",
    "        n = X.size\n",
    "        m = 1\n",
    "        X = X[None]  # Promote to a 2 dimensional array\n",
    "    else:\n",
    "        raise IndexError('Input X should be 1 or 2 dimensional.')\n",
    "\n",
    "    example_width = example_width or int(np.round(np.sqrt(n)))\n",
    "    example_height = n / example_width\n",
    "\n",
    "    # Compute number of items to display\n",
    "    display_rows = int(np.floor(np.sqrt(m)))\n",
    "    display_cols = int(np.ceil(m / display_rows))\n",
    "\n",
    "    fig, ax_array = plt.subplots(display_rows, display_cols, figsize=figsize)\n",
    "    fig.subplots_adjust(wspace=0.025, hspace=0.025)\n",
    "\n",
    "    ax_array = [ax_array] if m == 1 else ax_array.ravel()\n",
    "\n",
    "    for i, ax in enumerate(ax_array):\n",
    "        ax.imshow(X[i].reshape(example_width, example_width, order='F'),\n",
    "                  cmap='Greys', extent=[0, 1, 0, 1])\n",
    "        ax.axis('off')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 100 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Randomly select 100 data points to display\n",
    "rand_indices = np.random.choice(m, 100, replace=False)\n",
    "sel = X[rand_indices, :]\n",
    "\n",
    "displayData(sel)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have an understanding of the data we are working with, we can implement a cost function for linear regression."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "# test values for the parameters theta\n",
    "theta_t = np.array([-2, -1, 1, 2], dtype=float)\n",
    "\n",
    "# test values for the inputs\n",
    "X_t = np.concatenate([np.ones((5, 1)), np.arange(1, 16).reshape(5, 3, order='F')/10.0], axis=1)\n",
    "\n",
    "# test values for the labels\n",
    "y_t = np.array([1, 0, 1, 0, 1])\n",
    "\n",
    "# test value for the regularization parameter\n",
    "lambda_t = 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sigmoid(z):\n",
    "    \"\"\"\n",
    "    Compute sigmoid function given the input z.\n",
    "    \n",
    "    Parameters\n",
    "    ----------\n",
    "    z : array_like\n",
    "        The input to the sigmoid function. This can be a 1-D vector \n",
    "        or a 2-D matrix. \n",
    "    \n",
    "    Returns\n",
    "    -------\n",
    "    g : array_like\n",
    "        The computed sigmoid function. g has the same shape as z, since\n",
    "        the sigmoid is computed element-wise on z.\n",
    "    \"\"\"\n",
    "    # convert input to a numpy array\n",
    "    z = np.array(z)\n",
    "\n",
    "    g = 1 + np.exp(-1*z)\n",
    "    g = np.reciprocal(g)\n",
    "\n",
    "    return g"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "def lrCostFunction(theta, X, y, lambda_):\n",
    "    \"\"\"\n",
    "    Computes the cost of using theta as the parameter for regularized\n",
    "    logistic regression and the gradient of the cost w.r.t. to the parameters.\n",
    "    \n",
    "    Parameters\n",
    "    ----------\n",
    "    theta : array_like\n",
    "        Logistic regression parameters. A vector with shape (n, ). n is \n",
    "        the number of features including any intercept.  \n",
    "    \n",
    "    X : array_like\n",
    "        The data set with shape (m x n). m is the number of examples, and\n",
    "        n is the number of features (including intercept).\n",
    "    \n",
    "    y : array_like\n",
    "        The data labels. A vector with shape (m, ).\n",
    "    \n",
    "    lambda_ : float\n",
    "        The regularization parameter. \n",
    "    \n",
    "    Returns\n",
    "    -------\n",
    "    J : float\n",
    "        The computed value for the regularized cost function. \n",
    "    \n",
    "    grad : array_like\n",
    "        A vector of shape (n, ) which is the gradient of the cost\n",
    "        function with respect to theta, at the current values of theta.\n",
    "    \n",
    "    \"\"\"   \n",
    "    # convert labels to ints if their type is bool\n",
    "    if y.dtype == bool:\n",
    "        y = y.astype(int)\n",
    "    \n",
    "\n",
    "    ## Initialize some useful values\n",
    "    m = y.size\n",
    "    J = 0\n",
    "    grad = np.zeros(theta.shape)\n",
    "    h = sigmoid(X.dot(theta))\n",
    "    logh = np.log(h)\n",
    "    tempLog = np.log(1-h)\n",
    "    yTrans = y.transpose()\n",
    "    Xtrans = X.transpose()\n",
    "    tempTrans = (1-y).transpose()\n",
    "    \n",
    "    J = ((-yTrans).dot(logh))\n",
    "    J = J - tempTrans.dot(tempLog)\n",
    "    J = J * (1/m)\n",
    "    J = J + (lambda_/(2*m))*np.sum(np.square(theta[1:]))\n",
    "    \n",
    "    diff = np.subtract(sigmoid(X.dot(theta)),y)\n",
    "    grad = Xtrans.dot(diff)\n",
    "    grad = grad * (1/m)\n",
    "    grad[1:] = grad[1:] + (lambda_/m)*theta[1:]\n",
    "        \n",
    "    return J, grad"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can run our cost function on some test inputs to be sure it is running correctly. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cost         : 2.534819\n",
      "-----------------------\n",
      "Gradients:\n",
      " [0.146561, -0.548558, 0.724722, 1.398003]\n"
     ]
    }
   ],
   "source": [
    "J, grad = lrCostFunction(theta_t, X_t, y_t, lambda_t)\n",
    "\n",
    "print('Cost         : {:.6f}'.format(J))\n",
    "print('-----------------------')\n",
    "print('Gradients:')\n",
    "print(' [{:.6f}, {:.6f}, {:.6f}, {:.6f}]'.format(*grad))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have a working cost function, we can implement ove-vs all classification by training multiple regularized logistic regression classifiers, one for each our our K classes. Note that this classification will work for any value of K, not just our case where K = 10."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "def oneVsAll(X, y, num_labels, lambda_):\n",
    "    \"\"\"\n",
    "    Trains num_labels logistic regression classifiers and returns\n",
    "    each of these classifiers in a matrix all_theta, where the i-th\n",
    "    row of all_theta corresponds to the classifier for label i.\n",
    "    \n",
    "    Parameters\n",
    "    ----------\n",
    "    X : array_like\n",
    "        The input dataset of shape (m x n). m is the number of \n",
    "        data points, and n is the number of features. Note that we \n",
    "        do not assume that the intercept term (or bias) is in X, however\n",
    "        we provide the code below to add the bias term to X. \n",
    "    \n",
    "    y : array_like\n",
    "        The data labels. A vector of shape (m, ).\n",
    "    \n",
    "    num_labels : int\n",
    "        Number of possible labels.\n",
    "    \n",
    "    lambda_ : float\n",
    "        The logistic regularization parameter.\n",
    "    \n",
    "    Returns\n",
    "    -------\n",
    "    all_theta : array_like\n",
    "        The trained parameters for logistic regression for each class.\n",
    "        This is a matrix of shape (K x n+1) where K is number of classes\n",
    "        (ie. `numlabels`) and n is number of features without the bias.\n",
    "    \"\"\"\n",
    "    # Some useful variables\n",
    "    m, n = X.shape\n",
    "    all_theta = np.zeros((num_labels, n + 1))\n",
    "\n",
    "    # Add ones to the X data matrix\n",
    "    X = np.concatenate([np.ones((m, 1)), X], axis=1)\n",
    "   \n",
    "    for c in range(num_labels):\n",
    "        initial_theta = np.zeros(n+1)\n",
    "        options = {'maxiter': 50}\n",
    "        res = optimize.minimize(lrCostFunction, \n",
    "                                initial_theta, \n",
    "                                (X, (y == c), lambda_), \n",
    "                                jac=True, \n",
    "                                method='TNC',\n",
    "                                options=options) \n",
    "        all_theta[c,:] = res.x\n",
    "\n",
    "    return all_theta"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Run oneVsAll optimization with lambda = 0.1 to get a prediction for theta\n",
    "lambda_ = 0.1\n",
    "all_theta = oneVsAll(X, y, num_labels, lambda_)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have a working oneVsAll classification, we can use the resulting theta to predict what an input should be classified as."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predictOneVsAll(all_theta, X):\n",
    "    \"\"\"\n",
    "    Return a vector of predictions for each example in the matrix X. \n",
    "    Note that X contains the examples in rows. all_theta is a matrix where\n",
    "    the i-th row is a trained logistic regression theta vector for the \n",
    "    i-th class. You should set p to a vector of values from 0..K-1 \n",
    "    (e.g., p = [0, 2, 0, 1] predicts classes 0, 2, 0, 1 for 4 examples) .\n",
    "    \n",
    "    Parameters\n",
    "    ----------\n",
    "    all_theta : array_like\n",
    "        The trained parameters for logistic regression for each class.\n",
    "        This is a matrix of shape (K x n+1) where K is number of classes\n",
    "        and n is number of features without the bias.\n",
    "    \n",
    "    X : array_like\n",
    "        Data points to predict their labels. This is a matrix of shape \n",
    "        (m x n) where m is number of data points to predict, and n is number \n",
    "        of features without the bias term. Note we add the bias term for X in \n",
    "        this function. \n",
    "    \n",
    "    Returns\n",
    "    -------\n",
    "    p : array_like\n",
    "        The predictions for each data point in X. This is a vector of shape (m, ).\n",
    "    \"\"\"\n",
    "    m = X.shape[0];\n",
    "    num_labels = all_theta.shape[0]\n",
    "    p = np.zeros(m)\n",
    "\n",
    "    # Add ones to the X data matrix\n",
    "    X = np.concatenate([np.ones((m, 1)), X], axis=1)\n",
    "\n",
    "    all_theta_T = all_theta.transpose()\n",
    "    temp = sigmoid(X.dot(all_theta_T))\n",
    "    for i in range(m):\n",
    "        iTempMax = np.argmax(temp[i,:])\n",
    "        p[i] = iTempMax\n",
    "\n",
    "    return p"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Set Accuracy: 95.14%\n"
     ]
    }
   ],
   "source": [
    "pred = predictOneVsAll(all_theta, X)\n",
    "print('Training Set Accuracy: {:.2f}%'.format(np.mean(pred == y) * 100))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>2 Neural Networks</h3>\n",
    "\n",
    "We have now implemented multi-class logistic regression to recognize handwritten digits. However, because this is only a linear classifier, logistic regression cannot form more complex hypotheses. \n",
    "    In this portion of the exercise, we will implement a neural network to recognize handwritten digits using the same training set as before. The neural network will be able to represent more complex models to from non-linear hypotheses. In this exercise we will implement parameters from a neural network that has already been trained. Our goal is to implement the feedforward propagation algorithm to use our weights for prediction.\n",
    "    Our neural network is shown in the following figure. it has 3 layers and takes as input our pixel values of digital images. This gives us 400 input layer units (plus our extra bias unit outputting +1). Our network parameters are stored in ex3weights.mat. We begin by loading them into Theta1 and Theta2.\n",
    "    ![Neural network](Figures/neuralnetwork.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 100 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#  training data stored in arrays X, y\n",
    "data = loadmat(os.path.join('Data', 'ex3data1.mat'))\n",
    "X, y = data['X'], data['y'].ravel()\n",
    "\n",
    "# set the zero digit to 0, rather than its mapped 10 in this dataset\n",
    "# This is an artifact due to the fact that this dataset was used in \n",
    "# MATLAB where there is no index 0\n",
    "y[y == 10] = 0\n",
    "\n",
    "# get number of examples in dataset\n",
    "m = y.size\n",
    "\n",
    "# randomly permute examples, to be used for visualizing one \n",
    "# picture at a time\n",
    "indices = np.random.permutation(m)\n",
    "\n",
    "# Randomly select 100 data points to display\n",
    "rand_indices = np.random.choice(m, 100, replace=False)\n",
    "sel = X[rand_indices, :]\n",
    "\n",
    "displayData(sel)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Setup the parameters we will use for this exercise\n",
    "input_layer_size  = 400  # 20x20 Input Images of Digits\n",
    "hidden_layer_size = 25   # 25 hidden units\n",
    "num_labels = 10          # 10 labels, from 0 to 9\n",
    "\n",
    "# Load the .mat file, which returns a dictionary \n",
    "weights = loadmat(os.path.join('Data', 'ex3weights.mat'))\n",
    "\n",
    "# get the model weights from the dictionary\n",
    "# Theta1 has size 25 x 401\n",
    "# Theta2 has size 10 x 26\n",
    "Theta1, Theta2 = weights['Theta1'], weights['Theta2']\n",
    "\n",
    "# swap first and last columns of Theta2, due to legacy from MATLAB indexing, \n",
    "# since the weight file ex3weights.mat was saved based on MATLAB indexing\n",
    "Theta2 = np.roll(Theta2, 1, axis=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will now implement in predict() the feedforward computation which computes predictions for each training sample."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict(Theta1, Theta2, X):\n",
    "    \"\"\"\n",
    "    Predict the label of an input given a trained neural network.\n",
    "    \n",
    "    Parameters\n",
    "    ----------\n",
    "    Theta1 : array_like\n",
    "        Weights for the first layer in the neural network.\n",
    "        It has shape (2nd hidden layer size x input size)\n",
    "    \n",
    "    Theta2: array_like\n",
    "        Weights for the second layer in the neural network. \n",
    "        It has shape (output layer size x 2nd hidden layer size)\n",
    "    \n",
    "    X : array_like\n",
    "        The image inputs having shape (number of examples x image dimensions).\n",
    "    \n",
    "    Return \n",
    "    ------\n",
    "    p : array_like\n",
    "        Predictions vector containing the predicted label for each example.\n",
    "        It has a length equal to the number of examples.\n",
    "    \"\"\"\n",
    "    # Make sure the input has two dimensions\n",
    "    if X.ndim == 1:\n",
    "        X = X[None]  # promote to 2-dimensions\n",
    "    \n",
    "    # useful variables\n",
    "    m = X.shape[0]\n",
    "    num_labels = Theta2.shape[0]\n",
    "    \n",
    "    X = np.concatenate([np.ones((m, 1)), X], axis=1) # Add collumn of ones to X\n",
    "    z2 = Theta1.dot(X.transpose())\n",
    "    z2 = z2.transpose()\n",
    "    a2 = sigmoid(z2)\n",
    "    a2 = np.concatenate([np.ones((a2.shape[0], 1)), a2], axis=1) # Add collumn of ones to a2\n",
    "    z3 = Theta2.dot(a2.transpose())\n",
    "    a3 = sigmoid(z3)\n",
    "    a3 = a3.transpose()\n",
    "    p = np.argmax(a3, axis=1)\n",
    "\n",
    "    return p"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Set Accuracy: 97.5%\n"
     ]
    }
   ],
   "source": [
    "pred = predict(Theta1, Theta2, X)\n",
    "print('Training Set Accuracy: {:.1f}%'.format(np.mean(pred == y) * 100))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Neural Network Prediction: 0\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 288x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "if indices.size > 0:\n",
    "    i, indices = indices[0], indices[1:]\n",
    "    displayData(X[i, :], figsize=(4, 4))\n",
    "    pred = predict(Theta1, Theta2, X[i, :])\n",
    "    print('Neural Network Prediction: {}'.format(*pred))\n",
    "else:\n",
    "    print('No more images to display!')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}