From 6b14d88a2050aa313524176b45209fd86e18f108 Mon Sep 17 00:00:00 2001 From: rohitr45 <62831615+rohitr45@users.noreply.github.com> Date: Wed, 22 Apr 2020 10:57:41 +0530 Subject: [PATCH] Week 4 Assignment --- IntroToNeuralNetworks.ipynb | 666 ++++++++++++++++++++++++++++++++++++ 1 file changed, 666 insertions(+) create mode 100644 IntroToNeuralNetworks.ipynb diff --git a/IntroToNeuralNetworks.ipynb b/IntroToNeuralNetworks.ipynb new file mode 100644 index 000000000..7b861aa55 --- /dev/null +++ b/IntroToNeuralNetworks.ipynb @@ -0,0 +1,666 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 132, + "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\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", + "# library written for this exercise providing additional functions for assignment submission, and others\n", + "import utils\n", + "\n", + "# define the submission/grader object for this exercise\n", + "grader = utils.Grader()\n", + "\n", + "# tells matplotlib to embed plots within the notebook\n", + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 133, + "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('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": 134, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "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", + "utils.displayData(sel)" + ] + }, + { + "cell_type": "code", + "execution_count": 135, + "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": 136, + "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", + " Instructions\n", + " ------------\n", + " Compute the cost of a particular choice of theta. You should set J to the cost.\n", + " Compute the partial derivatives and set grad to the partial\n", + " derivatives of the cost w.r.t. each parameter in theta\n", + " \n", + " Hint 1\n", + " ------\n", + " The computation of the cost function and gradients can be efficiently\n", + " vectorized. For example, consider the computation\n", + " \n", + " sigmoid(X * theta)\n", + " \n", + " Each row of the resulting matrix will contain the value of the prediction\n", + " for that example. You can make use of this to vectorize the cost function\n", + " and gradient computations. \n", + " \n", + " Hint 2\n", + " ------\n", + " When computing the gradient of the regularized cost function, there are\n", + " many possible vectorized solutions, but one solution looks like:\n", + " \n", + " grad = (unregularized gradient for logistic regression)\n", + " temp = theta \n", + " temp[0] = 0 # because we don't add anything for j = 0\n", + " grad = grad + YOUR_CODE_HERE (using the temp variable)\n", + " \n", + " Hint 3\n", + " ------\n", + " We have provided the implementatation of the sigmoid function within \n", + " the file `utils.py`. At the start of the notebook, we imported this file\n", + " as a module. Thus to access the sigmoid function within that file, you can\n", + " do the following: `utils.sigmoid(z)`.\n", + " \n", + " \"\"\"\n", + " #Initialize some useful values\n", + " m = y.size\n", + " \n", + " # convert labels to ints if their type is bool\n", + " if y.dtype == bool:\n", + " y = y.astype(int)\n", + " \n", + " # You need to return the following variables correctly\n", + " J = 0\n", + " grad = np.zeros(theta.shape)\n", + " \n", + " # ====================== YOUR CODE HERE ======================\n", + " \n", + " z = np.array(theta.dot(X.transpose())) \n", + " H = np.array(utils.sigmoid(z))\n", + " \n", + " J += ((-1 / m) * ((np.log(H)).dot(y.transpose()) + (np.log(1 - H)).dot((1 - y).transpose())))\n", + " J += (lambda_ / (2 * m)) * (theta[1:]).dot(theta[1:].transpose())\n", + " \n", + " grad = (1 / m) * (H - y).dot(X) \n", + " grad[1:] += ((lambda_ / m) * theta[1:])\n", + " \n", + " # =============================================================\n", + " return J, grad" + ] + }, + { + "cell_type": "code", + "execution_count": 137, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Cost : 2.534819\n", + "Expected cost: 2.534819\n", + "-----------------------\n", + "Gradients:\n", + " [0.146561, -0.548558, 0.724722, 1.398003]\n", + "Expected 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('Expected cost: 2.534819')\n", + "print('-----------------------')\n", + "print('Gradients:')\n", + "print(' [{:.6f}, {:.6f}, {:.6f}, {:.6f}]'.format(*grad))\n", + "print('Expected gradients:')\n", + "print(' [0.146561, -0.548558, 0.724722, 1.398003]');" + ] + }, + { + "cell_type": "code", + "execution_count": 138, + "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", + " Instructions\n", + " ------------\n", + " You should complete the following code to train `num_labels`\n", + " logistic regression classifiers with regularization parameter `lambda_`. \n", + " \n", + " Hint\n", + " ----\n", + " You can use y == c to obtain a vector of 1's and 0's that tell you\n", + " whether the ground truth is true/false for this class.\n", + " \n", + " Note\n", + " ----\n", + " For this assignment, we recommend using `scipy.optimize.minimize(method='CG')`\n", + " to optimize the cost function. It is okay to use a for-loop \n", + " (`for c in range(num_labels):`) to loop over the different classes.\n", + " \n", + " Example Code\n", + " ------------\n", + " \n", + " # Set Initial theta\n", + " initial_theta = np.zeros(n + 1)\n", + " \n", + " # Set options for minimize\n", + " options = {'maxiter': 50}\n", + " \n", + " # Run minimize to obtain the optimal theta. This function will \n", + " # return a class object where theta is in `res.x` and cost in `res.fun`\n", + " res = optimize.minimize(lrCostFunction, \n", + " initial_theta, \n", + " (X, (y == c), lambda_), \n", + " jac=True, \n", + " method='TNC',\n", + " options=options) \n", + " \"\"\"\n", + " # Some useful variables\n", + " m, n = X.shape\n", + " \n", + " # You need to return the following variables correctly \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", + " # ====================== YOUR CODE HERE ======================\n", + " \n", + " for i 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 == i), lambda_), \n", + " jac=True, \n", + " method='TNC',\n", + " options=options) \n", + " all_theta[i,:] = res.x\n", + "\n", + " # ============================================================\n", + " return all_theta" + ] + }, + { + "cell_type": "code", + "execution_count": 139, + "metadata": {}, + "outputs": [], + "source": [ + "lambda_ = 0.1\n", + "all_theta = oneVsAll(X, y, num_labels, lambda_)" + ] + }, + { + "cell_type": "code", + "execution_count": 140, + "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", + " Instructions\n", + " ------------\n", + " Complete the following code to make predictions using your learned logistic\n", + " regression parameters (one-vs-all). You should set p to a vector of predictions\n", + " (from 0 to num_labels-1).\n", + " \n", + " Hint\n", + " ----\n", + " This code can be done all vectorized using the numpy argmax function.\n", + " In particular, the argmax function returns the index of the max element,\n", + " for more information see '?np.argmax' or search online. If your examples\n", + " are in rows, then, you can use np.argmax(A, axis=1) to obtain the index \n", + " of the max for each row.\n", + " \"\"\"\n", + " m = X.shape[0];\n", + " num_labels = all_theta.shape[0]\n", + "\n", + " # You need to return the following variables correctly \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", + " # ====================== YOUR CODE HERE ======================\n", + " \n", + " for i in range(m):\n", + " p[i] = np.argmax(all_theta.dot(X.transpose())[:, i])\n", + "\n", + " # ============================================================\n", + " return p" + ] + }, + { + "cell_type": "code", + "execution_count": 141, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Training Set Accuracy: 95.20%\n" + ] + } + ], + "source": [ + "pred = predictOneVsAll(all_theta, X)\n", + "print('Training Set Accuracy: {:.2f}%'.format(np.mean(pred == y) * 100))" + ] + }, + { + "cell_type": "code", + "execution_count": 142, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "# training data stored in arrays X, y\n", + "data = loadmat('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", + "utils.displayData(sel)" + ] + }, + { + "cell_type": "code", + "execution_count": 143, + "metadata": {}, + "outputs": [], + "source": [ + "# Setup the parameters you 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('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": "code", + "execution_count": 144, + "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", + " Instructions\n", + " ------------\n", + " Complete the following code to make predictions using your learned neural\n", + " network. You should set p to a vector containing labels \n", + " between 0 to (num_labels-1).\n", + " \n", + " Hint\n", + " ----\n", + " This code can be done all vectorized using the numpy argmax function.\n", + " In particular, the argmax function returns the index of the max element,\n", + " for more information see '?np.argmax' or search online. If your examples\n", + " are in rows, then, you can use np.argmax(A, axis=1) to obtain the index\n", + " of the max for each row.\n", + " \n", + " Note\n", + " ----\n", + " Remember, we have supplied the `sigmoid` function in the `utils.py` file. \n", + " You can use this function by calling `utils.sigmoid(z)`, where you can \n", + " replace `z` by the required input variable to sigmoid.\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", + " # You need to return the following variables correctly \n", + " p = np.zeros(X.shape[0])\n", + "\n", + " # ====================== YOUR CODE HERE ======================\n", + " \n", + " X = np.concatenate([np.ones((m, 1)), X], axis=1)\n", + " \n", + " A2 = utils.sigmoid((Theta1.dot(X.transpose())).transpose())\n", + " A2 = np.concatenate([np.ones((A2.shape[0], 1)), A2], axis=1)\n", + " \n", + " H = utils.sigmoid(Theta2.dot(A2.transpose()))\n", + " \n", + " for i in range(m):\n", + " p[i] = np.argmax(H[:, i])\n", + " \n", + " # =============================================================\n", + " return p" + ] + }, + { + "cell_type": "code", + "execution_count": 145, + "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": 160, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Neural Network Prediction: 8.0\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "if indices.size > 0:\n", + " i, indices = indices[0], indices[1:]\n", + " utils.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": 151, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Submitting Solutions | Programming Exercise multi-class-classification-and-neural-networks\n", + "\n", + "Use token from last successful submission (rohitramesh4547@gmail.com)? (Y/n): Y\n", + " Part Name | Score | Feedback\n", + " --------- | ----- | --------\n", + " Regularized Logistic Regression | 30 / 30 | Nice work!\n", + " One-vs-All Classifier Training | 20 / 20 | Nice work!\n", + " One-vs-All Classifier Prediction | 20 / 20 | Nice work!\n", + " Neural Network Prediction Function | 30 / 30 | Nice work!\n", + " --------------------------------\n", + " | 100 / 100 | \n", + "\n" + ] + } + ], + "source": [ + "grader[1] = lrCostFunction\n", + "grader.grade()" + ] + } + ], + "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": "3.7.6" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}