diff --git a/learning.ipynb b/learning.ipynb index 55e80bb14..87236282d 100644 --- a/learning.ipynb +++ b/learning.ipynb @@ -36,10 +36,7 @@ "* Decision Tree Learner\n", "* Naive Bayes Learner\n", "* Perceptron\n", - "* Learner Evaluation\n", - "* MNIST Handwritten Digits\n", - " * Loading and Visualising\n", - " * Testing" + "* Learner Evaluation" ] }, { @@ -1372,7 +1369,9 @@ { "cell_type": "code", "execution_count": null, - "metadata": {}, + "metadata": { + "collapsed": true + }, "outputs": [], "source": [ "psource(NaiveBayesSimple)" @@ -1743,489 +1742,6 @@ "source": [ "The Perceptron didn't fare very well mainly because the dataset is not linearly separated. On simpler datasets the algorithm performs much better, but unfortunately such datasets are rare in real life scenarios." ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## MNIST HANDWRITTEN DIGITS CLASSIFICATION\n", - "\n", - "The MNIST database, available from [this page](http://yann.lecun.com/exdb/mnist/), is a large database of handwritten digits that is commonly used for training and testing/validating in Machine learning.\n", - "\n", - "The dataset has **60,000 training images** each of size 28x28 pixels with labels and **10,000 testing images** of size 28x28 pixels with labels.\n", - "\n", - "In this section, we will use this database to compare performances of different learning algorithms.\n", - "\n", - "It is estimated that humans have an error rate of about **0.2%** on this problem. Let's see how our algorithms perform!\n", - "\n", - "NOTE: We will be using external libraries to load and visualize the dataset smoothly ([numpy](http://www.numpy.org/) for loading and [matplotlib](http://matplotlib.org/) for visualization). You do not need previous experience of the libraries to follow along." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Loading MNIST digits data\n", - "\n", - "Let's start by loading MNIST data into numpy arrays." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "The function `load_MNIST()` loads MNIST data from files saved in `aima-data/MNIST`. It returns four numpy arrays that we are going to use to train and classify hand-written digits in various learning approaches." - ] - }, - { - "cell_type": "code", - "execution_count": 46, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "train_img, train_lbl, test_img, test_lbl = load_MNIST()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Check the shape of these NumPy arrays to make sure we have loaded the database correctly.\n", - "\n", - "Each 28x28 pixel image is flattened to a 784x1 array and we should have 60,000 of them in training data. Similarly, we should have 10,000 of those 784x1 arrays in testing data." - ] - }, - { - "cell_type": "code", - "execution_count": 47, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Training images size: (60000, 784)\n", - "Training labels size: (60000,)\n", - "Testing images size: (10000, 784)\n", - "Training labels size: (10000,)\n" - ] - } - ], - "source": [ - "print(\"Training images size:\", train_img.shape)\n", - "print(\"Training labels size:\", train_lbl.shape)\n", - "print(\"Testing images size:\", test_img.shape)\n", - "print(\"Training labels size:\", test_lbl.shape)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Visualizing MNIST digits data\n", - "\n", - "To get a better understanding of the dataset, let's visualize some random images for each class from training and testing datasets." - ] - }, - { - "cell_type": "code", - "execution_count": 48, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAAKoCAYAAABUXzFLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# takes 5-10 seconds to execute this\n", - "show_MNIST(train_lbl, train_img)" - ] - }, - { - "cell_type": "code", - "execution_count": 49, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAAKoCAYAAABUXzFLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nVIPXAAAAAElFTkSuQmCC\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# takes 5-10 seconds to execute this\n", - "show_MNIST(test_lbl, test_img)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Let's have a look at the average of all the images of training and testing data." - ] - }, - { - "cell_type": "code", - "execution_count": 50, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Average of all images in training dataset.\n", - "Digit 0 : 5923 images.\n", - "Digit 1 : 6742 images.\n", - "Digit 2 : 5958 images.\n", - "Digit 3 : 6131 images.\n", - "Digit 4 : 5842 images.\n", - "Digit 5 : 5421 images.\n", - "Digit 6 : 5918 images.\n", - "Digit 7 : 6265 images.\n", - "Digit 8 : 5851 images.\n", - "Digit 9 : 5949 images.\n" - ] - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAACBCAYAAADjY3ScAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njDHGGGOMMaXi/wF5m/0aE3+CBgAAAABJRU5ErkJggg==\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Average of all images in testing dataset.\n", - "Digit 0 : 980 images.\n", - "Digit 1 : 1135 images.\n", - "Digit 2 : 1032 images.\n", - "Digit 3 : 1010 images.\n", - "Digit 4 : 982 images.\n", - "Digit 5 : 892 images.\n", - "Digit 6 : 958 images.\n", - "Digit 7 : 1028 images.\n", - "Digit 8 : 974 images.\n", - "Digit 9 : 1009 images.\n" - ] - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAACBCAYAAADjY3ScAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nJA/kAAAAAElFTkSuQmCC\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "print(\"Average of all images in training dataset.\")\n", - "show_ave_MNIST(train_lbl, train_img)\n", - "\n", - "print(\"Average of all images in testing dataset.\")\n", - "show_ave_MNIST(test_lbl, test_img)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Testing\n", - "\n", - "Now, let us convert this raw data into `DataSet.examples` to run our algorithms defined in `learning.py`. Every image is represented by 784 numbers (28x28 pixels) and we append them with its label or class to make them work with our implementations in learning module." - ] - }, - { - "cell_type": "code", - "execution_count": 51, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "(60000, 784) (60000,)\n", - "(60000, 785)\n" - ] - } - ], - "source": [ - "print(train_img.shape, train_lbl.shape)\n", - "temp_train_lbl = train_lbl.reshape((60000,1))\n", - "training_examples = np.hstack((train_img, temp_train_lbl))\n", - "print(training_examples.shape)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Now, we will initialize a DataSet with our training examples, so we can use it in our algorithms." - ] - }, - { - "cell_type": "code", - "execution_count": 52, - "metadata": { - "collapsed": true - }, - "outputs": [], - "source": [ - "# takes ~10 seconds to execute this\n", - "MNIST_DataSet = DataSet(examples=training_examples, distance=manhattan_distance)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Moving forward we can use `MNIST_DataSet` to test our algorithms." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Plurality Learner\n", - "\n", - "The Plurality Learner always returns the class with the most training samples. In this case, `1`." - ] - }, - { - "cell_type": "code", - "execution_count": 53, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "1\n" - ] - } - ], - "source": [ - "pL = PluralityLearner(MNIST_DataSet)\n", - "print(pL(177))" - ] - }, - { - "cell_type": "code", - "execution_count": 54, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Actual class of test image: 8\n" - ] - }, - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 54, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nivADSRF+ICnCDyT1/zuzOYWa4hAXAAAAAElFTkSuQmCC\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "%matplotlib inline\n", - "\n", - "print(\"Actual class of test image:\", test_lbl[177])\n", - "plt.imshow(test_img[177].reshape((28,28)))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "It is obvious that this Learner is not very efficient. In fact, it will guess correctly in only 1135/10000 of the samples, roughly 10%. It is very fast though, so it might have its use as a quick first guess." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Naive-Bayes\n", - "\n", - "The Naive-Bayes classifier is an improvement over the Plurality Learner. It is much more accurate, but a lot slower." - ] - }, - { - "cell_type": "code", - "execution_count": 55, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "7\n" - ] - } - ], - "source": [ - "# takes ~45 Secs. to execute this\n", - "\n", - "nBD = NaiveBayesLearner(MNIST_DataSet, continuous=False)\n", - "print(nBD(test_img[0]))" - ] - }, - { - "cell_type": "code", - "execution_count": 56, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Actual class of test image: 7\n" - ] - }, - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 56, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "%matplotlib inline\n", - "\n", - "print(\"Actual class of test image:\", test_lbl[0])\n", - "plt.imshow(test_img[0].reshape((28,28)))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### k-Nearest Neighbors\n", - "\n", - "We will now try to classify a random image from the dataset using the kNN classifier." - ] - }, - { - "cell_type": "code", - "execution_count": 57, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "5\n" - ] - } - ], - "source": [ - "# takes ~20 Secs. to execute this\n", - "kNN = NearestNeighborLearner(MNIST_DataSet, k=3)\n", - "print(kNN(test_img[211]))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "To make sure that the output we got is correct, let's plot that image along with its label." - ] - }, - { - "cell_type": "code", - "execution_count": 58, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Actual class of test image: 5\n" - ] - }, - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 58, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nCD8QFOEHgiL8QFCEHwiK8ANBEX4gqP8B1flLsMvfVy4AAAAASUVORK5CYII=\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "%matplotlib inline\n", - "\n", - "print(\"Actual class of test image:\", test_lbl[211])\n", - "plt.imshow(test_img[211].reshape((28,28)))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Hurray! We've got it correct. Don't worry if our algorithm predicted a wrong class. With this techinique we have only ~97% accuracy on this dataset." - ] } ], "metadata": { diff --git a/learning_apps.ipynb b/learning_apps.ipynb new file mode 100644 index 000000000..8d46732e1 --- /dev/null +++ b/learning_apps.ipynb @@ -0,0 +1,495 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# LEARNING APPLICATIONS\n", + "\n", + "In this notebook we will take a look at some indicative applications of machine learning techniques. We will cover content from [`learning.py`](https://github.com/aimacode/aima-python/blob/master/learning.py), for chapter 18 from Stuart Russel's and Peter Norvig's book [*Artificial Intelligence: A Modern Approach*](http://aima.cs.berkeley.edu/). Execute the cell below to get started:" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "from learning import *\n", + "from notebook import *" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## CONTENTS\n", + "\n", + "* MNIST Handwritten Digits\n", + " * Loading and Visualising\n", + " * Testing" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## MNIST HANDWRITTEN DIGITS CLASSIFICATION\n", + "\n", + "The MNIST database, available from [this page](http://yann.lecun.com/exdb/mnist/), is a large database of handwritten digits that is commonly used for training and testing/validating in Machine learning.\n", + "\n", + "The dataset has **60,000 training images** each of size 28x28 pixels with labels and **10,000 testing images** of size 28x28 pixels with labels.\n", + "\n", + "In this section, we will use this database to compare performances of different learning algorithms.\n", + "\n", + "It is estimated that humans have an error rate of about **0.2%** on this problem. Let's see how our algorithms perform!\n", + "\n", + "NOTE: We will be using external libraries to load and visualize the dataset smoothly ([numpy](http://www.numpy.org/) for loading and [matplotlib](http://matplotlib.org/) for visualization). You do not need previous experience of the libraries to follow along." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Loading MNIST Digits Data\n", + "\n", + "Let's start by loading MNIST data into numpy arrays.\n", + "\n", + "The function `load_MNIST()` loads MNIST data from files saved in `aima-data/MNIST`. It returns four numpy arrays that we are going to use to train and classify hand-written digits in various learning approaches." + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "train_img, train_lbl, test_img, test_lbl = load_MNIST()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Check the shape of these NumPy arrays to make sure we have loaded the database correctly.\n", + "\n", + "Each 28x28 pixel image is flattened to a 784x1 array and we should have 60,000 of them in training data. Similarly, we should have 10,000 of those 784x1 arrays in testing data." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Training images size: (60000, 784)\n", + "Training labels size: (60000,)\n", + "Testing images size: (10000, 784)\n", + "Training labels size: (10000,)\n" + ] + } + ], + "source": [ + "print(\"Training images size:\", train_img.shape)\n", + "print(\"Training labels size:\", train_lbl.shape)\n", + "print(\"Testing images size:\", test_img.shape)\n", + "print(\"Training labels size:\", test_lbl.shape)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Visualizing Data\n", + "\n", + "To get a better understanding of the dataset, let's visualize some random images for each class from training and testing datasets." + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAAKqCAYAAAAZl5BAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# takes 5-10 seconds to execute this\n", + "show_MNIST(train_lbl, train_img)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAAKqCAYAAAAZl5BAAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/wGjgMWJk2e4ogAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# takes 5-10 seconds to execute this\n", + "show_MNIST(test_lbl, test_img)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Let's have a look at the average of all the images of training and testing data." + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average of all images in training dataset.\n", + "Digit 0 : 5923 images.\n", + "Digit 1 : 6742 images.\n", + "Digit 2 : 5958 images.\n", + "Digit 3 : 6131 images.\n", + "Digit 4 : 5842 images.\n", + "Digit 5 : 5421 images.\n", + "Digit 6 : 5918 images.\n", + "Digit 7 : 6265 images.\n", + "Digit 8 : 5851 images.\n", + "Digit 9 : 5949 images.\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAACDCAYAAACuq9WXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average of all images in testing dataset.\n", + "Digit 0 : 980 images.\n", + "Digit 1 : 1135 images.\n", + "Digit 2 : 1032 images.\n", + "Digit 3 : 1010 images.\n", + "Digit 4 : 982 images.\n", + "Digit 5 : 892 images.\n", + "Digit 6 : 958 images.\n", + "Digit 7 : 1028 images.\n", + "Digit 8 : 974 images.\n", + "Digit 9 : 1009 images.\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzkAAACDCAYAAACuq9WXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxxhjjDHGGFMq/h+V5nVldnlnJQAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "print(\"Average of all images in training dataset.\")\n", + "show_ave_MNIST(train_lbl, train_img)\n", + "\n", + "print(\"Average of all images in testing dataset.\")\n", + "show_ave_MNIST(test_lbl, test_img)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Testing\n", + "\n", + "Now, let us convert this raw data into `DataSet.examples` to run our algorithms defined in `learning.py`. Every image is represented by 784 numbers (28x28 pixels) and we append them with its label or class to make them work with our implementations in learning module." + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(60000, 784) (60000,)\n", + "(60000, 785)\n" + ] + } + ], + "source": [ + "print(train_img.shape, train_lbl.shape)\n", + "temp_train_lbl = train_lbl.reshape((60000,1))\n", + "training_examples = np.hstack((train_img, temp_train_lbl))\n", + "print(training_examples.shape)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now, we will initialize a DataSet with our training examples, so we can use it in our algorithms." + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [ + "# takes ~10 seconds to execute this\n", + "MNIST_DataSet = DataSet(examples=training_examples, distance=manhattan_distance)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Moving forward we can use `MNIST_DataSet` to test our algorithms." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Plurality Learner\n", + "\n", + "The Plurality Learner always returns the class with the most training samples. In this case, `1`." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1\n" + ] + } + ], + "source": [ + "pL = PluralityLearner(MNIST_DataSet)\n", + "print(pL(177))" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Actual class of test image: 8\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nwg8E9X/46I56sOIdFgAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "%matplotlib inline\n", + "\n", + "print(\"Actual class of test image:\", test_lbl[177])\n", + "plt.imshow(test_img[177].reshape((28,28)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "It is obvious that this Learner is not very efficient. In fact, it will guess correctly in only 1135/10000 of the samples, roughly 10%. It is very fast though, so it might have its use as a quick first guess." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Naive-Bayes\n", + "\n", + "The Naive-Bayes classifier is an improvement over the Plurality Learner. It is much more accurate, but a lot slower." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "7\n" + ] + } + ], + "source": [ + "# takes ~45 Secs. to execute this\n", + "\n", + "nBD = NaiveBayesLearner(MNIST_DataSet, continuous=False)\n", + "print(nBD(test_img[0]))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### k-Nearest Neighbors\n", + "\n", + "We will now try to classify a random image from the dataset using the kNN classifier." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "5\n" + ] + } + ], + "source": [ + "# takes ~20 Secs. to execute this\n", + "kNN = NearestNeighborLearner(MNIST_DataSet, k=3)\n", + "print(kNN(test_img[211]))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To make sure that the output we got is correct, let's plot that image along with its label." + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Actual class of test image: 5\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAP8AAAD8CAYAAAC4nHJkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "%matplotlib inline\n", + "\n", + "print(\"Actual class of test image:\", test_lbl[211])\n", + "plt.imshow(test_img[211].reshape((28,28)))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Hurray! We've got it correct. Don't worry if our algorithm predicted a wrong class. With this techinique we have only ~97% accuracy on this dataset." + ] + } + ], + "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": "3.5.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}