PYTHON

{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "1. Load the Digits dataset" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "from sklearn.datasets import load_digits" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "digits = load_digits() " ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'data': array([[ 0., 0., 5., ..., 0., 0., 0.],\n", " [ 0., 0., 0., ..., 10., 0., 0.],\n", " [ 0., 0., 0., ..., 16., 9., 0.],\n", " ...,\n", " [ 0., 0., 1., ..., 6., 0., 0.],\n", " [ 0., 0., 2., ..., 12., 0., 0.],\n", " [ 0., 0., 10., ..., 12., 1., 0.]]),\n", " 'target': array([0, 1, 2, ..., 8, 9, 8]),\n", " 'target_names': array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9]),\n", " 'images': array([[[ 0., 0., 5., ..., 1., 0., 0.],\n", " [ 0., 0., 13., ..., 15., 5., 0.],\n", " [ 0., 3., 15., ..., 11., 8., 0.],\n", " ...,\n", " [ 0., 4., 11., ..., 12., 7., 0.],\n", " [ 0., 2., 14., ..., 12., 0., 0.],\n", " [ 0., 0., 6., ..., 0., 0., 0.]],\n", " \n", " [[ 0., 0., 0., ..., 5., 0., 0.],\n", " [ 0., 0., 0., ..., 9., 0., 0.],\n", " [ 0., 0., 3., ..., 6., 0., 0.],\n", " ...,\n", " [ 0., 0., 1., ..., 6., 0., 0.],\n", " [ 0., 0., 1., ..., 6., 0., 0.],\n", " [ 0., 0., 0., ..., 10., 0., 0.]],\n", " \n", " [[ 0., 0., 0., ..., 12., 0., 0.],\n", " [ 0., 0., 3., ..., 14., 0., 0.],\n", " [ 0., 0., 8., ..., 16., 0., 0.],\n", " ...,\n", " [ 0., 9., 16., ..., 0., 0., 0.],\n", " [ 0., 3., 13., ..., 11., 5., 0.],\n", " [ 0., 0., 0., ..., 16., 9., 0.]],\n", " \n", " ...,\n", " \n", " [[ 0., 0., 1., ..., 1., 0., 0.],\n", " [ 0., 0., 13., ..., 2., 1., 0.],\n", " [ 0., 0., 16., ..., 16., 5., 0.],\n", " ...,\n", " [ 0., 0., 16., ..., 15., 0., 0.],\n", " [ 0., 0., 15., ..., 16., 0., 0.],\n", " [ 0., 0., 2., ..., 6., 0., 0.]],\n", " \n", " [[ 0., 0., 2., ..., 0., 0., 0.],\n", " [ 0., 0., 14., ..., 15., 1., 0.],\n", " [ 0., 4., 16., ..., 16., 7., 0.],\n", " ...,\n", " [ 0., 0., 0., ..., 16., 2., 0.],\n", " [ 0., 0., 4., ..., 16., 2., 0.],\n", " [ 0., 0., 5., ..., 12., 0., 0.]],\n", " \n", " [[ 0., 0., 10., ..., 1., 0., 0.],\n", " [ 0., 2., 16., ..., 1., 0., 0.],\n", " [ 0., 0., 15., ..., 15., 0., 0.],\n", " ...,\n", " [ 0., 4., 16., ..., 16., 6., 0.],\n", " [ 0., 8., 16., ..., 16., 8., 0.],\n", " [ 0., 1., 8., ..., 12., 1., 0.]]]),\n", " 'DESCR': \".. _digits_dataset:\\n\\nOptical recognition of handwritten digits dataset\\n--------------------------------------------------\\n\\n**Data Set Characteristics:**\\n\\n :Number of Instances: 5620\\n :Number of Attributes: 64\\n :Attribute Information: 8x8 image of integer pixels in the range 0..16.\\n :Missing Attribute Values: None\\n :Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)\\n :Date: July; 1998\\n\\nThis is a copy of the test set of the UCI ML hand-written digits datasets\\nhttps://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits\\n\\nThe data set contains images of hand-written digits: 10 classes where\\neach class refers to a digit.\\n\\nPreprocessing programs made available by NIST were used to extract\\nnormalized bitmaps of handwritten digits from a preprinted form. From a\\ntotal of 43 people, 30 contributed to the training set and different 13\\nto the test set. 32x32 bitmaps are divided into nonoverlapping blocks of\\n4x4 and the number of on pixels are counted in each block. This generates\\nan input matrix of 8x8 where each element is an integer in the range\\n0..16. This reduces dimensionality and gives invariance to small\\ndistortions.\\n\\nFor info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G.\\nT. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C.\\nL. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469,\\n1994.\\n\\n.. topic:: References\\n\\n - C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their\\n Applications to Handwritten Digit Recognition, MSc Thesis, Institute of\\n Graduate Studies in Science and Engineering, Bogazici University.\\n - E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.\\n - Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.\\n Linear dimensionalityreduction using relevance weighted LDA. School of\\n Electrical and Electronic Engineering Nanyang Technological University.\\n 2005.\\n - Claudio Gentile. A New Approximate Maximal Margin Classification\\n Algorithm. NIPS. 2000.\"}" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "digits" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ ".. _digits_dataset:\n", "\n", "Optical recognition of handwritten digits dataset\n", "--------------------------------------------------\n", "\n", "**Data Set Characteristics:**\n", "\n", " :Number of Instances: 5620\n", " :Number of Attributes: 64\n", " :Attribute Information: 8x8 image of integer pixels in the range 0..16.\n", " :Missing Attribute Values: None\n", " :Creator: E. Alpaydin (alpaydin '@' boun.edu.tr)\n", " :Date: July; 1998\n", "\n", "This is a copy of the test set of the UCI ML hand-written digits datasets\n", "https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits\n", "\n", "The data set contains images of hand-written digits: 10 classes where\n", "each class refers to a digit.\n", "\n", "Preprocessing programs made available by NIST were used to extract\n", "normalized bitmaps of handwritten digits from a preprinted form. From a\n", "total of 43 people, 30 contributed to the training set and different 13\n", "to the test set. 32x32 bitmaps are divided into nonoverlapping blocks of\n", "4x4 and the number of on pixels are counted in each block. This generates\n", "an input matrix of 8x8 where each element is an integer in the range\n", "0..16. This reduces dimensionality and gives invariance to small\n", "distortions.\n", "\n", "For info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G.\n", "T. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C.\n", "L. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469,\n", "1994.\n", "\n", ".. topic:: References\n", "\n", " - C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their\n", " Applications to Handwritten Digit Recognition, MSc Thesis, Institute of\n", " Graduate Studies in Science and Engineering, Bogazici University.\n", " - E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika.\n", " - Ken Tang and Ponnuthurai N. Suganthan and Xi Yao and A. Kai Qin.\n", " Linear dimensionalityreduction using relevance weighted LDA. School of\n", " Electrical and Electronic Engineering Nanyang Technological University.\n", " 2005.\n", " - Claudio Gentile. A New Approximate Maximal Margin Classification\n", " Algorithm. NIPS. 2000.\n" ] } ], "source": [ "print(digits.DESCR)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1797, 64)" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "digits.data.shape" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1797,)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "digits.target.shape" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 4, 1, 7, 4, 8, 2, 2, 4, 4, 1, 9, 7, 3, 2, 1, 2, 5])" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "digits.target[::100] # target values of every 100th sample" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([[ 0., 2., 9., 15., 14., 9., 3., 0.],\n", " [ 0., 4., 13., 8., 9., 16., 8., 0.],\n", " [ 0., 0., 0., 6., 14., 15., 3., 0.],\n", " [ 0., 0., 0., 11., 14., 2., 0., 0.],\n", " [ 0., 0., 0., 2., 15., 11., 0., 0.],\n", " [ 0., 0., 0., 0., 2., 15., 4., 0.],\n", " [ 0., 1., 5., 6., 13., 16., 6., 0.],\n", " [ 0., 2., 12., 12., 13., 11., 0., 0.]])" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "digits.images[13] # show array for sample image at index 13" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([ 0., 2., 9., 15., 14., 9., 3., 0., 0., 4., 13., 8., 9.,\n", " 16., 8., 0., 0., 0., 0., 6., 14., 15., 3., 0., 0., 0.,\n", " 0., 11., 14., 2., 0., 0., 0., 0., 0., 2., 15., 11., 0.,\n", " 0., 0., 0., 0., 0., 2., 15., 4., 0., 0., 1., 5., 6.,\n", " 13., 16., 6., 0., 0., 2., 12., 12., 13., 11., 0., 0.])" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "digits.data[13]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "2. Visualize the data" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "<matplotlib.image.AxesImage at 0x1f7024f9448>" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "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": [ "plt.imshow(digits.images[13])" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "scrolled": false }, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "<Figure size 432x288 with 24 Axes>" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "figure, axes = plt.subplots(nrows=4, ncols=6, figsize=(6, 4))\n", "\n", "for item in zip(axes.ravel(), digits.images, digits.target): \n", " axes, image, target = item \n", " axes.imshow(image, cmap=plt.cm.gray_r)\n", " axes.set_xticks([]) # remove x-axis tick marks\n", " axes.set_yticks([]) # remove y-axis tick marks\n", " axes.set_title(target)\n", "plt.tight_layout() \n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "3. Splitting the data" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(\n", " digits.data, digits.target, random_state=11, test_size=0.20) \n", "# random_state for reproducibility\n" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1437, 64)" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_train.shape" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(360, 64)" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "X_test.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "4. Creating the model" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [], "source": [ "from sklearn.neighbors import KNeighborsClassifier\n", "knn = KNeighborsClassifier() # Create the KNN estimator (model) " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "5. Training the model" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n", " metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n", " weights='uniform')" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "knn.fit(X=X_train, y=y_train)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "6. Predicting" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "scrolled": true }, "outputs": [], "source": [ "predicted = knn.predict(X=X_test)\n", "expected = y_test" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "array([0, 4, 9, 9, 3, 1, 4, 1, 5, 0, 4, 9, 4, 1, 5, 3, 3, 8, 5, 6])" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "predicted[:20]" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([0, 4, 9, 9, 3, 1, 4, 1, 5, 0, 4, 9, 4, 1, 5, 3, 3, 8, 3, 6])" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "expected[:20]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "7. Evaluting the model" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [], "source": [ "wrong = [(p, e) for (p, e) in zip(predicted, expected) if p != e]" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[(5, 3), (8, 9), (4, 9), (7, 3), (7, 4)]" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "wrong" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model accuracy:98.61%\n" ] } ], "source": [ "print(\"Model accuracy:%.2f%%\" %(knn.score(X_test,y_test)*100))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "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": "3.7.6" } }, "nbformat": 4, "nbformat_minor": 4 }