{ "cells": [ { "cell_type": "code", "execution_count": 24, "id": "f503b4b3", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "training data points: 1212\n", "validation data points: 135\n", "testing data points: 450\n" ] }, { "data": { "text/plain": [ "KNeighborsClassifier(n_neighbors=3)" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn import neighbors, datasets\n", "from sklearn.model_selection import train_test_split\n", "import numpy as np\n", "mnist = datasets.load_digits()\n", "\n", "# take the MNIST data and construct the training and testing split, using 75% of the\n", "# data for training and 25% for testing\n", "(trainData, testData, trainLabels, testLabels) = train_test_split(np.array(mnist.data),\n", "mnist.target, test_size=0.25, random_state=42)\n", "\n", "# now, let's take 10% of the training data and use that for validation\n", "(trainData, valData, trainLabels, valLabels) = train_test_split(trainData, trainLabels,\n", "test_size=0.1, random_state=84)\n", "\n", "# show the sizes of each data split\n", "print(\"training data points: {}\".format(len(trainLabels)))\n", "print(\"validation data points: {}\".format(len(valLabels)))\n", "print(\"testing data points: {}\".format(len(testLabels)))\n", "model = neighbors.KNeighborsClassifier(n_neighbors=3)\n", "model.fit(trainData, trainLabels)\n" ] }, { "cell_type": "code", "execution_count": 25, "id": "871813e9", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([6, 9, 3, 7, 2, 1, 5, 2, 5, 2, 1, 9, 4, 0, 4, 2, 3, 7, 8, 8, 4, 3,\n", " 9, 7, 5, 6, 3, 5, 6, 3, 4, 9, 1, 4, 4, 6, 9, 4, 7, 6, 6, 9, 1, 3,\n", " 6, 1, 3, 0, 6, 5, 5, 1, 3, 5, 6, 0, 9, 0, 0, 1, 0, 4, 5, 2, 4, 5,\n", " 7, 0, 7, 5, 9, 5, 5, 4, 7, 0, 4, 5, 5, 9, 9, 0, 2, 3, 8, 0, 6, 4,\n", " 4, 9, 1, 2, 8, 3, 5, 2, 9, 0, 4, 4, 4, 3, 5, 3, 1, 3, 5, 9, 4, 2,\n", " 7, 7, 4, 4, 1, 9, 2, 7, 8, 7, 2, 6, 9, 4, 0, 7, 2, 7, 5, 8, 7, 5,\n", " 7, 9, 0, 6, 6, 4, 2, 8, 0, 9, 4, 6, 8, 9, 6, 9, 0, 3, 5, 6, 6, 0,\n", " 6, 4, 3, 9, 3, 4, 7, 2, 9, 0, 4, 5, 3, 6, 5, 9, 9, 8, 4, 2, 1, 3,\n", " 7, 7, 2, 2, 3, 9, 8, 0, 3, 2, 2, 5, 6, 9, 9, 4, 1, 5, 4, 2, 3, 6,\n", " 4, 8, 5, 9, 5, 7, 1, 9, 4, 8, 1, 5, 4, 4, 9, 6, 1, 8, 6, 0, 4, 5,\n", " 2, 7, 4, 6, 4, 5, 6, 0, 3, 2, 3, 6, 7, 1, 5, 1, 4, 7, 6, 8, 8, 5,\n", " 5, 1, 6, 2, 8, 8, 9, 5, 7, 6, 2, 2, 2, 3, 4, 8, 8, 3, 6, 0, 9, 7,\n", " 7, 0, 1, 0, 4, 5, 1, 5, 3, 6, 0, 4, 1, 0, 0, 3, 6, 5, 9, 7, 3, 5,\n", " 5, 9, 9, 8, 5, 3, 3, 2, 0, 5, 8, 3, 4, 0, 2, 4, 6, 4, 3, 4, 5, 0,\n", " 5, 2, 1, 3, 1, 4, 1, 1, 7, 0, 1, 5, 2, 1, 2, 8, 7, 0, 6, 4, 8, 8,\n", " 5, 1, 8, 4, 5, 8, 7, 9, 8, 5, 0, 6, 2, 0, 7, 9, 8, 9, 5, 2, 7, 7,\n", " 1, 8, 7, 4, 3, 8, 3, 5, 6, 0, 0, 3, 0, 5, 0, 0, 4, 1, 2, 8, 4, 5,\n", " 9, 6, 3, 1, 8, 8, 4, 2, 3, 8, 9, 8, 8, 5, 0, 6, 3, 3, 7, 1, 6, 4,\n", " 1, 2, 1, 1, 6, 4, 7, 4, 8, 3, 4, 0, 5, 1, 9, 4, 5, 7, 6, 3, 7, 0,\n", " 5, 9, 7, 5, 9, 7, 4, 2, 1, 9, 0, 7, 5, 3, 3, 6, 3, 9, 6, 9, 5, 0,\n", " 1, 5, 5, 8, 3, 3, 6, 2, 6, 5])" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_pred2=model.predict(testData)\n", "y_pred2" ] }, { "cell_type": "code", "execution_count": 26, "id": "e492c2d2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([6, 9, 3, 7, 2, 1, 5, 2, 5, 2, 1, 9, 4, 0, 4, 2, 3, 7, 8, 8, 4, 3,\n", " 9, 7, 5, 6, 3, 5, 6, 3, 4, 9, 1, 4, 4, 6, 9, 4, 7, 6, 6, 9, 1, 3,\n", " 6, 1, 3, 0, 6, 5, 5, 1, 9, 5, 6, 0, 9, 0, 0, 1, 0, 4, 5, 2, 4, 5,\n", " 7, 0, 7, 5, 9, 5, 5, 4, 7, 0, 4, 5, 5, 9, 9, 0, 2, 3, 8, 0, 6, 4,\n", " 4, 9, 1, 2, 8, 3, 5, 2, 9, 0, 4, 4, 4, 3, 5, 3, 1, 3, 5, 9, 4, 2,\n", " 7, 7, 4, 4, 1, 9, 2, 7, 8, 7, 2, 6, 9, 4, 0, 7, 2, 7, 5, 8, 7, 5,\n", " 7, 7, 0, 6, 6, 4, 2, 8, 0, 9, 4, 6, 9, 9, 6, 9, 0, 3, 5, 6, 6, 0,\n", " 6, 4, 3, 9, 3, 9, 7, 2, 9, 0, 4, 5, 3, 6, 5, 9, 9, 8, 4, 2, 1, 3,\n", " 7, 7, 2, 2, 3, 9, 8, 0, 3, 2, 2, 5, 6, 9, 9, 4, 1, 5, 4, 2, 3, 6,\n", " 4, 8, 5, 9, 5, 7, 8, 9, 4, 8, 1, 5, 4, 4, 9, 6, 1, 8, 6, 0, 4, 5,\n", " 2, 7, 4, 6, 4, 5, 6, 0, 3, 2, 3, 6, 7, 1, 5, 1, 4, 7, 6, 8, 8, 5,\n", " 5, 1, 6, 2, 8, 8, 9, 9, 7, 6, 2, 2, 2, 3, 4, 8, 8, 3, 6, 0, 9, 7,\n", " 7, 0, 1, 0, 4, 5, 1, 5, 3, 6, 0, 4, 1, 0, 0, 3, 6, 5, 9, 7, 3, 5,\n", " 5, 9, 9, 8, 5, 3, 3, 2, 0, 5, 8, 3, 4, 0, 2, 4, 6, 4, 3, 4, 5, 0,\n", " 5, 2, 1, 3, 1, 4, 1, 1, 7, 0, 1, 5, 2, 1, 2, 8, 7, 0, 6, 4, 8, 8,\n", " 5, 1, 8, 4, 5, 8, 7, 9, 8, 5, 0, 6, 2, 0, 7, 9, 8, 9, 5, 2, 7, 7,\n", " 1, 8, 7, 4, 3, 8, 3, 5, 6, 0, 0, 3, 0, 5, 0, 0, 4, 1, 2, 8, 4, 5,\n", " 9, 6, 3, 1, 8, 8, 4, 2, 3, 8, 9, 8, 8, 5, 0, 6, 3, 3, 7, 1, 6, 4,\n", " 1, 2, 1, 1, 6, 4, 7, 4, 8, 3, 4, 0, 5, 1, 9, 4, 5, 7, 6, 3, 7, 0,\n", " 5, 9, 7, 5, 9, 7, 4, 2, 1, 9, 0, 7, 5, 3, 3, 6, 3, 9, 6, 9, 5, 0,\n", " 1, 5, 5, 8, 3, 3, 6, 2, 6, 5])" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "testLabels" ] }, { "cell_type": "code", "execution_count": 27, "id": "eaf265c9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[43 0 0 0 0 0 0 0 0 0]\n", " [ 0 37 0 0 0 0 0 0 0 0]\n", " [ 0 0 38 0 0 0 0 0 0 0]\n", " [ 0 0 0 46 0 0 0 0 0 0]\n", " [ 0 0 0 0 55 0 0 0 0 0]\n", " [ 0 0 0 0 0 59 0 0 0 0]\n", " [ 0 0 0 0 0 0 45 0 0 0]\n", " [ 0 0 0 0 0 0 0 40 0 1]\n", " [ 0 1 0 0 0 0 0 0 37 0]\n", " [ 0 0 0 1 1 1 0 0 1 44]]\n", " precision recall f1-score support\n", "\n", " 0 1.000 1.000 1.000 43\n", " 1 0.974 1.000 0.987 37\n", " 2 1.000 1.000 1.000 38\n", " 3 0.979 1.000 0.989 46\n", " 4 0.982 1.000 0.991 55\n", " 5 0.983 1.000 0.992 59\n", " 6 1.000 1.000 1.000 45\n", " 7 1.000 0.976 0.988 41\n", " 8 0.974 0.974 0.974 38\n", " 9 0.978 0.917 0.946 48\n", "\n", " accuracy 0.987 450\n", " macro avg 0.987 0.987 0.987 450\n", "weighted avg 0.987 0.987 0.987 450\n", "\n" ] } ], "source": [ "from sklearn import metrics\n", "print(metrics.confusion_matrix(testLabels, y_pred2))\n", "\n", "# Print the precision and recall, among other metrics\n", "print(metrics.classification_report(testLabels, y_pred2, digits=3))" ] }, { "cell_type": "code", "execution_count": null, "id": "2daca0f3", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "e515ab2a", "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": "3.9.7" } }, "nbformat": 4, "nbformat_minor": 5 }