{ "cells": [ { "cell_type": "code", "execution_count": 8, "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/html": [ "
KNeighborsClassifier(n_neighbors=3)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ "KNeighborsClassifier(n_neighbors=3)" ] }, "execution_count": 8, "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", "mnist[\"DESCR\"]\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", "trainData.dtype\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": 3, "id": "a5c2e3b6", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1212, 64)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "trainData.shape" ] }, { "cell_type": "code", "execution_count": 4, "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": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "y_pred2=model.predict(testData)\n", "y_pred2" ] }, { "cell_type": "code", "execution_count": 5, "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": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "testLabels" ] }, { "cell_type": "code", "execution_count": 6, "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 (ipykernel)", "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": "3.9.16" } }, "nbformat": 4, "nbformat_minor": 5 }