diff --git a/第五章k近邻算法.ipynb b/第五章k近邻算法.ipynb new file mode 100644 index 0000000..4c9db50 --- /dev/null +++ b/第五章k近邻算法.ipynb @@ -0,0 +1,212 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "5893b1c0-fa37-40b0-bf86-5e542987634e", + "metadata": {}, + "source": [ + "# 1 获取数据" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "e5e89d3b-2384-4bbf-9197-2dbbca120838", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([0, 1, 2, ..., 8, 9, 8])" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.datasets import load_digits\n", + "digits = load_digits() # 加载数据\n", + "data = digits[\"data\"] # 属性列\n", + "target = digits[\"target\"] # 标签列\n", + "target" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "950a6379-974e-4e74-82b2-f58a8606682a", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "id": "8fac6553-56ad-4096-834a-55bd9f6cdab5", + "metadata": {}, + "source": [ + "# 2 划分数据集" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "86506fed-8cb6-4e54-88f4-a70150297947", + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "x_train,x_test,y_train,y_test=train_test_split(data, target, test_size=0.2, random_state=123)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3dd4bc37-cf06-41f2-a16b-b4851e497c8d", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "id": "e021dded-b3cb-4c04-bab2-e18f5374c037", + "metadata": {}, + "source": [ + "# 3 模型构建" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "525e6d7e-0140-4443-818f-71ce37baee79", + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.neighbors import KNeighborsClassifier\n", + "model= KNeighborsClassifier(n_neighbors=5).fit(x_train,y_train) # 模型构建\n", + "y_pred=model.predict(x_test) #预测\n" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "5766e641-8f3f-4a80-83d7-3edb3fa4a2b0", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([3, 3, 4, 4, 1, 3, 1, 0, 7, 4, 0, 0, 5, 1, 6, 0, 3, 1, 0, 6, 9, 7,\n", + " 7, 5, 4, 5, 7, 0, 0, 9, 1, 6, 8, 6, 1, 4, 6, 2, 1, 6, 0, 6, 2, 0,\n", + " 2, 3, 9, 8, 8, 1, 2, 8, 6, 5, 1, 6, 4, 6, 0, 4, 3, 5, 6, 2, 2, 8,\n", + " 8, 2, 0, 1, 7, 9, 4, 7, 3, 9, 4, 3, 3, 8, 3, 5, 4, 6, 1, 2, 4, 2,\n", + " 4, 5, 8, 4, 1, 7, 6, 7, 5, 5, 6, 3, 9, 4, 6, 6, 8, 1, 7, 5, 6, 4,\n", + " 9, 8, 7, 0, 9, 0, 2, 9, 0, 5, 1, 4, 4, 2, 2, 0, 7, 3, 6, 8, 2, 5,\n", + " 2, 3, 3, 9, 6, 7, 4, 0, 7, 3, 2, 2, 2, 3, 8, 1, 7, 1, 5, 7, 9, 1,\n", + " 3, 2, 6, 0, 7, 9, 6, 0, 2, 6, 3, 1, 5, 5, 9, 6, 1, 8, 6, 1, 3, 4,\n", + " 4, 2, 0, 5, 9, 0, 7, 0, 7, 5, 8, 4, 8, 8, 3, 7, 9, 8, 2, 0, 3, 4,\n", + " 9, 4, 1, 8, 7, 0, 5, 4, 5, 2, 2, 1, 4, 2, 0, 8, 7, 3, 2, 9, 2, 3,\n", + " 8, 0, 6, 0, 2, 8, 7, 5, 4, 8, 0, 1, 5, 5, 0, 9, 8, 7, 7, 1, 4, 2,\n", + " 4, 7, 1, 3, 0, 8, 2, 8, 6, 6, 3, 5, 6, 4, 5, 4, 6, 5, 7, 7, 9, 9,\n", + " 1, 0, 4, 6, 1, 7, 3, 9, 8, 1, 0, 4, 5, 6, 8, 2, 5, 8, 4, 0, 8, 3,\n", + " 1, 6, 6, 4, 6, 1, 4, 6, 6, 4, 1, 5, 3, 0, 1, 6, 0, 2, 5, 5, 8, 8,\n", + " 2, 6, 0, 1, 1, 5, 1, 6, 9, 2, 8, 2, 4, 9, 8, 3, 3, 3, 2, 4, 0, 9,\n", + " 4, 3, 6, 0, 2, 1, 3, 3, 2, 5, 9, 0, 7, 5, 9, 7, 6, 4, 7, 9, 6, 7,\n", + " 4, 1, 5, 9, 6, 5, 5, 0])" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "y_pred" + ] + }, + { + "cell_type": "markdown", + "id": "6469074a-0502-43ae-a076-16d3f744ce22", + "metadata": {}, + "source": [ + "# 4 模型评价" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "efd03e71-1992-4a5a-871f-2d544230a17d", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Confusion Matrix:\n", + "[[39 0 0 0 0 0 0 0 0 0]\n", + " [ 0 34 0 0 0 0 0 0 0 0]\n", + " [ 0 0 36 0 0 0 0 0 0 0]\n", + " [ 0 0 0 33 0 0 0 0 0 0]\n", + " [ 0 0 0 0 41 0 0 1 0 0]\n", + " [ 0 0 0 0 0 36 0 0 0 1]\n", + " [ 0 0 0 0 0 0 43 0 0 0]\n", + " [ 0 0 0 0 0 0 0 31 0 0]\n", + " [ 0 3 1 0 0 0 0 0 33 0]\n", + " [ 0 0 0 1 0 0 0 0 0 27]]\n", + "k邻近模型预测的正确率为： 0.9805555555555555\n" + ] + } + ], + "source": [ + "from sklearn.metrics import confusion_matrix, accuracy_score \n", + " \n", + "\n", + "# 计算混淆矩阵 \n", + "cm = confusion_matrix(y_test, y_pred)\n", + "print(\"Confusion Matrix:\")\n", + "print(cm)\n", + "\n", + "\n", + "print(\"k邻近模型预测的正确率为：\",accuracy_score(y_test,y_pred))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "37b7d2de-80da-4c41-99af-0aae3cc5d4ce", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "3609a180-6bc6-4b76-8269-7d620d45c2ce", + "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": "3.13.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}