{ "cells": [ { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "from sklearn.datasets import load_iris\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.model_selection import GridSearchCV" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# 1.获取数据 load_iris\n", "\n", "# 2.数据基本处理 数据集划分\n", "\n", "# 3.特征工程 标准化\n", "\n", "# 4.机器学习 \n", "# 4.1 建立模型\n", "# 4.2 训练模型\n", "\n", "# 5.模型评估 准确率" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "# 1.获取数据 load_iris\n", "iris = load_iris()\n", "\n", "# 2.数据基本处理 数据集划分\n", "x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2)\n", "\n", "# 3.特征工程 标准化\n", "# 3.1 实例化转换器\n", "transfer = StandardScaler()\n", "# 3.2 转换数据\n", "# transfer.fit(x_train)\n", "# x_train = transfer.transform(x_train)\n", "x_train = transfer.fit_transform(x_train)\n", "x_test = transfer.transform(x_test)\n", "\n", "# 4.机器学习 \n", "# 4.1 建立模型 实例化 估计器\n", "estimator = KNeighborsClassifier(n_neighbors=5, algorithm='kd_tree')\n", "\n", "# 4.2 训练模型\n", "estimator.fit(x_train, y_train)\n", "\n", "# 5.模型评估 准确率\n", "estimator.score(x_test, y_test)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 交叉验证和网格搜索" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.9666666666666667" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 1.获取数据 load_iris\n", "iris = load_iris()\n", "\n", "# 2.数据基本处理 数据集划分\n", "x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2)\n", "\n", "# 3.特征工程 标准化\n", "# 3.1 实例化转换器\n", "transfer = StandardScaler()\n", "# 3.2 转换数据\n", "# transfer.fit(x_train)\n", "# x_train = transfer.transform(x_train)\n", "x_train = transfer.fit_transform(x_train)\n", "x_test = transfer.transform(x_test)\n", "\n", "# 4.机器学习 \n", "# 4.1 建立模型 实例化 估计器\n", "# estimator = KNeighborsClassifier(n_neighbors=5, algorithm='kd_tree')\n", "estimator = KNeighborsClassifier(algorithm='kd_tree')\n", "\n", "# 交叉验证和网格搜索\n", "# 构建参数字典\n", "param_dict = {'n_neighbors':[1,3,5]}\n", "estimator_gscv = GridSearchCV(estimator, param_grid=param_dict, cv=2)\n", "\n", "# 4.2 训练模型\n", "# estimator.fit(x_train, y_train)\n", "estimator_gscv.fit(x_train, y_train)\n", "\n", "# 5.模型评估 准确率\n", "# estimator.score(x_test, y_test)\n", "estimator_gscv.score(x_test, y_test) # 最优模型的准确率" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "KNeighborsClassifier(algorithm='kd_tree', leaf_size=30, metric='minkowski',\n", " metric_params=None, n_jobs=None, n_neighbors=3, p=2,\n", " weights='uniform')" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 获取最优模型\n", "estimator_gscv.best_estimator_" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'n_neighbors': 3}" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 获取最优超参数\n", "estimator_gscv.best_params_" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/anaconda3/lib/python3.7/site-packages/sklearn/utils/deprecation.py:125: FutureWarning: You are accessing a training score ('split0_train_score'), which will not be available by default any more in 0.21. If you need training scores, please set return_train_score=True\n", " warnings.warn(*warn_args, **warn_kwargs)\n", "/anaconda3/lib/python3.7/site-packages/sklearn/utils/deprecation.py:125: FutureWarning: You are accessing a training score ('split1_train_score'), which will not be available by default any more in 0.21. If you need training scores, please set return_train_score=True\n", " warnings.warn(*warn_args, **warn_kwargs)\n", "/anaconda3/lib/python3.7/site-packages/sklearn/utils/deprecation.py:125: FutureWarning: You are accessing a training score ('mean_train_score'), which will not be available by default any more in 0.21. If you need training scores, please set return_train_score=True\n", " warnings.warn(*warn_args, **warn_kwargs)\n", "/anaconda3/lib/python3.7/site-packages/sklearn/utils/deprecation.py:125: FutureWarning: You are accessing a training score ('std_train_score'), which will not be available by default any more in 0.21. If you need training scores, please set return_train_score=True\n", " warnings.warn(*warn_args, **warn_kwargs)\n" ] }, { "data": { "text/plain": [ "{'mean_fit_time': array([0.0013026 , 0.00094354, 0.00073647]),\n", " 'std_fit_time': array([1.53779984e-05, 1.41501427e-04, 2.74658203e-04]),\n", " 'mean_score_time': array([0.00449395, 0.00462461, 0.00385988]),\n", " 'std_score_time': array([0.00016093, 0.0013926 , 0.00149882]),\n", " 'param_n_neighbors': masked_array(data=[1, 3, 5],\n", " mask=[False, False, False],\n", " fill_value='?',\n", " dtype=object),\n", " 'params': [{'n_neighbors': 1}, {'n_neighbors': 3}, {'n_neighbors': 5}],\n", " 'split0_test_score': array([0.93333333, 0.96666667, 0.91666667]),\n", " 'split1_test_score': array([0.91666667, 0.93333333, 0.95 ]),\n", " 'mean_test_score': array([0.925 , 0.95 , 0.93333333]),\n", " 'std_test_score': array([0.00833333, 0.01666667, 0.01666667]),\n", " 'rank_test_score': array([3, 1, 2], dtype=int32),\n", " 'split0_train_score': array([1. , 0.91666667, 0.95 ]),\n", " 'split1_train_score': array([1. , 0.95 , 0.98333333]),\n", " 'mean_train_score': array([1. , 0.93333333, 0.96666667]),\n", " 'std_train_score': array([0. , 0.01666667, 0.01666667])}" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 获取cv结果\n", "estimator_gscv.cv_results_" ] }, { "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": "3.7.3" } }, "nbformat": 4, "nbformat_minor": 2 }