1.KNN
查找距离已知的几个点最近的类型，并返回这个类型进行预测。
如小明在北京，小红在北京，小刚在河南，而我距离小明和小红比小刚近，则我最可能在北京而不是河南
#!/usr/bin/env python # -*- coding: utf-8 -*- # @File : KNN近邻算法.py # @Author: 赵路仓 # @Date : 2020/4/2 # @Desc : 学习网站：https://www.bilibili.com/video/BV1nt411r7tj?p=21 # @Contact : 398333404@qq.com from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.preprocessing import StandardScaler from sklearn.neighbors import KNeighborsClassifier import numpy as np def knn_iris(): """ 用KNN算法对鸢尾花进行分类 :return: """ # 1.获取数据 iris = load_iris() print(iris) # 2.划分数据集 x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6) # 3.特征工程：标准化 transfer = StandardScaler() x_train = transfer.fit_transform(x_train) x_test = transfer.transform(x_test) # 4.KNN算法预估器 estimator = KNeighborsClassifier(n_neighbors=6) estimator.fit(x_train, y_train) # 5.模型评估 # 方法一：直接对比真实数据和预测值 y_predit = estimator.predict(x_test) print("y_predit:\n", y_predit) print("对比真实值和预测值:\n", y_test == y_predit) # 方法2：计算准确率 score = estimator.score(x_test, y_test) print("准确率为：\n", score) # 预测新的鸾尾花品种 x_new = np.array([[5, 2.9, 1, 0.2]]) prediction = estimator.predict(x_new) print(prediction) return None def knn_iris_gscv(): """ 用KNN算法对鸢尾花进行分类,添加网格搜索与交叉验证 :return: """ # 1.获取数据 iris = load_iris() print(iris) # 2.划分数据集 x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6) # 3.特征工程：标准化 transfer = StandardScaler() x_train = transfer.fit_transform(x_train) x_test = transfer.transform(x_test) # 4.KNN算法预估器 estimator = KNeighborsClassifier(n_neighbors=5) # 加入网格搜索与交叉验证 # 参数准备 从下侧中取n_neighbors param_dict = { "n_neighbors": [1, 3, 5, 7, 9, 11] } estimator = GridSearchCV(estimator, param_grid=param_dict, cv=10) estimator.fit(x_train, y_train) # 5.模型评估 # 方法一：直接对比真实数据和预测值 y_predit = estimator.predict(x_test) print("y_predit:\n", y_predit) print("对比真实值和预测值:\n", y_test == y_predit) # 方法2：计算准确率 score = estimator.score(x_test, y_test) print("准确率为：\n", score) """ 最佳参数：best_params_ 最佳结果：best_score_ 最佳估计器：best_estimator_ 交叉验证结果：cv_results_ """ print("最佳参数:\n", estimator.best_params_) print("最佳结果:\n", estimator.best_score_) print("最佳估计器:\n", estimator.best_estimator_) print("交叉验证结果:\n", estimator.cv_results_) # 预测新的鸾尾花品种 x_new = np.array([[5, 2.9, 1, 0.2]]) prediction = estimator.predict(x_new) print(prediction) return None if __name__ == "__main__": # 代码1：KNN对鸾尾花分类 # knn_iris() # 代码2：KNN预测鸾尾花分类并添加网格搜索和交叉验证 knn_iris_gscv()