lession 5 KNN分类算法

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import  KNeighborsClassifier

def knn_demo():
    """
    用knn算法对鸢尾花进行分类
    :return:
    """

    # 加载sklearn自带的鸢尾花数据
    iris = load_iris()

    x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6)

    # 对数据进行标准化处理
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    # 测试集用transform，这样里面的参数才会和训练集是一样的,fit_transform是计算参数，并应用到数据中
    x_test = transfer.transform(x_test)

    # knn算法训练
    estimator = KNeighborsClassifier(n_neighbors=3)
    estimator.fit(x_train,y_train)

    # 计算一个预测值
    y_predict = estimator.predict(x_test)
    print("y_predict:" , y_predict)
    print("对比预测值和测试值", y_predict == y_test)

    # 用测试集计算评估的准确率
    scroe = estimator.score(x_test, y_test)
    print("准确率为：", scroe)
    return None


if __name__ == "__main__":
    knn_demo()

 对knn进行交叉验证和网络搜索，查找最优参数

def knn_gridsearch_demo():
    """
    用knn算法对鸢尾花进行分类，加入网格搜索和交叉验证
    :return:
    """

    # 加载sklearn自带的鸢尾花数据
    iris = load_iris()

    x_train, x_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=6)

    # 对数据进行标准化处理
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.fit_transform(x_test)

    # knn算法训练
    estimator = KNeighborsClassifier()

    # 加入网格搜索和交叉验证
    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)

    # 计算一个预测值
    y_predict = estimator.predict(x_test)
    print("y_predict:" , y_predict)
    print("对比预测值和测试值", y_predict == y_test)

    # 用测试集计算评估的准确率
    scroe = estimator.score(x_test, y_test)
    print("准确率为：", scroe)

    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_)
    return None