K-近邻算法

 

# coding=utf-8
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler,MinMaxScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split

def knc():
    # 水仙花数据
    # li.data 即为数据的特征值，是二维的
    # li.target 即为数据的目标值
    li = load_iris()

    # 准备数据
    x_train,x_test,y_train,y_test = train_test_split(li.data,li.target,test_size=0.25)

    # 标准化
    ss = StandardScaler()
    x_train = ss.fit_transform(x_train)
    # 需要用训练集的标准来标准化测试集
    x_test = ss.transform(x_test)

    print(x_train[:10])

    # 预测
    knn = KNeighborsClassifier(n_neighbors=4)

    knn.fit(x_train,y_train)

    print("预测的值为:",knn.predict(x_test))
    print("实际的值为:",y_test)
    print("预测的准确率为:",knn.score(x_test,y_test))

    return None

if __name__ == '__main__':
    knc()