sklearn 机器学习（二）——K-近邻（KNN）算法使用

import numpy as np
from sklearn import neighbors

def create_datasets():
    datasets = np.array([[8,4,2],[7,1,1,],[1,4,4],[3,0,5],[3,0,4],[5,2,1],[5,3,2]]) # 数据集
    labels = [0,0,1,1,0,0,1] #['非常热','非常热','一般热','一般热','一般热']                     # 类标签
    return datasets,labels

def knn_sklearn_predict():
    # 调用机器学习库knn分类器算法
    knn = neighbors.KNeighborsClassifier()
    datasets, labels = create_datasets()
    # 传入参数，特征数据和分类标签
    print(datasets)
    knn.fit(datasets, labels)
    # knn预测
    predictRes = knn.predict([[2, 4, 0]])
    print("天气：\t", "非常热" if predictRes[0] == 0 else '一般热')
    return predictRes

if __name__ == '__main__':
    knn_sklearn_predict()