1、数据处理

（1）原始数据

y_train=['male','male','male','male','famale','famale','famale','famale','famale']

[out]:

(2)LableBinarizer()的fit_transform()方法---将数据标签二值化

from sklearn.preprocessing import LabelBinarizer

lb=LabelBinarizer()
y_train_binarizer = lb.fit_transform(y_train)

[out]

(3)reshape(-1)------转数据转化为一行以用于实现K近邻算法

clf=KNeighborsClassifier(n_neighbors=K)
clf.fit(X_train,y_train_binarizer.reshape(-1))

[out]

(4)LableBinarizer()的inverse_transform()方法---将数据标签逆转还原成标签

predicted_label=lb.inverse_transform(prediction_binarized)

（5）KNeighborsClassifier()

KNN函数方法