手动实现分割

通过按比例取打乱索引的方式，分割训练集和测试集，接口仿照sklearn。

import numpy as npdef train_test_split(X,y,test_ratio=0.2,seed=None):"""按test_size的比例分割训练集测试集"""assert X.shape[0]==y.shape[0],\'the shape of X must equal to y'assert 0.0<=test_ratio<=1.0,'test_size must be valid'if seed is not None:np.random.seed(seed)shuffled_indices=np.random.permutation(len(X))#随机索引test_size=int(len(X)*test_ratio)test_indices=shuffled_indices[:test_size]train_indices=shuffled_indices[test_size:]X_train,y_train=X[train_indices],y[train_indices]X_test,y_test=X[test_indices],y[test_indices]return X_train,X_test,y_train,y_test

使用sklearn中的分割方式进行knn分类

import numpy as np
from sklearn.model_selection import train_test_split
import sklearn.datasets as datasets
from sklearn.neighbors import KNeighborsClassifierif __name__=='__main__':iris_data = datasets.load_iris()X = iris_data.datay = iris_data.targetX_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2)print(X_train.shape)print(y_train.shape)print(X_test.shape)print(y_test.shape)knn=KNeighborsClassifier(n_neighbors=3)knn.fit(X_train,y_train)y_predict=knn.predict(X_test)print(y_predict)print(np.sum(y_predict == y_test))print('accuracy:', np.sum(y_predict == y_test) / len(y_test))