# -*- coding: utf-8 -*-
"""
    將數(shù)據(jù)按比例切分
"""
from sklearn import model_selection
c = []
j = 0
#filename = r'E:\NER\CCKS2020\Data\ccks2020_2_task1_train\task1_train.txt'
filename = open(r'task1_train.txt','r',encoding='utf-8')
out_train = open(r'train.txt', 'w',encoding='utf-8')
out_test = open(r'temp.txt', 'w',encoding='utf-8')
for line in filename:
    #    items = line.strip().split()
    c.append(line)
c_train, c_test = model_selection.train_test_split(c, test_size=0.2)
for i in c_train:
    out_train.write(i)
for i in c_test:
    out_test.write(i)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
功能：數(shù)據(jù)集按比例切分為訓練集和測試集
時間：2017年3月11日 12:48:57
"""
# from sklearn.cross_validation import train_test_split
from sklearn.model_selection import train_test_split  # 更新
# 生成200個句子，前100個和后100個類別分別對應(yīng)1和2
X = [[u"這是", u"第1個", u"測試"]] * 100 + [[u"這是", u"第2個", u"測試"]] * 100
y = [1] * 100 + [2] * 100
# 隨機抽取20%的測試集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
print len(X_train), len(X_test)
# 查看句子和標簽是否仍然對應(yīng)
for i in range(len(X_test)):
    print "".join(X_test[i]), y_test[i]
if __name__ == "__main__":
    pass

from sklearn.model_selection import train_test_split