cross_validation.train_test_split

from sklearn import cross_validation
import os

root='F:\\SCI_1\\code\\split_data\\high_clef.txt'
img_name=[]
img_label=[]
with open(root,"r") as f:
    lines = f.readlines()
    for line in lines:
        items = line.split(' ')
        img_name.append(items[0])
        img_label.append(int(items[1]))

X_train, X_test, y_train, y_test = cross_validation.train_test_split(img_name, img_label, test_size=0.3, random_state=0)

label_high_clef_train='F:\\SCI_1\\code\\split_data\\high_clef_train.txt'
doc_label_high_clef_train = open(label_high_clef_train, 'a')

label_high_clef_test='F:\\SCI_1\\code\\split_data\\high_clef_test.txt'
doc_doc_label_high_clef_test = open(label_high_clef_train, 'a')

for i in len(X_train)
    labe_str_train=X_train[i]+' '+str(y_train[i])
    print >> doc_label_high_clef_train,labe_str_train

for j in len(X_test)
    labe_str_test=X_test[j]+' '+str(y_test[j])
    print >> doc_doc_label_high_clef_test,labe_str_test