假设我的数据框中有1010行数据。现在我想使用 train_test_split 将它们分割，使前1000行数据成为训练数据，接下来的10行数据成为测试数据。

# 自然语言处理# 导入库import numpy as npimport matplotlib.pyplot as pltimport pandas as pd# 导入数据集dataset = pd.read_csv('Restaurant_Reviews.tsv', delimiter = '\t', quoting = 3)newset=pd.read_csv('Test.tsv',delimiter='\t',quoting=3)frames=[dataset,newset]res=pd.concat(frames,ignore_index=True)# 清理文本import reimport nltknltk.download('stopwords')from nltk.corpus import stopwordsfrom nltk.stem.porter import PorterStemmercorpus = []for i in range(0, 1010):    review = re.sub('[^a-zA-Z]', ' ', res['Review'][i])    review = review.lower()    review = review.split()    ps = PorterStemmer()    review = [ps.stem(word) for word in review if not word in set(stopwords.words('english'))]    review = ' '.join(review)    corpus.append(review)from sklearn.feature_extraction.text import CountVectorizercv=CountVectorizer(max_features=1500)#X=cv.fit_transform(corpus).toarray()X=corpusy=res.iloc[:,1].values# 将数据集分割成训练集和测试集from sklearn.cross_validation import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.01, random_state = 0)

回答：

如果你知道需要前1000个样本作为训练数据，最后10个样本作为测试数据，最好手动进行分割，因为 train_test_split 是随机分割的。

X_train = X[:1000]X_test = X[1000:]y_train = y[:1000]y_test = y[1000:]