如何分割数据?

假设我的数据帧中有1010行。现在我想用 train_test_split 所以前1000行是训练数据,接下来10行是测试数据。

# Natural Language Processing
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
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)
# Cleaning the texts
import re
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
corpus = []
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 CountVectorizer
cv=CountVectorizer(max_features=1500)
#X=cv.fit_transform(corpus).toarray()
X=corpus
y=res.iloc[:,1].values

# Splitting the dataset into the Training set and Test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.01, random_state = 0)