maybe better

run.py

@@ -12,18 +12,19 @@ Y_train = []
 stop = 0
 
 with lzma.open('train/train.tsv.xz', 'rt', encoding="utf-8") as f:
-    data = pd.read_csv(f, sep='\t', names=['Begin', 'End', 'Title', 'Publisher', 'Text'])
+    data = pd.read_csv(f, sep='\t', names=['Begin', 'End', 'Text'])
 
 
-data = data[['Text', 'Begin']]
+data = data[['Text', 'End']]
 data = data[0:50000]
 
 X = data['Text']
-y = data['Begin']
+y = data['End']
 
 model = make_pipeline(TfidfVectorizer(), LinearRegression())
 model.fit(X, y)
 
+
 def readFile(filename):
     X_dev = []
     with open(filename, 'r', encoding="utf-8") as dev_in: