# In[13]:
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer()
bow = cv.fit_transform(train['Message'])
# In[14]:
#converting bow to tfidf
# In[15]:
from sklearn.feature_extraction.text import TfidfTransformer
bow = TfidfTransformer().fit_transform(bow)
bow = bow.toarray()
bow = bow.tolist()
# In[16]:
#concatenating length to bow
# In[62]:
for i in range(5572):
bow[i].append(train['Length'].iloc[i])
# In[18]:
#splitting train_test
# In[65]:
