tfv.py

# Always start with these features. They work (almost) everytime!
tfv = TfidfVectorizer(dtype=np.float32, min_df=3,  max_features=None, 
            strip_accents='unicode', analyzer='word',token_pattern=r'\w{1,}',
            ngram_range=(1, 3), use_idf=1,smooth_idf=1,sublinear_tf=1,
            stop_words = 'english')

# Fitting TF-IDF to both training and test sets (semi-supervised learning)
tfv.fit(list(train_df.cleaned_text.values) + list(test_df.cleaned_text.values))
xtrain_tfv =  tfv.transform(train_df.cleaned_text.values) 
xvalid_tfv = tfv.transform(test_df.cleaned_text.values)