005savariables.py

# Create the pipeline for the tweets
text = Pipeline([('process_tweets', process_tweets()),
                 ('vct', TfidfVectorizer(ngram_range=(1,2)))])

# Create the pipeline for the other variables and add selection to choose features
dummies = Pipeline([('dummies_transformation', dummies_transformation(columns=['weekday', 'calendar_day', 'hour', 'is_weekend', 'link']))])

# Merge pipelines using FeatureUnion
features = FeatureUnion([('text', text),
                         ('dummies', dummies)])

# Pipeline with the classifier
pipeline = Pipeline([('features',features),
                     ('clf', SVC(random_state=0, kernel='linear'))])