Set up airbnb pipelines

airbnb_pipelines.py

from sklearn.pipeline import Pipeline
 
#instantiate transformer classes
cat_onehot_transformer = cat_onehot_transformer_custom(cat_list)
url_onehot_transformer = url_onehot_transformer_custom(url_list)
 
convert_dates_transformer = convert_dates_transformer_custom(date_list)
to_float_transformer = to_float_transformer_custom(tofloat_list)
fillna_transformer = fillna_transformer_custom(fillna_list)
cap_reviews_per_month = cap_reviews_per_month_custom()
 
drop_features = drop_features_selector(drop_list)
 
#set up pipelines
cat_preprocessing_pipe = Pipeline(steps = [
   ('cat_onehot_transformer', cat_onehot_transformer),
   ('url_onehot_transformer', url_onehot_transformer)
])
 
num_preprocessing_pipe = Pipeline(steps = [
   ('convert_dates_transformer',convert_dates_transformer),
   ('to_float_transformer',to_float_transformer),
   ('fillna_transformer',fillna_transformer),
   ('cap_reviews_per_month', cap_reviews_per_month)
])
 
# combine both numerical and categorical preprocessing step
combined_preprocessing = Pipeline([
   ('drop_features', drop_features),
   ('numericals', num_preprocessing_pipe),
   ('categoricals', cat_preprocessing_pipe)
])