extract features function

extract_features.py

def ExtractFeatures(df):
  # adds is_red, is_white, is_rose, is_rose
  # is_sparkling, is_dry, is_sweet
  for key, value in desc_extracting_dict.items():
    interim_df = extract_features_from_description(df, "description", key, value)

  # adds year
  interim_df["title_numlist"] = (interim_df
                                 .title
                                 .str
                                 .findall(r'\b\d+\b'))

  interim_df["year"] = (interim_df
                        .title_numlist
                        .apply(extract_year_from_title))

  # adds is_blend
  interim_df["is_blend"] = (interim_df
                            .variety
                            .apply(extract_blend_from_variety))
  # drops unused features
  features_added_df = (interim_df
                       .drop(columns=["description",
                                      "title",
                                      "title_numlist"]))
  return features_added_df