def fit_transform(self, features: Features) -> Features:
df = features.as_pandas(copy=False)
cat_columns = [
features.names[i] for i, tf in enumerate(features.types)
if tf == FeatureType.CATEGORIAL
]
for name in cat_columns:
values = set(df[name].tolist())
logging.debug("Got values %s for feature %s: ", values, name)
self.feature_values[name] = list(values)
return self._transform_df(df, features)
def transform(self, features: Features) -> Features:
indexes_to_keep = []
remove_indexes = []
for i, name in enumerate(features.names):
if name in self.features:
indexes_to_keep.append(i)
else:
remove_indexes.append(i)
filtered_data = features.as_pandas()
filtered_data.drop(columns=filtered_data.columns[remove_indexes],
inplace=True)
indexes_to_keep = set(indexes_to_keep)
filtered_types = [
f_type for i, f_type in enumerate(features.types)
if i in indexes_to_keep
]
filtered_features = Features.from_pandas(df=filtered_data,
types=filtered_types)
return filtered_features
def transform(self, features: Features) -> Features:
df = features.as_pandas(copy=False)
return self._transform_df(df, features)