def drop_na(data: Dataset) -> Dataset:
data = data.copy()
tmp_concat = pd.concat([data.X, pd.DataFrame(data.y, columns=["_TARGET_"])], axis=1)
tmp_concat.dropna(inplace=True)
tmp_concat.reset_index(drop=True, inplace=True)
data.X = tmp_concat.drop(columns=["_TARGET_"]).copy()
data.y = tmp_concat["_TARGET_"].copy().to_numpy().ravel()
return data
def concat(data: Dataset) -> pd.DataFrame:
data = data.copy()
return pd.concat([data.X, pd.DataFrame(data.y, columns=["_TARGET_"])], axis=1)
def convert_protected(data: Dataset) -> Tuple[Dataset, LabelEncoder]:
data = data.copy()
encoder = LabelEncoder()
for feature in data.protected_features:
data.X[feature] = encoder.fit_transform(data.X[feature])
return data, encoder