sayakpaul / benchmarking-and-mli-experiments-on-the-adult-dataset Goto Github PK

from sklearn.preprocessing import LabelEncoder

train_preprocessed = train.apply(LabelEncoder().fit_transform)
test_preprocessed = test.apply(LabelEncoder().fit_transform)

from sklearn.preprocessing import OrdinalEncoder
oe = OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=-1)

train_preprocessed = oe.fit_transform(train.fillna("NaN"))
test_preprocessed = oe.transform(test.fillna("NaN"))
train_preprocessed = pd.DataFrame(train_preprocessed, columns=train.columns)
test_preprocessed = pd.DataFrame(test_preprocessed, columns=train.columns)