Function native

demo/guide-python/cat_pipeline.py:58–101

Using the native XGBoost interface.

()

def native() -> None:
    """Using the native XGBoost interface."""
    X, y, cat_feats = make_example_data()

    X_train, X_test, y_train, y_test = train_test_split(
        X, y, random_state=1994, test_size=0.2
    )

    # Create an encoder based on training data.
    enc = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=np.nan)
    enc.set_output(transform="pandas")
    enc = enc.fit(X_train[cat_feats])

    def enc_transform(X: pd.DataFrame) -> pd.DataFrame:
        # don't make change inplace so that we can have demonstrations for encoding
        X = X.copy()
        cat_cols = enc.transform(X[cat_feats])
        for i, name in enumerate(cat_feats):
            # create pd.Series based on the encoder
            cat_cols[name] = pd.Categorical.from_codes(
                codes=cat_cols[name].astype(np.int32), categories=enc.categories_[i]
            )
        X[cat_feats] = cat_cols
        return X

    # Encode the data based on fitted encoder.
    X_train_enc = enc_transform(X_train)
    X_test_enc = enc_transform(X_test)
    # Train XGBoost model using the native interface.
    Xy_train = xgb.QuantileDMatrix(X_train_enc, y_train, enable_categorical=True)
    Xy_test = xgb.QuantileDMatrix(
        X_test_enc, y_test, enable_categorical=True, ref=Xy_train
    )
    booster = xgb.train({}, Xy_train)
    booster.predict(Xy_test)

    # Following shows that data are encoded consistently.

    # We first obtain result from newly encoded data
    predt0 = booster.inplace_predict(enc_transform(X_train.head(16)))
    # then we obtain result from already encoded data from training.
    predt1 = booster.inplace_predict(X_train_enc.head(16))

    np.testing.assert_allclose(predt0, predt1)


def pipeline() -> None: