NotFittedError make_pipeline

Question

I have following pipeline

num_pipe = make_pipeline(
    StandardScaler()
)
cat_pipe = make_pipeline(
    OneHotEncoder(handle_unknown="ignore"),
)
preprocessor_tree = make_column_transformer(
    (num_pipe, selector(dtype_include="number")),
    (cat_pipe, selector(dtype_include="category")),
    n_jobs=2,
)
bag_clf = make_pipeline(
    preprocessor_tree,
    BalancedBaggingClassifier(
        base_estimator=HistGradientBoostingClassifier(random_state=42),
        n_estimators=10,
        random_state=42,
        n_jobs=2,
    ),
)
cv_result = cross_validate(bag_clf, X_train, y_train, scoring=scoring)

after cross validation i try

y_pred = bag_clf.predict(X_test)

and got This ColumnTransformer instance is not fitted yet. Call 'fit' with appropriate arguments before using this estimator. How evaluate classifiers on unseen data ?

Answer 1

You still need to .fit your pipeline after cross validation, as the error is indicating.