Exemplo n.º 1
0
def test_bagging_classifier_with_missing_inputs():
    # Check that BaggingClassifier can accept X with missing/infinite data
    X = np.array([
        [1, 3, 5],
        [2, None, 6],
        [2, np.nan, 6],
        [2, np.inf, 6],
        [2, np.NINF, 6],
    ])
    y = np.array([3, 6, 6, 6, 6])
    classifier = DecisionTreeClassifier()
    pipeline = make_pipeline(FunctionTransformer(replace), classifier)
    pipeline.fit(X, y).predict(X)
    bagging_classifier = BaggingClassifier(pipeline)
    bagging_classifier.fit(X, y)
    y_hat = bagging_classifier.predict(X)
    assert y.shape == y_hat.shape
    bagging_classifier.predict_log_proba(X)
    bagging_classifier.predict_proba(X)

    # Verify that exceptions can be raised by wrapper classifier
    classifier = DecisionTreeClassifier()
    pipeline = make_pipeline(classifier)
    assert_raises(ValueError, pipeline.fit, X, y)
    bagging_classifier = BaggingClassifier(pipeline)
    assert_raises(ValueError, bagging_classifier.fit, X, y)
Exemplo n.º 2
0
def test_probability():
    # Predict probabilities.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)

    with np.errstate(divide="ignore", invalid="ignore"):
        # Normal case
        ensemble = BaggingClassifier(base_estimator=DecisionTreeClassifier(),
                                     random_state=rng).fit(X_train, y_train)

        assert_array_almost_equal(
            np.sum(ensemble.predict_proba(X_test), axis=1),
            np.ones(len(X_test)))

        assert_array_almost_equal(ensemble.predict_proba(X_test),
                                  np.exp(ensemble.predict_log_proba(X_test)))

        # Degenerate case, where some classes are missing
        ensemble = BaggingClassifier(base_estimator=LogisticRegression(),
                                     random_state=rng,
                                     max_samples=5).fit(X_train, y_train)

        assert_array_almost_equal(
            np.sum(ensemble.predict_proba(X_test), axis=1),
            np.ones(len(X_test)))

        assert_array_almost_equal(ensemble.predict_proba(X_test),
                                  np.exp(ensemble.predict_log_proba(X_test)))
Exemplo n.º 3
0
def test_parallel_classification():
    # Check parallel classification.
    rng = check_random_state(0)

    # Classification
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)

    ensemble = BaggingClassifier(DecisionTreeClassifier(),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    # predict_proba
    ensemble.set_params(n_jobs=1)
    y1 = ensemble.predict_proba(X_test)
    ensemble.set_params(n_jobs=2)
    y2 = ensemble.predict_proba(X_test)
    assert_array_almost_equal(y1, y2)

    ensemble = BaggingClassifier(DecisionTreeClassifier(),
                                 n_jobs=1,
                                 random_state=0).fit(X_train, y_train)

    y3 = ensemble.predict_proba(X_test)
    assert_array_almost_equal(y1, y3)

    # decision_function
    ensemble = BaggingClassifier(SVC(decision_function_shape='ovr'),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    ensemble.set_params(n_jobs=1)
    decisions1 = ensemble.decision_function(X_test)
    ensemble.set_params(n_jobs=2)
    decisions2 = ensemble.decision_function(X_test)
    assert_array_almost_equal(decisions1, decisions2)

    X_err = np.hstack((X_test, np.zeros((X_test.shape[0], 1))))
    assert_raise_message(
        ValueError, "Number of features of the model "
        "must match the input. Model n_features is {0} "
        "and input n_features is {1} "
        "".format(X_test.shape[1], X_err.shape[1]), ensemble.decision_function,
        X_err)

    ensemble = BaggingClassifier(SVC(decision_function_shape='ovr'),
                                 n_jobs=1,
                                 random_state=0).fit(X_train, y_train)

    decisions3 = ensemble.decision_function(X_test)
    assert_array_almost_equal(decisions1, decisions3)