Beispiel #1
0
def test_model_properties_after_fitting():
    """Check the model properties after fitting a deep forest model."""
    model = CascadeForestClassifier(**toy_kwargs)
    model.fit(X_train, y_train)

    assert len(model) == model.n_layers_

    assert model[0] is model._get_layer(0)

    with pytest.raises(ValueError) as excinfo:
        model._get_layer(model.n_layers_)
    assert "The layer index should be in the range" in str(excinfo.value)

    with pytest.raises(RuntimeError) as excinfo:
        model._set_layer(0, None)
    assert "already exists in the internal container" in str(excinfo.value)

    with pytest.raises(ValueError) as excinfo:
        model._get_binner(model.n_layers_ + 1)
    assert "The binner index should be in the range" in str(excinfo.value)

    with pytest.raises(RuntimeError) as excinfo:
        model._set_binner(0, None)
    assert "already exists in the internal container" in str(excinfo.value)

    # Test the hook on forest estimator
    assert (
        model.get_forest(0, 0, "rf")
        is model._get_layer(0).estimators_["0-0-rf"].estimator_
    )

    with pytest.raises(ValueError) as excinfo:
        model.get_forest(model.n_layers_, 0, "rf")
    assert "`layer_idx` should be in the range" in str(excinfo.value)

    with pytest.raises(ValueError) as excinfo:
        model.get_forest(0, model.n_estimators, "rf")
    assert "`est_idx` should be in the range" in str(excinfo.value)

    with pytest.raises(ValueError) as excinfo:
        model.get_forest(0, 0, "Unknown")
    assert "`forest_type` should be one of" in str(excinfo.value)
Beispiel #2
0

X, y = shap.datasets.iris()

# print("X", X.head())
# print("y", y)

feature_names = X.columns
X = np.array(X)
y = np.array(y)

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

model = CascadeForestClassifier(backend="sklearn")
model.fit(X_train, y_train)
forest = model.get_forest(0, 0, "rf")
explainer = shap.TreeExplainer(forest)
shap_values = explainer.shap_values(X_test)

# shap_values = np.array(explainer.shap_values(X_train))
# print(shap_values.shape)
# print(shap_values[2].shape)

# shap.summary_plot(shap_values[2], X_train)
#
#
# clf = RandomForestClassifier(n_estimators=100)
# clf.fit(X_train, y_train)
# explainer = shap.TreeExplainer(clf)
# shap_values = np.array(explainer.shap_values(X_test))
# shap.summary_plot(shap_values[0],X_train)