def test_component_graph_dataset_with_target_imputer():
X = pd.DataFrame({
'column_1': ['a', 'b', 'c', 'd', 'a', 'a', 'b', 'c', 'b'],
'column_2': [1, 2, 3, 4, 5, 6, 5, 4, 3]
})
y = pd.Series([1, 0, 1, 0, 1, 1, 0, 0, np.nan])
graph = {
'Target Imputer': [TargetImputer],
'OneHot': [OneHotEncoder, 'Target Imputer.x', 'Target Imputer.y'],
'Random Forest':
[RandomForestClassifier, 'OneHot.x', 'Target Imputer.y'],
'Elastic Net': [ElasticNetClassifier, 'OneHot.x', 'Target Imputer.y'],
'Logistic Regression': [
LogisticRegressionClassifier, 'Random Forest', 'Elastic Net',
'Target Imputer.y'
]
}
component_graph = ComponentGraph(graph)
component_graph.instantiate({})
assert component_graph.get_parents('Target Imputer') == []
assert component_graph.get_parents('OneHot') == [
'Target Imputer.x', 'Target Imputer.y'
]
assert component_graph.get_parents('Random Forest') == [
'OneHot.x', 'Target Imputer.y'
]
assert component_graph.get_parents('Elastic Net') == [
'OneHot.x', 'Target Imputer.y'
]
component_graph.fit(X, y)
predictions = component_graph.predict(X)
assert not pd.isnull(predictions.to_series()).any()
def test_component_graph_sampler():
graph = {
'Imputer': [Imputer],
'OneHot': [OneHotEncoder, 'Imputer.x'],
'Undersampler': [Undersampler, 'OneHot.x'],
'Random Forest':
[RandomForestClassifier, 'Undersampler.x', 'Undersampler.y'],
'Elastic Net':
[ElasticNetClassifier, 'Undersampler.x', 'Undersampler.y'],
'Logistic Regression':
[LogisticRegressionClassifier, 'Random Forest', 'Elastic Net']
}
component_graph = ComponentGraph(graph)
component_graph.instantiate({})
assert component_graph.get_parents('Imputer') == []
assert component_graph.get_parents('OneHot') == ['Imputer.x']
assert component_graph.get_parents('Undersampler') == ['OneHot.x']
assert component_graph.get_parents('Random Forest') == [
'Undersampler.x', 'Undersampler.y'
]
assert component_graph.get_parents('Elastic Net') == [
'Undersampler.x', 'Undersampler.y'
]
assert component_graph.get_parents('Logistic Regression') == [
'Random Forest', 'Elastic Net'
]
def test_parents(example_graph):
graph = example_graph
component_graph = ComponentGraph(graph)
assert component_graph.get_parents('Imputer') == []
assert component_graph.get_parents('OneHot_RandomForest') == ['Imputer.x']
assert component_graph.get_parents('OneHot_ElasticNet') == ['Imputer.x']
assert component_graph.get_parents('Random Forest') == [
'OneHot_RandomForest.x'
]
assert component_graph.get_parents('Elastic Net') == [
'OneHot_ElasticNet.x'
]
assert component_graph.get_parents('Logistic Regression') == [
'Random Forest', 'Elastic Net'
]
with pytest.raises(ValueError, match='not in the graph'):
component_graph.get_parents('Fake component')
component_graph.instantiate({})
assert component_graph.get_parents('Imputer') == []
assert component_graph.get_parents('OneHot_RandomForest') == ['Imputer.x']
assert component_graph.get_parents('OneHot_ElasticNet') == ['Imputer.x']
assert component_graph.get_parents('Random Forest') == [
'OneHot_RandomForest.x'
]
assert component_graph.get_parents('Elastic Net') == [
'OneHot_ElasticNet.x'
]
assert component_graph.get_parents('Logistic Regression') == [
'Random Forest', 'Elastic Net'
]
with pytest.raises(ValueError, match='not in the graph'):
component_graph.get_parents('Fake component')
