def test_get_last_component(example_graph):
component_graph = ComponentGraph()
with pytest.raises(ValueError,
match='Cannot get last component from edgeless graph'):
component_graph.get_last_component()
component_graph = ComponentGraph(example_graph)
assert component_graph.get_last_component() == LogisticRegressionClassifier
component_graph.instantiate({})
assert component_graph.get_last_component(
) == LogisticRegressionClassifier()
component_graph = ComponentGraph({'Imputer': [Imputer]})
assert component_graph.get_last_component() == Imputer
component_graph = ComponentGraph({
'Imputer': [Imputer],
'OneHot': [OneHotEncoder, 'Imputer']
})
assert component_graph.get_last_component() == OneHotEncoder
component_graph = ComponentGraph({
'Imputer': [Imputer],
'OneHot': [OneHotEncoder]
})
with pytest.raises(ValueError,
match='Cannot get last component from edgeless graph'):
component_graph.get_last_component()
def test_generate_code():
expected_code = "from evalml.pipelines.components.estimators.classifiers.logistic_regression import LogisticRegressionClassifier" \
"\n\nlogisticRegressionClassifier = LogisticRegressionClassifier(**{'penalty': 'l2', 'C': 1.0, 'n_jobs': -1, 'multi_class': 'auto', 'solver': 'lbfgs'})"
component_code = generate_component_code(LogisticRegressionClassifier())
assert component_code == expected_code
expected_code = "from evalml.pipelines.components.estimators.regressors.et_regressor import ExtraTreesRegressor" \
"\n\nextraTreesRegressor = ExtraTreesRegressor(**{'n_estimators': 50, 'max_features': 'auto', 'max_depth': 6, 'min_samples_split': 2, 'min_weight_fraction_leaf': 0.0, 'n_jobs': -1})"
component_code = generate_component_code(ExtraTreesRegressor(n_estimators=50))
assert component_code == expected_code
expected_code = "from evalml.pipelines.components.transformers.imputers.imputer import Imputer" \
"\n\nimputer = Imputer(**{'categorical_impute_strategy': 'most_frequent', 'numeric_impute_strategy': 'mean', 'categorical_fill_value': None, 'numeric_fill_value': None})"
component_code = generate_component_code(Imputer())
assert component_code == expected_code
def test_get_estimators(example_graph):
component_graph = ComponentGraph(example_graph)
with pytest.raises(ValueError, match='Cannot get estimators until'):
component_graph.get_estimators()
component_graph.instantiate({})
assert component_graph.get_estimators() == [
RandomForestClassifier(),
ElasticNetClassifier(),
LogisticRegressionClassifier()
]
component_graph = ComponentGraph.from_list(['Imputer', 'One Hot Encoder'])
component_graph.instantiate({})
assert component_graph.get_estimators() == []
def test_serialization_protocol(mock_cloudpickle_dump, tmpdir):
path = os.path.join(str(tmpdir), 'pipe.pkl')
component = LogisticRegressionClassifier()
component.save(path)
assert len(mock_cloudpickle_dump.call_args_list) == 1
assert mock_cloudpickle_dump.call_args_list[0][1]['protocol'] == cloudpickle.DEFAULT_PROTOCOL
mock_cloudpickle_dump.reset_mock()
component.save(path, pickle_protocol=42)
assert len(mock_cloudpickle_dump.call_args_list) == 1
assert mock_cloudpickle_dump.call_args_list[0][1]['protocol'] == 42
def test_iteration(example_graph):
component_graph = ComponentGraph(example_graph)
expected = [
Imputer, OneHotEncoder, ElasticNetClassifier, OneHotEncoder,
RandomForestClassifier, LogisticRegressionClassifier
]
iteration = [component for component in component_graph]
assert iteration == expected
component_graph.instantiate({'OneHot_RandomForest': {'top_n': 32}})
expected = [
Imputer(),
OneHotEncoder(),
ElasticNetClassifier(),
OneHotEncoder(top_n=32),
RandomForestClassifier(),
LogisticRegressionClassifier()
]
iteration = [component for component in component_graph]
assert iteration == expected
def test_generate_code_pipeline_errors():
class MockBinaryPipeline(BinaryClassificationPipeline):
name = "Mock Binary Pipeline"
component_graph = ['Imputer', 'Random Forest Classifier']
class MockMulticlassPipeline(MulticlassClassificationPipeline):
name = "Mock Multiclass Pipeline"
component_graph = ['Imputer', 'Random Forest Classifier']
class MockRegressionPipeline(RegressionPipeline):
name = "Mock Regression Pipeline"
component_graph = ['Imputer', 'Random Forest Regressor']
with pytest.raises(ValueError,
match="Element must be a pipeline instance"):
generate_pipeline_code(MockBinaryPipeline)
with pytest.raises(ValueError,
match="Element must be a pipeline instance"):
generate_pipeline_code(MockMulticlassPipeline)
with pytest.raises(ValueError,
match="Element must be a pipeline instance"):
generate_pipeline_code(MockRegressionPipeline)
with pytest.raises(ValueError,
match="Element must be a pipeline instance"):
generate_pipeline_code([Imputer])
with pytest.raises(ValueError,
match="Element must be a pipeline instance"):
generate_pipeline_code([Imputer, LogisticRegressionClassifier])
with pytest.raises(ValueError,
match="Element must be a pipeline instance"):
generate_pipeline_code([Imputer(), LogisticRegressionClassifier()])
def test_describe_component():
enc = OneHotEncoder()
imputer = Imputer()
simple_imputer = SimpleImputer("mean")
column_imputer = PerColumnImputer({"a": "mean", "b": ("constant", 100)})
scaler = StandardScaler()
feature_selection_clf = RFClassifierSelectFromModel(n_estimators=10, number_features=5, percent_features=0.3, threshold=-np.inf)
feature_selection_reg = RFRegressorSelectFromModel(n_estimators=10, number_features=5, percent_features=0.3, threshold=-np.inf)
drop_col_transformer = DropColumns(columns=['col_one', 'col_two'])
drop_null_transformer = DropNullColumns()
datetime = DateTimeFeaturizer()
text_featurizer = TextFeaturizer()
lsa = LSA()
pca = PCA()
lda = LinearDiscriminantAnalysis()
ft = DFSTransformer()
us = Undersampler()
assert enc.describe(return_dict=True) == {'name': 'One Hot Encoder', 'parameters': {'top_n': 10,
'features_to_encode': None,
'categories': None,
'drop': 'if_binary',
'handle_unknown': 'ignore',
'handle_missing': 'error'}}
assert imputer.describe(return_dict=True) == {'name': 'Imputer', 'parameters': {'categorical_impute_strategy': "most_frequent",
'categorical_fill_value': None,
'numeric_impute_strategy': "mean",
'numeric_fill_value': None}}
assert simple_imputer.describe(return_dict=True) == {'name': 'Simple Imputer', 'parameters': {'impute_strategy': 'mean', 'fill_value': None}}
assert column_imputer.describe(return_dict=True) == {'name': 'Per Column Imputer', 'parameters': {'impute_strategies': {'a': 'mean', 'b': ('constant', 100)}, 'default_impute_strategy': 'most_frequent'}}
assert scaler.describe(return_dict=True) == {'name': 'Standard Scaler', 'parameters': {}}
assert feature_selection_clf.describe(return_dict=True) == {'name': 'RF Classifier Select From Model', 'parameters': {'number_features': 5, 'n_estimators': 10, 'max_depth': None, 'percent_features': 0.3, 'threshold': -np.inf, 'n_jobs': -1}}
assert feature_selection_reg.describe(return_dict=True) == {'name': 'RF Regressor Select From Model', 'parameters': {'number_features': 5, 'n_estimators': 10, 'max_depth': None, 'percent_features': 0.3, 'threshold': -np.inf, 'n_jobs': -1}}
assert drop_col_transformer.describe(return_dict=True) == {'name': 'Drop Columns Transformer', 'parameters': {'columns': ['col_one', 'col_two']}}
assert drop_null_transformer.describe(return_dict=True) == {'name': 'Drop Null Columns Transformer', 'parameters': {'pct_null_threshold': 1.0}}
assert datetime.describe(return_dict=True) == {'name': 'DateTime Featurization Component',
'parameters': {'features_to_extract': ['year', 'month', 'day_of_week', 'hour'],
'encode_as_categories': False}}
assert text_featurizer.describe(return_dict=True) == {'name': 'Text Featurization Component', 'parameters': {}}
assert lsa.describe(return_dict=True) == {'name': 'LSA Transformer', 'parameters': {}}
assert pca.describe(return_dict=True) == {'name': 'PCA Transformer', 'parameters': {'n_components': None, 'variance': 0.95}}
assert lda.describe(return_dict=True) == {'name': 'Linear Discriminant Analysis Transformer', 'parameters': {'n_components': None}}
assert ft.describe(return_dict=True) == {'name': 'DFS Transformer', 'parameters': {"index": "index"}}
assert us.describe(return_dict=True) == {'name': 'Undersampler', 'parameters': {"balanced_ratio": 4, "min_samples": 100, "min_percentage": 0.1}}
# testing estimators
base_classifier = BaselineClassifier()
base_regressor = BaselineRegressor()
lr_classifier = LogisticRegressionClassifier()
en_classifier = ElasticNetClassifier()
en_regressor = ElasticNetRegressor()
et_classifier = ExtraTreesClassifier(n_estimators=10, max_features="auto")
et_regressor = ExtraTreesRegressor(n_estimators=10, max_features="auto")
rf_classifier = RandomForestClassifier(n_estimators=10, max_depth=3)
rf_regressor = RandomForestRegressor(n_estimators=10, max_depth=3)
linear_regressor = LinearRegressor()
svm_classifier = SVMClassifier()
svm_regressor = SVMRegressor()
assert base_classifier.describe(return_dict=True) == {'name': 'Baseline Classifier', 'parameters': {'strategy': 'mode'}}
assert base_regressor.describe(return_dict=True) == {'name': 'Baseline Regressor', 'parameters': {'strategy': 'mean'}}
assert lr_classifier.describe(return_dict=True) == {'name': 'Logistic Regression Classifier', 'parameters': {'penalty': 'l2', 'C': 1.0, 'n_jobs': -1, 'multi_class': 'auto', 'solver': 'lbfgs'}}
assert en_classifier.describe(return_dict=True) == {'name': 'Elastic Net Classifier', 'parameters': {'alpha': 0.5, 'l1_ratio': 0.5, 'n_jobs': -1, 'max_iter': 1000, "loss": 'log', 'penalty': 'elasticnet'}}
assert en_regressor.describe(return_dict=True) == {'name': 'Elastic Net Regressor', 'parameters': {'alpha': 0.5, 'l1_ratio': 0.5, 'max_iter': 1000, 'normalize': False}}
assert et_classifier.describe(return_dict=True) == {'name': 'Extra Trees Classifier', 'parameters': {'n_estimators': 10, 'max_features': 'auto', 'max_depth': 6, 'min_samples_split': 2, 'min_weight_fraction_leaf': 0.0, 'n_jobs': -1}}
assert et_regressor.describe(return_dict=True) == {'name': 'Extra Trees Regressor', 'parameters': {'n_estimators': 10, 'max_features': 'auto', 'max_depth': 6, 'min_samples_split': 2, 'min_weight_fraction_leaf': 0.0, 'n_jobs': -1}}
assert rf_classifier.describe(return_dict=True) == {'name': 'Random Forest Classifier', 'parameters': {'n_estimators': 10, 'max_depth': 3, 'n_jobs': -1}}
assert rf_regressor.describe(return_dict=True) == {'name': 'Random Forest Regressor', 'parameters': {'n_estimators': 10, 'max_depth': 3, 'n_jobs': -1}}
assert linear_regressor.describe(return_dict=True) == {'name': 'Linear Regressor', 'parameters': {'fit_intercept': True, 'normalize': False, 'n_jobs': -1}}
assert svm_classifier.describe(return_dict=True) == {'name': 'SVM Classifier', 'parameters': {'C': 1.0, 'kernel': 'rbf', 'gamma': 'scale', 'probability': True}}
assert svm_regressor.describe(return_dict=True) == {'name': 'SVM Regressor', 'parameters': {'C': 1.0, 'kernel': 'rbf', 'gamma': 'scale'}}
try:
xgb_classifier = XGBoostClassifier(eta=0.1, min_child_weight=1, max_depth=3, n_estimators=75)
xgb_regressor = XGBoostRegressor(eta=0.1, min_child_weight=1, max_depth=3, n_estimators=75)
assert xgb_classifier.describe(return_dict=True) == {'name': 'XGBoost Classifier', 'parameters': {'eta': 0.1, 'max_depth': 3, 'min_child_weight': 1, 'n_estimators': 75}}
assert xgb_regressor.describe(return_dict=True) == {'name': 'XGBoost Regressor', 'parameters': {'eta': 0.1, 'max_depth': 3, 'min_child_weight': 1, 'n_estimators': 75}}
except ImportError:
pass
try:
cb_classifier = CatBoostClassifier()
cb_regressor = CatBoostRegressor()
assert cb_classifier.describe(return_dict=True) == {'name': 'CatBoost Classifier', 'parameters': {'allow_writing_files': False, 'n_estimators': 10, 'eta': 0.03, 'max_depth': 6, 'bootstrap_type': None, 'silent': True}}
assert cb_regressor.describe(return_dict=True) == {'name': 'CatBoost Regressor', 'parameters': {'allow_writing_files': False, 'n_estimators': 10, 'eta': 0.03, 'max_depth': 6, 'bootstrap_type': None, 'silent': False}}
except ImportError:
pass
try:
lg_classifier = LightGBMClassifier()
lg_regressor = LightGBMRegressor()
assert lg_classifier.describe(return_dict=True) == {'name': 'LightGBM Classifier', 'parameters': {'boosting_type': 'gbdt', 'learning_rate': 0.1, 'n_estimators': 100, 'max_depth': 0, 'num_leaves': 31,
'min_child_samples': 20, 'n_jobs': -1, 'bagging_fraction': 0.9, 'bagging_freq': 0}}
assert lg_regressor.describe(return_dict=True) == {'name': 'LightGBM Regressor', 'parameters': {'boosting_type': 'gbdt', 'learning_rate': 0.1, 'n_estimators': 20, 'max_depth': 0, 'num_leaves': 31,
'min_child_samples': 20, 'n_jobs': -1, 'bagging_fraction': 0.9, 'bagging_freq': 0}}
except ImportError:
pass
def logit_estimator():
est_class = LogisticRegressionClassifier()
return est_class