def test_imputer_fill_value(imputer_test_data):
X = imputer_test_data[[
"int with nan", "categorical with nan", "float with nan",
"object with nan", "bool col with nan"
]]
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer(categorical_impute_strategy="constant",
numeric_impute_strategy="constant",
categorical_fill_value="fill",
numeric_fill_value=-1)
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame({
"int with nan": [-1, 1, 0, 0, 1],
"categorical with nan":
pd.Series(["fill", "1", "fill", "0", "3"], dtype='category'),
"float with nan": [0.0, 1.0, -1, -1.0, 0.],
"object with nan":
pd.Series(["b", "b", "fill", "c", "fill"], dtype='category'),
"bool col with nan":
pd.Series([True, "fill", False, "fill", True], dtype='category')
})
assert_frame_equal(expected, transformed.to_dataframe(), check_dtype=False)
imputer = Imputer(categorical_impute_strategy="constant",
numeric_impute_strategy="constant",
categorical_fill_value="fill",
numeric_fill_value=-1)
transformed = imputer.fit_transform(X, y)
assert_frame_equal(expected, transformed.to_dataframe(), check_dtype=False)
def test_imputer_with_none():
X = pd.DataFrame({
"int with None": [1, 0, 5, None],
"float with None": [0.1, 0.0, 0.5, None],
"category with None":
pd.Series(["b", "a", "a", None], dtype='category'),
"boolean with None": [True, None, False, True],
"object with None": ["b", "a", "a", None],
"all None": [None, None, None, None]
})
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame({
"int with None": [1, 0, 5, 2],
"float with None": [0.1, 0.0, 0.5, 0.2],
"category with None":
pd.Series(["b", "a", "a", "a"], dtype='category'),
"boolean with None": [True, True, False, True],
"object with None":
pd.Series(["b", "a", "a", "a"], dtype='category')
})
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_categorical_only_input(imputer_test_data):
X = imputer_test_data[[
"categorical col", "object col", "bool col", "categorical with nan",
"object with nan", "bool col with nan", "all nan cat"
]]
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame({
"categorical col":
pd.Series(["zero", "one", "two", "zero", "three"], dtype='category'),
"object col":
pd.Series(["b", "b", "a", "c", "d"], dtype='category'),
"bool col": [True, False, False, True, True],
"categorical with nan":
pd.Series(["0", "1", "0", "0", "3"], dtype='category'),
"object with nan":
pd.Series(["b", "b", "b", "c", "b"], dtype='category'),
"bool col with nan": [True, True, False, True, True]
})
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_categorical_and_numeric_input(imputer_test_data):
X = imputer_test_data
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame({
"categorical col":
pd.Series(["zero", "one", "two", "zero", "three"], dtype='category'),
"int col": [0, 1, 2, 0, 3],
"object col":
pd.Series(["b", "b", "a", "c", "d"], dtype='category'),
"float col": [0.0, 1.0, 0.0, -2.0, 5.],
"bool col": [True, False, False, True, True],
"categorical with nan":
pd.Series(["0", "1", "0", "0", "3"], dtype='category'),
"int with nan": [0.5, 1.0, 0.0, 0.0, 1.0],
"float with nan": [0.0, 1.0, 0, -1.0, 0.],
"object with nan":
pd.Series(["b", "b", "b", "c", "b"], dtype='category'),
"bool col with nan": [True, True, False, True, True]
})
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_invalid_init():
invalid_graph = {'Imputer': [Imputer], 'OHE': OneHotEncoder}
with pytest.raises(
ValueError,
match='All component information should be passed in as a list'):
ComponentGraph(invalid_graph)
with pytest.raises(
ValueError,
match='may only contain str or ComponentBase subclasses'):
ComponentGraph({
'Imputer': [Imputer(numeric_impute_strategy="most_frequent")],
'OneHot': [OneHotEncoder]
})
graph = {
'Imputer':
[Imputer(numeric_impute_strategy='constant', numeric_fill_value=0)]
}
with pytest.raises(
ValueError,
match='may only contain str or ComponentBase subclasses'):
ComponentGraph(graph)
graph = {
'Imputer': ['Imputer', 'Fake'],
'Fake': ['Fake Component', 'Estimator'],
'Estimator': [ElasticNetClassifier]
}
with pytest.raises(MissingComponentError):
ComponentGraph(graph)
def test_drop_all_columns(imputer_test_data):
X = imputer_test_data[["all nan cat", "all nan"]]
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = X.drop(["all nan cat", "all nan"], axis=1)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_typed_imputer_numpy_input():
X = np.array([[1, 2, 2, 0], [np.nan, 0, 0, 0], [1, np.nan, np.nan,
np.nan]])
y = pd.Series([0, 0, 1])
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame(
np.array([[1, 2, 2, 0], [1, 0, 0, 0], [1, 1, 1, 0]]))
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_imputer_empty_data(data_type, make_data_type):
X = pd.DataFrame()
y = pd.Series()
X = make_data_type(data_type, X)
y = make_data_type(data_type, y)
expected = pd.DataFrame(index=pd.Index([]), columns=pd.Index([]))
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_imputer_datetime_input():
X = pd.DataFrame({'dates': ['20190902', '20200519', '20190607', np.nan],
'more dates': ['20190902', '20201010', '20190921', np.nan]})
X['dates'] = pd.to_datetime(X['dates'], format='%Y%m%d')
X['more dates'] = pd.to_datetime(X['more dates'], format='%Y%m%d')
y = pd.Series()
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
assert_frame_equal(transformed.to_dataframe(), X, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), X, check_dtype=False)
def test_imputer_all_bool_return_original(data_type, make_data_type):
X = make_data_type(data_type, pd.DataFrame([True, True, False, True, True], dtype=bool))
X_expected_arr = pd.DataFrame([True, True, False, True, True], dtype='boolean')
y = make_data_type(data_type, pd.Series([1, 0, 0, 1, 0]))
imputer = Imputer()
imputer.fit(X, y)
X_t = imputer.transform(X)
assert_frame_equal(X_expected_arr, X_t.to_dataframe())
def test_imputer_no_nans(imputer_test_data):
X = imputer_test_data[["categorical col", "object col", "bool col"]]
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer(categorical_impute_strategy="constant", numeric_impute_strategy="constant",
categorical_fill_value="fill", numeric_fill_value=-1)
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame({
"categorical col": pd.Series(["zero", "one", "two", "zero", "three"], dtype='category'),
"object col": pd.Series(["b", "b", "a", "c", "d"], dtype='category'),
"bool col": [True, False, False, True, True],
})
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer(categorical_impute_strategy="constant", numeric_impute_strategy="constant",
categorical_fill_value="fill", numeric_fill_value=-1)
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_numeric_only_input(imputer_test_data):
X = imputer_test_data[["int col", "float col",
"int with nan", "float with nan", "all nan"]]
y = pd.Series([0, 0, 1, 0, 1])
imputer = Imputer(numeric_impute_strategy="median")
imputer.fit(X, y)
transformed = imputer.transform(X, y)
expected = pd.DataFrame({
"int col": [0, 1, 2, 0, 3],
"float col": [0.0, 1.0, 0.0, -2.0, 5.],
"int with nan": [0.5, 1.0, 0.0, 0.0, 1.0],
"float with nan": [0.0, 1.0, 0, -1.0, 0.]
})
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed.to_dataframe(), expected, check_dtype=False)
def test_imputer_default_parameters():
imputer = Imputer()
expected_parameters = {
'categorical_impute_strategy': 'most_frequent',
'numeric_impute_strategy': 'mean',
'categorical_fill_value': None,
'numeric_fill_value': None
}
assert imputer.parameters == expected_parameters
def test_imputer_bool_dtype_object(data_type, make_data_type):
X = pd.DataFrame([True, np.nan, False, np.nan, True], dtype='boolean')
y = pd.Series([1, 0, 0, 1, 0])
X_expected_arr = pd.DataFrame([True, True, False, True, True], dtype='boolean')
X = make_data_type(data_type, X)
y = make_data_type(data_type, y)
imputer = Imputer()
imputer.fit(X, y)
X_t = imputer.transform(X)
assert_frame_equal(X_expected_arr, X_t.to_dataframe())
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_imputer_all_bool_return_original(data_type):
X = pd.DataFrame([True, True, False, True, True], dtype=bool)
X_expected_arr = pd.DataFrame([True, True, False, True, True], dtype=bool)
y = pd.Series([1, 0, 0, 1, 0])
if data_type == 'ww':
X = ww.DataTable(X)
y = ww.DataColumn(y)
imputer = Imputer()
imputer.fit(X, y)
X_t = imputer.transform(X)
assert_frame_equal(X_expected_arr, X_t)
def test_imputer_empty_data(data_type):
if data_type == 'pd':
X = pd.DataFrame()
y = pd.Series()
expected = pd.DataFrame(index=pd.Index([]), columns=pd.Index([]))
elif data_type == 'ww':
X = ww.DataTable(pd.DataFrame())
y = ww.DataColumn(pd.Series())
expected = pd.DataFrame(index=pd.Index([]), columns=pd.Index([]))
else:
X = np.array([[]])
y = np.array([])
expected = pd.DataFrame(index=pd.Index([0]), columns=pd.Int64Index([]))
imputer = Imputer()
imputer.fit(X, y)
transformed = imputer.transform(X, y)
assert_frame_equal(transformed, expected, check_dtype=False)
imputer = Imputer()
transformed = imputer.fit_transform(X, y)
assert_frame_equal(transformed, expected, check_dtype=False)
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_imputer_does_not_reset_index():
X = pd.DataFrame({'input_val': np.arange(10), 'target': np.arange(10),
'input_cat': ['a'] * 7 + ['b'] * 3})
X.loc[5, 'input_val'] = np.nan
X.loc[5, 'input_cat'] = np.nan
assert X.index.tolist() == list(range(10))
X.drop(0, inplace=True)
y = X.pop('target')
imputer = Imputer()
imputer.fit(X, y=y)
transformed = imputer.transform(X)
pd.testing.assert_frame_equal(transformed.to_dataframe(),
pd.DataFrame({'input_val': [1.0, 2, 3, 4, 5, 6, 7, 8, 9],
'input_cat': pd.Categorical(['a'] * 6 + ['b'] * 3)},
index=list(range(1, 10))))
def test_imputer_multitype_with_one_bool(data_type, make_data_type):
X_multi = pd.DataFrame({
"bool with nan": pd.Series([True, np.nan, False, np.nan, False], dtype='boolean'),
"bool no nan": pd.Series([False, False, False, False, True], dtype=bool),
})
y = pd.Series([1, 0, 0, 1, 0])
X_multi_expected_arr = pd.DataFrame({
"bool with nan": pd.Series([True, False, False, False, False], dtype='boolean'),
"bool no nan": pd.Series([False, False, False, False, True], dtype='boolean'),
})
X_multi = make_data_type(data_type, X_multi)
y = make_data_type(data_type, y)
imputer = Imputer()
imputer.fit(X_multi, y)
X_multi_t = imputer.transform(X_multi)
assert_frame_equal(X_multi_expected_arr, X_multi_t.to_dataframe())
def test_imputer_init(categorical_impute_strategy, numeric_impute_strategy):
imputer = Imputer(categorical_impute_strategy=categorical_impute_strategy,
numeric_impute_strategy=numeric_impute_strategy,
categorical_fill_value="str_fill_value",
numeric_fill_value=-1)
expected_parameters = {
'categorical_impute_strategy': categorical_impute_strategy,
'numeric_impute_strategy': numeric_impute_strategy,
'categorical_fill_value': 'str_fill_value',
'numeric_fill_value': -1
}
expected_hyperparameters = {
"categorical_impute_strategy": ["most_frequent"],
"numeric_impute_strategy": ["mean", "median", "most_frequent"]
}
assert imputer.name == "Imputer"
assert imputer.parameters == expected_parameters
assert imputer.hyperparameter_ranges == expected_hyperparameters
def test_generate_code_pipeline_json_with_objects():
class CustomEstimator(Estimator):
name = "My Custom Estimator"
hyperparameter_ranges = {}
supported_problem_types = [
ProblemTypes.BINARY, ProblemTypes.MULTICLASS
]
model_family = ModelFamily.NONE
def __init__(self, random_arg=False, numpy_arg=[], random_seed=0):
parameters = {'random_arg': random_arg, 'numpy_arg': numpy_arg}
super().__init__(parameters=parameters,
component_obj=None,
random_seed=random_seed)
component_graph = ['Imputer', CustomEstimator]
pipeline = BinaryClassificationPipeline(
component_graph,
custom_name="Mock Binary Pipeline with Transformer",
parameters={'My Custom Estimator': {
'numpy_arg': np.array([0])
}})
generated_pipeline_code = generate_pipeline_code(pipeline)
assert generated_pipeline_code == "from evalml.pipelines.binary_classification_pipeline import BinaryClassificationPipeline\n" \
"pipeline = BinaryClassificationPipeline(component_graph=['Imputer', CustomEstimator], " \
"parameters={'Imputer':{'categorical_impute_strategy': 'most_frequent', 'numeric_impute_strategy': 'mean', 'categorical_fill_value': None, 'numeric_fill_value': None}, " \
"'My Custom Estimator':{'random_arg': False, 'numpy_arg': array([0])}}, custom_name='Mock Binary Pipeline with Transformer', random_seed=0)"
pipeline = BinaryClassificationPipeline(
component_graph,
custom_name="Mock Binary Pipeline with Transformer",
parameters={'My Custom Estimator': {
'random_arg': Imputer()
}})
generated_pipeline_code = generate_pipeline_code(pipeline)
assert generated_pipeline_code == "from evalml.pipelines.binary_classification_pipeline import BinaryClassificationPipeline\n" \
"pipeline = BinaryClassificationPipeline(component_graph=['Imputer', CustomEstimator], " \
"parameters={'Imputer':{'categorical_impute_strategy': 'most_frequent', 'numeric_impute_strategy': 'mean', 'categorical_fill_value': None, 'numeric_fill_value': None}, " \
"'My Custom Estimator':{'random_arg': Imputer(categorical_impute_strategy='most_frequent', numeric_impute_strategy='mean', categorical_fill_value=None, numeric_fill_value=None), 'numpy_arg': []}}, " \
"custom_name='Mock Binary Pipeline with Transformer', random_seed=0)"
def test_imputer_multitype_with_one_bool(data_type):
X_multi = pd.DataFrame({
"bool with nan":
pd.Series([True, np.nan, False, np.nan, False], dtype=object),
"bool no nan":
pd.Series([False, False, False, False, True], dtype=bool),
})
y = pd.Series([1, 0, 0, 1, 0])
X_multi_expected_arr = pd.DataFrame({
"bool with nan":
pd.Series([True, False, False, False, False], dtype=object),
"bool no nan":
pd.Series([False, False, False, False, True], dtype=bool),
})
if data_type == 'ww':
X_multi = ww.DataTable(X_multi)
y = ww.DataColumn(y)
imputer = Imputer()
imputer.fit(X_multi, y)
X_multi_t = imputer.transform(X_multi)
assert_frame_equal(X_multi_expected_arr, X_multi_t)
def test_imputer_woodwork_custom_overrides_returned_by_components(X_df, has_nan, numeric_impute_strategy):
y = pd.Series([1, 2, 1])
if has_nan:
X_df.iloc[len(X_df) - 1, 0] = np.nan
override_types = [Integer, Double, Categorical, NaturalLanguage, Boolean]
for logical_type in override_types:
try:
X = ww.DataTable(X_df, logical_types={0: logical_type})
except TypeError:
continue
imputer = Imputer(numeric_impute_strategy=numeric_impute_strategy)
imputer.fit(X, y)
transformed = imputer.transform(X, y)
assert isinstance(transformed, ww.DataTable)
if numeric_impute_strategy == "most_frequent":
assert transformed.logical_types == {0: logical_type}
elif logical_type in [Categorical, NaturalLanguage] or not has_nan:
assert transformed.logical_types == {0: logical_type}
else:
assert transformed.logical_types == {0: Double}
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 test_make_pipeline_from_components(X_y_binary, logistic_regression_binary_pipeline_class):
with pytest.raises(ValueError, match="Pipeline needs to have an estimator at the last position of the component list"):
make_pipeline_from_components([Imputer()], problem_type='binary')
with pytest.raises(KeyError, match="Problem type 'invalid_type' does not exist"):
make_pipeline_from_components([RandomForestClassifier()], problem_type='invalid_type')
with pytest.raises(TypeError, match="Custom pipeline name must be a string"):
make_pipeline_from_components([RandomForestClassifier()], problem_type='binary', custom_name=True)
with pytest.raises(TypeError, match="Every element of `component_instances` must be an instance of ComponentBase"):
make_pipeline_from_components([RandomForestClassifier], problem_type='binary')
with pytest.raises(TypeError, match="Every element of `component_instances` must be an instance of ComponentBase"):
make_pipeline_from_components(['RandomForestClassifier'], problem_type='binary')
imp = Imputer(numeric_impute_strategy='median', random_seed=5)
est = RandomForestClassifier(random_seed=7)
pipeline = make_pipeline_from_components([imp, est], ProblemTypes.BINARY, custom_name='My Pipeline',
random_seed=15)
assert [c.__class__ for c in pipeline] == [Imputer, RandomForestClassifier]
assert [(c.random_seed == 15) for c in pipeline]
assert pipeline.problem_type == ProblemTypes.BINARY
assert pipeline.custom_name == 'My Pipeline'
expected_parameters = {
'Imputer': {
'categorical_impute_strategy': 'most_frequent',
'numeric_impute_strategy': 'median',
'categorical_fill_value': None,
'numeric_fill_value': None},
'Random Forest Classifier': {
'n_estimators': 100,
'max_depth': 6,
'n_jobs': -1}
}
assert pipeline.parameters == expected_parameters
assert pipeline.random_seed == 15
class DummyEstimator(Estimator):
name = "Dummy!"
model_family = "foo"
supported_problem_types = [ProblemTypes.BINARY]
parameters = {'bar': 'baz'}
random_seed = 42
pipeline = make_pipeline_from_components([DummyEstimator(random_seed=3)], ProblemTypes.BINARY,
random_seed=random_seed)
components_list = [c for c in pipeline]
assert len(components_list) == 1
assert isinstance(components_list[0], DummyEstimator)
assert components_list[0].random_seed == random_seed
expected_parameters = {'Dummy!': {'bar': 'baz'}}
assert pipeline.parameters == expected_parameters
assert pipeline.random_seed == random_seed
X, y = X_y_binary
pipeline = logistic_regression_binary_pipeline_class(parameters={"Logistic Regression Classifier": {"n_jobs": 1}},
random_seed=42)
component_instances = [c for c in pipeline]
new_pipeline = make_pipeline_from_components(component_instances, ProblemTypes.BINARY)
pipeline.fit(X, y)
predictions = pipeline.predict(X)
new_pipeline.fit(X, y)
new_predictions = new_pipeline.predict(X)
assert np.array_equal(predictions, new_predictions)
assert np.array_equal(pipeline.feature_importance, new_pipeline.feature_importance)
assert new_pipeline.name == 'Templated Pipeline'
assert pipeline.parameters == new_pipeline.parameters
for component, new_component in zip(pipeline._component_graph, new_pipeline._component_graph):
assert isinstance(new_component, type(component))
assert pipeline.describe() == new_pipeline.describe()
def test_invalid_strategy_parameters():
with pytest.raises(ValueError, match="Valid impute strategies are"):
Imputer(numeric_impute_strategy="not a valid strategy")
with pytest.raises(ValueError,
match="Valid categorical impute strategies are"):
Imputer(categorical_impute_strategy="mean")