def test_baseline_binary_mode(data_type, make_data_type):
X = pd.DataFrame({
'one': [1, 2, 3, 4],
'two': [2, 3, 4, 5],
'three': [1, 2, 3, 4]
})
y = pd.Series([10, 11, 10, 10])
X = make_data_type(data_type, X)
y = make_data_type(data_type, y)
clf = BaselineClassifier(strategy="mode")
fitted = clf.fit(X, y)
assert isinstance(fitted, BaselineClassifier)
assert clf.classes_ == [10, 11]
expected_predictions = pd.Series(np.array([10] * X.shape[0]),
dtype="Int64")
predictions = clf.predict(X)
assert_series_equal(expected_predictions, predictions.to_series())
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (X.shape[0], 2)
expected_predictions_proba = pd.DataFrame({
10: [1., 1., 1., 1.],
11: [0., 0., 0., 0.]
})
assert_frame_equal(expected_predictions_proba,
predicted_proba.to_dataframe())
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
def test_stacked_ensemble_nonstackable_model_families():
with pytest.raises(
ValueError,
match=
"Pipelines with any of the following model families cannot be used as base pipelines"
):
StackedEnsembleClassifier(input_pipelines=[
make_pipeline_from_components([BaselineClassifier()],
ProblemTypes.BINARY)
])
def test_baseline_binary_random_weighted(X_y_binary):
X, y = X_y_binary
values, counts = np.unique(y, return_counts=True)
percent_freq = counts.astype(float) / len(y)
assert percent_freq.sum() == 1.0
clf = BaselineClassifier(strategy="random_weighted", random_state=0)
clf.fit(X, y)
assert clf.classes_ == [0, 1]
expected_predictions = pd.Series(get_random_state(0).choice(
np.unique(y), len(X), p=percent_freq),
dtype="Int64")
predictions = clf.predict(X)
assert_series_equal(expected_predictions, predictions.to_series())
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 2)
expected_predictions_proba = pd.DataFrame(
np.array([[percent_freq[i] for i in range(len(values))]] * len(X)))
assert_frame_equal(expected_predictions_proba,
predicted_proba.to_dataframe())
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
def test_baseline_multiclass_mode():
X = pd.DataFrame({
'one': [1, 2, 3, 4],
'two': [2, 3, 4, 5],
'three': [1, 2, 3, 4]
})
y = pd.Series([10, 12, 11, 11])
clf = BaselineClassifier(strategy="mode")
clf.fit(X, y)
assert clf.classes_ == [10, 11, 12]
predictions = clf.predict(X)
expected_predictions = pd.Series([11] * len(X), dtype="Int64")
assert_series_equal(expected_predictions, predictions.to_series())
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 3)
expected_predictions_proba = pd.DataFrame({
10: [0., 0., 0., 0.],
11: [1., 1., 1., 1.],
12: [0., 0., 0., 0.]
})
assert_frame_equal(expected_predictions_proba,
predicted_proba.to_dataframe())
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
def test_baseline_binary_mode(data_type, X_y_binary):
X = pd.DataFrame({
'one': [1, 2, 3, 4],
'two': [2, 3, 4, 5],
'three': [1, 2, 3, 4]
})
y = pd.Series([10, 11, 10, 10])
if data_type == 'ww':
X = ww.DataTable(X)
y = ww.DataColumn(y)
clf = BaselineClassifier(strategy="mode")
fitted = clf.fit(X, y)
assert isinstance(fitted, BaselineClassifier)
assert clf.classes_ == [10, 11]
np.testing.assert_allclose(clf.predict(X), np.array([10] * X.shape[0]))
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (X.shape[0], 2)
expected_predicted_proba = pd.DataFrame({
10: [1., 1., 1., 1.],
11: [0., 0., 0., 0.]
})
pd.testing.assert_frame_equal(expected_predicted_proba, predicted_proba)
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
def test_baseline_no_mode():
X = pd.DataFrame([[1, 2, 3, 0, 1]])
y = pd.Series([1, 0, 2, 0, 1])
clf = BaselineClassifier()
clf.fit(X, y)
assert clf.classes_ == [0, 1, 2]
np.testing.assert_allclose(clf.predict(X), np.array([0] * len(X)))
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 3)
np.testing.assert_allclose(
predicted_proba,
np.array([[1.0 if i == 0 else 0.0 for i in range(3)]] * len(X)))
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
def test_baseline_multiclass_random(X_y_multi):
X, y = X_y_multi
values = np.unique(y)
clf = BaselineClassifier(strategy="random", random_seed=0)
clf.fit(X, y)
assert clf.classes_ == [0, 1, 2]
expected_predictions = pd.Series(get_random_state(0).choice(np.unique(y), len(X)), dtype="Int64")
predictions = clf.predict(X)
assert_series_equal(expected_predictions, predictions.to_series())
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 3)
assert_frame_equal(pd.DataFrame(np.array([[1. / 3 for i in range(len(values))]] * len(X))), predicted_proba.to_dataframe())
np.testing.assert_allclose(clf.feature_importance, np.array([0.0] * X.shape[1]))
def test_baseline_no_mode():
X = pd.DataFrame([[1, 2, 3, 0, 1]])
y = pd.Series([1, 0, 2, 0, 1])
clf = BaselineClassifier()
clf.fit(X, y)
assert clf.classes_ == [0, 1, 2]
expected_predictions = pd.Series([0] * len(X), dtype="Int64")
predictions = clf.predict(X)
assert_series_equal(expected_predictions, predictions.to_series())
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 3)
assert_frame_equal(pd.DataFrame(np.array([[1.0 if i == 0 else 0.0 for i in range(3)]] * len(X))), predicted_proba.to_dataframe())
np.testing.assert_allclose(clf.feature_importance, np.array([0.0] * X.shape[1]))
def test_baseline_binary_random(X_y_binary):
X, y = X_y_binary
values = np.unique(y)
clf = BaselineClassifier(strategy="random", random_state=0)
clf.fit(X, y)
assert clf.classes_ == [0, 1]
np.testing.assert_allclose(
clf.predict(X),
get_random_state(0).choice(np.unique(y), len(X)))
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 2)
np.testing.assert_allclose(
predicted_proba,
np.array([[0.5 for i in range(len(values))]] * len(X)))
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
def test_baseline_binary_random_weighted(X_y_binary):
X, y = X_y_binary
values, counts = np.unique(y, return_counts=True)
percent_freq = counts.astype(float) / len(y)
assert percent_freq.sum() == 1.0
clf = BaselineClassifier(strategy="random_weighted", random_state=0)
clf.fit(X, y)
assert clf.classes_ == [0, 1]
np.testing.assert_allclose(
clf.predict(X),
get_random_state(0).choice(np.unique(y), len(X), p=percent_freq))
predicted_proba = clf.predict_proba(X)
assert predicted_proba.shape == (len(X), 2)
np.testing.assert_allclose(
predicted_proba,
np.array([[percent_freq[i] for i in range(len(values))]] * len(X)))
np.testing.assert_allclose(clf.feature_importance,
np.array([0.0] * X.shape[1]))
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_baseline_y_is_None(X_y_binary):
X, _ = X_y_binary
with pytest.raises(ValueError):
BaselineClassifier().fit(X, y=None)
def test_baseline_invalid_strategy():
with pytest.raises(ValueError):
BaselineClassifier(strategy="unfortunately invalid strategy")
def test_baseline_init():
baseline = BaselineClassifier()
assert baseline.parameters["strategy"] == "mode"
assert baseline.model_family == ModelFamily.BASELINE
assert baseline.classes_ is None
