def test_basetransformer_params_are_attached():
"""Assert that the n_jobs and random_state params from atom are used."""
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
atom.add(PCA()) # When left to default
atom.add(PCA(random_state=2)) # When changed
assert atom.pipeline[0].get_params()["random_state"] == 1
assert atom.pipeline[1].get_params()["random_state"] == 2
def test_add_complete_dataset():
"""Assert that atom accepts transformers for the complete dataset."""
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
atom.add(StandardScaler())
assert check_scaling(atom.dataset)
len_dataset = len(atom.dataset)
atom.add(Pruner())
assert len(atom.dataset) != len_dataset
def test_add_train_only():
"""Assert that atom accepts transformers for the train set only."""
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
atom.add(StandardScaler(), train_only=True)
assert check_scaling(atom.X_train) and not check_scaling(atom.X_test)
len_train, len_test = len(atom.train), len(atom.test)
atom.add(Pruner(), train_only=True)
assert len(atom.train) != len_train and len(atom.test) == len_test
def test_add_pipeline():
"""Assert that adding a pipeline adds every individual step."""
pipeline = Pipeline(steps=[
("scaler", StandardScaler()),
("sfm", SelectFromModel(RandomForestClassifier())),
])
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
atom.add(pipeline)
assert isinstance(atom.pipeline[0], StandardScaler)
assert isinstance(atom.pipeline[1], SelectFromModel)
def test_keep_column_names():
"""Assert that the column names are kept after transforming."""
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
# When the columns are only transformed
cols = atom.columns.copy()
atom.add(StandardScaler())
assert atom.columns == cols
# When columns were removed
cols = atom.columns.copy()
atom.add(SelectFromModel(RandomForestClassifier()))
assert all(col in cols for col in atom.columns)
def test_sets_are_kept_equal():
"""Assert that the train and test sets always keep the same rows."""
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
len_train, len_test = len(atom.train), len(atom.test)
atom.add(Pruner())
assert len(atom.train) < len_train and len(atom.test) < len_test
def test_duplicate_columns_are_ignored():
"""Assert that duplicate columns are ignored for the transformers."""
atom = ATOMClassifier(X_bin, y_bin, random_state=1)
atom.add(StandardScaler(), columns=["mean radius", "mean radius"])
assert not atom["mean radius"].equals(X_bin["mean radius"])
def test_transformer_only_y():
"""Assert that atom accepts transformers with only an y parameter."""
atom = ATOMClassifier(X10, y10_str, random_state=1)
atom.add(LabelEncoder())
assert np.all((atom["target"] == 0) | (atom["target"] == 1))