def test_missing_values_param():
df = {
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"Age": [20, 21, 19, 18],
"Marks": [0.9, 0.8, 0.7, 0.6],
"dob": pd.date_range("2020-02-24", periods=4, freq="T"),
"const_feat_num": [1, 1, 1, np.nan],
"const_feat_cat": ["a", "a", "a", "a"],
"quasi_feat_num": [1, 1, 1, 2],
"quasi_feat_cat": ["a", "a", "a", np.nan],
}
df = pd.DataFrame(df)
# test raises error if there is na
with pytest.raises(ValueError):
transformer = DropConstantFeatures(missing_values="raise")
transformer.fit(df)
# test ignores na
transformer = DropConstantFeatures(missing_values="ignore").fit(df)
constant = ["const_feat_num", "const_feat_cat", "quasi_feat_cat"]
assert transformer.constant_features_ == constant
pd.testing.assert_frame_equal(df.drop(constant, axis=1),
transformer.transform(df))
# test includes na
transformer = DropConstantFeatures(tol=0.7,
missing_values="include").fit(df)
qconstant = [
"const_feat_num", "const_feat_cat", "quasi_feat_num", "quasi_feat_cat"
]
assert transformer.constant_features_ == qconstant
pd.testing.assert_frame_equal(df.drop(qconstant, axis=1),
transformer.transform(df))
def test_non_fitted_error(df_constant_features):
# test case 8: when fit is not called prior to transform
with pytest.raises(NotFittedError):
transformer = DropConstantFeatures()
transformer.transform(df_constant_features)