============================= test session starts ==============================
platform linux -- Python 3.12.3, pytest-8.3.2, pluggy-1.5.0 -- /home/adas/mljar/mljar-supervised/venv/bin/python3
cachedir: .pytest_cache
rootdir: /home/adas/mljar/mljar-supervised
configfile: pytest.ini
plugins: cov-5.0.0
collecting ... collected 1 item
tests/tests_preprocessing/test_scale.py::ScaleTest::test_fit_log_and_normal FAILED
=================================== FAILURES ===================================
______________________ ScaleTest.test_fit_log_and_normal _______________________
self = <tests.tests_preprocessing.test_scale.ScaleTest testMethod=test_fit_log_and_normal>
def test_fit_log_and_normal(self):
# training data
d = {
"col1": [12, 13, 3, 4, 5, 6, 7, 8000, 9000, 10000.0],
"col2": [21, 22, 23, 24, 25, 26, 27, 28, 29, 30.0],
"col3": [12, 2, 3, 4, 5, 6, 7, 8000, 9000, 10000.0],
}
df = pd.DataFrame(data=d)
scale = Scale(["col1", "col3"], scale_method=Scale.SCALE_LOG_AND_NORMAL)
scale.fit(df)
df = scale.transform(df)
val = float(df["col1"][0])
assert_almost_equal(np.mean(df["col1"]), 0)
self.assertTrue(
df["col1"][0] + 0.01 < df["col1"][1]
) # in case of wrong scaling the small values will be squeezed
df = scale.inverse_transform(df)
scale2 = Scale()
scale_params = scale.to_json()
scale2.from_json(scale_params)
> df = scale2.transform(df)
tests/tests_preprocessing/test_scale.py:38:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
supervised/preprocessing/scale.py:40: in transform
X.loc[:, self.columns] = self.scale.transform(X[self.columns])
venv/lib/python3.12/site-packages/sklearn/utils/_set_output.py:313: in wrapped
data_to_wrap = f(self, X, *args, **kwargs)
venv/lib/python3.12/site-packages/sklearn/preprocessing/_data.py:1045: in transform
X = self._validate_data(
venv/lib/python3.12/site-packages/sklearn/base.py:608: in _validate_data
self._check_feature_names(X, reset=reset)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = StandardScaler()
X = col1 col3
0 2.302585 2.397895
1 2.397895 0.000000
2 0.000000 0.693147
3 0.693147 1.098612
4 1.098... 1.386294
5 1.386294 1.609438
6 1.609438 1.791759
7 8.986947 8.987072
8 9.104758 9.104869
9 9.210140 9.210240
def _check_feature_names(self, X, *, reset):
"""Set or check the `feature_names_in_` attribute.
.. versionadded:: 1.0
Parameters
----------
X : {ndarray, dataframe} of shape (n_samples, n_features)
The input samples.
reset : bool
Whether to reset the `feature_names_in_` attribute.
If False, the input will be checked for consistency with
feature names of data provided when reset was last True.
.. note::
It is recommended to call `reset=True` in `fit` and in the first
call to `partial_fit`. All other methods that validate `X`
should set `reset=False`.
"""
if reset:
feature_names_in = _get_feature_names(X)
if feature_names_in is not None:
self.feature_names_in_ = feature_names_in
elif hasattr(self, "feature_names_in_"):
# Delete the attribute when the estimator is fitted on a new dataset
# that has no feature names.
delattr(self, "feature_names_in_")
return
fitted_feature_names = getattr(self, "feature_names_in_", None)
X_feature_names = _get_feature_names(X)
if fitted_feature_names is None and X_feature_names is None:
# no feature names seen in fit and in X
return
if X_feature_names is not None and fitted_feature_names is None:
> warnings.warn(
f"X has feature names, but {self.__class__.__name__} was fitted without"
" feature names"
)
E UserWarning: X has feature names, but StandardScaler was fitted without feature names
venv/lib/python3.12/site-packages/sklearn/base.py:486: UserWarning
=========================== short test summary info ============================
FAILED tests/tests_preprocessing/test_scale.py::ScaleTest::test_fit_log_and_normal
============================== 1 failed in 1.95s ===============================
