def test_fetch_openml_australian_pandas_error_sparse(monkeypatch):
data_id = 292
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
msg = 'Cannot return dataframe with sparse data'
with pytest.raises(ValueError, match=msg):
fetch_openml(data_id=data_id, as_frame=True, cache=False)
def test_convert_arff_data_dataframe_warning_low_memory_pandas(monkeypatch):
pytest.importorskip('pandas')
data_id = 1119
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
msg = 'Could not adhere to working_memory config.'
with pytest.warns(UserWarning, match=msg):
with config_context(working_memory=1e-6):
fetch_openml(data_id=data_id, as_frame=True, cache=False)
def test_fetch_openml_adultcensus_pandas(monkeypatch):
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
# Check because of the numeric row attribute (issue #12329)
data_id = 1119
data_shape = (10, 14)
target_shape = (10, )
frame_shape = (10, 15)
expected_data_categories = 8
expected_data_floats = 6
target_column = 'class'
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert data.shape == data_shape
n_categories = len([dtype for dtype in data.dtypes
if isinstance(dtype, CategoricalDtype)])
n_floats = len([dtype for dtype in data.dtypes if dtype.kind == 'f'])
assert expected_data_categories == n_categories
assert expected_data_floats == n_floats
assert isinstance(target, pd.Series)
assert target.shape == target_shape
assert target.name == target_column
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
def test_fetch_openml_adultcensus_pandas_return_X_y(monkeypatch):
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 1119
data_shape = (10, 14)
target_shape = (10, )
expected_data_categories = 8
expected_data_floats = 6
target_column = 'class'
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
X, y = fetch_openml(data_id=data_id, as_frame=True, cache=False,
return_X_y=True)
assert isinstance(X, pd.DataFrame)
assert X.shape == data_shape
n_categories = len([dtype for dtype in X.dtypes
if isinstance(dtype, CategoricalDtype)])
n_floats = len([dtype for dtype in X.dtypes if dtype.kind == 'f'])
assert expected_data_categories == n_categories
assert expected_data_floats == n_floats
assert isinstance(y, pd.Series)
assert y.shape == target_shape
assert y.name == target_column
def test_fetch_openml_anneal_pandas(monkeypatch):
# classification dataset with numeric and categorical columns
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 2
target_column = 'class'
data_shape = (11, 38)
target_shape = (11,)
frame_shape = (11, 39)
expected_data_categories = 32
expected_data_floats = 6
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True,
target_column=target_column, cache=False)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert data.shape == data_shape
n_categories = len([dtype for dtype in data.dtypes
if isinstance(dtype, CategoricalDtype)])
n_floats = len([dtype for dtype in data.dtypes if dtype.kind == 'f'])
assert expected_data_categories == n_categories
assert expected_data_floats == n_floats
assert isinstance(target, pd.Series)
assert target.shape == target_shape
assert isinstance(target.dtype, CategoricalDtype)
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
def _test_features_list(data_id):
# XXX Test is intended to verify/ensure correct decoding behavior
# Not usable with sparse data or datasets that have columns marked as
# {row_identifier, ignore}
def decode_column(data_bunch, col_idx):
col_name = data_bunch.feature_names[col_idx]
if col_name in data_bunch.categories:
# XXX: This would be faster with np.take, although it does not
# handle missing values fast (also not with mode='wrap')
cat = data_bunch.categories[col_name]
result = [None if is_scalar_nan(idx) else cat[int(idx)]
for idx in data_bunch.data[:, col_idx]]
return np.array(result, dtype='O')
else:
# non-nominal attribute
return data_bunch.data[:, col_idx]
data_bunch = fetch_openml(data_id=data_id, cache=False, target_column=None)
# also obtain decoded arff
data_description = _get_data_description_by_id(data_id, None)
sparse = data_description['format'].lower() == 'sparse_arff'
if sparse is True:
raise ValueError('This test is not intended for sparse data, to keep '
'code relatively simple')
data_arff = _download_data_arff(data_description['file_id'],
sparse, None, False)
data_downloaded = np.array(list(data_arff['data']), dtype='O')
for i in range(len(data_bunch.feature_names)):
# XXX: Test per column, as this makes it easier to avoid problems with
# missing values
np.testing.assert_array_equal(data_downloaded[:, i],
decode_column(data_bunch, i))
def test_fetch_openml_iris_pandas_equal_to_no_frame(monkeypatch):
# as_frame = True returns the same underlying data as as_frame = False
pytest.importorskip('pandas')
data_id = 61
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
frame_bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False)
frame_data = frame_bunch.data
frame_target = frame_bunch.target
norm_bunch = fetch_openml(data_id=data_id, as_frame=False, cache=False)
norm_data = norm_bunch.data
norm_target = norm_bunch.target
assert_allclose(norm_data, frame_data)
assert_array_equal(norm_target, frame_target)
def test_fetch_openml_titanic_pandas(monkeypatch):
# dataset with strings
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 40945
data_shape = (1309, 13)
target_shape = (1309, )
frame_shape = (1309, 14)
name_to_dtype = {
'pclass': np.float64,
'name': object,
'sex': CategoricalDtype(['female', 'male']),
'age': np.float64,
'sibsp': np.float64,
'parch': np.float64,
'ticket': object,
'fare': np.float64,
'cabin': object,
'embarked': CategoricalDtype(['C', 'Q', 'S']),
'boat': object,
'body': np.float64,
'home.dest': object,
'survived': CategoricalDtype(['0', '1'])
}
frame_columns = ['pclass', 'survived', 'name', 'sex', 'age', 'sibsp',
'parch', 'ticket', 'fare', 'cabin', 'embarked',
'boat', 'body', 'home.dest']
frame_dtypes = [name_to_dtype[col] for col in frame_columns]
feature_names = ['pclass', 'name', 'sex', 'age', 'sibsp',
'parch', 'ticket', 'fare', 'cabin', 'embarked',
'boat', 'body', 'home.dest']
target_name = 'survived'
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert data.shape == data_shape
assert np.all(data.columns == feature_names)
assert bunch.target_names == [target_name]
assert isinstance(target, pd.Series)
assert target.shape == target_shape
assert target.name == target_name
assert target.dtype == name_to_dtype[target_name]
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
assert np.all(frame.dtypes == frame_dtypes)
def test_fetch_openml_notarget(monkeypatch, gzip_response):
data_id = 61
target_column = None
expected_observations = 150
expected_features = 5
_monkey_patch_webbased_functions(monkeypatch, data_id, gzip_response)
data = fetch_openml(data_id=data_id, target_column=target_column,
cache=False)
assert data.data.shape == (expected_observations, expected_features)
assert data.target is None
def test_fetch_openml_cache(monkeypatch, gzip_response, tmpdir):
def _mock_urlopen_raise(request):
raise ValueError('This mechanism intends to test correct cache'
'handling. As such, urlopen should never be '
'accessed. URL: %s' % request.get_full_url())
data_id = 2
cache_directory = str(tmpdir.mkdir('scikit_learn_data'))
_monkey_patch_webbased_functions(
monkeypatch, data_id, gzip_response)
X_fetched, y_fetched = fetch_openml(data_id=data_id, cache=True,
data_home=cache_directory,
return_X_y=True)
monkeypatch.setattr(sklearn_lib.datasets._openml, 'urlopen',
_mock_urlopen_raise)
X_cached, y_cached = fetch_openml(data_id=data_id, cache=True,
data_home=cache_directory,
return_X_y=True)
np.testing.assert_array_equal(X_fetched, X_cached)
np.testing.assert_array_equal(y_fetched, y_cached)
def test_fetch_openml_cpu_pandas(monkeypatch):
# regression dataset with numeric and categorical columns
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 561
data_shape = (209, 7)
target_shape = (209, )
frame_shape = (209, 8)
cat_dtype = CategoricalDtype(['adviser', 'amdahl', 'apollo', 'basf',
'bti', 'burroughs', 'c.r.d', 'cdc',
'cambex', 'dec', 'dg', 'formation',
'four-phase', 'gould', 'hp', 'harris',
'honeywell', 'ibm', 'ipl', 'magnuson',
'microdata', 'nas', 'ncr', 'nixdorf',
'perkin-elmer', 'prime', 'siemens',
'sperry', 'sratus', 'wang'])
data_dtypes = [cat_dtype] + [np.float64] * 6
feature_names = ['vendor', 'MYCT', 'MMIN', 'MMAX', 'CACH',
'CHMIN', 'CHMAX']
target_name = 'class'
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert data.shape == data_shape
assert np.all(data.dtypes == data_dtypes)
assert np.all(data.columns == feature_names)
assert np.all(bunch.feature_names == feature_names)
assert bunch.target_names == [target_name]
assert isinstance(target, pd.Series)
assert target.shape == target_shape
assert target.dtype == np.float64
assert target.name == target_name
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
def test_fetch_openml_iris_multitarget_pandas(monkeypatch):
# classification dataset with numeric only columns
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 61
data_shape = (150, 3)
target_shape = (150, 2)
frame_shape = (150, 5)
target_column = ['petalwidth', 'petallength']
cat_dtype = CategoricalDtype(['Iris-setosa', 'Iris-versicolor',
'Iris-virginica'])
data_dtypes = [np.float64, np.float64] + [cat_dtype]
data_names = ['sepallength', 'sepalwidth', 'class']
target_dtypes = [np.float64, np.float64]
target_names = ['petalwidth', 'petallength']
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False,
target_column=target_column)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert np.all(data.dtypes == data_dtypes)
assert data.shape == data_shape
assert np.all(data.columns == data_names)
assert np.all(bunch.feature_names == data_names)
assert bunch.target_names == target_names
assert isinstance(target, pd.DataFrame)
assert np.all(target.dtypes == target_dtypes)
assert target.shape == target_shape
assert np.all(target.columns == target_names)
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
assert np.all(frame.dtypes == [np.float64] * 4 + [cat_dtype])
def test_fetch_openml_miceprotein_pandas(monkeypatch):
# JvR: very important check, as this dataset defined several row ids
# and ignore attributes. Note that data_features json has 82 attributes,
# and row id (1), ignore attributes (3) have been removed.
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 40966
data_shape = (7, 77)
target_shape = (7, )
frame_shape = (7, 78)
target_column = 'class'
frame_n_categories = 1
frame_n_floats = 77
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert data.shape == data_shape
assert np.all(data.dtypes == np.float64)
assert isinstance(target, pd.Series)
assert isinstance(target.dtype, CategoricalDtype)
assert target.shape == target_shape
assert target.name == target_column
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
n_categories = len([dtype for dtype in frame.dtypes
if isinstance(dtype, CategoricalDtype)])
n_floats = len([dtype for dtype in frame.dtypes if dtype.kind == 'f'])
assert frame_n_categories == n_categories
assert frame_n_floats == n_floats
def test_fetch_openml_emotions_pandas(monkeypatch):
# classification dataset with multiple targets (natively)
pd = pytest.importorskip('pandas')
CategoricalDtype = pd.api.types.CategoricalDtype
data_id = 40589
target_column = ['amazed.suprised', 'happy.pleased', 'relaxing.calm',
'quiet.still', 'sad.lonely', 'angry.aggresive']
data_shape = (13, 72)
target_shape = (13, 6)
frame_shape = (13, 78)
expected_frame_categories = 6
expected_frame_floats = 72
_monkey_patch_webbased_functions(monkeypatch, data_id, True)
bunch = fetch_openml(data_id=data_id, as_frame=True, cache=False,
target_column=target_column)
data = bunch.data
target = bunch.target
frame = bunch.frame
assert isinstance(data, pd.DataFrame)
assert data.shape == data_shape
assert isinstance(target, pd.DataFrame)
assert target.shape == target_shape
assert np.all(target.columns == target_column)
assert isinstance(frame, pd.DataFrame)
assert frame.shape == frame_shape
n_categories = len([dtype for dtype in frame.dtypes
if isinstance(dtype, CategoricalDtype)])
n_floats = len([dtype for dtype in frame.dtypes if dtype.kind == 'f'])
assert expected_frame_categories == n_categories
assert expected_frame_floats == n_floats
def _fetch_dataset_from_openml(data_id, data_name, data_version,
target_column,
expected_observations, expected_features,
expected_missing,
expected_data_dtype, expected_target_dtype,
expect_sparse, compare_default_target):
# fetches a dataset in three various ways from OpenML, using the
# fetch_openml function, and does various checks on the validity of the
# result. Note that this function can be mocked (by invoking
# _monkey_patch_webbased_functions before invoking this function)
data_by_name_id = fetch_openml(name=data_name, version=data_version,
cache=False)
assert int(data_by_name_id.details['id']) == data_id
# Please note that cache=False is crucial, as the monkey patched files are
# not consistent with reality
fetch_openml(name=data_name, cache=False)
# without specifying the version, there is no guarantee that the data id
# will be the same
# fetch with dataset id
data_by_id = fetch_openml(data_id=data_id, cache=False,
target_column=target_column)
assert data_by_id.details['name'] == data_name
assert data_by_id.data.shape == (expected_observations, expected_features)
if isinstance(target_column, str):
# single target, so target is vector
assert data_by_id.target.shape == (expected_observations, )
assert data_by_id.target_names == [target_column]
elif isinstance(target_column, list):
# multi target, so target is array
assert data_by_id.target.shape == (expected_observations,
len(target_column))
assert data_by_id.target_names == target_column
assert data_by_id.data.dtype == np.float64
assert data_by_id.target.dtype == expected_target_dtype
assert len(data_by_id.feature_names) == expected_features
for feature in data_by_id.feature_names:
assert isinstance(feature, str)
# TODO: pass in a list of expected nominal features
for feature, categories in data_by_id.categories.items():
feature_idx = data_by_id.feature_names.index(feature)
values = np.unique(data_by_id.data[:, feature_idx])
values = values[np.isfinite(values)]
assert set(values) <= set(range(len(categories)))
if compare_default_target:
# check whether the data by id and data by id target are equal
data_by_id_default = fetch_openml(data_id=data_id, cache=False)
if data_by_id.data.dtype == np.float64:
np.testing.assert_allclose(data_by_id.data,
data_by_id_default.data)
else:
assert np.array_equal(data_by_id.data, data_by_id_default.data)
if data_by_id.target.dtype == np.float64:
np.testing.assert_allclose(data_by_id.target,
data_by_id_default.target)
else:
assert np.array_equal(data_by_id.target, data_by_id_default.target)
if expect_sparse:
assert isinstance(data_by_id.data, scipy.sparse.csr_matrix)
else:
assert isinstance(data_by_id.data, np.ndarray)
# np.isnan doesn't work on CSR matrix
assert (np.count_nonzero(np.isnan(data_by_id.data)) ==
expected_missing)
# test return_X_y option
fetch_func = partial(fetch_openml, data_id=data_id, cache=False,
target_column=target_column)
check_return_X_y(data_by_id, fetch_func)
return data_by_id
