def test_knn_imputer_distance_weighted_not_enough_neighbors(
na, working_memory):
X = np.array([[3, na], [2, na], [na, 4], [5, 6], [6, 8], [na, 5]])
dist = pairwise_distances(X,
metric="nan_euclidean",
squared=False,
missing_values=na)
X_01 = np.average(X[3:5, 1], weights=1 / dist[0, 3:5])
X_11 = np.average(X[3:5, 1], weights=1 / dist[1, 3:5])
X_20 = np.average(X[3:5, 0], weights=1 / dist[2, 3:5])
X_50 = np.average(X[3:5, 0], weights=1 / dist[5, 3:5])
X_expected = np.array([[3, X_01], [2, X_11], [X_20, 4], [5, 6], [6, 8],
[X_50, 5]])
with config_context(working_memory=working_memory):
knn_3 = KNNImputer(missing_values=na,
n_neighbors=3,
weights='distance')
assert_allclose(knn_3.fit_transform(X), X_expected)
knn_4 = KNNImputer(missing_values=na,
n_neighbors=4,
weights='distance')
assert_allclose(knn_4.fit_transform(X), X_expected)
def test_config_context_exception():
assert get_config()['assume_finite'] is False
try:
with config_context(assume_finite=True):
assert get_config()['assume_finite'] is True
raise ValueError()
except ValueError:
pass
assert get_config()['assume_finite'] is 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_config_context():
assert get_config() == {
'assume_finite': False,
'working_memory': 1024,
'print_changed_only': False
}
# Not using as a context manager affects nothing
config_context(assume_finite=True)
assert get_config()['assume_finite'] is False
with config_context(assume_finite=True):
assert get_config() == {
'assume_finite': True,
'working_memory': 1024,
'print_changed_only': False
}
assert get_config()['assume_finite'] is False
with config_context(assume_finite=True):
with config_context(assume_finite=None):
assert get_config()['assume_finite'] is True
assert get_config()['assume_finite'] is True
with config_context(assume_finite=False):
assert get_config()['assume_finite'] is False
with config_context(assume_finite=None):
assert get_config()['assume_finite'] is False
# global setting will not be retained outside of context that
# did not modify this setting
set_config(assume_finite=True)
assert get_config()['assume_finite'] is True
assert get_config()['assume_finite'] is False
assert get_config()['assume_finite'] is True
assert get_config() == {
'assume_finite': False,
'working_memory': 1024,
'print_changed_only': False
}
# No positional arguments
assert_raises(TypeError, config_context, True)
# No unknown arguments
assert_raises(TypeError, config_context(do_something_else=True).__enter__)
def test_knn_imputer_with_simple_example(na, working_memory):
X = np.array([[0, na, 0, na], [1, 1, 1, na], [2, 2, na, 2], [3, 3, 3, 3],
[4, 4, 4, 4], [5, 5, 5, 5], [6, 6, 6, 6], [na, 7, 7, 7]])
r0c1 = np.mean(X[1:6, 1])
r0c3 = np.mean(X[2:-1, -1])
r1c3 = np.mean(X[2:-1, -1])
r2c2 = np.mean(X[[0, 1, 3, 4, 5], 2])
r7c0 = np.mean(X[2:-1, 0])
X_imputed = np.array([[0, r0c1, 0, r0c3], [1, 1, 1, r1c3], [2, 2, r2c2, 2],
[3, 3, 3, 3], [4, 4, 4, 4], [5, 5, 5, 5],
[6, 6, 6, 6], [r7c0, 7, 7, 7]])
with config_context(working_memory=working_memory):
imputer_comp = KNNImputer(missing_values=na)
assert_allclose(imputer_comp.fit_transform(X), X_imputed)
def test_get_chunk_n_rows(row_bytes, max_n_rows, working_memory, expected,
warning):
if warning is not None:
def check_warning(*args, **kw):
return assert_warns_message(UserWarning, warning, *args, **kw)
else:
check_warning = assert_no_warnings
actual = check_warning(get_chunk_n_rows,
row_bytes=row_bytes,
max_n_rows=max_n_rows,
working_memory=working_memory)
assert actual == expected
assert type(actual) is type(expected)
with config_context(working_memory=working_memory):
actual = check_warning(get_chunk_n_rows,
row_bytes=row_bytes,
max_n_rows=max_n_rows)
assert actual == expected
assert type(actual) is type(expected)