def test_mapping_colors_invalid_colors(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", "bar", "baz"], dtype="category")
with pytest.raises(ValueError):
_map_names_and_colors(
reference, query, colors_reference=["red", "green", "foo"]
)
def test_mapping_colors_different_index(self):
query = pd.Series(["foo", "bar", "baz"],
dtype="category",
index=[2, 3, 4])
reference = pd.Series(["foo", "bar", "baz"],
dtype="category",
index=[1, 2, 3])
with pytest.raises(ValueError):
_map_names_and_colors(reference, query)
def test_simple_wrong_index(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, np.nan, "d", "a"],
index=["foo", "bar", "baz", "quux", "quas"])
with pytest.raises(TypeError):
_ = _map_names_and_colors(x, y)
def test_mapping_colors_empty(self):
query = pd.Series([], dtype="category")
reference = pd.Series([], dtype="category")
r = _map_names_and_colors(reference, query)
assert isinstance(r, pd.Series)
assert is_categorical_dtype(r)
def test_mapping_colors_simple_2(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", "bar", "baz"], dtype="category")
res = _map_names_and_colors(reference, query)
assert isinstance(res, pd.Series)
assert len(res) == 3
assert is_categorical_dtype(res)
def test_mapping_colors_merging(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, np.nan, "d", "a"]).astype("category")
res, colors = _map_names_and_colors(x, y, colors_reference=["red", "green"])
assert isinstance(res, pd.Series)
assert isinstance(colors, list)
np.testing.assert_array_equal(colors, ["#b20000", "#e65c00", "#008000"])
def test_mapping_colors_empty_with_color(self):
query = pd.Series([], dtype="category")
reference = pd.Series([], dtype="category")
r, c = _map_names_and_colors(reference, query, colors_reference=[])
assert isinstance(r, pd.Series)
assert is_categorical_dtype(r)
assert isinstance(c, list)
assert len(c) == 0
def test_mapping_colors_0_en_cutoff(self):
query = pd.Series(["bar", "bar", "bar"], dtype="category")
reference = pd.Series(["bar", "bar", "bar"], dtype="category")
# TODO: somehow extract the custom logger and check for logs
r = _map_names_and_colors(reference, query, en_cutoff=0)
assert isinstance(r, pd.Series)
assert is_categorical_dtype(r)
assert list(r.index) == ["bar"]
assert list(r.values) == ["bar"]
def test_mapping_colors_diff_query_reference(self):
query = pd.Series(["bar", "bar", "bar"], dtype="category")
reference = pd.Series(["foo", "foo", "foo"], dtype="category")
r, c = _map_names_and_colors(
reference, query, colors_reference=["red", "red", "red"]
)
assert list(r.index) == ["bar"]
assert list(r.values) == ["foo"]
assert c == ["#ff0000"]
def test_mapping_colors_same_reference(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", "foo", "foo"], dtype="category")
r, c = _map_names_and_colors(
reference, query, colors_reference=["red", "red", "red"]
)
assert list(r.index) == ["bar", "baz", "foo"]
assert list(r.values) == ["foo_1", "foo_2", "foo_3"]
assert c == ["#b20000", "#d13200", "#f07300"]
def test_more_colors_than_reference_categories(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, np.nan, "d", "a"]).astype("category")
res, colors = _map_names_and_colors(
x, y, colors_reference=["red", "green", "blue", "yellow"])
assert isinstance(res, pd.Series)
assert isinstance(colors, list)
np.testing.assert_array_equal(colors,
["#bb2200", "#ee6655", "#008000"])
def test_simple_run(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, np.nan, "d", "a"]).astype("category")
expected = pd.Series(["a_1", "a_2", "b"])
expected_index = pd.Index(["a", "b", "d"])
res = _map_names_and_colors(x, y)
assert isinstance(res, pd.Series)
np.testing.assert_array_equal(res.values, expected.values)
np.testing.assert_array_equal(res.index.values, expected_index.values)
def test_mapping_colors_simple_colors(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", "bar", "baz"], dtype="category")
res, c = _map_names_and_colors(
reference, query, colors_reference=["red", "green", "blue"])
assert isinstance(res, pd.Series)
assert len(res) == 3
assert is_categorical_dtype(res)
assert isinstance(c, list)
assert c == ["#ff0000", "#008000", "#0000ff"]
def test_mapping_colors_name_order_same_as_cat_order(self):
x = pd.Series(["b", "a", np.nan, "a", np.nan]).astype("category")
y = pd.Series(["a", np.nan, np.nan, "d", "b"]).astype("category")
expected = pd.Series(["b", "a_1", "a_2"])
expected_index = pd.Index(["a", "b", "d"])
res = _map_names_and_colors(x, y)
assert isinstance(res, pd.Series)
assert is_categorical_dtype(res)
np.testing.assert_array_equal(res.values, expected.values)
np.testing.assert_array_equal(res.index.values, expected_index.values)
np.testing.assert_array_equal(res.cat.categories.values, res.values)
def test_mapping_colors_different_color_representation(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", "bar", "baz"], dtype="category")
res, c = _map_names_and_colors(
reference, query, colors_reference=[(1, 0, 0), "green", (0, 0, 1, 0)]
)
assert isinstance(res, pd.Series)
assert len(res) == 3
assert is_categorical_dtype(res)
assert isinstance(c, list)
assert c == ["#ff0000", "#008000", "#0000ff"]
def test_simple_not_invalid_color_length(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, np.nan, "d", "a"]).astype("category")
with pytest.raises(ValueError):
_ = _map_names_and_colors(x, y, colors_reference=["red"])
def _set_categorical_labels(
self,
attr_key: str,
color_key: str,
pretty_attr_key: str,
categories: Union[Series, Dict[Any, Any]],
add_to_existing_error_msg: Optional[str] = None,
cluster_key: Optional[str] = None,
en_cutoff: Optional[float] = None,
p_thresh: Optional[float] = None,
add_to_existing: bool = False,
) -> None:
if isinstance(categories, dict):
categories = _convert_to_categorical_series(
categories, list(self.adata.obs_names)
)
if not is_categorical_dtype(categories):
raise TypeError(
f"Object must be `categorical`, found `{infer_dtype(categories)}`."
)
if add_to_existing:
if getattr(self, attr_key) is None:
raise RuntimeError(add_to_existing_error_msg)
categories = _merge_categorical_series(
getattr(self, attr_key), categories, inplace=False
)
if cluster_key is not None:
logg.debug(f"Creating colors based on `{cluster_key}`")
# check that we can load the reference series from adata
if cluster_key not in self.adata.obs:
raise KeyError(
f"Cluster key `{cluster_key!r}` not found in `adata.obs`."
)
series_query, series_reference = categories, self.adata.obs[cluster_key]
# load the reference colors if they exist
if _colors(cluster_key) in self.adata.uns.keys():
colors_reference = _convert_to_hex_colors(
self.adata.uns[_colors(cluster_key)]
)
else:
colors_reference = _create_categorical_colors(
len(series_reference.cat.categories)
)
approx_rcs_names, colors = _map_names_and_colors(
series_reference=series_reference,
series_query=series_query,
colors_reference=colors_reference,
en_cutoff=en_cutoff,
)
setattr(self, color_key, colors)
# if approx_rcs_names is categorical, the info is take from .cat.categories
categories.cat.categories = approx_rcs_names
else:
setattr(
self,
color_key,
_create_categorical_colors(len(categories.cat.categories)),
)
if p_thresh is not None:
self._detect_cc_stages(categories, p_thresh=p_thresh)
# write to class and adata
if getattr(self, attr_key) is not None:
logg.debug(f"Overwriting `.{pretty_attr_key}`")
setattr(self, attr_key, categories)
def test_simple_not_categorical(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, np.nan, "d", "a"])
with pytest.raises(TypeError):
_ = _map_names_and_colors(x, y)
def test_mapping_colors_negative_en_cutoff(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", "bar", "baz"], dtype="category")
with pytest.raises(ValueError):
_map_names_and_colors(reference, query, en_cutoff=-1)
def test_mapping_colors_invalid_size(self):
query = pd.Series(["foo", "bar", "baz"], dtype="category")
reference = pd.Series(["foo", np.nan, "bar", "baz"], dtype="category")
with pytest.raises(ValueError):
_map_names_and_colors(reference, query)
def test_mapping_colors_not_categorical(self):
query = pd.Series(["foo", "bar", "baz"], dtype="str")
reference = pd.Series(["foo", np.nan, "bar", "baz"], dtype="category")
with pytest.raises(TypeError):
_map_names_and_colors(reference, query)
