def test_merge_colors_wrong_dict(self):
with pytest.raises(ValueError):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
colors_x = {"a": "red", "foo": "blue"}
_ = _merge_categorical_series(x, y, colors_old=colors_x, inplace=True)
def test_merge_different_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=[5, 4, 3, 2, 1]).astype(
"category"
)
with pytest.raises(ValueError):
_ = _merge_categorical_series(x, y)
def test_merge_colors_wrong_number_of_colors(self):
with pytest.raises(ValueError):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
colors_x = ["red"]
_ = _merge_categorical_series(x, y, colors_old=colors_x, inplace=True)
def test_merge_normal_run(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
expected = pd.Series(["b", "b", "a", "d", "a"]).astype("category")
res = _merge_categorical_series(x, y, inplace=False)
np.testing.assert_array_equal(res.values, expected.values)
def test_merge_normal_run_completely_different_categories(self):
x = pd.Series(["a", "a", "a"]).astype("category")
y = pd.Series(["b", "b", "b"]).astype("category")
expected = pd.Series(["b", "b", "b"]).astype("category")
res = _merge_categorical_series(x, y, inplace=False)
np.testing.assert_array_equal(res.values, expected.values)
np.testing.assert_array_equal(res.cat.categories.values, ["b"])
def test_merge_normal_run_inplace(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
expected = pd.Series(["b", "b", "a", "d", "a"]).astype("category")
_ = _merge_categorical_series(x, y, inplace=True)
assert _ is None
np.testing.assert_array_equal(x.values, expected.values)
def test_merge_colors_simple_old(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
colors_x = ["red", "blue"]
colors_merged = _merge_categorical_series(
x, y, colors_old=colors_x, inplace=True
)
np.testing.assert_array_equal(colors_merged, ["red", "blue", "#4daf4a"])
def test_merge_colors_simple_new(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
colors_y = ["red", "blue", "green"]
colors_merged = _merge_categorical_series(
x, y, colors_new=colors_y, inplace=True
)
np.testing.assert_array_equal(colors_merged, ["#e41a1c", "#377eb8", "green"])
def test_merge_colors_both(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
colors_x = ["red", "blue"]
colors_y = ["green", "yellow", "black"]
colors_merged = _merge_categorical_series(
x, y, colors_old=colors_x, colors_new=colors_y, inplace=True
)
np.testing.assert_array_equal(colors_merged, ["red", "blue", "black"])
def test_merge_colors_simple_old_no_inplace(self):
x = pd.Series(["a", "b", np.nan, "b", np.nan]).astype("category")
y = pd.Series(["b", np.nan, "a", "d", "a"]).astype("category")
expected = pd.Series(["b", "b", "a", "d", "a"]).astype("category")
colors_x = ["red", "blue"]
merged, colors_merged = _merge_categorical_series(
x, y, colors_old=colors_x, inplace=False
)
np.testing.assert_array_equal(merged.values, expected.values)
np.testing.assert_array_equal(colors_merged, ["red", "blue", "#4daf4a"])
def test_merge_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):
_ = _merge_categorical_series(x, y)
def _set_categorical_labels(
self,
attr_key: str,
pretty_attr_key: str,
cat_key: str,
add_to_existing_error_msg: str,
categories: Union[Series, Dict[Any, Any]],
cluster_key: Optional[str] = None,
en_cutoff: Optional[float] = None,
p_thresh: Optional[float] = None,
add_to_existing: bool = False,
):
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"DEBUG: 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, f"{attr_key}_colors", colors)
categories.cat.categories = approx_rcs_names
else:
setattr(
self,
f"{attr_key}_colors",
_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"DEBUG: Overwriting `.{pretty_attr_key}`")
setattr(self, attr_key, categories)
self._adata.obs[cat_key] = categories.values
self._adata.uns[_colors(cat_key)] = getattr(self, f"{attr_key}_colors")
