Fix ruff config

Signed-off-by: zethson <[email protected]>

docs/conf.py

@@ -15,8 +15,8 @@
 author = "Lukas Heumos"
 github_repo = "ehrapy"
 
-version = "0.6.0"
-release = "0.6.0"
+version = "0.7.0"
+release = "0.7.0"
 
 extensions = [
     "myst_parser",

ehrapy/__init__.py

@@ -2,7 +2,7 @@
 
 __author__ = "Lukas Heumos"
 __email__ = "[email protected]"
-__version__ = "0.6.0"
+__version__ = "0.7.0"
 
 from ehrapy._settings import EhrapyConfig, ehrapy_settings
 

ehrapy/anndata/anndata_ext.py

@@ -191,7 +191,7 @@ def move_to_obs(adata: AnnData, to_obs: list[str] | str, copy_obs: bool = False)
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> ep.ad.move_to_obs(adata, ['age'], copy_obs=False)
+        >>> ep.ad.move_to_obs(adata, ["age"], copy_obs=False)
     """
     if isinstance(to_obs, str):  # pragma: no cover
         to_obs = [to_obs]
@@ -255,8 +255,8 @@ def delete_from_obs(adata: AnnData, to_delete: list[str]) -> AnnData:
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> ep.ad.move_to_obs(adata, ['age'], copy_obs=True)
-        >>> ep.ad.delete_from_obs(adata, ['age'])
+        >>> ep.ad.move_to_obs(adata, ["age"], copy_obs=True)
+        >>> ep.ad.delete_from_obs(adata, ["age"])
     """
     if isinstance(to_delete, str):  # pragma: no cover
         to_delete = [to_delete]
@@ -287,8 +287,8 @@ def move_to_x(adata: AnnData, to_x: list[str] | str) -> AnnData:
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> ep.ad.move_to_obs(adata, ['age'], copy_obs=False)
-        >>> new_adata = ep.ad.move_to_x(adata, ['age'])
+        >>> ep.ad.move_to_obs(adata, ["age"], copy_obs=False)
+        >>> new_adata = ep.ad.move_to_x(adata, ["age"])
     """
     if isinstance(to_x, str):  # pragma: no cover
         to_x = [to_x]
@@ -807,7 +807,7 @@ def get_obs_df(  # pragma: no cover
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> ages = ep.ad.get_obs_df(adata, keys = ['age'])
+        >>> ages = ep.ad.get_obs_df(adata, keys=["age"])
     """
     return obs_df(adata=adata, keys=keys, obsm_keys=obsm_keys, layer=layer, gene_symbols=features)
 
@@ -833,7 +833,7 @@ def get_var_df(  # pragma: no cover
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> four_patients = ep.ad.get_var_df(adata, keys = ['0', '1', '2', '3'])
+        >>> four_patients = ep.ad.get_var_df(adata, keys=["0", "1", "2", "3"])
     """
     return var_df(adata=adata, keys=keys, varm_keys=varm_keys, layer=layer)
 

ehrapy/data/_datasets.py

@@ -483,7 +483,7 @@ def parkinsons(
 
     Examples:
         >>> import ehrapy as ep
-        >>> adata = ep.dt.parkinsons(columns_obs_only=['name'], encoded=True)
+        >>> adata = ep.dt.parkinsons(columns_obs_only=["name"], encoded=True)
     """
     adata: AnnData = read_csv(
         dataset_path=f"{ehrapy_settings.datasetdir}/parkinsons.csv",
@@ -582,7 +582,7 @@ def parkinson_dataset_with_replicated_acoustic_features(
 
     Examples:
         >>> import ehrapy as ep
-        >>> adata = ep.dt.parkinson_dataset_with_replicated_acoustic_features(columns_obs_only=['ID'], encoded=True)
+        >>> adata = ep.dt.parkinson_dataset_with_replicated_acoustic_features(columns_obs_only=["ID"], encoded=True)
     """
     adata: AnnData = read_csv(
         dataset_path=f"{ehrapy_settings.datasetdir}/parkinson_dataset_with_replicated_acoustic_features.csv",

ehrapy/io/_read.py

@@ -390,7 +390,10 @@ def read_fhir(
         Be aware that most FHIR datasets have nested data that might need to be removed.
         In such cases consider working with DataFrames.
         >>> df = ep.io.read_fhir("/path/to/fhir/resources", return_df=True)
-        >>> df.drop(columns=[col for col in df.columns if any(isinstance(x, (list, dict)) for x in df[col].dropna())], inplace=True)
+        >>> df.drop(
+        ...     columns=[col for col in df.columns if any(isinstance(x, (list, dict)) for x in df[col].dropna())],
+        ...     inplace=True,
+        ... )
         >>> df.drop(columns=df.columns[df.isna().all()], inplace=True)
     """
     _check_columns_only_params(columns_obs_only, columns_x_only)

ehrapy/plot/_missingno_pl_api.py

@@ -50,7 +50,7 @@ def missing_values_matrix(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.data.mimic_2(encoded=True)
-        >>> ep.pl.missing_values_matrix(adata, filter='bottom', max_cols=15, max_percentage=0.999)
+        >>> ep.pl.missing_values_matrix(adata, filter="bottom", max_cols=15, max_percentage=0.999)
 
     Preview:
         .. image:: /_static/docstring_previews/missingno_matrix.png
@@ -128,7 +128,7 @@ def missing_values_barplot(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.data.mimic_2(encoded=True)
-        >>> ep.pl.missing_values_barplot(adata, filter='bottom', max_cols=15, max_percentage=0.999)
+        >>> ep.pl.missing_values_barplot(adata, filter="bottom", max_cols=15, max_percentage=0.999)
 
     Preview:
         .. image:: /_static/docstring_previews/missingno_barplot.png
@@ -210,7 +210,7 @@ def missing_values_heatmap(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.data.mimic_2(encoded=True)
-        >>> ep.pl.missing_values_heatmap(adata, filter='bottom', max_cols=15, max_percentage=0.999)
+        >>> ep.pl.missing_values_heatmap(adata, filter="bottom", max_cols=15, max_percentage=0.999)
 
     Preview:
         .. image:: /_static/docstring_previews/missingno_heatmap.png
@@ -288,7 +288,7 @@ def missing_values_dendrogram(
     Example:
         >>> import ehrapy as ep
         >>> adata = ep.data.mimic_2(encoded=True)
-        >>> ep.pl.missing_values_dendrogram(adata, filter='bottom', max_cols=15, max_percentage=0.999)
+        >>> ep.pl.missing_values_dendrogram(adata, filter="bottom", max_cols=15, max_percentage=0.999)
 
     Preview:
         .. image:: /_static/docstring_previews/missingno_dendrogram.png

ehrapy/plot/_scanpy_pl_api.py

@@ -1076,7 +1076,7 @@ def pca_loadings(
         >>> ep.pp.log_norm(adata, offset=1)
         >>> ep.pp.neighbors(adata)
         >>> ep.pp.pca(adata)
-        >>> ep.pl.pca_loadings(adata, components='1,2,3')
+        >>> ep.pl.pca_loadings(adata, components="1,2,3")
 
     Preview:
         .. image:: /_static/docstring_previews/pca_loadings.png
@@ -1143,7 +1143,7 @@ def pca_overview(adata: AnnData, **params):  # pragma: no cover
         >>> ep.pp.log_norm(adata, offset=1)
         >>> ep.pp.neighbors(adata)
         >>> ep.pp.pca(adata)
-        >>> ep.pl.pca_overview(adata, components='1,2,3', color="service_unit")
+        >>> ep.pl.pca_overview(adata, components="1,2,3", color="service_unit")
 
     Preview:
         .. image:: /_static/docstring_previews/pca_overview_1.png
@@ -1185,7 +1185,9 @@ def tsne(adata, **kwargs) -> Axes | list[Axes] | None:  # pragma: no cover
 
         .. image:: /_static/docstring_previews/tsne_1.png
 
-        >>> ep.pl.tsne(adata, color=["day_icu_intime", "service_unit"], wspace=0.5, title=["Day of ICU admission", "Service unit"])
+        >>> ep.pl.tsne(
+        ...     adata, color=["day_icu_intime", "service_unit"], wspace=0.5, title=["Day of ICU admission", "Service unit"]
+        ... )
 
         .. image:: /_static/docstring_previews/tsne_2.png
 
@@ -1228,7 +1230,9 @@ def umap(adata: AnnData, **kwargs) -> Axes | list[Axes] | None:  # pragma: no co
 
         .. image:: /_static/docstring_previews/umap_1.png
 
-        >>> ep.pl.umap(adata, color=["day_icu_intime", "service_unit"], wspace=0.5, title=["Day of ICU admission", "Service unit"])
+        >>> ep.pl.umap(
+        ...     adata, color=["day_icu_intime", "service_unit"], wspace=0.5, title=["Day of ICU admission", "Service unit"]
+        ... )
 
         .. image:: /_static/docstring_previews/umap_2.png
 
@@ -1265,7 +1269,7 @@ def diffmap(adata, **kwargs) -> Axes | list[Axes] | None:  # pragma: no cover
         >>> ep.pp.log_norm(adata, offset=1)
         >>> ep.pp.neighbors(adata)
         >>> ep.tl.diffmap(adata)
-        >>> ep.pl.diffmap(adata, color='day_icu_intime')
+        >>> ep.pl.diffmap(adata, color="day_icu_intime")
 
     Preview:
         .. image:: /_static/docstring_previews/diffmap.png
@@ -1402,7 +1406,7 @@ def embedding(
         >>> ep.pp.log_norm(adata, offset=1)
         >>> ep.pp.neighbors(adata)
         >>> ep.tl.umap(adata)
-        >>> ep.pl.embedding(adata, 'X_umap', color='icu_exp_flg')
+        >>> ep.pl.embedding(adata, "X_umap", color="icu_exp_flg")
 
     Preview:
         .. image:: /_static/docstring_previews/embedding.png
@@ -1580,10 +1584,10 @@ def dpt_groups_pseudotime(
         >>> adata = ep.dt.mimic_2(encoded=True)
         >>> ep.pp.knn_impute(adata)
         >>> ep.pp.log_norm(adata, offset=1)
-        >>> ep.pp.neighbors(adata, method='gauss')
+        >>> ep.pp.neighbors(adata, method="gauss")
         >>> ep.tl.leiden(adata, resolution=0.5, key_added="leiden_0_5")
         >>> ep.tl.diffmap(adata, n_comps=10)
-        >>> adata.uns['iroot'] = np.flatnonzero(adata.obs['leiden_0_5'] == '0')[0]
+        >>> adata.uns["iroot"] = np.flatnonzero(adata.obs["leiden_0_5"] == "0")[0]
         >>> ep.tl.dpt(adata, n_branchings=3)
         >>> ep.pl.dpt_groups_pseudotime(adata)
 
@@ -1615,10 +1619,10 @@ def dpt_timeseries(
         >>> adata = ep.dt.mimic_2(encoded=True)
         >>> ep.pp.knn_impute(adata)
         >>> ep.pp.log_norm(adata, offset=1)
-        >>> ep.pp.neighbors(adata, method='gauss')
+        >>> ep.pp.neighbors(adata, method="gauss")
         >>> ep.tl.leiden(adata, resolution=0.5, key_added="leiden_0_5")
         >>> ep.tl.diffmap(adata, n_comps=10)
-        >>> adata.uns['iroot'] = np.flatnonzero(adata.obs['leiden_0_5'] == '0')[0]
+        >>> adata.uns["iroot"] = np.flatnonzero(adata.obs["leiden_0_5"] == "0")[0]
         >>> ep.tl.dpt(adata, n_branchings=3)
         >>> ep.pl.dpt_timeseries(adata)
 

ehrapy/plot/_survival_analysis.py

@@ -65,8 +65,18 @@ def ols(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=False)
-        >>> co2_lm_result = ep.tl.ols(adata, var_names=['pco2_first', 'tco2_first'], formula='tco2_first ~ pco2_first', missing="drop").fit()
-        >>> ep.pl.ols(adata, x='pco2_first', y='tco2_first', ols_results=[co2_lm_result], ols_color=['red'], xlabel="PCO2", ylabel="TCO2")
+        >>> co2_lm_result = ep.tl.ols(
+        ...     adata, var_names=["pco2_first", "tco2_first"], formula="tco2_first ~ pco2_first", missing="drop"
+        ... ).fit()
+        >>> ep.pl.ols(
+        ...     adata,
+        ...     x="pco2_first",
+        ...     y="tco2_first",
+        ...     ols_results=[co2_lm_result],
+        ...     ols_color=["red"],
+        ...     xlabel="PCO2",
+        ...     ylabel="TCO2",
+        ... )
 
         .. image:: /_static/docstring_previews/ols_plot_1.png
 
@@ -175,21 +185,23 @@ def kmf(
         # While in KaplanMeierFitter, `event_observed` is True if the the death was observed, False if the event was lost (right-censored).
         # So we need to flip `censor_fl` when pass `censor_fl` to KaplanMeierFitter
 
-        >>> adata[:, ['censor_flg']].X = np.where(adata[:, ['censor_flg']].X == 0, 1, 0)
-        >>> kmf = ep.tl.kmf(adata[:, ['mort_day_censored']].X, adata[:, ['censor_flg']].X)
-        >>> ep.pl.kmf([kmf], color=['r'], xlim=[0, 700], ylim=[0, 1], xlabel="Days", ylabel="Proportion Survived", show=True)
+        >>> adata[:, ["censor_flg"]].X = np.where(adata[:, ["censor_flg"]].X == 0, 1, 0)
+        >>> kmf = ep.tl.kmf(adata[:, ["mort_day_censored"]].X, adata[:, ["censor_flg"]].X)
+        >>> ep.pl.kmf(
+        ...     [kmf], color=["r"], xlim=[0, 700], ylim=[0, 1], xlabel="Days", ylabel="Proportion Survived", show=True
+        ... )
 
         .. image:: /_static/docstring_previews/kmf_plot_1.png
 
-        >>> T = adata[:, ['mort_day_censored']].X
-        >>> E = adata[:, ['censor_flg']].X
-        >>> groups = adata[:, ['service_unit']].X
-        >>> ix1 = (groups == 'FICU')
-        >>> ix2 = (groups == 'MICU')
-        >>> ix3 = (groups == 'SICU')
-        >>> kmf_1 = ep.tl.kmf(T[ix1], E[ix1], label='FICU')
-        >>> kmf_2 = ep.tl.kmf(T[ix2], E[ix2], label='MICU')
-        >>> kmf_3 = ep.tl.kmf(T[ix3], E[ix3], label='SICU')
+        >>> T = adata[:, ["mort_day_censored"]].X
+        >>> E = adata[:, ["censor_flg"]].X
+        >>> groups = adata[:, ["service_unit"]].X
+        >>> ix1 = groups == "FICU"
+        >>> ix2 = groups == "MICU"
+        >>> ix3 = groups == "SICU"
+        >>> kmf_1 = ep.tl.kmf(T[ix1], E[ix1], label="FICU")
+        >>> kmf_2 = ep.tl.kmf(T[ix2], E[ix2], label="MICU")
+        >>> kmf_3 = ep.tl.kmf(T[ix3], E[ix3], label="SICU")
         >>> ep.pl.kmf([kmf_1, kmf_2, kmf_3], ci_show=[False,False,False], color=['k','r', 'g'],
         >>>           xlim=[0, 750], ylim=[0, 1], xlabel="Days", ylabel="Proportion Survived")
 

ehrapy/preprocessing/_encoding.py

@@ -60,7 +60,7 @@ def encode(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2()
-        >>> adata_encoded = ep.pp.encode(adata, autodetect=True, encodings='one_hot_encoding')
+        >>> adata_encoded = ep.pp.encode(adata, autodetect=True, encodings="one_hot_encoding")
 
         >>> # Example using custom encodings per columns:
         >>> import ehrapy as ep

ehrapy/preprocessing/_outliers.py

@@ -37,7 +37,7 @@ def winsorize(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> ep.pp.winsorize(adata, ['bmi'])
+        >>> ep.pp.winsorize(adata, ["bmi"])
     """
     _validate_outlier_input(adata, obs_cols, vars)
 
@@ -88,7 +88,7 @@ def clip_quantile(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=True)
-        >>> ep.pp.clip_quantile(adata, ['bmi'])
+        >>> ep.pp.clip_quantile(adata, ["bmi"])
     """
     obs_cols, vars = _validate_outlier_input(adata, obs_cols, vars)  # type: ignore
 

ehrapy/tools/_sa.py

@@ -43,9 +43,9 @@ def ols(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=False)
-        >>> formula = 'tco2_first ~ pco2_first'
-        >>> var_names = ['tco2_first', 'pco2_first']
-        >>> ols = ep.tl.ols(adata, var_names, formula, missing = 'drop')
+        >>> formula = "tco2_first ~ pco2_first"
+        >>> var_names = ["tco2_first", "pco2_first"]
+        >>> ols = ep.tl.ols(adata, var_names, formula, missing="drop")
     """
     if isinstance(var_names, list):
         data = pd.DataFrame(adata[:, var_names].X, columns=var_names).astype(float)
@@ -85,10 +85,10 @@ def glm(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=False)
-        >>> formula = 'day_28_flg ~ age'
-        >>> var_names = ['day_28_flg', 'age']
-        >>> family = 'Binomial'
-        >>> glm = ep.tl.glm(adata, var_names, formula, family, missing = 'drop', ascontinus = ['age'])
+        >>> formula = "day_28_flg ~ age"
+        >>> var_names = ["day_28_flg", "age"]
+        >>> family = "Binomial"
+        >>> glm = ep.tl.glm(adata, var_names, formula, family, missing="drop", ascontinus=["age"])
     """
     family_dict = {
         "Gaussian": sm.families.Gaussian(),
@@ -149,8 +149,8 @@ def kmf(
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=False)
         >>> # Flip 'censor_fl' because 0 = death and 1 = censored
-        >>> adata[:, ['censor_flg']].X = np.where(adata[:, ['censor_flg']].X == 0, 1, 0)
-        >>> kmf = ep.tl.kmf(adata[:, ['mort_day_censored']].X, adata[:, ['censor_flg']].X)
+        >>> adata[:, ["censor_flg"]].X = np.where(adata[:, ["censor_flg"]].X == 0, 1, 0)
+        >>> kmf = ep.tl.kmf(adata[:, ["mort_day_censored"]].X, adata[:, ["censor_flg"]].X)
     """
     kmf = KaplanMeierFitter()
     if censoring == "None" or "right":
@@ -288,7 +288,7 @@ def cox_ph(adata: AnnData, duration_col: str, event_col: str, entry_col: str = N
         >>> import ehrapy as ep
         >>> adata = ep.dt.mimic_2(encoded=False)
         >>> # Flip 'censor_fl' because 0 = death and 1 = censored
-        >>> adata[:, ['censor_flg']].X = np.where(adata[:, ['censor_flg']].X == 0, 1, 0)
+        >>> adata[:, ["censor_flg"]].X = np.where(adata[:, ["censor_flg"]].X == 0, 1, 0)
         >>> cph = ep.tl.cox_ph(adata, "mort_day_censored", "censor_flg")
     """
     df = anndata_to_df(adata)

ehrapy/tools/_scanpy_tl_api.py

@@ -340,8 +340,8 @@ def embedding_density(
         >>> import ehrapy as ep
         >>> adata = ep.data.mimic_2(encoded=True)
         >>> ep.tl.umap(adata)
-        >>> ep.tl.embedding_density(adata, basis='umap', groupby='phase')
-        >>> ep.pl.embedding_density(adata, basis='umap', key='umap_density_phase', group='G1')
+        >>> ep.tl.embedding_density(adata, basis="umap", groupby="phase")
+        >>> ep.pl.embedding_density(adata, basis="umap", key="umap_density_phase", group="G1")
     """
     sc.tl.embedding_density(adata=adata, basis=basis, groupby=groupby, key_added=key_added, components=components)
 
@@ -477,7 +477,7 @@ def dendrogram(
     Examples:
         >>> import ehrapy as ep
         >>> adata = ep.data.mimic_2(encoded=True)
-        >>> ep.tl.dendrogram(adata, groupby='service_unit')
+        >>> ep.tl.dendrogram(adata, groupby="service_unit")
         >>> ep.pl.dendrogram(adata)
     """
     return sc.tl.dendrogram(

ehrapy/tools/feature_ranking/_rank_features_groups.py

@@ -389,14 +389,21 @@ def rank_features_groups(
          >>> adata = ep.dt.mimic_2(encoded=False)
          >>> # want to move some metadata to the obs field
          >>> ep.anndata.move_to_obs(adata, to_obs=["service_unit", "service_num", "age", "mort_day_censored"])
-         >>> ep.tl.rank_features_groups(adata, "service_unit", field_to_rank="obs", columns_to_rank={"obs_names": ["age", "mort_day_censored"]})
+         >>> ep.tl.rank_features_groups(
+         ...     adata, "service_unit", field_to_rank="obs", columns_to_rank={"obs_names": ["age", "mort_day_censored"]}
+         ... )
          >>> ep.pl.rank_features_groups(adata)
 
          >>> import ehrapy as ep
          >>> adata = ep.dt.mimic_2(encoded=False)
          >>> # want to move some metadata to the obs field
          >>> ep.anndata.move_to_obs(adata, to_obs=["service_unit", "service_num", "age", "mort_day_censored"])
-         >>> ep.tl.rank_features_groups(adata, "service_unit", field_to_rank="layer_and_obs", columns_to_rank={"var_names": ['copd_flg', 'renal_flg'], "obs_names": ["age", "mort_day_censored"]})
+         >>> ep.tl.rank_features_groups(
+         ...     adata,
+         ...     "service_unit",
+         ...     field_to_rank="layer_and_obs",
+         ...     columns_to_rank={"var_names": ["copd_flg", "renal_flg"], "obs_names": ["age", "mort_day_censored"]},
+         ... )
          >>> ep.pl.rank_features_groups(adata)
 
     """