[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

dance/atlas/sc_similarity/anndata_similarity.py

@@ -231,10 +231,7 @@ def compute_mmd_alternative(self) -> float:
     def compute_mmd(self) -> float:
         """Compute Maximum Mean Discrepancy between datasets.
 
-        Returns
-        -------
-        float
-            Normalized MMD similarity score between 0 and 1
+        Returns ------- float     Normalized MMD similarity score between 0 and 1
 
         """
         X = self.X
@@ -276,10 +273,8 @@ def data_company(self):
     def wasserstein_dist(self) -> float:
         """Compute Wasserstein distance between datasets.
 
-        Returns
-        -------
-        float
-            Normalized Wasserstein similarity score between 0 and 1
+        Returns ------- float     Normalized Wasserstein similarity score between 0 and
+        1
 
         """
         X = self.X
@@ -359,10 +354,7 @@ def get_dataset_meta_sim(self):
         """Compute metadata similarity between datasets based on discrete and continuous
         features.
 
-        Returns
-        -------
-        float
-            Average similarity score across all metadata features
+        Returns ------- float     Average similarity score across all metadata features
 
         """
         # dis_cols=['assay', 'cell_type', 'development_stage','disease','is_primary_data','self_reported_ethnicity','sex', 'suspension_type', 'tissue','tissue_type', 'tissue_general']

dance/data/base.py

@@ -204,34 +204,30 @@ def y(self):
     def config(self) -> Dict[str, Any]:
         """Return the dance data object configuration dict.
 
-        Notes
-        -----
-        The configuration dictionary is saved in the ``data`` attribute, which is an :class:`~anndata.AnnData`
-        object. Inparticular, the config will be saved in the ``.uns`` attribute with the key ``"dance_config"``.
+        Notes ----- The configuration dictionary is saved in the ``data`` attribute,
+        which is an :class:`~anndata.AnnData` object. Inparticular, the config will be
+        saved in the ``.uns`` attribute with the key ``"dance_config"``.
 
         """
         return self._data.uns["dance_config"]
 
     def set_config(self, *, overwrite: bool = False, **kwargs):
         """Set dance data object configuration.
 
-        See
-        :meth: `~BaseData.set_config_from_dict`.
+        See :meth: `~BaseData.set_config_from_dict`.
 
         """
         self.set_config_from_dict(kwargs, overwrite=overwrite)
 
     def set_config_from_dict(self, config_dict: Dict[str, Any], *, overwrite: bool = False):
         """Set dance data object configuration from a config dict.
 
-        Parameters
-        ----------
-        config_dict
-            Configuration dictionary.
-        overwrite
-            Used to determine the behaviour of resolving config conflicts. In the case of a conflict, where the config
-            dict passed contains a key with value that differs from an existing setting, if ``overwrite`` is set to
-            ``False``, then raise a ``KeyError``. Otherwise, overwrite the configuration with the new values.
+        Parameters ---------- config_dict     Configuration dictionary. overwrite
+        Used to determine the behaviour of resolving config conflicts. In the case of a
+        conflict, where the config     dict passed contains a key with value that
+        differs from an existing setting, if ``overwrite`` is set to     ``False``, then
+        raise a ``KeyError``. Otherwise, overwrite the configuration with the new
+        values.
 
         """
         # Check config key validity
@@ -304,29 +300,20 @@ def copy(self):
     def set_split_idx(self, split_name: str, split_idx: Sequence[int]):
         """Set cell indices for a particular split.
 
-        Parameters
-        ----------
-        split_name
-            Name of the split to set.
-        split_idx
-            Indices to be used in this split.
+        Parameters ---------- split_name     Name of the split to set. split_idx
+        Indices to be used in this split.
 
         """
         self._split_idx_dict[split_name] = split_idx
 
     def get_split_idx(self, split_name: str, error_on_miss: bool = False):
         """Obtain cell indices for a particular split.
 
-        Parameters
-        ----------
-        split_name
-            Name of the split to retrieve.
-        error_on_miss
-            If set to True, raise KeyError if the queried split does not exit, otherwise return None.
+        Parameters ---------- split_name     Name of the split to retrieve.
+        error_on_miss     If set to True, raise KeyError if the queried split does not
+        exit, otherwise return None.
 
-        See Also
-        --------
-        :meth:`~get_split_mask`
+        See Also -------- :meth:`~get_split_mask`
 
         """
         if split_name is None:
@@ -341,12 +328,8 @@ def get_split_idx(self, split_name: str, error_on_miss: bool = False):
     def get_split_mask(self, split_name: str, return_type: FeatType = "numpy") -> Union[np.ndarray, torch.Tensor]:
         """Obtain mask representation of a particular split.
 
-        Parameters
-        ----------
-        split_name
-            Name of the split to retrieve.
-        return_type
-            Return numpy array if set to 'numpy', or torch Tensor if set to 'torch'.
+        Parameters ---------- split_name     Name of the split to retrieve. return_type
+        Return numpy array if set to 'numpy', or torch Tensor if set to 'torch'.
 
         """
         split_idx = self.get_split_idx(split_name, error_on_miss=True)
@@ -362,10 +345,7 @@ def get_split_mask(self, split_name: str, return_type: FeatType = "numpy") -> Un
     def get_split_data(self, split_name: str) -> Union[anndata.AnnData, mudata.MuData]:
         """Obtain the underlying data of a particular split.
 
-        Parameters
-        ----------
-        split_name
-            Name of the split to retrieve.
+        Parameters ---------- split_name     Name of the split to retrieve.
 
         """
         split_idx = self.get_split_idx(split_name, error_on_miss=True)
@@ -417,24 +397,20 @@ def get_feature(self, *, split_name: Optional[str] = None, return_type: FeatType
                     mod: Optional[str] = None):  # yapf: disable
         """Retrieve features from data.
 
-        Parameters
-        ----------
-        split_name
-            Name of the split to retrieve. If not set, return all.
-        return_type
-            How should the features be returned. **sparse**: return as a sparse matrix; **numpy**: return as a numpy
-            array; **torch**: return as a torch tensor; **anndata**: return as an anndata object.
-        channel
-            Return a particular channel as features. If ``channel_type`` is ``X`` or ``raw_X``, then return ``.X`` or
-            the ``.raw.X`` attribute from the :class:`~anndata.AnnData` directly. If ``channel_type`` is ``obs``, return
-            the column named by ``channel``, similarly for ``var``. Finally, if ``channel_type`` is ``obsm``, ``obsp``,
-            ``varm``, ``varp``, ``layers``, or ``uns``, then return the value correspond to the ``channel`` in the
-            dictionary.
-        channel_type
-            Channel type to use, default to ``obsm`` (will be changed to ``X`` in the near future).
-        mod
-            Modality to use, default to ``None``. Options other than ``None`` are only available when the underlying
-            data object is :class:`~mudata.Mudata`.
+        Parameters ---------- split_name     Name of the split to retrieve. If not set,
+        return all. return_type     How should the features be returned. **sparse**:
+        return as a sparse matrix; **numpy**: return as a numpy     array; **torch**:
+        return as a torch tensor; **anndata**: return as an anndata object. channel
+        Return a particular channel as features. If ``channel_type`` is ``X`` or
+        ``raw_X``, then return ``.X`` or     the ``.raw.X`` attribute from the
+        :class:`~anndata.AnnData` directly. If ``channel_type`` is ``obs``, return
+        the column named by ``channel``, similarly for ``var``. Finally, if
+        ``channel_type`` is ``obsm``, ``obsp``,     ``varm``, ``varp``, ``layers``, or
+        ``uns``, then return the value correspond to the ``channel`` in the
+        dictionary. channel_type     Channel type to use, default to ``obsm`` (will be
+        changed to ``X`` in the near future). mod     Modality to use, default to
+        ``None``. Options other than ``None`` are only available when the underlying
+        data object is :class:`~mudata.Mudata`.
 
         """
         feature = self._get_feature(self.data, channel, channel_type, mod)
@@ -486,27 +462,22 @@ def append(
     ):
         """Append another dance data object to the current data object.
 
-        Parameters
-        ----------
-        data
-            New dance data object to be added.
-        mode
-            How to combine the splits from the new data and the current data. (1) ``"merge"``: merge the splits from
-            the data, e.g., the training indexes from both data are used as the training indexes in the new combined
-            data. (2) ``"rename"``: rename the splits of the new data and add to the current split index dictionary,
-            e.g., renaming 'train' to 'ref'. Requires passing the ``rename_dict``. Raise an error if the newly renamed
-            key is already used in the current split index dictionary. (3) ``"new_split"``: assign the whole new data
-            to a new split. Requires pssing the ``new_split_name`` that is not already used as a split name in the
-            current data. (4) ``None``: do not specify split index to the newly added data.
-        rename_dict
-            Optional argument that is only used when ``mode="rename"``. A dictionary to map the split names in the new
-            data to other names.
-        new_split_name
-            Optional argument that is only used when ``mode="new_split"``. Name of the split to assign to the new data.
-        label_batch
-            Add "batch" column to ``.obs`` when set to True.
-        **concat_kwargs
-            See :meth:`anndata.concat`.
+        Parameters ---------- data     New dance data object to be added. mode     How
+        to combine the splits from the new data and the current data. (1) ``"merge"``:
+        merge the splits from     the data, e.g., the training indexes from both data
+        are used as the training indexes in the new combined     data. (2) ``"rename"``:
+        rename the splits of the new data and add to the current split index dictionary,
+        e.g., renaming 'train' to 'ref'. Requires passing the ``rename_dict``. Raise an
+        error if the newly renamed     key is already used in the current split index
+        dictionary. (3) ``"new_split"``: assign the whole new data     to a new split.
+        Requires pssing the ``new_split_name`` that is not already used as a split name
+        in the     current data. (4) ``None``: do not specify split index to the newly
+        added data. rename_dict     Optional argument that is only used when
+        ``mode="rename"``. A dictionary to map the split names in the new     data to
+        other names. new_split_name     Optional argument that is only used when
+        ``mode="new_split"``. Name of the split to assign to the new data. label_batch
+        Add "batch" column to ``.obs`` when set to True. **concat_kwargs     See
+        :meth:`anndata.concat`.
 
         """
         offset = self.shape[0]
@@ -580,29 +551,21 @@ def pop(self, *, split_name: str):
     def filter_cells(self, **kwargs):
         """Apply cell filtering using scanpy.pp.filter_cells and update splits.
 
-        Filters the cells in `self.data` based on the provided criteria,
-        similar to `scanpy.pp.filter_cells`. Crucially, this method also
-        updates the internal split indices (`train_idx`, `val_idx`, etc.)
-        to reflect the cells remaining after filtering.
+        Filters the cells in `self.data` based on the provided criteria, similar to
+        `scanpy.pp.filter_cells`. Crucially, this method also updates the internal split
+        indices (`train_idx`, `val_idx`, etc.) to reflect the cells remaining after
+        filtering.
 
-        Parameters
-        ----------
-        **kwargs
-            Arguments passed directly to `scanpy.pp.filter_cells`.
-            Common arguments include `min_counts`, `max_counts`,
-            `min_genes`, `max_genes`. Note: `inplace` is forced to `False`
-            internally to get the filter mask, then applied effectively inplace.
+        Parameters ---------- **kwargs     Arguments passed directly to
+        `scanpy.pp.filter_cells`.     Common arguments include `min_counts`,
+        `max_counts`,     `min_genes`, `max_genes`. Note: `inplace` is forced to `False`
+        internally to get the filter mask, then applied effectively inplace.
 
-        Returns
-        -------
-        self
-            Returns the instance to allow method chaining.
+        Returns ------- self     Returns the instance to allow method chaining.
 
-        Raises
-        ------
-        NotImplementedError
-            If the underlying `self.data` is not an `anndata.AnnData` object.
-            Filtering `MuData` requires more careful consideration of modalities.
+        Raises ------ NotImplementedError     If the underlying `self.data` is not an
+        `anndata.AnnData` object.     Filtering `MuData` requires more careful
+        consideration of modalities.
 
         """
         if not isinstance(self.data, anndata.AnnData):
@@ -856,13 +819,10 @@ def get_data(
     ) -> Tuple[Any, Any]:
         """Retrieve cell features and labels from a particular split.
 
-        Parameters
-        ----------
-        split_name
-            Name of the split to retrieve. If not set, return all.
-        return_type
-            How should the features be returned. **numpy**: return as a numpy array; **torch**: return as a torch
-            tensor; **anndata**: return as an anndata object.
+        Parameters ---------- split_name     Name of the split to retrieve. If not set,
+        return all. return_type     How should the features be returned. **numpy**:
+        return as a numpy array; **torch**: return as a torch     tensor; **anndata**:
+        return as an anndata object.
 
         """
         x = self.get_x(split_name, return_type, **x_kwargs)

dance/datasets/base.py

@@ -15,12 +15,8 @@
 class BaseDataset(ABC):
     """BaseDataset abstract object.
 
-    Parameters
-    ----------
-    root
-        Root directory of the dataset.
-    full_download
-        If set to ``True``, then attempt to download all raw files of the dataset.
+    Parameters ---------- root     Root directory of the dataset. full_download     If
+    set to ``True``, then attempt to download all raw files of the dataset.
 
     """
 

dance/datasets/singlemodality.py

@@ -375,16 +375,10 @@ def _load_dfs(paths: List[str], *, index_col: Optional[int] = 0, transpose: bool
     def get_map_dict(map_file_path: str, tissue: str) -> Dict[str, Set[str]]:
         """Load cell-type mappings.
 
-        Parameters
-        ----------
-        map_file_path
-            Path to the mapping file.
-        tissue
-            Tissue of interest.
+        Parameters ---------- map_file_path     Path to the mapping file. tissue
+        Tissue of interest.
 
-        Notes
-        -----
-        Merge mapping across all test sets for the required tissue.
+        Notes ----- Merge mapping across all test sets for the required tissue.
 
         """
         map_df = pd.read_excel(osp.join(map_file_path, "map.xlsx"))
@@ -399,12 +393,9 @@ def get_map_dict(map_file_path: str, tissue: str) -> Dict[str, Set[str]]:
 class ClusteringDataset(BaseDataset):
     """Data downloading and loading for clustering.
 
-    Parameters
-    ----------
-    data_dir
-        Path to store datasets.
-    dataset
-        Choice of dataset. Available options are '10X_PBMC', 'mouse_bladder_cell', 'mouse_ES_cell', 'worm_neuron_cell'.
+    Parameters ---------- data_dir     Path to store datasets. dataset     Choice of
+    dataset. Available options are '10X_PBMC', 'mouse_bladder_cell', 'mouse_ES_cell',
+    'worm_neuron_cell'.
 
     """
 

dance/datasets/spatial.py

@@ -161,11 +161,9 @@ def _raw_to_dance(self, raw_data):
 class CellTypeDeconvoDataset(BaseDataset):
     """Load raw data.
 
-    Parameters
-    ----------
-    subset_common_celltypes
-        If set to True, then subset both the reference and the real data to contain only cell types that are
-        present in both reference and real.
+    Parameters ---------- subset_common_celltypes     If set to True, then subset both
+    the reference and the real data to contain only cell types that are     present in
+    both reference and real.
 
     """
 

dance/models/nn/gnn.py

@@ -18,18 +18,18 @@ class AdaptiveSAGE(nn.Module):
     Parameters
     ----------
     dim_in
-        Input feature dimensions.
+    Input feature dimensions.
     dim_out
-        output feature dimensions.
+    output feature dimensions.
     alpha
-        Shared learnable parameters containing gene-cell interaction strengths and those for the cell and gene
-        self-loops.
+    Shared learnable parameters containing gene-cell interaction strengths and those for the cell and gene
+    self-loops.
     dropout_layer
-        Dropout layer.
+    Dropout layer.
     act_layer
-        Activation layer.
+    Activation layer.
     norm_layer
-        Normalization layer.
+    Normalization layer.
 
     Note
     ----
@@ -62,10 +62,11 @@ def __init__(
     def message_func(self, edges):
         """Message update function.
 
-        Reweight messages based on 1) the shared learnable interaction strengths and 2) the underlying edgeweights of
-        the graph. In particular, for 1), gene-cell interaction (undirectional) will be weighted by the gene specific
-        ``beta`` value, and the cell and gene self-interactions will be weighted based on the corresponding ``alpha``
-        values.
+        Reweight messages based on 1) the shared learnable interaction strengths and 2)
+        the underlying edgeweights of the graph. In particular, for 1), gene-cell
+        interaction (undirectional) will be weighted by the gene specific ``beta``
+        value, and the cell and gene self-interactions will be weighted based on the
+        corresponding ``alpha`` values.
 
         """
         number_of_edges = edges.src["h"].shape[0]