lint

apis/python/src/tiledbsoma/io.py

@@ -43,7 +43,7 @@ def _from_h5ad_common(
     experiment: SOMAExperiment,
     input_path: Path,
     measurement_name: str,
-    handler_func: Callable[[SOMAExperiment, ad.AnnData], None],
+    handler_func: Callable[[SOMAExperiment, ad.AnnData, str, tiledb.Ctx], None],
     ctx: Optional[tiledb.Ctx] = None,
 ) -> None:
     """
@@ -64,7 +64,7 @@ def _from_h5ad_common(
         util.format_elapsed(s, f"{experiment._indent}FINISH READING {input_path}"),
     )
 
-    handler_func(experiment, anndata, measurement_name, ctx=ctx)
+    handler_func(experiment, anndata, measurement_name, ctx)
 
     logging.log_io(
         None,
@@ -143,11 +143,14 @@ def from_anndata(
 
     # TODO: more types to check?
     if isinstance(anndata.X, np.ndarray):
-        Xdata = SOMADenseNdArray(uri=f"{measurement.X.get_uri()}/data", ctx=ctx)
+        ddata = SOMADenseNdArray(uri=f"{measurement.X.get_uri()}/data", ctx=ctx)
+        # Code here and in else-block duplicated for linter appeasement
+        ddata.from_matrix(anndata.X)
+        measurement.X.set(ddata)
     else:
-        Xdata = SOMASparseNdArray(uri=f"{measurement.X.get_uri()}/data", ctx=ctx)
-    Xdata.from_matrix(anndata.X)
-    measurement.X.set(Xdata)
+        sdata = SOMASparseNdArray(uri=f"{measurement.X.get_uri()}/data", ctx=ctx)
+        sdata.from_matrix(anndata.X)
+        measurement.X.set(sdata)
 
     # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
     # TODO: port from v0
@@ -163,25 +166,25 @@ def from_anndata(
     if len(anndata.varm.keys()) > 0:  # do not create an empty collection
         measurement.varm.create()
         for key in anndata.varm.keys():
-            arr = SOMADenseNdArray(uri=f"{measurement.varm.get_uri()}/{key}", ctx=ctx)
-            arr.from_matrix(anndata.varm[key])
-            measurement.varm.set(arr)
+            darr = SOMADenseNdArray(uri=f"{measurement.varm.get_uri()}/{key}", ctx=ctx)
+            darr.from_matrix(anndata.varm[key])
+            measurement.varm.set(darr)
         measurement.set(measurement.varm)
 
     if len(anndata.obsp.keys()) > 0:  # do not create an empty collection
         measurement.obsp.create()
         for key in anndata.obsp.keys():
-            arr = SOMASparseNdArray(uri=f"{measurement.obsp.get_uri()}/{key}", ctx=ctx)
-            arr.from_matrix(anndata.obsp[key])
-            measurement.obsp.set(arr)
+            sarr = SOMASparseNdArray(uri=f"{measurement.obsp.get_uri()}/{key}", ctx=ctx)
+            sarr.from_matrix(anndata.obsp[key])
+            measurement.obsp.set(sarr)
         measurement.set(measurement.obsp)
 
     if len(anndata.varp.keys()) > 0:  # do not create an empty collection
         measurement.varp.create()
         for key in anndata.varp.keys():
-            arr = SOMASparseNdArray(uri=f"{measurement.varp.get_uri()}/{key}", ctx=ctx)
-            arr.from_matrix(anndata.varp[key])
-            measurement.varp.set(arr)
+            sarr = SOMASparseNdArray(uri=f"{measurement.varp.get_uri()}/{key}", ctx=ctx)
+            sarr.from_matrix(anndata.varp[key])
+            measurement.varp.set(sarr)
         measurement.set(measurement.varp)
 
     # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

apis/python/src/tiledbsoma/soma_collection.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from typing import Any, Dict, Iterator, List, Optional, Sequence
+from typing import Any, Dict, Iterator, Optional, Sequence
 
 import tiledb
 
@@ -148,7 +148,7 @@ def __repr__(self) -> str:
         """
         return "\n".join(self._repr_aux())
 
-    def _repr_aux(self) -> List[str]:
+    def _repr_aux(self) -> Sequence[str]:
         """
         Internal helper function for ``__repr__`` which is nesting-aware.
         """

apis/python/src/tiledbsoma/soma_dataframe.py

@@ -25,6 +25,7 @@ class SOMADataFrame(TileDBArray):
 
     _shape: Optional[NTuple] = None
     _is_sparse: Optional[bool]
+    _index_column_names: List[str]
 
     def __init__(
         self,
@@ -126,7 +127,7 @@ def __repr__(self) -> str:
         """
         return "\n".join(self._repr_aux())
 
-    def _repr_aux(self) -> List[str]:
+    def _repr_aux(self) -> Sequence[str]:
         if not self.exists():
             return ["Unpopulated"]
         lines = [
@@ -147,7 +148,7 @@ def __getattr__(self, name: str) -> Any:
         elif name == "ndims":
             return self._get_ndims()
 
-    def keys(self) -> List[str]:
+    def keys(self) -> Sequence[str]:
         """
         Returns the names of the columns when read back as a dataframe.  TODO: make it clear whether or not this will read back ``soma_rowid`` / ``soma_joinid``.
         """
@@ -171,7 +172,7 @@ def _get_ndims(self) -> int:
     def get_indexed(self) -> bool:
         return False
 
-    def get_index_column_names(self) -> List[str]:
+    def get_index_column_names(self) -> Sequence[str]:
         return []
 
     def read(

apis/python/src/tiledbsoma/soma_dense_nd_array.py

@@ -106,7 +106,7 @@ def __repr__(self) -> str:
         """
         return "\n".join(self._repr_aux())
 
-    def _repr_aux(self) -> List[str]:
+    def _repr_aux(self) -> Sequence[str]:
         if not self.exists():
             return ["Unpopulated"]
         lines = [

apis/python/src/tiledbsoma/soma_indexed_dataframe.py

@@ -1,4 +1,4 @@
-from typing import Any, Generator, Iterator, List, Optional, Sequence, TypeVar, Union
+from typing import Any, Iterator, List, Optional, Sequence, TypeVar, Union
 
 import numpy as np
 import pandas as pd
@@ -151,7 +151,7 @@ def __repr__(self) -> str:
         """
         return "\n".join(self._repr_aux())
 
-    def _repr_aux(self) -> List[str]:
+    def _repr_aux(self) -> Sequence[str]:
         if not self.exists():
             return ["Unpopulated"]
         lines = [
@@ -172,7 +172,7 @@ def __getattr__(self, name: str) -> Any:
         elif name == "ndims":
             return self._get_ndims()
 
-    def keys(self) -> List[str]:
+    def keys(self) -> Sequence[str]:
         """
         Returns the names of the columns when read back as a dataframe.  TODO: make it clear whether or not this will read back ``soma_rowid`` / ``soma_joinid``.
         """
@@ -196,7 +196,7 @@ def _get_ndims(self) -> int:
     def get_indexed(self) -> bool:
         return False
 
-    def get_index_column_names(self) -> List[str]:
+    def get_index_column_names(self) -> Sequence[str]:
         """
         Return index (dimension) column names.
         """
@@ -337,7 +337,7 @@ def read_as_pandas(
         attrs: Optional[Sequence[str]] = None,
         # to rename index to 'obs_id' or 'var_id', if desired, for anndata
         id_column_name: Optional[str] = None,
-    ) -> Generator:
+    ) -> Iterator[pd.DataFrame]:
         """
         For ``to_anndata``, as well as for any interactive use where the user wants a Pandas dataframe.
         """

apis/python/src/tiledbsoma/soma_metadata_mapping.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Iterator, List
+from typing import Any, Dict, Iterator, Sequence
 
 # importing tiledbsoma.TileDBObject leads to a circular reference as TileDBObject imports us. This
 # is, in turn, because this class requires a back-link to the underlying object -- hence,
@@ -12,7 +12,7 @@ class SOMAMetadataMapping:
     def __init__(self, underlying: "tiledbsoma.TileDBObject"):
         self._underlying = underlying
 
-    def keys(self) -> List[str]:
+    def keys(self) -> Sequence[str]:
         """
         Returns the object's metadata keys as a list.
         """

apis/python/src/tiledbsoma/soma_sparse_nd_array.py

@@ -104,7 +104,7 @@ def __repr__(self) -> str:
         """
         return "\n".join(self._repr_aux())
 
-    def _repr_aux(self) -> List[str]:
+    def _repr_aux(self) -> Sequence[str]:
         if not self.exists():
             return ["Unpopulated"]
         lines = [
@@ -527,7 +527,7 @@ def _ingest_data_cols_chunked(self, matrix: sp.csc_matrix) -> None:
             while j < ncol:
                 t1 = time.time()
                 # Find a number of CSC columns which will result in a desired nnz for the chunk.
-                chunk_size = util.find_csc_chunk_size(
+                chunk_size = util_scipy.find_csc_chunk_size(
                     matrix, j, self._tiledb_platform_config.goal_chunk_nnz
                 )
                 j2 = j + chunk_size

apis/python/src/tiledbsoma/tiledb_object.py

@@ -1,6 +1,6 @@
 import os
 from abc import ABC, abstractmethod
-from typing import Optional, Union
+from typing import Optional, Sequence, Union
 
 import tiledb
 
@@ -66,6 +66,9 @@ def __repr__(self) -> str:
         """
         return f"name={self._name},uri={self._uri}"
 
+    def _repr_aux(self) -> Sequence[str]:
+        raise Exception("Must be overridden by inherting classes.")
+
     def get_name(self) -> str:
         return self._name
 

apis/python/src/tiledbsoma/util_arrow.py

@@ -1,4 +1,4 @@
-from typing import Generator, Optional, Union
+from typing import Any, Iterator, Optional, Union
 
 import numpy as np
 import pyarrow as pa
@@ -17,7 +17,7 @@ def tiledb_type_from_arrow_type(t: pa.DataType) -> Union[type, np.dtype]:
     else:
         # mypy says:
         # Returning Any from function declared to return "type"  [no-any-return]
-        return t.to_pandas_dtype()  # type: ignore
+        return t.to_pandas_dtype()
 
 
 def get_arrow_type_from_tiledb_dtype(tiledb_dtype: np.dtype) -> pa.DataType:
@@ -76,7 +76,7 @@ def ascii_to_unicode_pyarrow_readback(record_batch: pa.RecordBatch) -> pa.Record
     return pa.RecordBatch.from_arrays(new_fields, names=names)
 
 
-def concat_batches(batch_generator: Generator) -> pa.RecordBatch:
+def concat_batches(batch_generator: Iterator[Any]) -> pa.RecordBatch:
     """
     Iterates a generator of ``pyarrow.RecordBatch`` (e.g. ``SOMADataFrame.read``) and returns a concatenation of all the record batches found. The nominal use is to simply unit-test cases.
     """