Update ASCII storage for dataframes

Author: johnkerl

apis/python/src/tiledbsc/annotation_dataframe.py

@@ -1,7 +1,6 @@
 from concurrent.futures import ThreadPoolExecutor
 from typing import Optional, Sequence, Set, Tuple, Union
 
-import numpy as np
 import pandas as pd
 import pyarrow as pa
 import tiledb
@@ -74,10 +73,15 @@ def ids(self) -> Sequence[str]:
         Returns the `obs_ids` in the matrix (for `obs`) or the `var_ids` (for `var`).
         """
         with self._open("r") as A:
-            # TileDB string dims are ASCII not UTF-8. Decode them so they readback
-            # not like `b"AKR1C3"` but rather like `"AKR1C3"`.
+            # TileDB string dims are ASCII not UTF-8. Decode them so they readback not like
+            # `b"AKR1C3"` but rather like `"AKR1C3"`. Update as of
+            # https://github.com/TileDB-Inc/TileDB-Py/pull/1304 these dims will read back OK.
             retval = A.query(attrs=[], dims=[self.dim_name])[:][self.dim_name].tolist()
-            return [e.decode() for e in retval]
+            if len(retval) > 0 and isinstance(retval[0], bytes):
+                return [e.decode() for e in retval]
+            else:
+                # list(...) is there to appease the linter which thinks we're returning `Any`
+                return list(retval)
 
     # ----------------------------------------------------------------
     def __repr__(self) -> str:
@@ -377,7 +381,7 @@ def from_dataframe(self, dataframe: pd.DataFrame, extent: int = 2048) -> None:
             dfc = dataframe[column_name]
             if len(dfc) > 0 and type(dfc[0]) == str:
                 # Force ASCII storage if string, in order to make obs/var columns queryable.
-                column_types[column_name] = np.dtype("S")
+                column_types[column_name] = "ascii"
 
         tiledb.from_pandas(
             uri=self.uri,