Merge branch 'main' into mg/refactor_load_into_core

NVIDIA · Nov 8, 2024 · c621c92 · c621c92
2 parents d80b3dd + 95028cf
commit c621c92
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 6 deletions.
diff --git a/sub-packages/bionemo-llm/src/bionemo/llm/utils/logger_utils.py b/sub-packages/bionemo-llm/src/bionemo/llm/utils/logger_utils.py
@@ -42,14 +42,14 @@ class WandbConfig(BaseModel):
         anonymous: Enables or explicitly disables anonymous logging.
     """  # noqa: D205
 
-    entity: str  # The team posting this run (default: your username or your default team)
+    entity: str | None  # The team posting this run (default: your username or your default team)
     project: str  # The name of the project to which this run will belong.
     # name: #Display name for the run. "This is handled by NeMoLogger"
     # save_dir: #Path where data is saved. "This is handled by NeMoLogger"
-    tags: List[str]  # Tags associated with this run.
-    group: str  # A unique string shared by all runs in a given group
+    tags: List[str] | None  # Tags associated with this run.
+    group: str | None  # A unique string shared by all runs in a given group
     offline: bool  # Run offline (data can be streamed later to wandb servers).
-    id: str  # Sets the version, mainly used to resume a previous run.
+    id: str | None  # Sets the version, mainly used to resume a previous run.
     anonymous: bool  # Enables or explicitly disables anonymous logging.
     log_model: bool  # Save checkpoints in wandb dir to upload on W&B servers.
 

diff --git a/sub-packages/bionemo-scdl/pyproject.toml b/sub-packages/bionemo-scdl/pyproject.toml
@@ -14,7 +14,7 @@ dependencies = [
     # bionemo sub-packages
     'bionemo-core',
     # external
-    'anndata>=0.10.7',
+    'anndata>=0.11.0',
     'pandas>=2.2.1',
     'pyarrow>=16.0.0',
     'scipy>=1.11.1',

diff --git a/sub-packages/bionemo-scdl/src/bionemo/scdl/io/single_cell_memmap_dataset.py b/sub-packages/bionemo-scdl/src/bionemo/scdl/io/single_cell_memmap_dataset.py
@@ -552,7 +552,7 @@ def paginated_load_h5ad(
         # Read the row indices into a memory map.
         mode = Mode.CREATE_APPEND
         self.row_index = _create_row_memmaps(num_rows, Path(self.data_path), mode, self.dtypes)
-        self.row_index[:] = adata.X.indptr.astype(int)
+        self.row_index[:] = adata.X._indptr.astype(int)
 
         # The data from each column and data chunk of the original anndata file is read in. This is saved into the final
         # location of the memmap file. In this step, it is saved in the binary file format.