wip

cellxgene_schema_cli/cellxgene_schema/utils.py

@@ -125,16 +125,6 @@ def read_h5ad(h5ad_path: Union[str, bytes, os.PathLike]) -> ad.AnnData:
     """
     try:
         adata = ad.read_h5ad(h5ad_path, backed="r")
-
-        # This code, and AnnData in general, is optimized for row access.
-        # Running backed, with CSC, is prohibitively slow. Read the entire
-        # AnnData into memory if it is CSC.
-        if (get_matrix_format(adata, adata.X) == "csc") or (
-            (adata.raw is not None) and (get_matrix_format(adata, adata.raw.X) == "csc")
-        ):
-            logger.warning("Matrices are in CSC format; loading entire dataset into memory.")
-            adata = adata.to_memory()
-
     except (OSError, TypeError):
         logger.info(f"Unable to open '{h5ad_path}' with AnnData")
         sys.exit(1)

cellxgene_schema_cli/cellxgene_schema/validate.py

@@ -1069,6 +1069,20 @@ def _validate_uns_dict(self, uns_dict: dict) -> None:
                     self.errors.append(
                         f"Colors in uns[{key}] must be either all hex colors or all CSS4 named colors. Found: {value}"
                     )
+
+    def _validate_X(self):
+        to_validate = [(self.adata.X, "X")]
+
+        # check if there's raw data
+        if self.adata.raw:
+            to_validate.append((self.adata.raw.X, "raw.X"))
+
+        for x, x_name in to_validate:
+            matrix_format = get_matrix_format(self.adata, x)
+            if matrix_format != "csr":
+                self.errors.append(
+                    f"Matrix '{x_name}' is not a 'scipy.sparse.csr_matrix'. Please convert to CSR format."
+                )
 
     def _validate_sparsity(self):
         """
@@ -2055,6 +2069,8 @@ def _deep_check(self):
         logger.debug("Validating sparsity...")
         self._validate_sparsity()
 
+        self._validate_X()
+
         # Checks spatial
         self._check_spatial()