Merge pull request #21 from klarman-cell-observatory/boli

Updated
lilab-bcb · Jun 9, 2020 · 83e034b · 83e034b
2 parents 6a16ef5 + 8d31f23
commit 83e034b
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 3 deletions.
diff --git a/pegasusio/aggr_data.py b/pegasusio/aggr_data.py
@@ -25,7 +25,17 @@ def _get_fillna_dict(self, df: pd.DataFrame) -> dict:
         """ Generate a fillna dict for columns in a df """
         fillna_dict = {}
         for column in df:
-            fillna_dict[column] = "" if df[column].dtype.kind in {"O", "S"} else 0
+            if df[column].dtype.kind == "b":
+                fillna_dict[column] = False
+            elif df[column].dtpye.kind in {"i", "u", "f", "c"}:
+                fillna_dict[column] = 0
+            elif df[column].dtype.kind == "S":
+                fillna_dict[column] = b""
+            elif df[column].dtype.kind in {"O", "U"}:
+                fillna_dict[column] = ""
+            else:
+                raise ValueError(f"{column} has unsupported dtype {df[column].dtype}!")
+
         return fillna_dict
 
 

diff --git a/pegasusio/readwrite.py b/pegasusio/readwrite.py
@@ -93,7 +93,7 @@ def read_input(
     black_list: Set[str] = None,
     select_data: Set[str] = None,
     select_genome: Set[str] = None,
-    select_modality: Set[str] = None, 
+    select_modality: Set[str] = None,
 ) -> MultimodalData:
     """Load data into memory.
 
@@ -164,7 +164,7 @@ def read_input(
 
     data.subset_data(select_data, select_genome, select_modality)
     data.kick_start()
-    data.scan_black_list(black_list)    
+    data.scan_black_list(black_list)
 
     logger.info(f"{file_type} file '{input_file}' is loaded.")