Merge pull request #14 from AI-sandbox/fix-mspreader-bug

Fix MSPreader bug related to dtype of chromosomes

snputils/ancestry/io/local/read/msp.py

@@ -1,10 +1,9 @@
 from pathlib import Path
-from typing import List, Dict, Optional
+from typing import List, Dict, Optional, Union
 import logging
 import warnings
 import numpy as np
 import pandas as pd
-from typing import Union
 
 from .base import LAIBaseReader
 from snputils.ancestry.genobj.local import LocalAncestryObject
@@ -96,8 +95,15 @@ def _replace_nan_with_none(self, array: Optional[np.ndarray]) -> Optional[np.nda
         Returns:
             Optional[np.ndarray]: Returns `None` if the array is fully NaN, otherwise returns the original array.
         """
-        if array is not None and np.isnan(array).all():
-            return None
+        if array is not None:
+            if array.size == 0:  # Check if the array is empty
+                return None
+            if np.issubdtype(array.dtype, np.number):  # Check for numeric types
+                if np.isnan(array).all():  # Fully NaN numeric array
+                    return None
+            elif array.dtype == np.object_ or np.issubdtype(array.dtype, np.str_):  # String or object types
+                if all(elem == '' or elem is None for elem in array):  # Empty or None strings
+                    return None
         return array
 
     def read(self) -> 'LocalAncestryObject':