Merge pull request #175 from pfizer-opensource/development

Version 0.16.11

meson.build

@@ -1,7 +1,7 @@
 project(
     'scikit-digital-health',
     'c',
-    version: '0.16.10.post1',
+    version: '0.16.11',
     license: 'MIT',
     meson_version: '>=1.1',
 )

src/skdh/io/base.py

@@ -58,9 +58,17 @@ def wrapper_check_input_file(self, **kwargs):
                     return kwargs
 
             # check file size if desired
-            if check_size and not hasattr(self, "_skip_file_size_check"):
-                if pfile.stat().st_size < 1000:
+            if pfile.stat().st_size < 1000:
+                if check_size and not hasattr(self, "_skip_file_size_check"):
                     raise FileSizeError("File is less than 1kb, nothing to read.")
+                elif hasattr(self, "_skip_file_size_check"):
+                    warn(
+                        f"File is less than 1kb, but the file size check has been "
+                        f"skipped, returning empty dictionary: {file}",
+                        UserWarning,
+                    )
+                    return {}
+
 
             return func(self, **kwargs)
 

src/skdh/io/multireader.py

@@ -122,6 +122,7 @@ def __init__(
         fill_value=None,
         gaps_error="raise",
         require_all_keys=True,
+        ignore_file_size_check=True,
     ):
         super().__init__(
             mode=mode,
@@ -130,6 +131,8 @@ def __init__(
             fill_gaps=fill_gaps,
             fill_value=fill_value,
             gaps_error=gaps_error,
+            require_all_keys=require_all_keys,
+            ignore_file_size_check=ignore_file_size_check,
         )
 
         # Set a variable here so that we can ignore file size checking when reading
@@ -148,6 +151,10 @@ def __init__(
         self.rdr = getattr(io, reader)
         self.reader_kw = reader_kw
 
+        # set an attribute if we want to skip file size checks
+        if ignore_file_size_check:
+            self.rdr._skip_file_size_check = True  # just needs to be set to anything
+
         self.resample_to_lowest = resample_to_lowest
 
         self.fill_gaps = fill_gaps
@@ -196,6 +203,12 @@ def handle_combine(self, res):
             res = [
                 v for _, v in res.items()
             ]  # standardize since we dont care about labels
+
+        # drop any empty dictionaries - might occur due to some empty files
+        res = [i for i in res if i]  # "if i" === "if i != {}"
+        # check now that we have any data
+        if not res:
+            raise ValueError("No data found in any of the files.")
 
         # get the last time available
         t_ends = [i["time"][-1] for i in res]
@@ -311,6 +324,12 @@ def handle_concatenation(self, res):
             res = [
                 v for _, v in res.items()
             ]  # standardize since we dont care about labels
+
+        # drop any empty dictionaries - might occur due to some empty files
+        res = [i for i in res if i]  # "if i" === "if i != {}"
+        # check now that we have any data
+        if not res:
+            raise ValueError("No data found in any of the files.")
 
         t0s = [i["time"][0] for i in res]
         # get sorted index