[New Check] Entire column of a table is not NaN

nwbinspector/checks/tables.py

@@ -13,6 +13,7 @@
     is_ascending_series,
     is_dict_in_string,
     is_string_json_loadable,
+    safe_uniform_selection,
 )
 
 
@@ -183,3 +184,19 @@ def check_table_values_for_dict(table: DynamicTable, nelems: int = 200):
                 if is_string_json_loadable(string=string):
                     message += " This string is also JSON loadable, so call `json.loads(...)` on the string to unpack."
                 yield InspectorMessage(message=message)
+
+
+@register_check(importance=Importance.BEST_PRACTICE_SUGGESTION, neurodata_type=DynamicTable)
+def check_col_not_nan(table: DynamicTable, nelems: Optional[int] = 200):
+    """Check if all of the values in a single column of a table are NaN."""
+    for column in table.columns:
+        if not hasattr(column, "data") or isinstance(column, VectorIndex) or isinstance(column.data[0], str):
+            continue
+        if nelems is not None and not all(np.isnan(column[:nelems]).flatten()):
+            continue
+
+        subindex_selection = safe_uniform_selection(length=column.shape[0], nelems=nelems)
+        if all(np.isnan(column[subindex_selection])):
+            yield InspectorMessage(
+                message=f"Column {column.name} has all NaN values. Consider removing it from the table."
+            )

nwbinspector/utils.py

@@ -57,6 +57,13 @@ def is_ascending_series(series: np.ndarray, nelems=None):
     return np.all(np.diff(series[:nelems]) > 0)
 
 
+def safe_uniform_selection(length: int, nelems: Optional[int] = 200) -> slice:
+    """General purpose function for safely generating an evenly spaced slice ."""
+    if nelems is None:
+        return slice(0, None)
+    return slice(0, length, np.ceil(length / nelems).astype(int))
+
+
 def is_dict_in_string(string: str):
     """
     Determine if the string value contains an encoded Python dictionary.

tests/unit_tests/test_tables.py

@@ -17,6 +17,7 @@
     check_column_binary_capability,
     check_single_row,
     check_table_values_for_dict,
+    check_col_not_nan,
 )
 from nwbinspector.utils import get_package_version
 
@@ -237,8 +238,8 @@ def test_check_single_row_ignore_units():
 
 def test_check_single_row_ignore_electrodes():
     table = ElectrodeTable(
-        name="electrodes",  # default name when building through nwbfile
-    )
+        name="electrodes",
+    )  # default name when building through nwbfile
     if get_package_version(name="pynwb") >= version.Version("2.1.0"):
         table.add_row(
             location="unknown",
@@ -291,7 +292,7 @@ def test_check_table_values_for_dict_pass():
     assert check_table_values_for_dict(table=table) is None
 
 
-def test_check_table_values_for_dict():
+def test_check_table_values_for_dict_fail():
     table = DynamicTable(name="test_table", description="")
     table.add_column(name="test_column", description="")
     table.add_row(test_column=str(dict(a=1)))
@@ -308,19 +309,59 @@ def test_check_table_values_for_dict():
     )
 
 
-def test_check_table_values_for_dict_json_case():
+def test_check_table_values_for_dict_json_case_fail():
     table = DynamicTable(name="test_table", description="")
     table.add_column(name="test_column", description="")
     table.add_row(test_column=json.dumps(dict(a=1)))
-    assert check_table_values_for_dict(table=table)[0] == InspectorMessage(
-        message=(
-            "The column 'test_column' contains a string value that contains a dictionary! Please unpack "
-            "dictionaries as additional rows or columns of the table. This string is also JSON loadable, so call "
-            "`json.loads(...)` on the string to unpack."
+    assert check_table_values_for_dict(table=table) == [
+        InspectorMessage(
+            message=(
+                "The column 'test_column' contains a string value that contains a dictionary! Please unpack "
+                "dictionaries as additional rows or columns of the table. This string is also JSON loadable, so call "
+                "`json.loads(...)` on the string to unpack."
+            ),
+            importance=Importance.BEST_PRACTICE_VIOLATION,
+            check_function_name="check_table_values_for_dict",
+            object_type="DynamicTable",
+            object_name="test_table",
+            location="/",
+        )
+    ]
+
+
+def test_check_col_not_nan_pass():
+    table = DynamicTable(name="test_table", description="")
+    for name in ["test_column_not_nan", "test_column_string"]:
+        table.add_column(name=name, description="")
+    table.add_row(test_column_not_nan=1.0, test_column_string="abc")
+    assert check_col_not_nan(table=table) is None
+
+
+def test_check_col_not_nan_fail():
+    table = DynamicTable(name="test_table", description="")
+    for name in ["test_column_not_nan_1", "test_column_nan_1", "test_column_not_nan_2", "test_column_nan_2"]:
+        table.add_column(name=name, description="")
+    for _ in range(400):
+        table.add_row(
+            test_column_not_nan_1=1.0, test_column_nan_1=np.nan, test_column_not_nan_2=1.0, test_column_nan_2=np.nan
+        )
+    assert check_col_not_nan(table=table) == [
+        InspectorMessage(
+            message="Column test_column_nan_1 has all NaN values. Consider removing it from the table.",
+            importance=Importance.BEST_PRACTICE_SUGGESTION,
+            check_function_name="check_col_not_nan",
+            object_type="DynamicTable",
+            object_name="test_table",
+            location="/",
+            file_path=None,
         ),
-        importance=Importance.BEST_PRACTICE_VIOLATION,
-        check_function_name="check_table_values_for_dict",
-        object_type="DynamicTable",
-        object_name="test_table",
-        location="/",
-    )
+        InspectorMessage(
+            message="Column test_column_nan_2 has all NaN values. Consider removing it from the table.",
+            importance=Importance.BEST_PRACTICE_SUGGESTION,
+            check_function_name="check_col_not_nan",
+            object_type="DynamicTable",
+            object_name="test_table",
+            location="/",
+            file_path=None,
+        ),
+    ]