Merge branch 'dev' into document_formatter

Author: CodyCBakerPhD

nwbinspector/__init__.py

@@ -1,11 +1,12 @@
 from .register_checks import available_checks, Importance
 from .nwbinspector import inspect_nwb, inspect_all, load_config
-from .checks.nwbfile_metadata import *
+from .checks.behavior import *
+from .checks.ecephys import *
 from .checks.general import *
+from .checks.image_series import *
 from .checks.nwb_containers import *
-from .checks.time_series import *
-from .checks.tables import *
-from .checks.ecephys import *
+from .checks.nwbfile_metadata import *
 from .checks.ogen import *
-from .checks.image_series import *
-from .checks.behavior import *
+from .checks.ophys import *
+from .checks.tables import *
+from .checks.time_series import *

nwbinspector/checks/ecephys.py

@@ -37,17 +37,21 @@ def check_electrical_series_dims(electrical_series: ElectricalSeries):
     if data_shape and len(data_shape) == 2 and data_shape[1] != len(electrodes.data):
         if data_shape[0] == len(electrodes.data):
             return InspectorMessage(
-                message="The second dimension of data does not match the length of electrodes, "
-                "but instead the first does. Data is oriented incorrectly and should be transposed."
+                message=(
+                    "The second dimension of data does not match the length of electrodes, "
+                    "but instead the first does. Data is oriented incorrectly and should be transposed."
+                )
             )
         return InspectorMessage(
-            message="The second dimension of data does not match the length of electrodes. Your "
-            "data may be transposed."
+            message=(
+                "The second dimension of data does not match the length of electrodes. Your " "data may be transposed."
+            )
         )
 
 
 @register_check(importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=ElectricalSeries)
 def check_electrical_series_reference_electrodes_table(electrical_series: ElectricalSeries):
+    """Check that the 'electrodes' of an ElectricalSeries references the ElectrodesTable."""
     if electrical_series.electrodes.table.name != "electrodes":
         return InspectorMessage(message="electrodes does not  reference an electrodes table.")
 

nwbinspector/checks/icephys.py

@@ -13,7 +13,6 @@ def check_image_series_external_file_valid(image_series: ImageSeries):
     if image_series.external_file is None:
         return
     nwbfile_path = Path(get_nwbfile_path_from_internal_object(obj=image_series))
-    print(nwbfile_path)
     for file_path in image_series.external_file:
         if not Path(file_path).is_absolute() and not (nwbfile_path.parent / file_path).exists():
             yield InspectorMessage(

nwbinspector/checks/image_series.py

@@ -16,11 +16,9 @@ def check_large_dataset_compression(nwb_container: NWBContainer, gb_lower_bound:
     Will only return an inspector warning if the size of the h5py.Dataset is larger than 20 GB.
     """
     for field in getattr(nwb_container, "fields", dict()).values():
-        if (
-            isinstance(field, h5py.Dataset)
-            and field.compression is None
-            and field.size * field.dtype.itemsize > gb_lower_bound * 1e9
-        ):
+        if not isinstance(field, h5py.Dataset):
+            continue
+        if field.compression is None and field.size * field.dtype.itemsize > gb_lower_bound * 1e9:
             return InspectorMessage(
                 severity=Severity.HIGH,
                 message=f"{os.path.split(field.name)[1]} is a large uncompressed dataset! Please enable compression.",
@@ -40,9 +38,10 @@ def check_small_dataset_compression(
     Will only return an inspector warning if the size of the h5py.Dataset is larger than bytes_threshold.
     """
     for field in getattr(nwb_container, "fields", dict()).values():
+        if not isinstance(field, h5py.Dataset):
+            continue
         if (
-            isinstance(field, h5py.Dataset)
-            and field.compression is None
+            field.compression is None
             and mb_lower_bound * 1e6 < field.size * field.dtype.itemsize < gb_upper_bound * 1e9
         ):
             if field.size * field.dtype.itemsize > gb_severity_threshold * 1e9:
@@ -56,28 +55,3 @@ def check_small_dataset_compression(
                     "dataset."
                 ),
             )
-
-
-# TODO: break up extra logic
-# def check_data_uniqueness(ts):
-#     """Check whether data of a timeseries has few unique values and can be stored in a better way."""
-#     uniq = np.unique(ts.data)
-#     if len(uniq) == 1:
-#         error_code = "A101"
-#         print("- %s: '%s' %s data has all values = %s" % (error_code, ts.name, type(ts).__name__, uniq[0]))
-#     elif np.array_equal(uniq, [0.0, 1.0]):
-#         if ts.data.dtype != bool and type(ts) is TimeSeries:
-#             # if a base TimeSeries object has 0/1 data but is not using booleans
-#             # note that this tests only base TimeSeries objects. TimeSeries subclasses may require numeric/int/etc.
-#             error_code = "A101"
-#             print(
-#                 "- %s: '%s' %s data only contains values 0 and 1. Consider changing to type boolean instead of %s"
-#                 % (error_code, ts.name, type(ts).__name__, ts.data.dtype)
-#             )
-#     elif len(uniq) == 2:
-#         print(
-#             "- NOTE: '%s' %s data has only 2 unique values: %s. Consider storing the data as boolean."
-#             % (ts.name, type(ts).__name__, uniq)
-#         )
-#     elif len(uniq) <= 4:
-#         print("- NOTE: '%s' %s data has only unique values %s" % (ts.name, type(ts).__name__, uniq))

nwbinspector/checks/nwb_containers.py

@@ -79,7 +79,6 @@ def check_doi_publications(nwbfile: NWBFile):
 
     if not nwbfile.related_publications:
         return
-
     for publication in nwbfile.related_publications:
         if isinstance(publication, bytes):
             publication = publication.decode()
@@ -100,8 +99,10 @@ def check_subject_age(subject: Subject):
             return InspectorMessage(message="Subject is missing age and date_of_birth.")
     elif not re.fullmatch(duration_regex, subject.age):
         return InspectorMessage(
-            message=f"Subject age, '{subject.age}', does not follow ISO 8601 duration format, e.g. 'P2Y' for 2 years "
-            f"or 'P23W' for 23 weeks."
+            message=(
+                f"Subject age, '{subject.age}', does not follow ISO 8601 duration format, e.g. 'P2Y' for 2 years "
+                "or 'P23W' for 23 weeks."
+            )
         )
 
 
@@ -135,8 +136,10 @@ def check_subject_species_latin_binomial(subject: Subject):
     """Check if the subject species follows latin binomial form."""
     if subject.species and not re.fullmatch(species_regex, subject.species):
         return InspectorMessage(
-            message=f"Subject species '{subject.species}' should be in latin binomial form, e.g. 'Mus musculus' and "
-            f"'Homo sapiens'",
+            message=(
+                f"Subject species '{subject.species}' should be in latin binomial form, e.g. 'Mus musculus' and "
+                "'Homo sapiens'"
+            ),
         )
 
 
@@ -145,6 +148,8 @@ def check_processing_module_name(processing_module: ProcessingModule):
     """Check if the name of a processing module is of a valid modality."""
     if processing_module.name not in PROCESSING_MODULE_CONFIG:
         return InspectorMessage(
-            f"Processing module is named {processing_module.name}. It is recommended to use the "
-            f"schema module names: {', '.join(PROCESSING_MODULE_CONFIG)}"
+            message=(
+                f"Processing module is named {processing_module.name}. It is recommended to use the "
+                f"schema module names: {', '.join(PROCESSING_MODULE_CONFIG)}"
+            )
         )

nwbinspector/checks/nwbfile_metadata.py

@@ -1,5 +1,10 @@
 """Check functions specific to optical electrophysiology neurodata types."""
-from pynwb.ophys import RoiResponseSeries, PlaneSegmentation, OpticalChannel, ImagingPlane
+from pynwb.ophys import (
+    RoiResponseSeries,
+    PlaneSegmentation,
+    OpticalChannel,
+    ImagingPlane,
+)
 
 from hdmf.utils import get_data_shape
 
@@ -19,30 +24,46 @@ def check_roi_response_series_dims(roi_response_series: RoiResponseSeries):
     if data_shape and len(data_shape) == 2 and data_shape[1] != len(rois.data):
         if data_shape[0] == len(rois.data):
             return InspectorMessage(
-                message="The second dimension of data does not match the length of rois, "
-                "but instead the first does. Data is oriented incorrectly and should be transposed."
+                message=(
+                    "The second dimension of data does not match the length of rois, "
+                    "but instead the first does. Data is oriented incorrectly and should be transposed."
+                )
             )
         return InspectorMessage(
             message="The second dimension of data does not match the length of rois. Your data may be transposed."
         )
 
 
-@register_check(importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=RoiResponseSeries)
-def check_roi_response_series_link_to_plane_segmentation(roi_response_series: RoiResponseSeries):
+@register_check(
+    importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=RoiResponseSeries
+)
+def check_roi_response_series_link_to_plane_segmentation(
+    roi_response_series: RoiResponseSeries,
+):
     """Check that each ROI response series links to a plane segmentation."""
     if not isinstance(roi_response_series.rois.table, PlaneSegmentation):
-        return InspectorMessage(message="rois field does not point to a PlaneSegmentation table.")
+        return InspectorMessage(
+            message="rois field does not point to a PlaneSegmentation table."
+        )
 
 
-@register_check(importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=OpticalChannel)
+@register_check(
+    importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=OpticalChannel
+)
 def check_emission_lambda_in_nm(optical_channel: OpticalChannel):
     """Check that emission lambda is in feasible range for unit nanometers."""
     if optical_channel.emission_lambda < MIN_LAMBDA:
-        return InspectorMessage(f"emission lambda of {optical_channel.emission_lambda} should be in units of nm.")
+        return InspectorMessage(
+            f"emission lambda of {optical_channel.emission_lambda} should be in units of nm."
+        )
 
 
-@register_check(importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=ImagingPlane)
+@register_check(
+    importance=Importance.BEST_PRACTICE_VIOLATION, neurodata_type=ImagingPlane
+)
 def check_excitation_lambda_in_nm(imaging_plane: ImagingPlane):
     """Check that emission lambda is in feasible range for unit nanometers."""
     if imaging_plane.excitation_lambda < MIN_LAMBDA:
-        return InspectorMessage(f"excitation lambda of {imaging_plane.excitation_lambda} should be in units of nm.")
+        return InspectorMessage(
+            f"excitation lambda of {imaging_plane.excitation_lambda} should be in units of nm."
+        )