Exposed block_index to OpenEphys interfaces (#695)

* exposed block_index to all open ephys and added test * Update CHANGELOG.md * Update tests/test_on_data/test_recording_interfaces.py Co-authored-by: Cody Baker <[email protected]> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: Heberto Mayorquin <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
catalystneuro · Dec 19, 2023 · baccf8f · baccf8f
1 parent acd9fb3
commit baccf8f
Show file tree

Hide file tree

Showing 5 changed files with 86 additions and 28 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -13,7 +13,8 @@
 ### Improvements
 * `nwbinspector` has been removed as a minimal dependency. It becomes an extra (optional) dependency with `neuroconv[dandi]`. [PR #672](https://github.com/catalystneuro/neuroconv/pull/672)
 * Added a `from_nwbfile` class method constructor to all `BackendConfiguration` models. [PR #673](https://github.com/catalystneuro/neuroconv/pull/673)
-* Added compression to `FicTracDataInterface` [PR #678](https://github.com/catalystneuro/neuroconv/pull/678)
+* Added compression to `FicTracDataInterface`. [PR #678](https://github.com/catalystneuro/neuroconv/pull/678)
+* Exposed `block_index` to all OpenEphys interfaces. [PR #695](https://github.com/catalystneuro/neuroconv/pull/695)
 
 
 

diff --git a/src/neuroconv/datainterfaces/ecephys/openephys/openephysbinarydatainterface.py b/src/neuroconv/datainterfaces/ecephys/openephys/openephysbinarydatainterface.py
@@ -20,8 +20,11 @@ def _open_with_pyopenephys(folder_path: FolderPathType):
 
 
 class OpenEphysBinaryRecordingInterface(BaseRecordingExtractorInterface):
-    """Primary data interface for converting binary OpenEphys data (.dat files). Uses
-    :py:class:`~spikeinterface.extractors.OpenEphysBinaryRecordingExtractor`."""
+    """
+    Primary data interface for converting binary OpenEphys data (.dat files).
+
+    Uses :py:class:`~spikeinterface.extractors.OpenEphysBinaryRecordingExtractor`.
+    """
 
     ExtractorName = "OpenEphysBinaryRecordingExtractor"
 
@@ -47,6 +50,7 @@ def __init__(
         self,
         folder_path: FolderPathType,
         stream_name: Optional[str] = None,
+        block_index: Optional[int] = None,
         stub_test: bool = False,
         verbose: bool = True,
         es_key: str = "ElectricalSeries",
@@ -61,23 +65,25 @@ def __init__(
         stream_name : str, optional
             The name of the recording stream to load; only required if there is more than one stream detected.
             Call `OpenEphysRecordingInterface.get_stream_names(folder_path=...)` to see what streams are available.
+        block_index : int, optional, default: None
+            The index of the block to extract from the data.
         stub_test : bool, default: False
         verbose : bool, default: True
         es_key : str, default: "ElectricalSeries"
         """
-
         try:
             _open_with_pyopenephys(folder_path=folder_path)
         except Exception as error:
             # Type of error might depend on pyopenephys version and/or platform
             error_case_1 = (
-                type(error) == Exception
+                type(error) is Exception
                 and str(error) == "Only 'binary' and 'openephys' format are supported by pyopenephys"
             )
-            error_case_2 = type(error) == OSError and "Unique settings file not found in" in str(error)
+            error_case_2 = type(error) is OSError and "Unique settings file not found in" in str(error)
             if error_case_1 or error_case_2:  # Raise a more informative error instead.
                 raise ValueError(
-                    "Unable to identify the OpenEphys folder structure! Please check that your `folder_path` contains sub-folders of the "
+                    "Unable to identify the OpenEphys folder structure! "
+                    "Please check that your `folder_path` contains sub-folders of the "
                     "following form: 'experiment<index>' -> 'recording<index>' -> 'continuous'."
                 )
             else:
@@ -86,15 +92,19 @@ def __init__(
         available_streams = self.get_stream_names(folder_path=folder_path)
         if len(available_streams) > 1 and stream_name is None:
             raise ValueError(
-                "More than one stream is detected! Please specify which stream you wish to load with the `stream_name` argument. "
-                "To see what streams are available, call `OpenEphysRecordingInterface.get_stream_names(folder_path=...)`."
+                "More than one stream is detected! "
+                "Please specify which stream you wish to load with the `stream_name` argument. "
+                "To see what streams are available, call "
+                " `OpenEphysRecordingInterface.get_stream_names(folder_path=...)`."
             )
         if stream_name is not None and stream_name not in available_streams:
             raise ValueError(
                 f"The selected stream '{stream_name}' is not in the available streams '{available_streams}'!"
             )
 
-        super().__init__(folder_path=folder_path, stream_name=stream_name, verbose=verbose, es_key=es_key)
+        super().__init__(
+            folder_path=folder_path, stream_name=stream_name, block_index=block_index, verbose=verbose, es_key=es_key
+        )
 
         if stub_test:
             self.subset_channels = [0, 1]

diff --git a/src/neuroconv/datainterfaces/ecephys/openephys/openephysdatainterface.py b/src/neuroconv/datainterfaces/ecephys/openephys/openephysdatainterface.py
@@ -16,11 +16,13 @@ def __new__(
         cls,
         folder_path: FolderPathType,
         stream_name: Optional[str] = None,
+        block_index: Optional[int] = None,
         verbose: bool = True,
         es_key: str = "ElectricalSeries",
     ):
         """
         Abstract class that defines which interface class to use for a given Open Ephys recording.
+
         For "legacy" format (.continuous files) the interface redirects to OpenEphysLegacyRecordingInterface.
         For "binary" format (.dat files) the interface redirects to OpenEphysBinaryRecordingInterface.
 
@@ -32,6 +34,8 @@ def __new__(
             The name of the recording stream.
             When the recording stream is not specified the channel stream is chosen if available.
             When channel stream is not available the name of the stream must be specified.
+        block_index : int, optional, default: None
+            The index of the block to extract from the data.
         verbose : bool, default: True
         es_key : str, default: "ElectricalSeries"
         """
@@ -40,12 +44,20 @@ def __new__(
         folder_path = Path(folder_path)
         if any(folder_path.rglob("*.continuous")):
             return OpenEphysLegacyRecordingInterface(
-                folder_path=folder_path, stream_name=stream_name, verbose=verbose, es_key=es_key
+                folder_path=folder_path,
+                stream_name=stream_name,
+                block_index=block_index,
+                verbose=verbose,
+                es_key=es_key,
             )
 
         elif any(folder_path.rglob("*.dat")):
             return OpenEphysBinaryRecordingInterface(
-                folder_path=folder_path, stream_name=stream_name, verbose=verbose, es_key=es_key
+                folder_path=folder_path,
+                stream_name=stream_name,
+                block_index=block_index,
+                verbose=verbose,
+                es_key=es_key,
             )
 
         else:

diff --git a/src/neuroconv/datainterfaces/ecephys/openephys/openephyslegacydatainterface.py b/src/neuroconv/datainterfaces/ecephys/openephys/openephyslegacydatainterface.py
@@ -7,8 +7,11 @@
 
 
 class OpenEphysLegacyRecordingInterface(BaseRecordingExtractorInterface):
-    """Primary data interface for converting legacy Open Ephys data (.continuous files).
-    Uses :py:class:`~spikeinterface.extractors.OpenEphysLegacyRecordingExtractor`."""
+    """
+    Primary data interface for converting legacy Open Ephys data (.continuous files).
+
+    Uses :py:class:`~spikeinterface.extractors.OpenEphysLegacyRecordingExtractor`.
+    """
 
     @classmethod
     def get_stream_names(cls, folder_path: FolderPathType) -> List[str]:
@@ -31,11 +34,13 @@ def __init__(
         self,
         folder_path: FolderPathType,
         stream_name: Optional[str] = None,
+        block_index: Optional[int] = None,
         verbose: bool = True,
         es_key: str = "ElectricalSeries",
     ):
         """
         Initialize reading of OpenEphys legacy recording (.continuous files).
+
         See :py:class:`~spikeinterface.extractors.OpenEphysLegacyRecordingExtractor` for options.
 
         Parameters
@@ -44,21 +49,27 @@ def __init__(
             Path to OpenEphys directory.
         stream_name : str, optional
             The name of the recording stream.
+        block_index : int, optional, default: None
+            The index of the block to extract from the data.
         verbose : bool, default: True
         es_key : str, default: "ElectricalSeries"
         """
         available_streams = self.get_stream_names(folder_path=folder_path)
         if len(available_streams) > 1 and stream_name is None:
             raise ValueError(
-                "More than one stream is detected! Please specify which stream you wish to load with the `stream_name` argument. "
-                "To see what streams are available, call `OpenEphysRecordingInterface.get_stream_names(folder_path=...)`."
+                "More than one stream is detected! "
+                "Please specify which stream you wish to load with the `stream_name` argument. "
+                "To see what streams are available, call "
+                "`OpenEphysRecordingInterface.get_stream_names(folder_path=...)`."
             )
         if stream_name is not None and stream_name not in available_streams:
             raise ValueError(
                 f"The selected stream '{stream_name}' is not in the available streams '{available_streams}'!"
             )
 
-        super().__init__(folder_path=folder_path, stream_name=stream_name, verbose=verbose, es_key=es_key)
+        super().__init__(
+            folder_path=folder_path, stream_name=stream_name, block_index=block_index, verbose=verbose, es_key=es_key
+        )
 
     def get_metadata(self):
         metadata = super().get_metadata()
@@ -74,7 +85,10 @@ def get_metadata(self):
                 extracted_date, extracted_timestamp = date_created.split(" ")
                 if len(extracted_timestamp) != len("%H%M%S"):
                     warn(
-                        f"The timestamp for starting time from openephys metadata is ambiguous ('{extracted_timestamp}')! Only the date will be auto-populated in metadata. Please update the timestamp manually to record this value with the highest known temporal resolution."
+                        "The timestamp for starting time from openephys metadata is ambiguous "
+                        f"('{extracted_timestamp}')! Only the date will be auto-populated in metadata. "
+                        "Please update the timestamp manually to record this value with the highest known "
+                        "temporal resolution."
                     )
                     session_start_time = datetime.strptime(extracted_date, "%d-%b-%Y")
                 else:

diff --git a/tests/test_on_data/test_recording_interfaces.py b/tests/test_on_data/test_recording_interfaces.py
@@ -211,7 +211,8 @@ def check_extracted_metadata(self, metadata: dict):
         assert len(metadata["Ecephys"]["Device"]) == 1
         assert metadata["Ecephys"]["Device"][0]["name"] == "Neuronexus-32"
         assert metadata["Ecephys"]["Device"][0]["description"] == "The ecephys device for the MEArec recording."
-        # assert len(metadata["Ecephys"]["ElectrodeGroup"]) == 1 # do not test this condition because in the test we are setting a mock probe
+        # assert len(metadata["Ecephys"]["ElectrodeGroup"]) == 1
+        # do not test this condition because in the test we are setting a mock probe
         assert metadata["Ecephys"]["ElectrodeGroup"][0]["device"] == "Neuronexus-32"
         assert metadata["Ecephys"]["ElectricalSeries"]["description"] == (
             '{"angle_tol": 15, "bursting": false, "chunk_duration": 0, "color_noise_floor": 1, '
@@ -341,7 +342,8 @@ def test_folder_structure_assertion(self):
         with self.assertRaisesWith(
             exc_type=ValueError,
             exc_msg=(
-                "Unable to identify the OpenEphys folder structure! Please check that your `folder_path` contains sub-folders of the "
+                "Unable to identify the OpenEphys folder structure! "
+                "Please check that your `folder_path` contains sub-folders of the "
                 "following form: 'experiment<index>' -> 'recording<index>' -> 'continuous'."
             ),
         ):
@@ -354,8 +356,10 @@ def test_stream_name_missing_assertion(self):
         with self.assertRaisesWith(
             exc_type=ValueError,
             exc_msg=(
-                "More than one stream is detected! Please specify which stream you wish to load with the `stream_name` argument. "
-                "To see what streams are available, call `OpenEphysRecordingInterface.get_stream_names(folder_path=...)`."
+                "More than one stream is detected! "
+                "Please specify which stream you wish to load with the `stream_name` argument. "
+                "To see what streams are available, call "
+                " `OpenEphysRecordingInterface.get_stream_names(folder_path=...)`."
             ),
         ):
             OpenEphysBinaryRecordingInterface(
@@ -409,6 +413,23 @@ def check_extracted_metadata(self, metadata: dict):
         assert metadata["NWBFile"]["session_start_time"] == datetime(2020, 11, 24, 15, 46, 56)
 
 
+class TestOpenEphysBinaryRecordingInterfaceWithBlocks_version_0_6_block_1_stream_1(
+    RecordingExtractorInterfaceTestMixin, TestCase
+):
+    """From Issue #695, exposed `block_index` argument and added tests on data that include multiple blocks."""
+
+    data_interface_cls = OpenEphysBinaryRecordingInterface
+    interface_kwargs = dict(
+        folder_path=str(DATA_PATH / "openephysbinary" / "v0.6.x_neuropixels_multiexp_multistream" / "Record Node 101"),
+        stream_name="Record Node 101#NI-DAQmx-103.PXIe-6341",
+        block_index=1,
+    )
+    save_directory = OUTPUT_PATH
+
+    def check_extracted_metadata(self, metadata: dict):
+        assert metadata["NWBFile"]["session_start_time"] == datetime(2022, 5, 3, 10, 52, 24)
+
+
 class TestOpenEphysLegacyRecordingInterface(RecordingExtractorInterfaceTestMixin, TestCase):
     data_interface_cls = OpenEphysLegacyRecordingInterface
     interface_kwargs = dict(folder_path=str(DATA_PATH / "openephys" / "OpenEphys_SampleData_1"))
@@ -438,12 +459,12 @@ class TestOpenEphysRecordingInterfaceRouter(RecordingExtractorInterfaceTestMixin
 class TestSpikeGadgetsRecordingInterface(RecordingExtractorInterfaceTestMixin, TestCase):
     data_interface_cls = SpikeGadgetsRecordingInterface
     interface_kwargs = [
-        dict(file_path=str(DATA_PATH / "spikegadgets" / f"20210225_em8_minirec2_ac.rec")),
-        dict(file_path=str(DATA_PATH / "spikegadgets" / f"20210225_em8_minirec2_ac.rec"), gains=[0.195]),
-        dict(file_path=str(DATA_PATH / "spikegadgets" / f"20210225_em8_minirec2_ac.rec"), gains=[0.385] * 512),
-        dict(file_path=str(DATA_PATH / "spikegadgets" / f"W122_06_09_2019_1_fromSD.rec")),
-        dict(file_path=str(DATA_PATH / "spikegadgets" / f"W122_06_09_2019_1_fromSD.rec"), gains=[0.195]),
-        dict(file_path=str(DATA_PATH / "spikegadgets" / f"W122_06_09_2019_1_fromSD.rec"), gains=[0.385] * 128),
+        dict(file_path=str(DATA_PATH / "spikegadgets" / "20210225_em8_minirec2_ac.rec")),
+        dict(file_path=str(DATA_PATH / "spikegadgets" / "20210225_em8_minirec2_ac.rec"), gains=[0.195]),
+        dict(file_path=str(DATA_PATH / "spikegadgets" / "20210225_em8_minirec2_ac.rec"), gains=[0.385] * 512),
+        dict(file_path=str(DATA_PATH / "spikegadgets" / "W122_06_09_2019_1_fromSD.rec")),
+        dict(file_path=str(DATA_PATH / "spikegadgets" / "W122_06_09_2019_1_fromSD.rec"), gains=[0.195]),
+        dict(file_path=str(DATA_PATH / "spikegadgets" / "W122_06_09_2019_1_fromSD.rec"), gains=[0.385] * 128),
     ]
     save_directory = OUTPUT_PATH