Merge remote-tracking branch 'origin/main'

.github/workflows/build_and_upload_docker_image_yaml_variable.yml

@@ -31,7 +31,7 @@ jobs:
         uses: docker/build-push-action@v5
         with:
           push: true  # Push is a shorthand for --output=type=registry
-          tags: ghcr.io/catalystneuro/neuroconv:yaml_variable
+          tags: ghcr.io/catalystneuro/neuroconv_yaml_variable:latest
           context: .
           file: dockerfiles/neuroconv_latest_yaml_variable
           provenance: false

.pre-commit-config.yaml

@@ -1,19 +1,19 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
     -   id: check-yaml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 
 -   repo: https://github.com/psf/black
-    rev: 24.8.0
+    rev: 24.10.0
     hooks:
     -   id: black
         exclude: ^docs/
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.6.5
+  rev: v0.6.9
   hooks:
   - id: ruff
     args: [ --fix ]

CHANGELOG.md

@@ -7,6 +7,7 @@
 ## Features
 * Using in-house `GenericDataChunkIterator` [PR #1068](https://github.com/catalystneuro/neuroconv/pull/1068)
 * Data interfaces now perform source (argument inputs) validation with the json schema  [PR #1020](https://github.com/catalystneuro/neuroconv/pull/1020)
+* Added `channels_to_skip` to `EDFRecordingInterface` so the user can skip non-neural channels [PR #1110](https://github.com/catalystneuro/neuroconv/pull/1110)
 
 ## Improvements
 * Remove dev test from PR  [PR #1092](https://github.com/catalystneuro/neuroconv/pull/1092)

dockerfiles/neuroconv_latest_yaml_variable

@@ -1,4 +1,5 @@
-FROM ghcr.io/catalystneuro/neuroconv:latest
+# TODO: make this neuroconv:latest once optional installations are working again
+FROM ghcr.io/catalystneuro/neuroconv:dev
 LABEL org.opencontainers.image.source=https://github.com/catalystneuro/neuroconv
 LABEL org.opencontainers.image.description="A docker image for the most recent official release of the NeuroConv package. Modified to take in environment variables for the YAML conversion specification and other command line arguments."
-CMD echo "$NEUROCONV_YAML" > run.yml && python -m neuroconv run.yml --data-folder-path "$NEUROCONV_DATA_PATH" --output-folder-path "$NEUROCONV_OUTPUT_PATH" --overwrite
+CMD printf "$NEUROCONV_YAML" > ./run.yml && neuroconv run.yml --data-folder-path "$NEUROCONV_DATA_PATH" --output-folder-path "$NEUROCONV_OUTPUT_PATH" --overwrite

docs/user_guide/docker_demo.rst

@@ -30,7 +30,7 @@ It relies on some of the GIN data from the main testing suite, see :ref:`example
 
 3. Create a file in this folder named ``demo_neuroconv_docker_yaml.yml`` with the following content...
 
-.. code::
+.. code-block:: yaml
 
     metadata:
       NWBFile:
@@ -102,7 +102,11 @@ It relies on some of the GIN data from the main testing suite, see :ref:`example
 
 .. code::
 
-    docker run -t --volume /home/user/demo_neuroconv_docker:/demo_neuroconv_docker ghcr.io/catalystneuro/neuroconv:latest neuroconv /demo_neuroconv_docker/demo_neuroconv_docker_yaml.yml --output-folder-path /demo_neuroconv_docker/demo_output
+    docker run -t \
+        --volume /home/user/demo_neuroconv_docker:/demo_neuroconv_docker \
+        ghcr.io/catalystneuro/neuroconv:latest \
+        neuroconv /demo_neuroconv_docker/demo_neuroconv_docker_yaml.yml \
+        --output-folder-path /demo_neuroconv_docker/demo_output
 
 Voilà! If everything occurred successfully, you should see...
 
@@ -142,6 +146,10 @@ Then, you can use the following command to run the Rclone Docker image:
 
 .. code::
 
-    docker run -t --volume destination_folder:destination_folder -e RCLONE_CONFIG="$RCLONE_CONFIG" -e RCLONE_COMMAND="$RCLONE_COMMAND" ghcr.io/catalystneuro/rclone_with_config:latest
+    docker run -t \
+        --volume destination_folder:destination_folder \
+        -e RCLONE_CONFIG="$RCLONE_CONFIG" \
+        -e RCLONE_COMMAND="$RCLONE_COMMAND" \
+        ghcr.io/catalystneuro/rclone_with_config:latest
 
 This image is particularly designed for convenience with AWS Batch (EC2) tools that rely heavily on atomic Docker operations. Alternative AWS approaches would have relied on transferring the Rclone configuration file to the EC2 instances using separate transfer protocols or dependent steps, both of which add complexity to the workflow.

src/neuroconv/datainterfaces/ecephys/edf/edfdatainterface.py

@@ -1,3 +1,5 @@
+from typing import Optional
+
 from pydantic import FilePath
 
 from ..baserecordingextractorinterface import BaseRecordingExtractorInterface
@@ -23,7 +25,22 @@ def get_source_schema(cls) -> dict:
         source_schema["properties"]["file_path"]["description"] = "Path to the .edf file."
         return source_schema
 
-    def __init__(self, file_path: FilePath, verbose: bool = True, es_key: str = "ElectricalSeries"):
+    def _source_data_to_extractor_kwargs(self, source_data: dict) -> dict:
+
+        extractor_kwargs = source_data.copy()
+        extractor_kwargs.pop("channels_to_skip")
+        extractor_kwargs["all_annotations"] = True
+        extractor_kwargs["use_names_as_ids"] = True
+
+        return extractor_kwargs
+
+    def __init__(
+        self,
+        file_path: FilePath,
+        verbose: bool = True,
+        es_key: str = "ElectricalSeries",
+        channels_to_skip: Optional[list] = None,
+    ):
         """
         Load and prepare data for EDF.
         Currently, only continuous EDF+ files (EDF+C) and original EDF files (EDF) are supported
@@ -36,15 +53,24 @@ def __init__(self, file_path: FilePath, verbose: bool = True, es_key: str = "Ele
         verbose : bool, default: True
             Allows verbose.
         es_key : str, default: "ElectricalSeries"
+            Key for the ElectricalSeries metadata
+        channels_to_skip : list, default: None
+            Channels to skip when adding the data to the nwbfile. These parameter can be used to skip non-neural
+            channels that are present in the EDF file.
+
         """
         get_package(
             package_name="pyedflib",
-            excluded_platforms_and_python_versions=dict(darwin=dict(arm=["3.8", "3.9"])),
+            excluded_platforms_and_python_versions=dict(darwin=dict(arm=["3.9"])),
         )
 
-        super().__init__(file_path=file_path, verbose=verbose, es_key=es_key)
+        super().__init__(file_path=file_path, verbose=verbose, es_key=es_key, channels_to_skip=channels_to_skip)
         self.edf_header = self.recording_extractor.neo_reader.edf_header
 
+        # We remove the channels that are not neural
+        if channels_to_skip:
+            self.recording_extractor = self.recording_extractor.remove_channels(remove_channel_ids=channels_to_skip)
+
     def extract_nwb_file_metadata(self) -> dict:
         nwbfile_metadata = dict(
             session_start_time=self.edf_header["startdate"],