diff --git a/CHANGELOG.md b/CHANGELOG.md index 63c16c386..b644e3491 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -29,15 +29,16 @@ ## Improvements * Use mixing tests for ecephy's mocks [PR #1136](https://github.com/catalystneuro/neuroconv/pull/1136) * Use pytest format for dandi tests to avoid window permission error on teardown [PR #1151](https://github.com/catalystneuro/neuroconv/pull/1151) +* Added many docstrings for public functions [PR #1063](https://github.com/catalystneuro/neuroconv/pull/1063) # v0.6.5 (November 1, 2024) -## Deprecations - ## Bug Fixes * Fixed formatwise installation from pipy [PR #1118](https://github.com/catalystneuro/neuroconv/pull/1118) * Fixed dailies [PR #1113](https://github.com/catalystneuro/neuroconv/pull/1113) +## Deprecations + ## 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) diff --git a/pyproject.toml b/pyproject.toml index a4f391512..e318cc9c1 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -356,7 +356,7 @@ doctest_optionflags = "ELLIPSIS" [tool.black] line-length = 120 -target-version = ['py38', 'py39', 'py310'] +target-version = ['py39', 'py310'] include = '\.pyi?$' extend-exclude = ''' /( diff --git a/src/neuroconv/basedatainterface.py b/src/neuroconv/basedatainterface.py index 530eec60c..d9e9dc11e 100644 --- a/src/neuroconv/basedatainterface.py +++ b/src/neuroconv/basedatainterface.py @@ -36,7 +36,14 @@ class BaseDataInterface(ABC): @classmethod def get_source_schema(cls) -> dict: - """Infer the JSON schema for the source_data from the method signature (annotation typing).""" + """ + Infer the JSON schema for the source_data from the method signature (annotation typing). + + Returns + ------- + dict + The JSON schema for the source_data. + """ return get_json_schema_from_method_signature(cls, exclude=["source_data"]) @classmethod diff --git a/src/neuroconv/datainterfaces/behavior/lightningpose/lightningposeconverter.py b/src/neuroconv/datainterfaces/behavior/lightningpose/lightningposeconverter.py index 505aa144d..62edaf140 100644 --- a/src/neuroconv/datainterfaces/behavior/lightningpose/lightningposeconverter.py +++ b/src/neuroconv/datainterfaces/behavior/lightningpose/lightningposeconverter.py @@ -111,6 +111,28 @@ def add_to_nwbfile( starting_frames_labeled_videos: Optional[list[int]] = None, stub_test: bool = False, ): + """ + Add behavior and pose estimation data, including original and labeled videos, to the specified NWBFile. + + Parameters + ---------- + nwbfile : NWBFile + The NWBFile object to which the data will be added. + metadata : dict + Metadata dictionary containing information about the behavior and videos. + reference_frame : str, optional + Description of the reference frame for pose estimation, by default None. + confidence_definition : str, optional + Definition for the confidence levels in pose estimation, by default None. + external_mode : bool, optional + If True, the videos will be referenced externally rather than embedded within the NWB file, by default True. + starting_frames_original_videos : list of int, optional + List of starting frames for the original videos, by default None. + starting_frames_labeled_videos : list of int, optional + List of starting frames for the labeled videos, by default None. + stub_test : bool, optional + If True, only a subset of the data will be added for testing purposes, by default False. + """ original_video_interface = self.data_interface_objects["OriginalVideo"] original_video_metadata = next( @@ -172,6 +194,33 @@ def run_conversion( starting_frames_labeled_videos: Optional[list] = None, stub_test: bool = False, ) -> None: + """ + Run the full conversion process, adding behavior, video, and pose estimation data to an NWB file. + + Parameters + ---------- + nwbfile_path : FilePath, optional + The file path where the NWB file will be saved. If None, the file is handled in memory. + nwbfile : NWBFile, optional + An in-memory NWBFile object. If None, a new NWBFile object will be created. + metadata : dict, optional + Metadata dictionary for describing the NWB file contents. If None, it is auto-generated. + overwrite : bool, optional + If True, overwrites the NWB file at `nwbfile_path` if it exists. If False, appends to the file, by default False. + reference_frame : str, optional + Description of the reference frame for pose estimation, by default None. + confidence_definition : str, optional + Definition for confidence levels in pose estimation, by default None. + external_mode : bool, optional + If True, the videos will be referenced externally rather than embedded within the NWB file, by default True. + starting_frames_original_videos : list of int, optional + List of starting frames for the original videos, by default None. + starting_frames_labeled_videos : list of int, optional + List of starting frames for the labeled videos, by default None. + stub_test : bool, optional + If True, only a subset of the data will be added for testing purposes, by default False. + + """ if metadata is None: metadata = self.get_metadata() diff --git a/src/neuroconv/datainterfaces/behavior/medpc/medpcdatainterface.py b/src/neuroconv/datainterfaces/behavior/medpc/medpcdatainterface.py index 09f9111d7..d519dc71a 100644 --- a/src/neuroconv/datainterfaces/behavior/medpc/medpcdatainterface.py +++ b/src/neuroconv/datainterfaces/behavior/medpc/medpcdatainterface.py @@ -187,6 +187,7 @@ def add_to_nwbfile( nwbfile: NWBFile, metadata: dict, ) -> None: + ndx_events = get_package(package_name="ndx_events", installation_instructions="pip install ndx-events") medpc_name_to_info_dict = metadata["MedPC"].get("medpc_name_to_info_dict", None) assert medpc_name_to_info_dict is not None, "medpc_name_to_info_dict must be provided in metadata" diff --git a/src/neuroconv/datainterfaces/ecephys/basesortingextractorinterface.py b/src/neuroconv/datainterfaces/ecephys/basesortingextractorinterface.py index dca2dea5f..8eeb59324 100644 --- a/src/neuroconv/datainterfaces/ecephys/basesortingextractorinterface.py +++ b/src/neuroconv/datainterfaces/ecephys/basesortingextractorinterface.py @@ -220,6 +220,19 @@ def set_aligned_segment_starting_times(self, aligned_segment_starting_times: lis sorting_segment._t_start = aligned_segment_starting_time def subset_sorting(self): + """ + Generate a subset of the sorting extractor based on spike timing data. + + This method identifies the earliest spike time across all units in the sorting extractor and creates a + subset of the sorting data up to 110% of the earliest spike time. If the sorting extractor is associated + with a recording, the subset is further limited by the total number of samples in the recording. + + Returns + ------- + SortingExtractor + A new `SortingExtractor` object representing the subset of the original sorting data, + sliced from the start frame to the calculated end frame. + """ max_min_spike_time = max( [ min(x) diff --git a/src/neuroconv/datainterfaces/ecephys/cellexplorer/cellexplorerdatainterface.py b/src/neuroconv/datainterfaces/ecephys/cellexplorer/cellexplorerdatainterface.py index 46e825fb5..9ffeb78a2 100644 --- a/src/neuroconv/datainterfaces/ecephys/cellexplorer/cellexplorerdatainterface.py +++ b/src/neuroconv/datainterfaces/ecephys/cellexplorer/cellexplorerdatainterface.py @@ -518,6 +518,33 @@ def __init__(self, file_path: FilePath, verbose: bool = True): ) def generate_recording_with_channel_metadata(self): + """ + Generate a dummy recording extractor with channel metadata from session data. + + This method reads session data from a `.session.mat` file (if available) and generates a dummy recording + extractor. The recording extractor is then populated with channel metadata extracted from the session file. + + Returns + ------- + NumpyRecording + A `NumpyRecording` object representing the dummy recording extractor, containing the channel metadata. + + Notes + ----- + - The method reads the `.session.mat` file using `pymatreader` and extracts `extracellular` data. + - It creates a dummy recording extractor using `spikeinterface.core.numpyextractors.NumpyRecording`. + - The generated extractor includes channel IDs and other relevant metadata such as number of channels, + number of samples, and sampling frequency. + - Channel metadata is added to the dummy extractor using the `add_channel_metadata_to_recoder` function. + - If the `.session.mat` file is not found, no extractor is returned. + + Warnings + -------- + Ensure that the `.session.mat` file is correctly located in the expected session path, or the method will not generate + a recording extractor. The expected session is self.session_path / f"{self.session_id}.session.mat" + + """ + session_data_file_path = self.session_path / f"{self.session_id}.session.mat" if session_data_file_path.is_file(): from pymatreader import read_mat diff --git a/src/neuroconv/datainterfaces/ophys/baseimagingextractorinterface.py b/src/neuroconv/datainterfaces/ophys/baseimagingextractorinterface.py index 0019b8bd7..04407a3d4 100644 --- a/src/neuroconv/datainterfaces/ophys/baseimagingextractorinterface.py +++ b/src/neuroconv/datainterfaces/ophys/baseimagingextractorinterface.py @@ -47,6 +47,17 @@ def __init__( def get_metadata_schema( self, ) -> dict: + """ + Retrieve the metadata schema for the optical physiology (Ophys) data, with optional handling of photon series type. + + Parameters + ---------- + photon_series_type : {"OnePhotonSeries", "TwoPhotonSeries"}, optional + The type of photon series to include in the schema. If None, the value from the instance is used. + This argument is deprecated and will be removed in a future version. Set `photon_series_type` during + the initialization of the `BaseImagingExtractorInterface` instance. + + """ metadata_schema = super().get_metadata_schema() @@ -93,6 +104,16 @@ def get_metadata_schema( def get_metadata( self, ) -> DeepDict: + """ + Retrieve the metadata for the imaging data, with optional handling of photon series type. + + Parameters + ---------- + photon_series_type : {"OnePhotonSeries", "TwoPhotonSeries"}, optional + The type of photon series to include in the metadata. If None, the value from the instance is used. + This argument is deprecated and will be removed in a future version. Instead, set `photon_series_type` + during the initialization of the `BaseImagingExtractorInterface` instance. + """ from ...tools.roiextractors import get_nwb_imaging_metadata diff --git a/src/neuroconv/datainterfaces/ophys/basesegmentationextractorinterface.py b/src/neuroconv/datainterfaces/ophys/basesegmentationextractorinterface.py index 0f2e41bb9..66d35f57a 100644 --- a/src/neuroconv/datainterfaces/ophys/basesegmentationextractorinterface.py +++ b/src/neuroconv/datainterfaces/ophys/basesegmentationextractorinterface.py @@ -24,6 +24,27 @@ def __init__(self, verbose: bool = False, **source_data): self.segmentation_extractor = self.get_extractor()(**source_data) def get_metadata_schema(self) -> dict: + """ + Generate the metadata schema for Ophys data, updating required fields and properties. + + This method builds upon the base schema and customizes it for Ophys-specific metadata, including required + components such as devices, fluorescence data, imaging planes, and two-photon series. It also applies + temporary schema adjustments to handle certain use cases until a centralized metadata schema definition + is available. + + Returns + ------- + dict + A dictionary representing the updated Ophys metadata schema. + + Notes + ----- + - Ensures that `Device` and `ImageSegmentation` are marked as required. + - Updates various properties, including ensuring arrays for `ImagingPlane` and `TwoPhotonSeries`. + - Adjusts the schema for `Fluorescence`, including required fields and pattern properties. + - Adds schema definitions for `DfOverF`, segmentation images, and summary images. + - Applies temporary fixes, such as setting additional properties for `ImageSegmentation` to True. + """ metadata_schema = super().get_metadata_schema() metadata_schema["required"] = ["Ophys"] metadata_schema["properties"]["Ophys"] = get_base_schema() diff --git a/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffconverter.py b/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffconverter.py index 2a67da720..1fc854b81 100644 --- a/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffconverter.py +++ b/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffconverter.py @@ -31,6 +31,7 @@ def get_source_schema(cls): return source_schema def get_conversion_options_schema(self): + """get the conversion options schema.""" interface_name = list(self.data_interface_objects.keys())[0] return self.data_interface_objects[interface_name].get_conversion_options_schema() @@ -91,6 +92,20 @@ def add_to_nwbfile( stub_test: bool = False, stub_frames: int = 100, ): + """ + Add data from multiple data interfaces to the specified NWBFile. + + Parameters + ---------- + nwbfile : NWBFile + The NWBFile object to which the data will be added. + metadata : dict + Metadata dictionary containing information to describe the data being added to the NWB file. + stub_test : bool, optional + If True, only a subset of the data (up to `stub_frames`) will be added for testing purposes. Default is False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True. Default is 100. + """ for photon_series_index, (interface_name, data_interface) in enumerate(self.data_interface_objects.items()): data_interface.add_to_nwbfile( nwbfile=nwbfile, @@ -109,6 +124,24 @@ def run_conversion( stub_test: bool = False, stub_frames: int = 100, ) -> None: + """ + Run the conversion process for the instantiated data interfaces and add data to the NWB file. + + Parameters + ---------- + nwbfile_path : FilePath, optional + Path where the NWB file will be written. If None, the file will be handled in-memory. + nwbfile : NWBFile, optional + An in-memory NWBFile object. If None, a new NWBFile object will be created. + metadata : dict, optional + Metadata dictionary for describing the NWB file. If None, it will be auto-generated using the `get_metadata()` method. + overwrite : bool, optional + If True, overwrites the existing NWB file at `nwbfile_path`. If False, appends to the file (default is False). + stub_test : bool, optional + If True, only a subset of the data (up to `stub_frames`) will be added for testing purposes, by default False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True, by default 100. + """ if metadata is None: metadata = self.get_metadata() @@ -141,6 +174,7 @@ def get_source_schema(cls): return get_json_schema_from_method_signature(cls) def get_conversion_options_schema(self): + """Get the conversion options schema.""" interface_name = list(self.data_interface_objects.keys())[0] return self.data_interface_objects[interface_name].get_conversion_options_schema() @@ -187,6 +221,21 @@ def add_to_nwbfile( stub_test: bool = False, stub_frames: int = 100, ): + """ + Add data from all instantiated data interfaces to the provided NWBFile. + + Parameters + ---------- + nwbfile : NWBFile + The NWBFile object to which the data will be added. + metadata : dict + Metadata dictionary containing information about the data to be added. + stub_test : bool, optional + If True, only a subset of the data (defined by `stub_frames`) will be added for testing purposes, + by default False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True, by default 100. + """ for photon_series_index, (interface_name, data_interface) in enumerate(self.data_interface_objects.items()): data_interface.add_to_nwbfile( nwbfile=nwbfile, @@ -205,6 +254,24 @@ def run_conversion( stub_test: bool = False, stub_frames: int = 100, ) -> None: + """ + Run the NWB conversion process for all instantiated data interfaces. + + Parameters + ---------- + nwbfile_path : FilePath, optional + The file path where the NWB file will be written. If None, the file is handled in-memory. + nwbfile : NWBFile, optional + An existing in-memory NWBFile object. If None, a new NWBFile object will be created. + metadata : dict, optional + Metadata dictionary used to create or validate the NWBFile. If None, metadata is automatically generated. + overwrite : bool, optional + If True, the NWBFile at `nwbfile_path` is overwritten if it exists. If False (default), data is appended. + stub_test : bool, optional + If True, only a subset of the data (up to `stub_frames`) is used for testing purposes. By default False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True. By default 100. + """ if metadata is None: metadata = self.get_metadata() diff --git a/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffdatainterface.py b/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffdatainterface.py index 9742711e1..f7e7bee1b 100644 --- a/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffdatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/brukertiff/brukertiffdatainterface.py @@ -16,6 +16,7 @@ class BrukerTiffMultiPlaneImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """Get the source schema for the Bruker TIFF imaging data.""" source_schema = super().get_source_schema() source_schema["properties"]["folder_path"][ "description" @@ -28,6 +29,23 @@ def get_streams( folder_path: DirectoryPath, plane_separation_type: Literal["contiguous", "disjoint"] = None, ) -> dict: + """ + Get streams for the Bruker TIFF imaging data. + + Parameters + ---------- + folder_path : DirectoryPath + Path to the folder containing the Bruker TIFF files. + plane_separation_type : Literal["contiguous", "disjoint"], optional + Type of plane separation to apply. If "contiguous", only the first plane stream for each channel is retained. + + Returns + ------- + dict + A dictionary containing the streams for the Bruker TIFF imaging data. The dictionary has the following keys: + - "channel_streams": List of channel stream names. + - "plane_streams": Dictionary where keys are channel stream names and values are lists of plane streams. + """ from roiextractors import BrukerTiffMultiPlaneImagingExtractor streams = BrukerTiffMultiPlaneImagingExtractor.get_streams(folder_path=folder_path) @@ -117,6 +135,7 @@ def _determine_position_current(self) -> list[float]: return position_values def get_metadata(self) -> DeepDict: + """get metadata for the Bruker TIFF imaging data.""" metadata = super().get_metadata() xml_metadata = self.imaging_extractor.xml_metadata @@ -183,6 +202,7 @@ class BrukerTiffSinglePlaneImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """Get the source schema for the Bruker TIFF imaging data.""" source_schema = super().get_source_schema() source_schema["properties"]["folder_path"][ "description" @@ -191,6 +211,19 @@ def get_source_schema(cls) -> dict: @classmethod def get_streams(cls, folder_path: DirectoryPath) -> dict: + """ + Get streams for the Bruker TIFF imaging data. + + Parameters + ---------- + folder_path : DirectoryPath + Path to the folder containing the Bruker TIFF files. + + Returns + ------- + dict + A dictionary containing the streams extracted from the Bruker TIFF files. + """ from roiextractors import BrukerTiffMultiPlaneImagingExtractor streams = BrukerTiffMultiPlaneImagingExtractor.get_streams(folder_path=folder_path) @@ -263,6 +296,7 @@ def _determine_position_current(self) -> list[float]: return position_values def get_metadata(self) -> DeepDict: + """get metadata for the Bruker TIFF imaging data.""" metadata = super().get_metadata() xml_metadata = self.imaging_extractor.xml_metadata diff --git a/src/neuroconv/datainterfaces/ophys/caiman/caimandatainterface.py b/src/neuroconv/datainterfaces/ophys/caiman/caimandatainterface.py index 386c03d3c..802645139 100644 --- a/src/neuroconv/datainterfaces/ophys/caiman/caimandatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/caiman/caimandatainterface.py @@ -12,6 +12,7 @@ class CaimanSegmentationInterface(BaseSegmentationExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """Get the source schema for the Caiman segmentation interface.""" source_metadata = super().get_source_schema() source_metadata["properties"]["file_path"]["description"] = "Path to .hdf5 file." return source_metadata diff --git a/src/neuroconv/datainterfaces/ophys/micromanagertiff/micromanagertiffdatainterface.py b/src/neuroconv/datainterfaces/ophys/micromanagertiff/micromanagertiffdatainterface.py index 17cbc95ed..5373b7004 100644 --- a/src/neuroconv/datainterfaces/ophys/micromanagertiff/micromanagertiffdatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/micromanagertiff/micromanagertiffdatainterface.py @@ -13,6 +13,7 @@ class MicroManagerTiffImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """get the source schema for the Micro-Manager TIFF imaging interface.""" source_schema = super().get_source_schema() source_schema["properties"]["folder_path"]["description"] = "The folder containing the OME-TIF image files." @@ -37,6 +38,7 @@ def __init__(self, folder_path: DirectoryPath, verbose: bool = True): self.imaging_extractor._channel_names = [f"OpticalChannel{channel_name}"] def get_metadata(self) -> dict: + """Get metadata for the Micro-Manager TIFF imaging data.""" metadata = super().get_metadata() micromanager_metadata = self.imaging_extractor.micromanager_metadata diff --git a/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeconverter.py b/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeconverter.py index d1a0fb701..59424d7a5 100644 --- a/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeconverter.py +++ b/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeconverter.py @@ -61,6 +61,7 @@ def __init__(self, folder_path: DirectoryPath, verbose: bool = True): ) def get_conversion_options_schema(self) -> dict: + """get the conversion options schema.""" return self.data_interface_objects["MiniscopeImaging"].get_conversion_options_schema() def add_to_nwbfile( @@ -70,6 +71,21 @@ def add_to_nwbfile( stub_test: bool = False, stub_frames: int = 100, ): + """ + Add Miniscope imaging and behavioral camera data to the specified NWBFile. + + Parameters + ---------- + nwbfile : NWBFile + The NWBFile object to which the imaging and behavioral data will be added. + metadata : dict + Metadata dictionary containing information about the imaging and behavioral recordings. + stub_test : bool, optional + If True, only a subset of the data (defined by `stub_frames`) will be added for testing purposes, + by default False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True, by default 100. + """ self.data_interface_objects["MiniscopeImaging"].add_to_nwbfile( nwbfile=nwbfile, metadata=metadata, @@ -90,6 +106,25 @@ def run_conversion( stub_test: bool = False, stub_frames: int = 100, ) -> None: + """ + Run the NWB conversion process for the instantiated data interfaces. + + Parameters + ---------- + nwbfile_path : str, optional + Path where the NWBFile will be written. If None, the file is handled in-memory. + nwbfile : NWBFile, optional + An in-memory NWBFile object to be written to the file. If None, a new NWBFile is created. + metadata : dict, optional + Metadata dictionary with information to create the NWBFile. If None, metadata is auto-generated. + overwrite : bool, optional + If True, overwrites the existing NWBFile at `nwbfile_path`. If False (default), data is appended. + stub_test : bool, optional + If True, only a subset of the data (up to `stub_frames`) is written for testing purposes, + by default False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True, by default 100. + """ if metadata is None: metadata = self.get_metadata() diff --git a/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeimagingdatainterface.py b/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeimagingdatainterface.py index 64a180c46..5a1f6d521 100644 --- a/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeimagingdatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/miniscope/miniscopeimagingdatainterface.py @@ -19,6 +19,7 @@ class MiniscopeImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """Get the source schema for the Miniscope imaging interface.""" source_schema = super().get_source_schema() source_schema["properties"]["folder_path"][ "description" @@ -49,6 +50,7 @@ def __init__(self, folder_path: DirectoryPath): self.photon_series_type = "OnePhotonSeries" def get_metadata(self) -> DeepDict: + """Get metadata for the Miniscope imaging data.""" from ....tools.roiextractors import get_nwb_imaging_metadata metadata = super().get_metadata() @@ -74,6 +76,7 @@ def get_metadata(self) -> DeepDict: return metadata def get_metadata_schema(self) -> dict: + """Get the metadata schema for the Miniscope imaging data.""" metadata_schema = super().get_metadata_schema() metadata_schema["properties"]["Ophys"]["definitions"]["Device"]["additionalProperties"] = True return metadata_schema @@ -92,6 +95,23 @@ def add_to_nwbfile( stub_test: bool = False, stub_frames: int = 100, ): + """ + Add imaging data to the specified NWBFile, including device and photon series information. + + Parameters + ---------- + nwbfile : NWBFile + The NWBFile object to which the imaging data will be added. + metadata : dict, optional + Metadata containing information about the imaging device and photon series. If None, default metadata is used. + photon_series_type : {"TwoPhotonSeries", "OnePhotonSeries"}, optional + The type of photon series to be added, either "TwoPhotonSeries" or "OnePhotonSeries", by default "OnePhotonSeries". + stub_test : bool, optional + If True, only a subset of the data (defined by `stub_frames`) will be added for testing purposes, + by default False. + stub_frames : int, optional + The number of frames to include if `stub_test` is True, by default 100. + """ from ndx_miniscope.utils import add_miniscope_device from ....tools.roiextractors import add_photon_series_to_nwbfile diff --git a/src/neuroconv/datainterfaces/ophys/sbx/sbxdatainterface.py b/src/neuroconv/datainterfaces/ophys/sbx/sbxdatainterface.py index 554cc5aba..49e556d06 100644 --- a/src/neuroconv/datainterfaces/ophys/sbx/sbxdatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/sbx/sbxdatainterface.py @@ -37,6 +37,7 @@ def __init__( ) def get_metadata(self) -> dict: + """Get metadata for the Scanbox imaging data.""" metadata = super().get_metadata() metadata["Ophys"]["Device"][0]["description"] = "Scanbox imaging" return metadata diff --git a/src/neuroconv/datainterfaces/ophys/scanimage/scanimageimaginginterfaces.py b/src/neuroconv/datainterfaces/ophys/scanimage/scanimageimaginginterfaces.py index c74161e55..7d9d7003b 100644 --- a/src/neuroconv/datainterfaces/ophys/scanimage/scanimageimaginginterfaces.py +++ b/src/neuroconv/datainterfaces/ophys/scanimage/scanimageimaginginterfaces.py @@ -28,6 +28,7 @@ class ScanImageImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """Get the source schema for the ScanImage imaging interface.""" source_schema = super().get_source_schema() source_schema["properties"]["file_path"]["description"] = "Path to Tiff file." return source_schema @@ -139,6 +140,7 @@ def __init__( super().__init__(file_path=file_path, fallback_sampling_frequency=fallback_sampling_frequency, verbose=verbose) def get_metadata(self) -> dict: + """get metadata for the ScanImage imaging data""" device_number = 0 # Imaging plane metadata is a list with metadata for each plane metadata = super().get_metadata() @@ -174,6 +176,7 @@ class ScanImageMultiFileImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """get the source schema for the ScanImage multi-file imaging interface.""" source_schema = super().get_source_schema() source_schema["properties"]["folder_path"]["description"] = "Path to the folder containing the TIFF files." return source_schema @@ -304,6 +307,7 @@ def __init__( ) def get_metadata(self) -> dict: + """get metadata for the ScanImage imaging data""" metadata = super().get_metadata() extracted_session_start_time = datetime.datetime.strptime( @@ -421,6 +425,7 @@ def __init__( ) def get_metadata(self) -> dict: + """get metadata for the ScanImage imaging data""" metadata = super().get_metadata() extracted_session_start_time = datetime.datetime.strptime( @@ -548,6 +553,7 @@ def __init__( ) def get_metadata(self) -> dict: + """get metadata for the ScanImage imaging data""" metadata = super().get_metadata() extracted_session_start_time = datetime.datetime.strptime( @@ -677,6 +683,7 @@ def __init__( ) def get_metadata(self) -> dict: + """get metadata for the ScanImage imaging data""" metadata = super().get_metadata() extracted_session_start_time = datetime.datetime.strptime( diff --git a/src/neuroconv/datainterfaces/ophys/suite2p/suite2pdatainterface.py b/src/neuroconv/datainterfaces/ophys/suite2p/suite2pdatainterface.py index 056616ce5..8a3f876c2 100644 --- a/src/neuroconv/datainterfaces/ophys/suite2p/suite2pdatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/suite2p/suite2pdatainterface.py @@ -50,6 +50,7 @@ class Suite2pSegmentationInterface(BaseSegmentationExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """Get the source schema for the Suite2p segmentation interface.""" schema = super().get_source_schema() schema["properties"]["folder_path"][ "description" @@ -113,6 +114,7 @@ def __init__( self.verbose = verbose def get_metadata(self) -> DeepDict: + """get metadata for the Suite2p segmentation data""" metadata = super().get_metadata() # No need to update the metadata links for the default plane segmentation name @@ -140,6 +142,40 @@ def add_to_nwbfile( iterator_options: Optional[dict] = None, compression_options: Optional[dict] = None, ): + """ + Add segmentation data to the specified NWBFile. + + Parameters + ---------- + nwbfile : NWBFile + The NWBFile object to which the segmentation data will be added. + metadata : dict, optional + Metadata containing information about the segmentation. If None, default metadata is used. + stub_test : bool, optional + If True, only a subset of the data (defined by `stub_frames`) will be added for testing purposes, + by default False. + stub_frames : int, optional + The number of frames to include in the subset if `stub_test` is True, by default 100. + include_roi_centroids : bool, optional + Whether to include the centroids of regions of interest (ROIs) in the data, by default True. + include_roi_acceptance : bool, optional + Whether to include acceptance status of ROIs, by default True. + mask_type : str, default: 'image' + There are three types of ROI masks in NWB, 'image', 'pixel', and 'voxel'. + + * 'image' masks have the same shape as the reference images the segmentation was applied to, and weight each pixel + by its contribution to the ROI (typically boolean, with 0 meaning 'not in the ROI'). + * 'pixel' masks are instead indexed by ROI, with the data at each index being the shape of the image by the number + of pixels in each ROI. + * 'voxel' masks are instead indexed by ROI, with the data at each index being the shape of the volume by the number + of voxels in each ROI. + + Specify your choice between these two as mask_type='image', 'pixel', 'voxel', or None. + plane_segmentation_name : str, optional + The name of the plane segmentation object, by default None. + iterator_options : dict, optional + Additional options for iterating over the data, by default None. + """ super().add_to_nwbfile( nwbfile=nwbfile, metadata=metadata, diff --git a/src/neuroconv/datainterfaces/ophys/tdt_fp/tdtfiberphotometrydatainterface.py b/src/neuroconv/datainterfaces/ophys/tdt_fp/tdtfiberphotometrydatainterface.py index 8b092464e..0c6b90aea 100644 --- a/src/neuroconv/datainterfaces/ophys/tdt_fp/tdtfiberphotometrydatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/tdt_fp/tdtfiberphotometrydatainterface.py @@ -47,6 +47,7 @@ def __init__(self, folder_path: DirectoryPath, verbose: bool = True): import ndx_fiber_photometry # noqa: F401 def get_metadata(self) -> DeepDict: + """Get metadata for the TDTFiberPhotometryInterface.""" metadata = super().get_metadata() tdt_photometry = self.load(evtype=["scalars"]) # This evtype quickly loads info without loading all the data. start_timestamp = tdt_photometry.info.start_date.timestamp() @@ -55,6 +56,7 @@ def get_metadata(self) -> DeepDict: return metadata def get_metadata_schema(self) -> dict: + """Get the metadata schema for the TDTFiberPhotometryInterface.""" metadata_schema = super().get_metadata_schema() return metadata_schema diff --git a/src/neuroconv/datainterfaces/ophys/tiff/tiffdatainterface.py b/src/neuroconv/datainterfaces/ophys/tiff/tiffdatainterface.py index 1eaa3b55e..ce98561de 100644 --- a/src/neuroconv/datainterfaces/ophys/tiff/tiffdatainterface.py +++ b/src/neuroconv/datainterfaces/ophys/tiff/tiffdatainterface.py @@ -14,6 +14,7 @@ class TiffImagingInterface(BaseImagingExtractorInterface): @classmethod def get_source_schema(cls) -> dict: + """ "Get the source schema for the TIFF imaging interface.""" source_schema = super().get_source_schema() source_schema["properties"]["file_path"]["description"] = "Path to Tiff file." return source_schema diff --git a/src/neuroconv/datainterfaces/text/timeintervalsinterface.py b/src/neuroconv/datainterfaces/text/timeintervalsinterface.py index 5f5b1107d..a1de63a07 100644 --- a/src/neuroconv/datainterfaces/text/timeintervalsinterface.py +++ b/src/neuroconv/datainterfaces/text/timeintervalsinterface.py @@ -24,16 +24,20 @@ def __init__( verbose: bool = True, ): """ + Initialize the TimeIntervalsInterface. + Parameters ---------- file_path : FilePath + The path to the file containing time intervals data. read_kwargs : dict, optional - verbose : bool, default: True + Additional arguments for reading the file, by default None. + verbose : bool, optional + If True, provides verbose output, by default True. """ read_kwargs = read_kwargs or dict() super().__init__(file_path=file_path) self.verbose = verbose - self._read_kwargs = read_kwargs self.dataframe = self._read_file(file_path, **read_kwargs) self.time_intervals = None @@ -50,22 +54,74 @@ def get_metadata(self) -> dict: return metadata def get_metadata_schema(self) -> dict: + """ + Get the metadata schema for the time intervals. + + Returns + ------- + dict + The schema dictionary for time intervals metadata. + """ fpath = Path(__file__).parent.parent.parent / "schemas" / "timeintervals_schema.json" return load_dict_from_file(fpath) def get_original_timestamps(self, column: str) -> np.ndarray: + """ + Get the original timestamps for a given column. + + Parameters + ---------- + column : str + The name of the column containing timestamps. + + Returns + ------- + np.ndarray + The original timestamps from the specified column. + + Raises + ------ + ValueError + If the column name does not end with '_time'. + """ if not column.endswith("_time"): raise ValueError("Timing columns on a TimeIntervals table need to end with '_time'!") return self._read_file(**self.source_data, **self._read_kwargs)[column].values def get_timestamps(self, column: str) -> np.ndarray: + """ + Get the current timestamps for a given column. + + Parameters + ---------- + column : str + The name of the column containing timestamps. + + Returns + ------- + np.ndarray + The current timestamps from the specified column. + + Raises + ------ + ValueError + If the column name does not end with '_time'. + """ if not column.endswith("_time"): raise ValueError("Timing columns on a TimeIntervals table need to end with '_time'!") return self.dataframe[column].values def set_aligned_starting_time(self, aligned_starting_time: float): + """ + Align the starting time by shifting all timestamps by the given value. + + Parameters + ---------- + aligned_starting_time : float + The aligned starting time to shift all timestamps by. + """ timing_columns = [column for column in self.dataframe.columns if column.endswith("_time")] for column in timing_columns: @@ -74,6 +130,23 @@ def set_aligned_starting_time(self, aligned_starting_time: float): def set_aligned_timestamps( self, aligned_timestamps: np.ndarray, column: str, interpolate_other_columns: bool = False ): + """ + Set aligned timestamps for the given column and optionally interpolate other columns. + + Parameters + ---------- + aligned_timestamps : np.ndarray + The aligned timestamps to set for the given column. + column : str + The name of the column to update with the aligned timestamps. + interpolate_other_columns : bool, optional + If True, interpolate the timestamps in other columns, by default False. + + Raises + ------ + ValueError + If the column name does not end with '_time'. + """ if not column.endswith("_time"): raise ValueError("Timing columns on a TimeIntervals table need to end with '_time'!") @@ -96,6 +169,18 @@ def set_aligned_timestamps( ) def align_by_interpolation(self, unaligned_timestamps: np.ndarray, aligned_timestamps: np.ndarray, column: str): + """ + Align timestamps using linear interpolation. + + Parameters + ---------- + unaligned_timestamps : np.ndarray + The original unaligned timestamps that map to the aligned timestamps. + aligned_timestamps : np.ndarray + The target aligned timestamps corresponding to the unaligned timestamps. + column : str + The name of the column containing the timestamps to be aligned. + """ current_timestamps = self.get_timestamps(column=column) assert ( current_timestamps[1] >= unaligned_timestamps[0] diff --git a/src/neuroconv/nwbconverter.py b/src/neuroconv/nwbconverter.py index fe1b09915..2d70cf8ee 100644 --- a/src/neuroconv/nwbconverter.py +++ b/src/neuroconv/nwbconverter.py @@ -177,7 +177,21 @@ def create_nwbfile(self, metadata: Optional[dict] = None, conversion_options: Op self.add_to_nwbfile(nwbfile=nwbfile, metadata=metadata, conversion_options=conversion_options) return nwbfile - def add_to_nwbfile(self, nwbfile: NWBFile, metadata, conversion_options: Optional[dict] = None) -> None: + def add_to_nwbfile(self, nwbfile: NWBFile, metadata, conversion_options: Optional[dict] = None): + """ + Add data from the instantiated data interfaces to the given NWBFile. + + Parameters + ---------- + nwbfile : NWBFile + The NWB file object to which the data from the data interfaces will be added. + metadata : dict + The metadata dictionary that contains information used to describe the data. + conversion_options : dict, optional + A dictionary containing conversion options for each interface, where non-default behavior is requested. + Each key corresponds to a data interface name, and the values are dictionaries with options for that interface. + By default, None. + """ conversion_options = conversion_options or dict() for interface_name, data_interface in self.data_interface_objects.items(): data_interface.add_to_nwbfile( diff --git a/src/neuroconv/tools/hdmf.py b/src/neuroconv/tools/hdmf.py index 660971df5..f32ea23a0 100644 --- a/src/neuroconv/tools/hdmf.py +++ b/src/neuroconv/tools/hdmf.py @@ -50,6 +50,7 @@ def estimate_default_chunk_shape(chunk_mb: float, maxshape: tuple[int, ...], dty def estimate_default_buffer_shape( buffer_gb: float, chunk_shape: tuple[int, ...], maxshape: tuple[int, ...], dtype: np.dtype ) -> tuple[int, ...]: + # TODO: Ad ddocstring to this once someone understands it better # Elevate any overflow warnings to trigger error. # This is usually an indicator of something going terribly wrong with the estimation calculations and should be # avoided at all costs. diff --git a/src/neuroconv/tools/testing/mock_interfaces.py b/src/neuroconv/tools/testing/mock_interfaces.py index 5a96b4b68..0350806bb 100644 --- a/src/neuroconv/tools/testing/mock_interfaces.py +++ b/src/neuroconv/tools/testing/mock_interfaces.py @@ -57,31 +57,70 @@ def get_source_schema(cls) -> dict: def __init__(self, event_times: Optional[ArrayType] = None): """ - Define event times for some behavior. + Initialize the interface with event times for behavior. Parameters ---------- event_times : list of floats, optional The event times to set as timestamps for this interface. - The default is the array [1.2, 2.3, 3.4] for similarity to the timescale of the MockSpikeGLXNIDQInterface. + The default is the array [1.2, 2.3, 3.4] to simulate a time series similar to the + MockSpikeGLXNIDQInterface. """ event_times = event_times or [1.2, 2.3, 3.4] self.event_times = np.array(event_times) self.original_event_times = np.array(event_times) # Make a copy of the initial loaded timestamps def get_original_timestamps(self) -> np.ndarray: + """ + Get the original event times before any alignment or transformation. + + Returns + ------- + np.ndarray + The original event times as a NumPy array. + """ return self.original_event_times def get_timestamps(self) -> np.ndarray: + """ + Get the current (possibly aligned) event times. + + Returns + ------- + np.ndarray + The current event times as a NumPy array, possibly modified after alignment. + """ return self.event_times def set_aligned_timestamps(self, aligned_timestamps: np.ndarray): + """ + Set the event times after alignment. + + Parameters + ---------- + aligned_timestamps : np.ndarray + The aligned event timestamps to update the internal event times. + """ self.event_times = aligned_timestamps def add_to_nwbfile(self, nwbfile: NWBFile, metadata: dict): + """ + Add the event times to an NWBFile as a DynamicTable. + + Parameters + ---------- + nwbfile : NWBFile + The NWB file to which the event times will be added. + metadata : dict + Metadata to describe the event times in the NWB file. + + Notes + ----- + This method creates a DynamicTable to store event times and adds it to the NWBFile's acquisition. + """ table = DynamicTable(name="BehaviorEvents", description="Times of various classified behaviors.") table.add_column(name="event_time", description="Time of each event.") - for timestamp in self.get_timestamps(): # adding data by column gives error + for timestamp in self.get_timestamps(): table.add_row(event_time=timestamp) nwbfile.add_acquisition(table) @@ -182,6 +221,9 @@ def __init__( ) def get_metadata(self) -> dict: + """ + Returns the metadata dictionary for the current object. + """ metadata = super().get_metadata() session_start_time = datetime.now().astimezone() metadata["NWBFile"]["session_start_time"] = session_start_time @@ -229,7 +271,7 @@ def __init__( verbose=verbose, ) - def get_metadata(self) -> dict: # noqa D102 + def get_metadata(self) -> dict: metadata = super().get_metadata() session_start_time = datetime.now().astimezone() metadata["NWBFile"]["session_start_time"] = session_start_time diff --git a/src/neuroconv/utils/dict.py b/src/neuroconv/utils/dict.py index f0507b653..a6cef630a 100644 --- a/src/neuroconv/utils/dict.py +++ b/src/neuroconv/utils/dict.py @@ -209,12 +209,29 @@ class DeepDict(defaultdict): """A defaultdict of defaultdicts""" def __init__(self, *args: Any, **kwargs: Any) -> None: + """A defaultdict of defaultdicts""" super().__init__(lambda: DeepDict(), *args, **kwargs) for key, value in self.items(): if isinstance(value, dict): self[key] = DeepDict(value) def deep_update(self, other: Optional[Union[dict, "DeepDict"]] = None, **kwargs) -> None: + """ + Recursively update the DeepDict with another dictionary or DeepDict. + + Parameters + ---------- + other : dict or DeepDict, optional + The dictionary or DeepDict to update the current instance with. + **kwargs : Any + Additional keyword arguments representing key-value pairs to update the DeepDict. + + Notes + ----- + For any keys that exist in both the current instance and the provided dictionary, the values are merged + recursively if both are dictionaries. Otherwise, the value from `other` or `kwargs` will overwrite the + existing value. + """ for key, value in (other or kwargs).items(): if key in self and isinstance(self[key], dict) and isinstance(value, dict): self[key].deep_update(value)