eegdash 0.4.0.dev153__py3-none-any.whl → 0.4.0.dev162__py3-none-any.whl

eegdash/data_utils.py

@@ -37,10 +37,26 @@ from .paths import get_default_cache_dir
 
 
 class EEGDashBaseDataset(BaseDataset):
-    """A single EEG recording hosted on AWS S3 and cached locally upon first access.
+    """A single EEG recording dataset.
+
+    Represents a single EEG recording, typically hosted on a remote server (like AWS S3)
+    and cached locally upon first access. This class is a subclass of
+    :class:`braindecode.datasets.BaseDataset` and can be used with braindecode's
+    preprocessing and training pipelines.
+
+    Parameters
+    ----------
+    record : dict
+        A fully resolved metadata record for the data to load.
+    cache_dir : str
+        The local directory where the data will be cached.
+    s3_bucket : str, optional
+        The S3 bucket to download data from. If not provided, defaults to the
+        OpenNeuro bucket.
+    **kwargs
+        Additional keyword arguments passed to the
+        :class:`braindecode.datasets.BaseDataset` constructor.
 
-    This is a subclass of braindecode's BaseDataset, which can consequently be used in
-    conjunction with the preprocessing and training pipelines of braindecode.
     """
 
     _AWS_BUCKET = "s3://openneuro.org"
@@ -52,20 +68,6 @@ class EEGDashBaseDataset(BaseDataset):
         s3_bucket: str | None = None,
         **kwargs,
     ):
-        """Create a new EEGDashBaseDataset instance. Users do not usually need to call this
-        directly -- instead use the EEGDashDataset class to load a collection of these
-        recordings from a local BIDS folder or using a database query.
-
-        Parameters
-        ----------
-        record : dict
-            A fully resolved metadata record for the data to load.
-        cache_dir : str
-            A local directory where the data will be cached.
-        kwargs : dict
-            Additional keyword arguments to pass to the BaseDataset constructor.
-
-        """
         super().__init__(None, **kwargs)
         self.record = record
         self.cache_dir = Path(cache_dir)
@@ -121,14 +123,12 @@ class EEGDashBaseDataset(BaseDataset):
         self._raw = None
 
     def _get_raw_bids_args(self) -> dict[str, Any]:
-        """Helper to restrict the metadata record to the fields needed to locate a BIDS
-        recording.
-        """
+        """Extract BIDS-related arguments from the metadata record."""
         desired_fields = ["subject", "session", "task", "run"]
         return {k: self.record[k] for k in desired_fields if self.record[k]}
 
     def _ensure_raw(self) -> None:
-        """Download the S3 file and BIDS dependencies if not already cached."""
+        """Ensure the raw data file and its dependencies are cached locally."""
         # TO-DO: remove this once is fixed on the our side
         # for the competition
         if not self.s3_open_neuro:
@@ -190,42 +190,53 @@ class EEGDashBaseDataset(BaseDataset):
         return len(self._raw)
 
     @property
-    def raw(self):
-        """Return the MNE Raw object for this recording. This will perform the actual
-        retrieval if not yet done so.
+    def raw(self) -> BaseRaw:
+        """The MNE Raw object for this recording.
+
+        Accessing this property triggers the download and caching of the data
+        if it has not been accessed before.
+
+        Returns
+        -------
+        mne.io.BaseRaw
+            The loaded MNE Raw object.
+
         """
         if self._raw is None:
             self._ensure_raw()
         return self._raw
 
     @raw.setter
-    def raw(self, raw):
+    def raw(self, raw: BaseRaw):
         self._raw = raw
 
 
 class EEGDashBaseRaw(BaseRaw):
-    """Wrapper around the MNE BaseRaw class that automatically fetches the data from S3
-    (when _read_segment is called) and caches it locally. Currently for internal use.
+    """MNE BaseRaw wrapper for automatic S3 data fetching.
+
+    This class extends :class:`mne.io.BaseRaw` to automatically fetch data
+    from an S3 bucket and cache it locally when data is first accessed.
+    It is intended for internal use within the EEGDash ecosystem.
 
     Parameters
     ----------
-    input_fname : path-like
-        Path to the S3 file
+    input_fname : str
+        The path to the file on the S3 bucket (relative to the bucket root).
     metadata : dict
-        The metadata record for the recording (e.g., from the database).
-    preload : bool
-        Whether to pre-loaded the data before the first access.
-    cache_dir : str
-        Local path under which the data will be cached.
-    bids_dependencies : list
-        List of additional BIDS metadata files that should be downloaded and cached
-        alongside the main recording file.
-    verbose : str | int | None
-        Optionally the verbosity level for MNE logging (see MNE documentation for possible values).
+        The metadata record for the recording, containing information like
+        sampling frequency, channel names, etc.
+    preload : bool, default False
+        If True, preload the data into memory.
+    cache_dir : str, optional
+        Local directory for caching data. If None, a default directory is used.
+    bids_dependencies : list of str, default []
+        A list of BIDS metadata files to download alongside the main recording.
+    verbose : str, int, or None, default None
+        The MNE verbosity level.
 
     See Also
     --------
-    mne.io.Raw : Documentation of attributes and methods.
+    mne.io.Raw : The base class for Raw objects in MNE.
 
     """
 
@@ -241,7 +252,6 @@ class EEGDashBaseRaw(BaseRaw):
         bids_dependencies: list[str] = [],
         verbose: Any = None,
     ):
-        """Get to work with S3 endpoint first, no caching"""
         # Create a simple RawArray
         sfreq = metadata["sfreq"]  # Sampling frequency
         n_times = metadata["n_times"]
@@ -277,6 +287,7 @@ class EEGDashBaseRaw(BaseRaw):
     def _read_segment(
         self, start=0, stop=None, sel=None, data_buffer=None, *, verbose=None
     ):
+        """Read a segment of data, downloading if necessary."""
         if not os.path.exists(self.filecache):  # not preload
             if self.bids_dependencies:  # this is use only to sidecars for now
                 downloader.download_dependencies(
@@ -297,22 +308,23 @@ class EEGDashBaseRaw(BaseRaw):
         return super()._read_segment(start, stop, sel, data_buffer, verbose=verbose)
 
     def _read_segment_file(self, data, idx, fi, start, stop, cals, mult):
-        """Read a chunk of data from the file."""
+        """Read a chunk of data from a local file."""
         _read_segments_file(self, data, idx, fi, start, stop, cals, mult, dtype="<f4")
 
 
 class EEGBIDSDataset:
-    """A one-stop shop interface to a local BIDS dataset containing EEG recordings.
+    """An interface to a local BIDS dataset containing EEG recordings.
 
-    This is mainly tailored to the needs of EEGDash application and is used to centralize
-    interactions with the BIDS dataset, such as parsing the metadata.
+    This class centralizes interactions with a BIDS dataset on the local
+    filesystem, providing methods to parse metadata, find files, and
+    retrieve BIDS-related information.
 
     Parameters
     ----------
-    data_dir : str | Path
+    data_dir : str or Path
         The path to the local BIDS dataset directory.
     dataset : str
-        A name for the dataset.
+        A name for the dataset (e.g., "ds002718").
 
     """
 
@@ -357,7 +369,14 @@ class EEGBIDSDataset:
         assert self.check_eeg_dataset(), ValueError("Dataset is not an EEG dataset.")
 
     def check_eeg_dataset(self) -> bool:
-        """Check if the dataset is EEG."""
+        """Check if the BIDS dataset contains EEG data.
+
+        Returns
+        -------
+        bool
+            True if the dataset's modality is EEG, False otherwise.
+
+        """
         return self.get_bids_file_attribute("modality", self.files[0]).lower() == "eeg"
 
     def _get_recordings(self, layout: BIDSLayout) -> list[str]:
@@ -370,14 +389,12 @@ class EEGBIDSDataset:
         return files
 
     def _get_relative_bidspath(self, filename: str) -> str:
-        """Make the given file path relative to the BIDS directory."""
+        """Make a file path relative to the BIDS parent directory."""
         bids_parent_dir = self.bidsdir.parent.absolute()
         return str(Path(filename).relative_to(bids_parent_dir))
 
     def _get_property_from_filename(self, property: str, filename: str) -> str:
-        """Parse a property out of a BIDS-compliant filename. Returns an empty string
-        if not found.
-        """
+        """Parse a BIDS entity from a filename."""
         import platform
 
         if platform.system() == "Windows":
@@ -387,159 +404,106 @@ class EEGBIDSDataset:
         return lookup.group(1) if lookup else ""
 
     def _merge_json_inheritance(self, json_files: list[str | Path]) -> dict:
-        """Internal helper to merge list of json files found by get_bids_file_inheritance,
-        expecting the order (from left to right) is from lowest
-        level to highest level, and return a merged dictionary
-        """
+        """Merge a list of JSON files according to BIDS inheritance."""
         json_files.reverse()
         json_dict = {}
         for f in json_files:
-            json_dict.update(json.load(open(f)))  # FIXME: should close file
+            with open(f) as fp:
+                json_dict.update(json.load(fp))
         return json_dict
 
     def _get_bids_file_inheritance(
         self, path: str | Path, basename: str, extension: str
     ) -> list[Path]:
-        """Get all file paths that apply to the basename file in the specified directory
-        and that end with the specified suffix, recursively searching parent directories
-        (following the BIDS inheritance principle in the order of lowest level first).
-
-        Parameters
-        ----------
-        path : str | Path
-            The directory path to search for files.
-        basename : str
-            BIDS file basename without _eeg.set extension for example
-        extension : str
-            Only consider files that end with the specified suffix; e.g. channels.tsv
-
-        Returns
-        -------
-        list[Path]
-            A list of file paths that match the given basename and extension.
-
-        """
+        """Find all applicable metadata files using BIDS inheritance."""
         top_level_files = ["README", "dataset_description.json", "participants.tsv"]
         bids_files = []
 
-        # check if path is str object
         if isinstance(path, str):
             path = Path(path)
-        if not path.exists:
-            raise ValueError("path {path} does not exist")
+        if not path.exists():
+            raise ValueError(f"path {path} does not exist")
 
-        # check if file is in current path
         for file in os.listdir(path):
-            # target_file = path / f"{cur_file_basename}_{extension}"
-            if os.path.isfile(path / file):
-                # check if file has extension extension
-                # check if file basename has extension
-                if file.endswith(extension):
-                    filepath = path / file
-                    bids_files.append(filepath)
-
-        # check if file is in top level directory
+            if os.path.isfile(path / file) and file.endswith(extension):
+                bids_files.append(path / file)
+
         if any(file in os.listdir(path) for file in top_level_files):
             return bids_files
         else:
-            # call get_bids_file_inheritance recursively with parent directory
             bids_files.extend(
                 self._get_bids_file_inheritance(path.parent, basename, extension)
             )
             return bids_files
 
     def get_bids_metadata_files(
-        self, filepath: str | Path, metadata_file_extension: list[str]
+        self, filepath: str | Path, metadata_file_extension: str
     ) -> list[Path]:
-        """Retrieve all metadata file paths that apply to a given data file path and that
-        end with a specific suffix (following the BIDS inheritance principle).
+        """Retrieve all metadata files that apply to a given data file.
+
+        Follows the BIDS inheritance principle to find all relevant metadata
+        files (e.g., ``channels.tsv``, ``eeg.json``) for a specific recording.
 
         Parameters
         ----------
-        filepath: str | Path
-            The filepath to get the associated metadata files for.
+        filepath : str or Path
+            The path to the data file.
         metadata_file_extension : str
-            Consider only metadata files that end with the specified suffix,
-            e.g., channels.tsv or eeg.json
+            The extension of the metadata file to search for (e.g., "channels.tsv").
 
         Returns
         -------
-        list[Path]:
-            A list of filepaths for all matching metadata files
+        list of Path
+            A list of paths to the matching metadata files.
 
         """
         if isinstance(filepath, str):
             filepath = Path(filepath)
-        if not filepath.exists:
-            raise ValueError("filepath {filepath} does not exist")
+        if not filepath.exists():
+            raise ValueError(f"filepath {filepath} does not exist")
         path, filename = os.path.split(filepath)
         basename = filename[: filename.rfind("_")]
-        # metadata files
         meta_files = self._get_bids_file_inheritance(
             path, basename, metadata_file_extension
         )
         return meta_files
 
     def _scan_directory(self, directory: str, extension: str) -> list[Path]:
-        """Return a list of file paths that end with the given extension in the specified
-        directory. Ignores certain special directories like .git, .datalad, derivatives,
-        and code.
-        """
+        """Scan a directory for files with a given extension."""
         result_files = []
         directory_to_ignore = [".git", ".datalad", "derivatives", "code"]
         with os.scandir(directory) as entries:
             for entry in entries:
                 if entry.is_file() and entry.name.endswith(extension):
-                    result_files.append(entry.path)
-                elif entry.is_dir():
-                    # check that entry path doesn't contain any name in ignore list
-                    if not any(name in entry.name for name in directory_to_ignore):
-                        result_files.append(entry.path)  # Add directory to scan later
+                    result_files.append(Path(entry.path))
+                elif entry.is_dir() and not any(
+                    name in entry.name for name in directory_to_ignore
+                ):
+                    result_files.append(Path(entry.path))
         return result_files
 
     def _get_files_with_extension_parallel(
         self, directory: str, extension: str = ".set", max_workers: int = -1
     ) -> list[Path]:
-        """Efficiently scan a directory and its subdirectories for files that end with
-        the given extension.
-
-        Parameters
-        ----------
-        directory : str
-            The root directory to scan for files.
-        extension : str
-            Only consider files that end with this suffix, e.g. '.set'.
-        max_workers : int
-            Optionally specify the maximum number of worker threads to use for parallel scanning.
-            Defaults to all available CPU cores if set to -1.
-
-        Returns
-        -------
-        list[Path]:
-            A list of filepaths for all matching metadata files
-
-        """
+        """Scan a directory tree in parallel for files with a given extension."""
         result_files = []
         dirs_to_scan = [directory]
 
-        # Use joblib.Parallel and delayed to parallelize directory scanning
         while dirs_to_scan:
             logger.info(
                 f"Directories to scan: {len(dirs_to_scan)}, files: {dirs_to_scan}"
             )
-            # Run the scan_directory function in parallel across directories
             results = Parallel(n_jobs=max_workers, prefer="threads", verbose=1)(
                 delayed(self._scan_directory)(d, extension) for d in dirs_to_scan
             )
 
-            # Reset the directories to scan and process the results
             dirs_to_scan = []
             for res in results:
                 for path in res:
                     if os.path.isdir(path):
-                        dirs_to_scan.append(path)  # Queue up subdirectories to scan
+                        dirs_to_scan.append(path)
                     else:
-                        result_files.append(path)  # Add files to the final result
+                        result_files.append(path)
             logger.info(f"Found {len(result_files)} files.")
 
         return result_files
@@ -547,19 +511,29 @@ class EEGBIDSDataset:
     def load_and_preprocess_raw(
         self, raw_file: str, preprocess: bool = False
     ) -> np.ndarray:
-        """Utility function to load a raw data file with MNE and apply some simple
-        (hardcoded) preprocessing and return as a numpy array. Not meant for purposes
-        other than testing or debugging.
+        """Load and optionally preprocess a raw data file.
+
+        This is a utility function for testing or debugging, not for general use.
+
+        Parameters
+        ----------
+        raw_file : str
+            Path to the raw EEGLAB file (.set).
+        preprocess : bool, default False
+            If True, apply a high-pass filter, notch filter, and resample the data.
+
+        Returns
+        -------
+        numpy.ndarray
+            The loaded and processed data as a NumPy array.
+
         """
         logger.info(f"Loading raw data from {raw_file}")
         EEG = mne.io.read_raw_eeglab(raw_file, preload=True, verbose="error")
 
         if preprocess:
-            # highpass filter
             EEG = EEG.filter(l_freq=0.25, h_freq=25, verbose=False)
-            # remove 60Hz line noise
             EEG = EEG.notch_filter(freqs=(60), verbose=False)
-            # bring to common sampling rate
             sfreq = 128
             if EEG.info["sfreq"] != sfreq:
                 EEG = EEG.resample(sfreq)
@@ -570,26 +544,35 @@ class EEGBIDSDataset:
             raise ValueError("Expect raw data to be CxT dimension")
         return mat_data
 
-    def get_files(self) -> list[Path]:
-        """Get all EEG recording file paths (with valid extensions) in the BIDS folder."""
+    def get_files(self) -> list[str]:
+        """Get all EEG recording file paths in the BIDS dataset.
+
+        Returns
+        -------
+        list of str
+            A list of file paths for all valid EEG recordings.
+
+        """
         return self.files
 
     def resolve_bids_json(self, json_files: list[str]) -> dict:
-        """Resolve the BIDS JSON files and return a dictionary of the resolved values.
+        """Resolve BIDS JSON inheritance and merge files.
 
         Parameters
         ----------
-        json_files : list
-            A list of JSON file paths to resolve in order of leaf level first.
+        json_files : list of str
+            A list of JSON file paths, ordered from the lowest (most specific)
+            to highest level of the BIDS hierarchy.
 
         Returns
         -------
-            dict: A dictionary of the resolved values.
+        dict
+            A dictionary containing the merged JSON data.
 
         """
-        if len(json_files) == 0:
+        if not json_files:
             raise ValueError("No JSON files provided")
-        json_files.reverse()  # TODO undeterministic
+        json_files.reverse()
 
         json_dict = {}
         for json_file in json_files:
@@ -598,8 +581,20 @@ class EEGBIDSDataset:
         return json_dict
 
     def get_bids_file_attribute(self, attribute: str, data_filepath: str) -> Any:
-        """Retrieve a specific attribute from the BIDS file metadata applicable
-        to the provided recording file path.
+        """Retrieve a specific attribute from BIDS metadata.
+
+        Parameters
+        ----------
+        attribute : str
+            The name of the attribute to retrieve (e.g., "sfreq", "subject").
+        data_filepath : str
+            The path to the data file.
+
+        Returns
+        -------
+        Any
+            The value of the requested attribute, or None if not found.
+
         """
         entities = self.layout.parse_file_entities(data_filepath)
         bidsfile = self.layout.get(**entities)[0]
@@ -618,21 +613,59 @@ class EEGBIDSDataset:
         return attribute_value
 
     def channel_labels(self, data_filepath: str) -> list[str]:
-        """Get a list of channel labels for the given data file path."""
+        """Get a list of channel labels from channels.tsv.
+
+        Parameters
+        ----------
+        data_filepath : str
+            The path to the data file.
+
+        Returns
+        -------
+        list of str
+            A list of channel names.
+
+        """
         channels_tsv = pd.read_csv(
             self.get_bids_metadata_files(data_filepath, "channels.tsv")[0], sep="\t"
         )
         return channels_tsv["name"].tolist()
 
     def channel_types(self, data_filepath: str) -> list[str]:
-        """Get a list of channel types for the given data file path."""
+        """Get a list of channel types from channels.tsv.
+
+        Parameters
+        ----------
+        data_filepath : str
+            The path to the data file.
+
+        Returns
+        -------
+        list of str
+            A list of channel types.
+
+        """
         channels_tsv = pd.read_csv(
             self.get_bids_metadata_files(data_filepath, "channels.tsv")[0], sep="\t"
         )
         return channels_tsv["type"].tolist()
 
     def num_times(self, data_filepath: str) -> int:
-        """Get the approximate number of time points in the EEG recording based on the BIDS metadata."""
+        """Get the number of time points in the recording.
+
+        Calculated from ``SamplingFrequency`` and ``RecordingDuration`` in eeg.json.
+
+        Parameters
+        ----------
+        data_filepath : str
+            The path to the data file.
+
+        Returns
+        -------
+        int
+            The approximate number of time points.
+
+        """
         eeg_jsons = self.get_bids_metadata_files(data_filepath, "eeg.json")
         eeg_json_dict = self._merge_json_inheritance(eeg_jsons)
         return int(
@@ -640,38 +673,71 @@ class EEGBIDSDataset:
         )
 
     def subject_participant_tsv(self, data_filepath: str) -> dict[str, Any]:
-        """Get BIDS participants.tsv record for the subject to which the given file
-        path corresponds, as a dictionary.
+        """Get the participants.tsv record for a subject.
+
+        Parameters
+        ----------
+        data_filepath : str
+            The path to a data file belonging to the subject.
+
+        Returns
+        -------
+        dict
+            A dictionary of the subject's information from participants.tsv.
+
         """
-        participants_tsv = pd.read_csv(
-            self.get_bids_metadata_files(data_filepath, "participants.tsv")[0], sep="\t"
-        )
-        # if participants_tsv is not empty
+        participants_tsv_path = self.get_bids_metadata_files(
+            data_filepath, "participants.tsv"
+        )[0]
+        participants_tsv = pd.read_csv(participants_tsv_path, sep="\t")
         if participants_tsv.empty:
             return {}
-        # set 'participant_id' as index
         participants_tsv.set_index("participant_id", inplace=True)
         subject = f"sub-{self.get_bids_file_attribute('subject', data_filepath)}"
         return participants_tsv.loc[subject].to_dict()
 
     def eeg_json(self, data_filepath: str) -> dict[str, Any]:
-        """Get BIDS eeg.json metadata for the given data file path."""
+        """Get the merged eeg.json metadata for a data file.
+
+        Parameters
+        ----------
+        data_filepath : str
+            The path to the data file.
+
+        Returns
+        -------
+        dict
+            The merged eeg.json metadata.
+
+        """
         eeg_jsons = self.get_bids_metadata_files(data_filepath, "eeg.json")
-        eeg_json_dict = self._merge_json_inheritance(eeg_jsons)
-        return eeg_json_dict
+        return self._merge_json_inheritance(eeg_jsons)
 
     def channel_tsv(self, data_filepath: str) -> dict[str, Any]:
-        """Get BIDS channels.tsv metadata for the given data file path, as a dictionary
-        of lists and/or single values.
+        """Get the channels.tsv metadata as a dictionary.
+
+        Parameters
+        ----------
+        data_filepath : str
+            The path to the data file.
+
+        Returns
+        -------
+        dict
+            The channels.tsv data, with columns as keys.
+
         """
-        channels_tsv = pd.read_csv(
-            self.get_bids_metadata_files(data_filepath, "channels.tsv")[0], sep="\t"
-        )
-        channel_tsv = channels_tsv.to_dict()
-        # 'name' and 'type' now have a dictionary of index-value. Convert them to list
+        channels_tsv_path = self.get_bids_metadata_files(data_filepath, "channels.tsv")[
+            0
+        ]
+        channels_tsv = pd.read_csv(channels_tsv_path, sep="\t")
+        channel_tsv_dict = channels_tsv.to_dict()
         for list_field in ["name", "type", "units"]:
-            channel_tsv[list_field] = list(channel_tsv[list_field].values())
-        return channel_tsv
+            if list_field in channel_tsv_dict:
+                channel_tsv_dict[list_field] = list(
+                    channel_tsv_dict[list_field].values()
+                )
+        return channel_tsv_dict
 
 
 __all__ = ["EEGDashBaseDataset", "EEGBIDSDataset", "EEGDashBaseRaw"]