Braindecode 1.3.2.dev182822510__tar.gz → 1.3.2.dev183330317__tar.gz

{braindecode-1.3.2.dev182822510/braindecode.egg-info → braindecode-1.3.2.dev183330317}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.3.2.dev182822510
+Version: 1.3.2.dev183330317
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/braindecode/datasets/base.py

@@ -617,15 +617,6 @@ class WindowsDataset(RecordDataset):
         last_target_only: bool = True,
     ):
         super().__init__(description, transform)
-        self._fast_disk = self._can_use_fast_get_epoch_from_raw(windows)
-        if not (self._fast_disk or windows.preload):
-            warnings.warn(
-                "The provided mne.Epochs object does not meet the requirements for "
-                "fast epoch access. This may lead to slow data loading from disk. "
-                "Consider preloading the epochs or checking the conditions in "
-                "WindowsDataset._can_use_fast_get_epoch_from_raw.",
-                UserWarning,
-            )
         self.windows = windows
         self.last_target_only = last_target_only
         if targets_from not in ("metadata", "channels"):
@@ -642,20 +633,6 @@ class WindowsDataset(RecordDataset):
         self.raw_preproc_kwargs: list[dict[str, Any]] = []
         self.window_preproc_kwargs: list[dict[str, Any]] = []
 
-    @staticmethod
-    def _can_use_fast_get_epoch_from_raw(epochs: mne.BaseEpochs) -> bool:
-        """Check if we can use the fast _get_epoch_from_raw method,
-        or if we need to use the slow get_data method."""
-        return (
-            not epochs.preload
-            and epochs._bad_dropped
-            and epochs.detrend is None
-            and not epochs._do_baseline  # baseline is None
-            and (epochs._decim == 1)
-            and epochs._offset is None
-            and epochs._projector is None
-        )
-
     def __getitem__(self, index: int):
         """Get a window and its target.
 
@@ -673,10 +650,7 @@ class WindowsDataset(RecordDataset):
         np.ndarray
             Crop indices.
         """
-        if self._fast_disk:
-            X = self.windows._get_epoch_from_raw(index).astype("float32")
-        else:
-            X = self.windows.get_data(item=index)[0].astype("float32")
+        X = self.windows.get_data(item=index)[0].astype("float32")
         if self.transform is not None:
             X = self.transform(X)
         if self.targets_from == "metadata":

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/braindecode/datasets/bids/hub.py

@@ -27,7 +27,6 @@ The format follows a BIDS-inspired sourcedata structure:
 #
 # License: BSD (3-clause)
 
-import contextlib
 import json
 import logging
 import tempfile
@@ -70,8 +69,6 @@ huggingface_hub = _soft_import(
 
 log = logging.getLogger(__name__)
 
-_LOCK_FILE = "format_info.json"
-
 
 class HubDatasetMixin:
     """
@@ -87,6 +84,7 @@ class HubDatasetMixin:
     >>> dataset = NMT(path=path, preload=True)
     >>> dataset.push_to_hub(
     ...     repo_id="username/nmt-dataset",
+    ...     commit_message="Add NMT dataset"
     ... )
     >>>
     >>> # Load dataset from Hub
@@ -98,14 +96,13 @@ class HubDatasetMixin:
     def push_to_hub(
         self,
         repo_id: str,
+        commit_message: Optional[str] = None,
         private: bool = False,
         token: Optional[str] = None,
+        create_pr: bool = False,
         compression: str = "blosc",
         compression_level: int = 5,
         pipeline_name: str = "braindecode",
-        chunk_size: int = 10000,
-        local_cache_dir: str | Path | None = None,
-        **kwargs,
     ) -> str:
         """
         Upload the dataset to the Hugging Face Hub in BIDS-like Zarr format.
@@ -119,38 +116,20 @@ class HubDatasetMixin:
         ----------
         repo_id : str
             Repository ID on the Hugging Face Hub (e.g., "username/dataset-name").
+        commit_message : str | None
+            Commit message. If None, a default message is generated.
         private : bool, default=False
             Whether to create a private repository.
         token : str | None
             Hugging Face API token. If None, uses cached token.
+        create_pr : bool, default=False
+            Whether to create a Pull Request instead of directly committing.
         compression : str, default="blosc"
             Compression algorithm for Zarr. Options: "blosc", "zstd", "gzip", None.
         compression_level : int, default=5
             Compression level (0-9). Level 5 provides optimal balance.
         pipeline_name : str, default="braindecode"
             Name of the processing pipeline for BIDS sourcedata.
-        chunk_size : int, default=10000
-            Number of samples per chunk in Zarr. Larger chunk size will create fewer
-            but larger files. Only used for RawDataset and EEGWindowsDataset (continuous data).
-            With WindowsDataset (pre-cut epochs), each window is saved as a separate chunk.
-        local_cache_dir : str | Path | None
-            Local directory to use for temporary files during upload. If None, uses
-            the system temp directory and cleans it up after upload. If provided,
-            the directory is used as a persistent cache:
-
-            - If the directory is empty (or does not exist), the cache is built
-              there and a lock file (``format_info.json``) is written once
-              the cache is complete, before the upload starts. The file
-              contains the zarr conversion parameters as JSON.
-            - If the lock file is present and its JSON parameters match the
-              current call, cache creation is skipped and the upload resumes
-              directly (useful for retrying interrupted uploads).
-            - If the lock file is present but its JSON parameters differ from
-              the current call, a ``ValueError`` is raised.
-            - If the directory is non-empty but the lock file is absent, a
-              ``ValueError`` is raised listing the files found.
-        **kwargs
-            Additional arguments passed to huggingface_hub.upload_large_folder().
 
         Returns
         -------
@@ -170,6 +149,7 @@ class HubDatasetMixin:
         >>> # Upload with BIDS-like structure
         >>> url = dataset.push_to_hub(
         ...     repo_id="myusername/nmt-dataset",
+        ...     commit_message="Upload NMT EEG dataset"
         ... )
         """
         if huggingface_hub is False or zarr is False:
@@ -179,12 +159,13 @@ class HubDatasetMixin:
             )
 
         # Create API instance
-        hf_api = huggingface_hub.HfApi(token=token)
+        _ = huggingface_hub.HfApi(token=token)
 
         # Create repository if it doesn't exist
         try:
-            hf_api.create_repo(
+            huggingface_hub.create_repo(
                 repo_id=repo_id,
+                token=token,
                 private=private,
                 repo_type="dataset",
                 exist_ok=True,
@@ -192,68 +173,74 @@ class HubDatasetMixin:
         except Exception as e:
             raise RuntimeError(f"Failed to create repository: {e}")
 
-        format_info = self._get_format_info_inline()
-        format_info_lock = {
-            "format": "zarr",
-            "pipeline_name": pipeline_name,
-            "compression": compression,
-            "compression_level": compression_level,
-            "chunk_size": chunk_size,
-            "braindecode_version": braindecode.__version__,
-            **format_info,
-        }
+        # Create a temporary directory for upload
+        with tempfile.TemporaryDirectory() as tmpdir:
+            tmp_path = Path(tmpdir)
 
-        # Determine upload directory and whether to build the cache
-        with contextlib.ExitStack() as stack:
-            if local_cache_dir is None:
-                tmpdir = stack.enter_context(tempfile.TemporaryDirectory())
-                tmp_path = Path(tmpdir)
-                build_cache = True
-            else:
-                tmp_path = Path(local_cache_dir)
-                lock_path = tmp_path / _LOCK_FILE
-                if lock_path.exists():
-                    with open(lock_path, "r", encoding="utf-8") as _f:
-                        _lock_params = json.load(_f)
-                    if _lock_params != format_info_lock:
-                        raise ValueError(
-                            f"Lock file found at '{lock_path}' but its "
-                            f"parameters {_lock_params} differ from the "
-                            f"current call parameters {format_info_lock}. "
-                            "Provide an empty directory or match the "
-                            "original parameters."
-                        )
-                    log.info(
-                        f"Lock file found at '{lock_path}', skipping cache "
-                        "creation and resuming upload."
-                    )
-                    build_cache = False
-                else:
-                    if tmp_path.exists():
-                        existing = list(tmp_path.iterdir())
-                        if existing:
-                            entries = ", ".join(p.name for p in existing)
-                            raise ValueError(
-                                f"local_cache_dir '{tmp_path}' is not empty and "
-                                f"has no lock file. Found: {entries}. Provide an "
-                                "empty directory or one previously prepared by "
-                                "push_to_hub()."
-                            )
-                    else:
-                        tmp_path.mkdir(parents=True)
-                    build_cache = True
-
-            if build_cache:
-                self._build_local_cache(tmp_path, format_info_lock)
+            # Create BIDS-like sourcedata structure
+            log.info("Creating BIDS-like sourcedata structure...")
+            bids_layout = hub_format.BIDSSourcedataLayout(
+                tmp_path, pipeline_name=pipeline_name
+            )
+            sourcedata_dir = bids_layout.create_structure()
+
+            # Save dataset_description.json
+            bids_layout.save_dataset_description()
+
+            # Save participants.tsv
+            descriptions = [ds.description for ds in self.datasets]
+            bids_layout.save_participants(descriptions)
+
+            # Save BIDS sidecar files for each recording
+            self._save_bids_sidecar_files(bids_layout)
+
+            # Convert dataset to Zarr format inside sourcedata
+            log.info("Converting dataset to Zarr format...")
+            dataset_path = sourcedata_dir / "dataset.zarr"
+
+            self._convert_to_zarr_inline(
+                dataset_path,
+                compression,
+                compression_level,
+            )
+
+            # Save dataset metadata (README.md)
+            self._save_dataset_card(tmp_path)
+
+            # Save format info
+            format_info_path = tmp_path / "format_info.json"
+            with open(format_info_path, "w", encoding="utf-8") as f:
+                format_info = self._get_format_info_inline()
+                json.dump(
+                    {
+                        "format": "zarr",
+                        "pipeline_name": pipeline_name,
+                        "compression": compression,
+                        "compression_level": compression_level,
+                        "braindecode_version": braindecode.__version__,
+                        **format_info,
+                    },
+                    f,
+                    indent=2,
+                )
+
+            # Default commit message
+            if commit_message is None:
+                commit_message = (
+                    f"Upload EEG dataset in BIDS-like "
+                    f"Zarr format ({len(self.datasets)} recordings)"
+                )
 
             # Upload folder to Hub
             log.info(f"Uploading to Hugging Face Hub ({repo_id})...")
             try:
-                url = hf_api.upload_large_folder(
+                url = huggingface_hub.upload_folder(
                     repo_id=repo_id,
                     folder_path=str(tmp_path),
                     repo_type="dataset",
-                    **kwargs,
+                    commit_message=commit_message,
+                    token=token,
+                    create_pr=create_pr,
                 )
                 log.info(f"Dataset uploaded successfully to {repo_id}")
                 log.info(f"URL: https://huggingface.co/datasets/{repo_id}")
@@ -261,55 +248,6 @@ class HubDatasetMixin:
             except Exception as e:
                 raise RuntimeError(f"Failed to upload dataset: {e}")
 
-    def _build_local_cache(
-        self,
-        tmp_path,
-        format_info_lock,
-    ):
-        """Build the local cache directory with the dataset in Zarr format and BIDS-like structure.
-        This folder will be uploaded to the Hub"""
-        compression = format_info_lock["compression"]
-        compression_level = format_info_lock["compression_level"]
-        pipeline_name = format_info_lock["pipeline_name"]
-        chunk_size = format_info_lock["chunk_size"]
-
-        # Create BIDS-like sourcedata structure
-        log.info("Creating BIDS-like sourcedata structure...")
-        bids_layout = hub_format.BIDSSourcedataLayout(
-            tmp_path, pipeline_name=pipeline_name
-        )
-        sourcedata_dir = bids_layout.create_structure()
-
-        # Save dataset_description.json
-        bids_layout.save_dataset_description()
-
-        # Save participants.tsv
-        descriptions = [ds.description for ds in self.datasets]
-        bids_layout.save_participants(descriptions)
-
-        # Save BIDS sidecar files for each recording
-        self._save_bids_sidecar_files(bids_layout)
-
-        # Convert dataset to Zarr format inside sourcedata
-        log.info("Converting dataset to Zarr format...")
-        dataset_path = sourcedata_dir / "dataset.zarr"
-
-        self._convert_to_zarr_inline(
-            dataset_path,
-            compression,
-            compression_level,
-            chunk_size,
-        )
-
-        # Save dataset metadata (README.md)
-        self._save_dataset_card(tmp_path)
-
-        # Save format info
-        # This marks the cache as complete
-        format_info_path = tmp_path / _LOCK_FILE
-        with open(format_info_path, "w", encoding="utf-8") as f:
-            json.dump(format_info_lock, f, indent=2)
-
     def _save_dataset_card(self, path: Path, bids_inspired: bool = True) -> None:
         """Generate and save a dataset card (README.md) with metadata.
 
@@ -527,7 +465,7 @@ class HubDatasetMixin:
             )
 
             # Load format info
-            format_info_path = Path(dataset_dir) / _LOCK_FILE
+            format_info_path = Path(dataset_dir) / "format_info.json"
             if format_info_path.exists():
                 with open(format_info_path, "r") as f:
                     format_info = json.load(f)
@@ -657,7 +595,6 @@ class HubDatasetMixin:
         output_path: Path,
         compression: str,
         compression_level: int,
-        chunk_size: int = 10000,
     ) -> None:
         """Convert dataset to Zarr format (inline implementation)."""
 
@@ -745,7 +682,6 @@ class HubDatasetMixin:
                     targets_from,
                     last_target_only,
                     compressor,
-                    chunk_size,
                 )
 
             elif dataset_type == "RawDataset":
@@ -757,13 +693,7 @@ class HubDatasetMixin:
 
                 # Save using inlined function
                 _save_raw_to_zarr(
-                    grp,
-                    raw,
-                    description,
-                    info_dict,
-                    target_name,
-                    compressor,
-                    chunk_size,
+                    grp, raw, description, info_dict, target_name, compressor
                 )
 
     def _get_format_info_inline(self):

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/braindecode/datasets/bids/hub_io.py

@@ -70,15 +70,7 @@ def _save_windows_to_zarr(
 
 
 def _save_eegwindows_to_zarr(
-    grp,
-    raw,
-    metadata,
-    description,
-    info,
-    targets_from,
-    last_target_only,
-    compressor,
-    chunk_size,
+    grp, raw, metadata, description, info, targets_from, last_target_only, compressor
 ):
     """Save EEG continuous raw data to Zarr group (low-level function)."""
     continuous_data = raw.get_data()
@@ -88,7 +80,7 @@ def _save_eegwindows_to_zarr(
     grp.create_array(
         "data",
         data=continuous_float,
-        chunks=(continuous_float.shape[0], min(chunk_size, continuous_float.shape[1])),
+        chunks=(continuous_float.shape[0], min(10000, continuous_float.shape[1])),
         compressors=compressors_list,
     )
 
@@ -151,7 +143,7 @@ def _load_eegwindows_from_zarr(grp, preload):
     return data, metadata, description, info_dict, targets_from, last_target_only
 
 
-def _save_raw_to_zarr(grp, raw, description, info, target_name, compressor, chunk_size):
+def _save_raw_to_zarr(grp, raw, description, info, target_name, compressor):
     """Save RawDataset continuous raw data to Zarr group (low-level function)."""
     continuous_data = raw.get_data()
     continuous_float = continuous_data.astype(np.float32)
@@ -160,7 +152,7 @@ def _save_raw_to_zarr(grp, raw, description, info, target_name, compressor, chun
     grp.create_array(
         "data",
         data=continuous_float,
-        chunks=(continuous_float.shape[0], min(chunk_size, continuous_float.shape[1])),
+        chunks=(continuous_float.shape[0], min(10000, continuous_float.shape[1])),
         compressors=compressors_list,
     )
 

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/braindecode/datautil/hub_formats.py

@@ -36,7 +36,6 @@ def convert_to_zarr(
     output_path: Union[str, Path],
     compression: str = "blosc",
     compression_level: int = 5,
-    chunk_size: int = 10000,
     overwrite: bool = False,
 ) -> Path:
     """Convert BaseConcatDataset to Zarr format.
@@ -59,10 +58,6 @@ def convert_to_zarr(
         blosc uses zstd codec by default, providing best balance of speed and compression.
     compression_level : int, default=5
         Compression level (0-9). Level 5 provides optimal balance based on benchmarks.
-    chunk_size : int, default=10000
-        Number of samples per chunk in Zarr. Larger chunk size will create fewer
-        but larger files. Only used for RawDataset and EEGWindowsDataset (continuous data).
-        With WindowsDataset (pre-cut epochs), each window is saved as a separate chunk.
     overwrite : bool, default=False
         Whether to overwrite existing directory.
 
@@ -101,9 +96,7 @@ def convert_to_zarr(
         shutil.rmtree(output_path)
 
     # Delegate to HubDatasetMixin method
-    dataset._convert_to_zarr_inline(
-        output_path, compression, compression_level, chunk_size
-    )
+    dataset._convert_to_zarr_inline(output_path, compression, compression_level)
 
     return output_path
 

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/braindecode/preprocessing/windowers.py

@@ -12,7 +12,6 @@
 #          Mohammed Fattouh <mo.fattouh@gmail.com>
 #          Robin Schirrmeister <robintibor@gmail.com>
 #          Matthew Chen <matt.chen42601@gmail.com>
-#          Sarthak Tayal <sarthaktayal2@gmail.com>
 #
 # License: BSD (3-clause)
 
@@ -1046,12 +1045,8 @@ def _create_windows_from_target_channels(
     stop = ds.raw.n_times + ds.raw.first_samp
 
     target = ds.raw.get_data(picks="misc")
-
-    # check all misc channels for valid targets, not just the first one.
-    # when multiple target channels exist, some may have values at timepoints
-    # where others are nan. using any() across channels catches all of them.
-    has_target = np.any(~np.isnan(target), axis=0)
-    stops = np.nonzero(has_target)[0] + 1
+    # TODO: handle multi targets present only for some events
+    stops = np.nonzero((~np.isnan(target[0, :])))[0] + 1
     stops = stops[(stops < stop) & (stops >= window_size_samples)]
     stops = stops.astype(int)
     metadata = pd.DataFrame(

braindecode-1.3.2.dev183330317/braindecode/version.py

@@ -0,0 +1 @@
+__version__ = "1.3.2.dev183330317"

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/braindecode/visualization/gradients.py

@@ -1,5 +1,4 @@
 # Authors: Robin Schirrmeister <robintibor@gmail.com>
-#          Sarthak Tayal <sarthaktayal2@gmail.com>
 #
 # License: BSD (3-clause)
 
@@ -36,17 +35,18 @@ def compute_amplitude_gradients_for_X(model, X):
     amps_th = to_tensor(amps.astype(np.float32), device=device).requires_grad_(True)
     phases_th = to_tensor(phases.astype(np.float32), device=device).requires_grad_(True)
 
-    # rebuild fft coefficients from amplitude and phase as real valued pairs,
-    # convert to complex, and invert back to the time domain.
-    # torch.irfft was removed after being deprecated since pytorch 1.7,
-    # so we use torch.fft.irfft which expects complex input directly.
     fft_coefs = amps_th.unsqueeze(-1) * torch.stack(
         (torch.cos(phases_th), torch.sin(phases_th)), dim=-1
     )
     fft_coefs = fft_coefs.squeeze(3)
 
-    complex_fft_coefs = torch.view_as_complex(fft_coefs)
-    iffted = torch.fft.irfft(complex_fft_coefs, n=X.shape[2], dim=2)
+    try:
+        complex_fft_coefs = torch.view_as_complex(fft_coefs)
+        iffted = torch.fft.irfft(complex_fft_coefs, n=X.shape[2], dim=2)
+    except AttributeError:
+        iffted = torch.irfft(  # Deprecated since 1.7
+            fft_coefs, signal_ndim=1, signal_sizes=(X.shape[2],)
+        )
 
     outs = model(iffted)
 

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317/braindecode.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: braindecode
-Version: 1.3.2.dev182822510
+Version: 1.3.2.dev183330317
 Summary: Deep learning software to decode EEG, ECG or MEG signals
 Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
 Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>

{braindecode-1.3.2.dev182822510 → braindecode-1.3.2.dev183330317}/docs/whats_new.rst

@@ -54,7 +54,6 @@ Enhancements
   (:gh:`941` by `Aman Srivastava`_).
 - Per-event-type windowing parameters in :func:`braindecode.preprocessing.windowers.create_windows_from_events` (:gh:`942` by `Pierre Guetschel`_)
 - Add ``use_mne_epochs`` support to :func:`braindecode.preprocessing.windowers.create_fixed_length_windows` (:gh:`943` by `Pierre Guetschel`_)
-- Faster loading from epochs on disk with :class:`braindecode.datasets.base.WindowsDataset` (:gh:`944` by `Pierre Guetschel`_)
 
 API changes
 ============
@@ -66,9 +65,6 @@ Requirements
 
 Bugs
 =====
-- Fix multi-target channel windowing in :func:`braindecode.preprocessing.windowers.create_windows_from_target_channels`
-  to use the union of valid target positions across all misc channels instead of only the first channel
-  (by `Sarthak Tayal`_)
 - Fix :func:`braindecode.preprocessing.preprocess.filterbank` to preserve info fields
   (``description``, ``line_freq``, ``device_info``, etc.) when creating filtered copies,
   avoiding merge conflicts in MNE when adding channels (:gh:`928` by `Bruno Aristimunha`_)
@@ -77,13 +73,10 @@ Bugs
 - Fix Zenodo citation: update to global concept DOI and add BibTeX/APA citation formats
   in ``docs/cite.rst``, ``README.rst``, ``CITATION.cff``, and ``docs/conf.py``
   (:gh:`937` by `Bruno Aristimunha`_)
-- Push large datasets to HuggingFace Hub using :func:`huggingface_hub.upload_large_folder` to avoid limitations, and allow resuming downloads (:gh:`945` by `Pierre Guetschel`_)
 
 Code health
 ============
-- Remove deprecated ``torch.irfft`` fallback in :func:`braindecode.visualization.gradients.compute_amplitude_gradients_for_X`,
-  now uses ``torch.fft.irfft`` directly since braindecode requires ``torch>=2.2``
-  (by `Sarthak Tayal`_)
+- None yet.
 
 
 Current 1.3.2 (stable)
@@ -831,4 +824,3 @@ Authors
 .. _Aniela Bulicz: https://github.com/AryaDro
 .. _Mattew Chew: https://github.com/MatthewChen37
 .. _Aman Srivastava: https://github.com/aman-coder03
-.. _Sarthak Tayal: https://github.com/tayal-sarthak

braindecode-1.3.2.dev182822510/braindecode/version.py

@@ -1 +0,0 @@
-__version__ = "1.3.2.dev182822510"