eegdash 0.3.2.dev54__py3-none-any.whl → 0.3.3.dev61__py3-none-any.whl

eegdash/__init__.py

@@ -5,4 +5,4 @@ from .utils import __init__mongo_client
 __init__mongo_client()
 
 __all__ = ["EEGDash", "EEGDashDataset", "EEGChallengeDataset"]
-__version__ = "0.3.2.dev54"
+__version__ = "0.3.3.dev61"

eegdash/api.py

@@ -534,6 +534,7 @@ class EEGDashDataset(BaseConcatDataset):
         ],
         cache_dir: str = "~/eegdash_cache",
         s3_bucket: str | None = None,
+        eeg_dash_instance=None,
         **kwargs,
     ):
         """Create a new EEGDashDataset from a given query or local BIDS dataset directory
@@ -568,29 +569,51 @@ class EEGDashDataset(BaseConcatDataset):
         """
         self.cache_dir = cache_dir
         self.s3_bucket = s3_bucket
-        if query:
-            datasets = self.find_datasets(query, description_fields, **kwargs)
-        elif data_dir:
-            if isinstance(data_dir, str):
-                datasets = self.load_bids_dataset(
-                    dataset, data_dir, description_fields, s3_bucket
-                )
+        self.eeg_dash = eeg_dash_instance or EEGDash()
+        _owns_client = eeg_dash_instance is None
+
+        try:
+            if query:
+                datasets = self.find_datasets(query, description_fields, **kwargs)
+            elif data_dir:
+                if isinstance(data_dir, str):
+                    datasets = self.load_bids_dataset(
+                        dataset, data_dir, description_fields, s3_bucket, **kwargs
+                    )
+                else:
+                    assert len(data_dir) == len(dataset), (
+                        "Number of datasets and their directories must match"
+                    )
+                    datasets = []
+                    for i, _ in enumerate(data_dir):
+                        datasets.extend(
+                            self.load_bids_dataset(
+                                dataset[i],
+                                data_dir[i],
+                                description_fields,
+                                s3_bucket,
+                                **kwargs,
+                            )
+                        )
             else:
-                assert len(data_dir) == len(dataset), (
-                    "Number of datasets and their directories must match"
+                raise ValueError(
+                    "Exactly one of 'query' or 'data_dir' must be provided."
                 )
-                datasets = []
-                for i, _ in enumerate(data_dir):
-                    datasets.extend(
-                        self.load_bids_dataset(
-                            dataset[i], data_dir[i], description_fields, s3_bucket
-                        )
-                    )
+        finally:
+            # If we created the client, close it now that construction is done.
+            if _owns_client:
+                try:
+                    self.eeg_dash.close()
+                except Exception:
+                    # Don't let close errors break construction
+                    pass
 
         self.filesystem = S3FileSystem(
             anon=True, client_kwargs={"region_name": "us-east-2"}
         )
 
+        self.eeg_dash.close()
+
         super().__init__(datasets)
 
     def find_key_in_nested_dict(self, data: Any, target_key: str) -> Any:
@@ -628,27 +651,23 @@ class EEGDashDataset(BaseConcatDataset):
             A list of EEGDashBaseDataset objects that match the query.
 
         """
-        eeg_dash_instance = EEGDash()
-        try:
-            datasets = []
-            for record in eeg_dash_instance.find(query):
-                description = {}
-                for field in description_fields:
-                    value = self.find_key_in_nested_dict(record, field)
-                    if value is not None:
-                        description[field] = value
-                datasets.append(
-                    EEGDashBaseDataset(
-                        record,
-                        self.cache_dir,
-                        self.s3_bucket,
-                        description=description,
-                        **kwargs,
-                    )
+        datasets: list[EEGDashBaseDataset] = []
+        for record in self.eeg_dash.find(query):
+            description = {}
+            for field in description_fields:
+                value = self.find_key_in_nested_dict(record, field)
+                if value is not None:
+                    description[field] = value
+            datasets.append(
+                EEGDashBaseDataset(
+                    record,
+                    self.cache_dir,
+                    self.s3_bucket,
+                    description=description,
+                    **kwargs,
                 )
-            return datasets
-        finally:
-            eeg_dash_instance.close()
+            )
+        return datasets
 
     def load_bids_dataset(
         self,
@@ -676,36 +695,28 @@ class EEGDashDataset(BaseConcatDataset):
             data_dir=data_dir,
             dataset=dataset,
         )
-        eeg_dash_instance = EEGDash()
-        try:
-            datasets = Parallel(n_jobs=-1, prefer="threads", verbose=1)(
-                delayed(self.get_base_dataset_from_bids_file)(
-                    bids_dataset=bids_dataset,
-                    bids_file=bids_file,
-                    eeg_dash_instance=eeg_dash_instance,
-                    s3_bucket=s3_bucket,
-                    description_fields=description_fields,
-                )
-                for bids_file in bids_dataset.get_files()
+        datasets = Parallel(n_jobs=-1, prefer="threads", verbose=1)(
+            delayed(self.get_base_dataset_from_bids_file)(
+                bids_dataset=bids_dataset,
+                bids_file=bids_file,
+                s3_bucket=s3_bucket,
+                description_fields=description_fields,
+                **kwargs,
             )
-            return datasets
-        finally:
-            eeg_dash_instance.close()
+            for bids_file in bids_dataset.get_files()
+        )
+        return datasets
 
     def get_base_dataset_from_bids_file(
         self,
-        bids_dataset: EEGBIDSDataset,
+        bids_dataset: "EEGBIDSDataset",
         bids_file: str,
-        eeg_dash_instance: EEGDash,
         s3_bucket: str | None,
         description_fields: list[str],
-    ) -> EEGDashBaseDataset:
-        """Instantiate a single EEGDashBaseDataset given a local BIDS file. Note
-        this does not actually load the data from disk, but will access the metadata.
-        """
-        record = eeg_dash_instance.load_eeg_attrs_from_bids_file(
-            bids_dataset, bids_file
-        )
+        **kwargs,
+    ) -> "EEGDashBaseDataset":
+        """Instantiate a single EEGDashBaseDataset given a local BIDS file (metadata only)."""
+        record = self.eeg_dash.load_eeg_attrs_from_bids_file(bids_dataset, bids_file)
         description = {}
         for field in description_fields:
             value = self.find_key_in_nested_dict(record, field)
@@ -716,4 +727,5 @@ class EEGDashDataset(BaseConcatDataset):
             self.cache_dir,
             s3_bucket,
             description=description,
+            **kwargs,
         )

eegdash/data_utils.py

@@ -10,6 +10,7 @@ import numpy as np
 import pandas as pd
 import s3fs
 from bids import BIDSLayout
+from fsspec.callbacks import TqdmCallback
 from joblib import Parallel, delayed
 from mne._fiff.utils import _read_segments_file
 from mne.io import BaseRaw
@@ -98,8 +99,27 @@ class EEGDashBaseDataset(BaseDataset):
             self.s3file = re.sub(r"(^|/)ds\d{6}/", r"\1", self.s3file, count=1)
 
         self.filecache.parent.mkdir(parents=True, exist_ok=True)
+        info = filesystem.info(self.s3file)
+        size = info.get("size") or info.get("Size")
+
+        callback = TqdmCallback(
+            size=size,
+            tqdm_kwargs=dict(
+                desc=f"Downloading {Path(self.s3file).name}",
+                unit="B",
+                unit_scale=True,
+                unit_divisor=1024,
+                dynamic_ncols=True,
+                leave=True,
+                mininterval=0.2,
+                smoothing=0.1,
+                miniters=1,
+                bar_format="{desc}: {percentage:3.0f}%|{bar}| {n_fmt}/{total_fmt} "
+                "[{elapsed}<{remaining}, {rate_fmt}]",
+            ),
+        )
+        filesystem.get(self.s3file, self.filecache, callback=callback)
 
-        filesystem.download(self.s3file, self.filecache)
         self.filenames = [self.filecache]
 
     def _download_dependencies(self) -> None:
@@ -119,7 +139,26 @@ class EEGDashBaseDataset(BaseDataset):
             # in the case of the competition.
             if not filepath.exists():
                 filepath.parent.mkdir(parents=True, exist_ok=True)
-                filesystem.download(s3path, filepath)
+                info = filesystem.info(s3path)
+                size = info.get("size") or info.get("Size")
+
+                callback = TqdmCallback(
+                    size=size,
+                    tqdm_kwargs=dict(
+                        desc=f"Downloading {Path(s3path).name}",
+                        unit="B",
+                        unit_scale=True,
+                        unit_divisor=1024,
+                        dynamic_ncols=True,
+                        leave=True,
+                        mininterval=0.2,
+                        smoothing=0.1,
+                        miniters=1,
+                        bar_format="{desc}: {percentage:3.0f}%|{bar}| {n_fmt}/{total_fmt} "
+                        "[{elapsed}<{remaining}, {rate_fmt}]",
+                    ),
+                )
+                filesystem.get(s3path, filepath, callback=callback)
 
     def get_raw_bids_args(self) -> dict[str, Any]:
         """Helper to restrict the metadata record to the fields needed to locate a BIDS

{eegdash-0.3.2.dev54.dist-info → eegdash-0.3.3.dev61.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.2.dev54
+Version: 0.3.3.dev61
 Summary: EEG data for machine learning
 Author-email: Young Truong <dt.young112@gmail.com>, Arnaud Delorme <adelorme@gmail.com>, Aviv Dotan <avivd220@gmail.com>, Oren Shriki <oren70@gmail.com>, Bruno Aristimunha <b.aristimunha@gmail.com>
 License: GNU General Public License
@@ -60,6 +60,8 @@ Requires-Dist: s3fs
 Requires-Dist: scipy
 Requires-Dist: tqdm
 Requires-Dist: xarray
+Requires-Dist: h5io>=0.2.4
+Requires-Dist: pymatreader
 Provides-Extra: tests
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"

{eegdash-0.3.2.dev54.dist-info → eegdash-0.3.3.dev61.dist-info}/RECORD

@@ -1,7 +1,7 @@
-eegdash/__init__.py,sha256=52uzfdLjujAnXKER5pn7ft52HHmDirUOIeqT-68J7Sk,238
-eegdash/api.py,sha256=lYCILa69Y_RRd4_13x1Ge77FDGswnEG2DEfdPzMygAY,26865
+eegdash/__init__.py,sha256=PQbCZHVxYTBpYOu1wIrGntJNKXt7bK0qh5kq8mb3ufo,238
+eegdash/api.py,sha256=OqOZ27GYURSAZwTQHSs0QcW_6Mq1i_5XHP6KMcihb8A,27295
 eegdash/data_config.py,sha256=OS6ERO-jHrnEOfMJUehY7ieABdsRw_qWzOKJ4pzSfqw,1323
-eegdash/data_utils.py,sha256=h1FLCTjRj2JDn6IFnVgWrogDYnHFR4mcuDF23KNtLZI,24530
+eegdash/data_utils.py,sha256=8Jb_94uVbdknNPpx3GBl4dCDYUIJNzl3zkLwbfH90N4,26052
 eegdash/dataset.py,sha256=GVELU-eXq9AQDzOeg6Lkykd-Pctyn42e5UEcAV0Go4s,2348
 eegdash/mongodb.py,sha256=GD3WgA253oFgpzOHrYaj4P1mRjNtDMT5Oj4kVvHswjI,2006
 eegdash/preprocessing.py,sha256=7S_TTRKPKEk47tTnh2D6WExBt4cctAMxUxGDjJqq5lU,2221
@@ -21,8 +21,8 @@ eegdash/features/feature_bank/dimensionality.py,sha256=j_Ds71Y1AbV2uLFQj8EuXQ4kz
 eegdash/features/feature_bank/signal.py,sha256=3Tb8z9gX7iZipxQJ9DSyy30JfdmW58kgvimSyZX74p8,3404
 eegdash/features/feature_bank/spectral.py,sha256=bNB7skusePs1gX7NOU6yRlw_Gr4UOCkO_ylkCgybzug,3319
 eegdash/features/feature_bank/utils.py,sha256=DGh-Q7-XFIittP7iBBxvsJaZrlVvuY5mw-G7q6C-PCI,1237
-eegdash-0.3.2.dev54.dist-info/licenses/LICENSE,sha256=asisR-xupy_NrQBFXnx6yqXeZcYWLvbAaiETl25iXT0,931
-eegdash-0.3.2.dev54.dist-info/METADATA,sha256=xGiRhU968Kcvz5Wj6RiavV6yMG72G5eSpnXsxvFX9hU,11429
-eegdash-0.3.2.dev54.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-eegdash-0.3.2.dev54.dist-info/top_level.txt,sha256=zavO69HQ6MyZM0aQMR2zUS6TAFc7bnN5GEpDpOpFZzU,8
-eegdash-0.3.2.dev54.dist-info/RECORD,,
+eegdash-0.3.3.dev61.dist-info/licenses/LICENSE,sha256=asisR-xupy_NrQBFXnx6yqXeZcYWLvbAaiETl25iXT0,931
+eegdash-0.3.3.dev61.dist-info/METADATA,sha256=W_KFw8Hn3ekBmHKfVPzX-WS3Ylv3Xkn_yWbauePYbOY,11483
+eegdash-0.3.3.dev61.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+eegdash-0.3.3.dev61.dist-info/top_level.txt,sha256=zavO69HQ6MyZM0aQMR2zUS6TAFc7bnN5GEpDpOpFZzU,8
+eegdash-0.3.3.dev61.dist-info/RECORD,,