eegdash 0.3.0.dev46__tar.gz → 0.3.1__tar.gz

{eegdash-0.3.0.dev46 → eegdash-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.0.dev46
+Version: 0.3.1
 Summary: EEG data for machine learning
 Author-email: Young Truong <dt.young112@gmail.com>, Arnaud Delorme <adelorme@gmail.com>, Bruno Aristimunha <b.aristimunha@gmail.com>
 License: GNU General Public License

{eegdash-0.3.0.dev46 → eegdash-0.3.1}/eegdash/__init__.py

@@ -5,4 +5,4 @@ from .utils import __init__mongo_client
 __init__mongo_client()
 
 __all__ = ["EEGDash", "EEGDashDataset", "EEGChallengeDataset"]
-__version__ = "0.3.0.dev46"
+__version__ = "0.3.1"

{eegdash-0.3.0.dev46 → eegdash-0.3.1}/eegdash/data_utils.py

@@ -6,7 +6,6 @@ from pathlib import Path
 from typing import Any
 
 import mne
-import mne_bids
 import numpy as np
 import pandas as pd
 import s3fs
@@ -62,10 +61,23 @@ class EEGDashBaseDataset(BaseDataset):
             suffix="eeg",
             **bids_kwargs,
         )
-        self.s3_bucket = s3_bucket if s3_bucket else self._AWS_BUCKET
+        if s3_bucket:
+            self.s3_bucket = s3_bucket
+            self.s3_open_neuro = False
+        else:
+            self.s3_bucket = self._AWS_BUCKET
+            self.s3_open_neuro = True
+
         self.s3file = self.get_s3path(record["bidspath"])
         self.filecache = self.cache_dir / record["bidspath"]
         self.bids_dependencies = record["bidsdependencies"]
+        # Temporary fix for BIDS dependencies path
+        # just to release to the competition
+        if not self.s3_open_neuro:
+            self.bids_dependencies = [
+                dep.split("/", 1)[1] for dep in self.bids_dependencies
+            ]
+
         self._raw = None
 
     def get_s3path(self, filepath: str) -> str:
@@ -78,6 +90,9 @@ class EEGDashBaseDataset(BaseDataset):
         filesystem = s3fs.S3FileSystem(
             anon=True, client_kwargs={"region_name": "us-east-2"}
         )
+        if not self.s3_open_neuro:
+            self.s3file = re.sub(r"(^|/)ds\d{6}/", r"\1", self.s3file, count=1)
+
         filesystem.download(self.s3file, self.filecache)
         self.filenames = [self.filecache]
 
@@ -109,7 +124,7 @@ class EEGDashBaseDataset(BaseDataset):
                 self._download_dependencies()
             self._download_s3()
         if self._raw is None:
-            self._raw = mne_bids.read_raw_bids(self.bidspath, verbose=False)
+            self._raw = mne.io.read_raw(fname=self.bidspath, verbose=False)
 
     # === BaseDataset and PyTorch Dataset interface ===
 
@@ -216,6 +231,7 @@ class EEGDashBaseRaw(BaseRaw):
         )
 
     def get_s3path(self, filepath):
+        print(f"Getting S3 path for {filepath}")
         return f"{self._AWS_BUCKET}/{filepath}"
 
     def _download_s3(self):

{eegdash-0.3.0.dev46 → eegdash-0.3.1}/eegdash/dataset.py

@@ -1,5 +1,19 @@
 from .api import EEGDashDataset
 
+RELEASE_TO_OPENNEURO_DATASET_MAP = {
+    "R11": "ds005516",
+    "R10": "ds005515",
+    "R9": "ds005514",
+    "R8": "ds005512",
+    "R7": "ds005511",
+    "R6": "ds005510",
+    "R4": "ds005508",
+    "R5": "ds005509",
+    "R3": "ds005507",
+    "R2": "ds005506",
+    "R1": "ds005505",
+}
+
 
 class EEGChallengeDataset(EEGDashDataset):
     def __init__(
@@ -7,7 +21,7 @@ class EEGChallengeDataset(EEGDashDataset):
         release: str = "R5",
         query: dict | None = None,
         cache_dir: str = ".eegdash_cache",
-        s3_bucket: str | None = "s3://nmdatasets/NeurIPS25/",
+        s3_bucket: str | None = "s3://nmdatasets/NeurIPS25",
         **kwargs,
     ):
         """Create a new EEGDashDataset from a given query or local BIDS dataset directory
@@ -32,25 +46,11 @@ class EEGChallengeDataset(EEGDashDataset):
             constructor.
 
         """
-        dsnumber_release_map = {
-            "R11": "ds005516",
-            "R10": "ds005515",
-            "R9": "ds005514",
-            "R8": "ds005512",
-            "R7": "ds005511",
-            "R6": "ds005510",
-            "R4": "ds005508",
-            "R5": "ds005509",
-            "R3": "ds005507",
-            "R2": "ds005506",
-            "R1": "ds005505",
-        }
-
         self.release = release
-        if release not in dsnumber_release_map:
+        if release not in RELEASE_TO_OPENNEURO_DATASET_MAP:
             raise ValueError(f"Unknown release: {release}")
 
-        dataset = dsnumber_release_map[release]
+        dataset = RELEASE_TO_OPENNEURO_DATASET_MAP[release]
         if query is None:
             query = {"dataset": dataset}
         elif "dataset" not in query:

{eegdash-0.3.0.dev46 → eegdash-0.3.1}/eegdash.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.0.dev46
+Version: 0.3.1
 Summary: EEG data for machine learning
 Author-email: Young Truong <dt.young112@gmail.com>, Arnaud Delorme <adelorme@gmail.com>, Bruno Aristimunha <b.aristimunha@gmail.com>
 License: GNU General Public License

{eegdash-0.3.0.dev46 → eegdash-0.3.1}/tests/test_dataset.py

@@ -30,7 +30,7 @@ def test_eeg_challenge_dataset_initialization():
     dataset = EEGChallengeDataset(release="R5")
 
     release = "R5"
-    expected_bucket_prefix = f"s3://nmdatasets/NeurIPS25//{release}_L100"
+    expected_bucket_prefix = f"s3://nmdatasets/NeurIPS25/{release}_L100"
     assert dataset.s3_bucket == expected_bucket_prefix, (
         f"Unexpected s3_bucket: {dataset.s3_bucket} (expected {expected_bucket_prefix})"
     )
@@ -79,4 +79,10 @@ def test_mongodb_load_under_slo(release):
     start_time = time.perf_counter()
     _ = EEGChallengeDataset(release=release)
     duration = time.perf_counter() - start_time
-    assert duration < 10, f"{release} took {duration:.2f}s"
+    assert duration < 30, f"{release} took {duration:.2f}s"
+
+
+def test_consuming_data_r5():
+    dataset_obj = EEGChallengeDataset(release="R5", query=dict(task="RestingState"))
+    raw = dataset_obj.datasets[0].raw
+    assert raw is not None