eegdash 0.3.1.dev50__tar.gz → 0.3.2.dev52__tar.gz

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.1.dev50
+Version: 0.3.2.dev52
 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

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/eegdash/__init__.py

@@ -5,4 +5,4 @@ from .utils import __init__mongo_client
 __init__mongo_client()
 
 __all__ = ["EEGDash", "EEGDashDataset", "EEGChallengeDataset"]
-__version__ = "0.3.1.dev50"
+__version__ = "0.3.2.dev52"

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/eegdash/api.py

@@ -532,7 +532,7 @@ class EEGDashDataset(BaseConcatDataset):
             "gender",
             "sex",
         ],
-        cache_dir: str = ".eegdash_cache",
+        cache_dir: str = "~/eegdash_cache",
         s3_bucket: str | None = None,
         **kwargs,
     ):
@@ -587,6 +587,10 @@ class EEGDashDataset(BaseConcatDataset):
                         )
                     )
 
+        self.filesystem = S3FileSystem(
+            anon=True, client_kwargs={"region_name": "us-east-2"}
+        )
+
         super().__init__(datasets)
 
     def find_key_in_nested_dict(self, data: Any, target_key: str) -> Any:

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/eegdash/data_utils.py

@@ -53,24 +53,24 @@ class EEGDashBaseDataset(BaseDataset):
         super().__init__(None, **kwargs)
         self.record = record
         self.cache_dir = Path(cache_dir)
-        bids_kwargs = self.get_raw_bids_args()
+        self.bids_kwargs = self.get_raw_bids_args()
 
         if s3_bucket:
             self.s3_bucket = s3_bucket
             self.s3_open_neuro = False
-            bids_root = self.cache_dir
-            self.filecache = self.cache_dir / record["bidspath"]
         else:
             self.s3_bucket = self._AWS_BUCKET
             self.s3_open_neuro = True
-            bids_root = self.cache_dir / record["dataset"]
-            self.filecache = self.cache_dir / record["bidspath"]
+
+        self.filecache = self.cache_dir / record["bidspath"]
+
+        self.bids_root = self.cache_dir / record["dataset"]
 
         self.bidspath = BIDSPath(
-            root=bids_root,
+            root=self.bids_root,
             datatype="eeg",
             suffix="eeg",
-            **bids_kwargs,
+            **self.bids_kwargs,
         )
 
         self.s3file = self.get_s3path(record["bidspath"])
@@ -78,6 +78,7 @@ class EEGDashBaseDataset(BaseDataset):
         # Temporary fix for BIDS dependencies path
         # just to release to the competition
         if not self.s3_open_neuro:
+            self.bids_dependencies_original = self.bids_dependencies
             self.bids_dependencies = [
                 dep.split("/", 1)[1] for dep in self.bids_dependencies
             ]
@@ -95,12 +96,9 @@ class EEGDashBaseDataset(BaseDataset):
         )
         if not self.s3_open_neuro:
             self.s3file = re.sub(r"(^|/)ds\d{6}/", r"\1", self.s3file, count=1)
-            self.filecache = re.sub(
-                r"(^|/)ds\d{6}/", r"\1", str(self.filecache), count=1
-            )
-            self.filecache = Path(self.filecache)
 
         self.filecache.parent.mkdir(parents=True, exist_ok=True)
+
         filesystem.download(self.s3file, self.filecache)
         self.filenames = [self.filecache]
 
@@ -111,8 +109,11 @@ class EEGDashBaseDataset(BaseDataset):
         filesystem = s3fs.S3FileSystem(
             anon=True, client_kwargs={"region_name": "us-east-2"}
         )
-        for dep in self.bids_dependencies:
+        for i, dep in enumerate(self.bids_dependencies):
             s3path = self.get_s3path(dep)
+            if not self.s3_open_neuro:
+                dep = self.bids_dependencies_original[i]
+
             filepath = self.cache_dir / dep
             # here, we download the dependency and it is fine
             # in the case of the competition.
@@ -207,7 +208,7 @@ class EEGDashBaseRaw(BaseRaw):
         metadata: dict[str, Any],
         preload: bool = False,
         *,
-        cache_dir: str = "./.eegdash_cache",
+        cache_dir: str = "~/eegdash_cache",
         bids_dependencies: list[str] = [],
         verbose: Any = None,
     ):
@@ -244,7 +245,7 @@ class EEGDashBaseRaw(BaseRaw):
         print(f"Getting S3 path for {filepath}")
         return f"{self._AWS_BUCKET}/{filepath}"
 
-    def _download_s3(self):
+    def _download_s3(self) -> None:
         self.filecache.parent.mkdir(parents=True, exist_ok=True)
         filesystem = s3fs.S3FileSystem(
             anon=True, client_kwargs={"region_name": "us-east-2"}

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/eegdash/dataset.py

@@ -18,9 +18,9 @@ RELEASE_TO_OPENNEURO_DATASET_MAP = {
 class EEGChallengeDataset(EEGDashDataset):
     def __init__(
         self,
-        release: str = "R5",
+        release: str,
+        cache_dir: str,
         query: dict | None = None,
-        cache_dir: str = ".eegdash_cache",
         s3_bucket: str | None = "s3://nmdatasets/NeurIPS25",
         **kwargs,
     ):

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/eegdash.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.1.dev50
+Version: 0.3.2.dev52
 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

{eegdash-0.3.1.dev50 → eegdash-0.3.2.dev52}/tests/test_dataset.py

@@ -1,4 +1,5 @@
 import time
+from pathlib import Path
 
 import pytest
 
@@ -10,9 +11,12 @@ FILES_PER_RELEASE = [1342, 1405, 1812, 3342, 3326, 1227, 3100, 2320, 2885, 2516,
 
 RELEASE_FILES = list(zip(RELEASES, FILES_PER_RELEASE))
 
+CACHE_DIR = Path("~/mne_data").resolve() / "eeg_challenge_cache"
+CACHE_DIR.mkdir(parents=True, exist_ok=True)
+
 
 def _load_release(release):
-    ds = EEGChallengeDataset(release=release)
+    ds = EEGChallengeDataset(release=release, cache_dir=CACHE_DIR)
     getattr(ds, "description", None)
     return ds
 
@@ -27,7 +31,7 @@ def warmed_mongo():
 
 def test_eeg_challenge_dataset_initialization():
     """Test the initialization of EEGChallengeDataset."""
-    dataset = EEGChallengeDataset(release="R5")
+    dataset = EEGChallengeDataset(release="R5", cache_dir=CACHE_DIR)
 
     release = "R5"
     expected_bucket_prefix = f"s3://nmdatasets/NeurIPS25/{release}_L100"
@@ -56,7 +60,7 @@ def test_eeg_challenge_dataset_initialization():
 
 @pytest.mark.parametrize("release, number_files", RELEASE_FILES)
 def test_eeg_challenge_dataset_amount_files(release, number_files):
-    dataset = EEGChallengeDataset(release=release)
+    dataset = EEGChallengeDataset(release=release, cache_dir=CACHE_DIR)
     assert len(dataset.datasets) == number_files
 
 
@@ -64,6 +68,7 @@ def test_eeg_challenge_dataset_amount_files(release, number_files):
 def test_mongodb_load_benchmark(benchmark, warmed_mongo, release):
     # Group makes the report nicer when comparing releases
     benchmark.group = "EEGChallengeDataset.load"
+
     result = benchmark.pedantic(
         _load_release,
         args=(release,),
@@ -71,18 +76,23 @@ def test_mongodb_load_benchmark(benchmark, warmed_mongo, release):
         rounds=5,  # take min/median across several cold-ish runs
         warmup_rounds=1,  # do one warmup round
     )
+
     assert result is not None
 
 
 @pytest.mark.parametrize("release", RELEASES)
-def test_mongodb_load_under_slo(release):
+def test_mongodb_load_under_sometime(release):
     start_time = time.perf_counter()
-    _ = EEGChallengeDataset(release=release)
+    _ = EEGChallengeDataset(release=release, cache_dir=CACHE_DIR)
     duration = time.perf_counter() - start_time
     assert duration < 30, f"{release} took {duration:.2f}s"
 
 
 def test_consuming_data_r5():
-    dataset_obj = EEGChallengeDataset(release="R5", query=dict(task="RestingState"))
+    dataset_obj = EEGChallengeDataset(
+        release="R5",
+        query=dict(task="RestingState", subject="NDARAC350XUM"),
+        cache_dir=CACHE_DIR,
+    )
     raw = dataset_obj.datasets[0].raw
     assert raw is not None