eegdash 0.3.2.dev52__tar.gz → 0.3.3.dev58__tar.gz

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.2.dev52
+Version: 0.3.3.dev58
 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"
@@ -98,6 +100,14 @@ Dynamic: license-file
 
 # EEG-Dash
 
+[![PyPI version](https://img.shields.io/pypi/v/eegdash)](https://pypi.org/project/eegdash/)
+[![Docs](https://img.shields.io/badge/docs-stable-brightgreen.svg)](https://sccn.github.io/eegdash)
+
+[![License: GPL-2.0-or-later](https://img.shields.io/badge/License-GPL--2.0--or--later-blue.svg)](LICENSE)
+[![Python versions](https://img.shields.io/pypi/pyversions/eegdash.svg)](https://pypi.org/project/eegdash/)
+[![Downloads](https://pepy.tech/badge/eegdash)](https://pepy.tech/project/eegdash)
+<!-- [![Coverage](https://img.shields.io/codecov/c/github/sccn/eegdash)](https://codecov.io/gh/sccn/eegdash) -->
+
 To leverage recent and ongoing advancements in large-scale computational methods and to ensure the preservation of scientific data generated from publicly funded research, the EEG-DaSh data archive will create a data-sharing resource for MEEG (EEG, MEG) data contributed by collaborators for machine learning (ML) and deep learning (DL) applications. 
 
 ## Data source
@@ -143,7 +153,9 @@ To use the data from a single subject, enter:
 from eegdash import EEGDashDataset
 
 ds_NDARDB033FW5 = EEGDashDataset(
-    {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
+    {"dataset": "ds005514", "task":
+     "RestingState", "subject": "NDARDB033FW5"}, 
+     cache_dir="."
 )
 ```
 
@@ -155,7 +167,7 @@ To use the data from multiple subjects, enter:
 from eegdash import EEGDashDataset
 
 ds_ds005505rest = EEGDashDataset(
-    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
+    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex", cache_dir=".
 )
 ```
 

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/README.md

@@ -1,5 +1,13 @@
 # EEG-Dash
 
+[![PyPI version](https://img.shields.io/pypi/v/eegdash)](https://pypi.org/project/eegdash/)
+[![Docs](https://img.shields.io/badge/docs-stable-brightgreen.svg)](https://sccn.github.io/eegdash)
+
+[![License: GPL-2.0-or-later](https://img.shields.io/badge/License-GPL--2.0--or--later-blue.svg)](LICENSE)
+[![Python versions](https://img.shields.io/pypi/pyversions/eegdash.svg)](https://pypi.org/project/eegdash/)
+[![Downloads](https://pepy.tech/badge/eegdash)](https://pepy.tech/project/eegdash)
+<!-- [![Coverage](https://img.shields.io/codecov/c/github/sccn/eegdash)](https://codecov.io/gh/sccn/eegdash) -->
+
 To leverage recent and ongoing advancements in large-scale computational methods and to ensure the preservation of scientific data generated from publicly funded research, the EEG-DaSh data archive will create a data-sharing resource for MEEG (EEG, MEG) data contributed by collaborators for machine learning (ML) and deep learning (DL) applications. 
 
 ## Data source
@@ -45,7 +53,9 @@ To use the data from a single subject, enter:
 from eegdash import EEGDashDataset
 
 ds_NDARDB033FW5 = EEGDashDataset(
-    {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
+    {"dataset": "ds005514", "task":
+     "RestingState", "subject": "NDARDB033FW5"}, 
+     cache_dir="."
 )
 ```
 
@@ -57,7 +67,7 @@ To use the data from multiple subjects, enter:
 from eegdash import EEGDashDataset
 
 ds_ds005505rest = EEGDashDataset(
-    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
+    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex", cache_dir=".
 )
 ```
 

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/eegdash/__init__.py

@@ -5,4 +5,4 @@ from .utils import __init__mongo_client
 __init__mongo_client()
 
 __all__ = ["EEGDash", "EEGDashDataset", "EEGChallengeDataset"]
-__version__ = "0.3.2.dev52"
+__version__ = "0.3.3.dev58"

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/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.dev52 → eegdash-0.3.3.dev58}/eegdash.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.2.dev52
+Version: 0.3.3.dev58
 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"
@@ -98,6 +100,14 @@ Dynamic: license-file
 
 # EEG-Dash
 
+[![PyPI version](https://img.shields.io/pypi/v/eegdash)](https://pypi.org/project/eegdash/)
+[![Docs](https://img.shields.io/badge/docs-stable-brightgreen.svg)](https://sccn.github.io/eegdash)
+
+[![License: GPL-2.0-or-later](https://img.shields.io/badge/License-GPL--2.0--or--later-blue.svg)](LICENSE)
+[![Python versions](https://img.shields.io/pypi/pyversions/eegdash.svg)](https://pypi.org/project/eegdash/)
+[![Downloads](https://pepy.tech/badge/eegdash)](https://pepy.tech/project/eegdash)
+<!-- [![Coverage](https://img.shields.io/codecov/c/github/sccn/eegdash)](https://codecov.io/gh/sccn/eegdash) -->
+
 To leverage recent and ongoing advancements in large-scale computational methods and to ensure the preservation of scientific data generated from publicly funded research, the EEG-DaSh data archive will create a data-sharing resource for MEEG (EEG, MEG) data contributed by collaborators for machine learning (ML) and deep learning (DL) applications. 
 
 ## Data source
@@ -143,7 +153,9 @@ To use the data from a single subject, enter:
 from eegdash import EEGDashDataset
 
 ds_NDARDB033FW5 = EEGDashDataset(
-    {"dataset": "ds005514", "task": "RestingState", "subject": "NDARDB033FW5"}
+    {"dataset": "ds005514", "task":
+     "RestingState", "subject": "NDARDB033FW5"}, 
+     cache_dir="."
 )
 ```
 
@@ -155,7 +167,7 @@ To use the data from multiple subjects, enter:
 from eegdash import EEGDashDataset
 
 ds_ds005505rest = EEGDashDataset(
-    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex"
+    {"dataset": "ds005505", "task": "RestingState"}, target_name="sex", cache_dir=".
 )
 ```
 

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/eegdash.egg-info/SOURCES.txt

@@ -32,5 +32,6 @@ eegdash/features/feature_bank/utils.py
 tests/test_correctness.py
 tests/test_dataset.py
 tests/test_eegdash.py
+tests/test_functional.py
 tests/test_init.py
 tests/test_mongo_connection.py

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/eegdash.egg-info/requires.txt

@@ -10,6 +10,8 @@ s3fs
 scipy
 tqdm
 xarray
+h5io>=0.2.4
+pymatreader
 
 [all]
 pre-commit

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/pyproject.toml

@@ -48,6 +48,8 @@ dependencies = [
   "scipy",
   "tqdm",
   "xarray",
+  "h5io >= 0.2.4",
+  "pymatreader",
 ]
 
 [project.urls]

{eegdash-0.3.2.dev52 → eegdash-0.3.3.dev58}/tests/test_dataset.py

@@ -11,7 +11,7 @@ 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 = (Path.home() / "mne_data" / "eeg_challenge_cache").resolve()
 CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 

eegdash-0.3.3.dev58/tests/test_functional.py

@@ -0,0 +1,28 @@
+import shutil
+from pathlib import Path
+
+from eegdash.dataset import EEGDashDataset
+
+
+def test_progress_bar_output(capsys, tmp_path):
+    temporary = (Path.home() / "mne_data" / "temp").resolve()
+
+    if temporary.exists():
+        shutil.rmtree(temporary)
+
+    temporary.mkdir(parents=True, exist_ok=True)
+
+    eegdash_dataset = EEGDashDataset(
+        query={
+            "dataset": "ds005514",
+            "task": "RestingState",
+            "subject": "NDARDB033FW5",
+        },
+        cache_dir=temporary,
+    )
+    _ = eegdash_dataset.datasets[0].raw
+
+    out = capsys.readouterr()
+    # tqdm uses carriage returns; just assert a stable fragment:
+    assert "Downloading" in out.err
+    assert out.err  # non-empty