eegdash 0.3.4.dev69__tar.gz → 0.3.4.dev70__tar.gz

{eegdash-0.3.4.dev69/eegdash.egg-info → eegdash-0.3.4.dev70}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.4.dev69
+Version: 0.3.4.dev70
 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-Expression: GPL-3.0-only
@@ -38,6 +38,7 @@ Requires-Dist: tqdm
 Requires-Dist: xarray
 Requires-Dist: h5io>=0.2.4
 Requires-Dist: pymatreader
+Requires-Dist: tabulate
 Provides-Extra: tests
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"

{eegdash-0.3.4.dev69 → eegdash-0.3.4.dev70}/docs/source/conf.py

@@ -96,7 +96,7 @@ html_sidebars = {"api": [], "dataset_summary": [], "installation": []}
 
 
 # -- Extension configurations ------------------------------------------------
-
+autoclass_content = "both"
 
 # Numpydoc
 numpydoc_show_class_members = False

{eegdash-0.3.4.dev69 → eegdash-0.3.4.dev70}/eegdash/__init__.py

@@ -7,4 +7,4 @@ __init__mongo_client()
 
 __all__ = ["EEGDash", "EEGDashDataset", "EEGChallengeDataset"]
 
-__version__ = "0.3.4.dev69"
+__version__ = "0.3.4.dev70"

eegdash-0.3.4.dev70/eegdash/registry.py

@@ -0,0 +1,136 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict
+
+import pandas as pd
+from tabulate import tabulate
+
+
+def register_openneuro_datasets(
+    summary_file: str | Path,
+    *,
+    base_class=None,
+    namespace: Dict[str, Any] | None = None,
+    add_to_all: bool = True,
+) -> Dict[str, type]:
+    """Dynamically create dataset classes from a summary file."""
+    if base_class is None:
+        from .api import EEGDashDataset as base_class  # lazy import
+
+    summary_path = Path(summary_file)
+    namespace = namespace if namespace is not None else globals()
+    module_name = namespace.get("__name__", __name__)
+    registered: Dict[str, type] = {}
+
+    df = pd.read_csv(summary_path, comment="#", skip_blank_lines=True)
+    for _, row_series in df.iterrows():
+        row = row_series.tolist()
+        dataset_id = str(row[0]).strip()
+        if not dataset_id:
+            continue
+
+        class_name = dataset_id.upper()
+
+        # avoid zero-arg super() here
+        def make_init(_dataset: str):
+            def __init__(
+                self,
+                cache_dir: str,
+                query: dict | None = None,
+                s3_bucket: str | None = None,
+                **kwargs,
+            ):
+                q = {"dataset": _dataset}
+                if query:
+                    q.update(query)
+                # call base_class.__init__ directly
+                base_class.__init__(
+                    self,
+                    query=q,
+                    cache_dir=cache_dir,
+                    s3_bucket=s3_bucket,
+                    **kwargs,
+                )
+
+            return __init__
+
+        init = make_init(dataset_id)
+
+        doc = f"""Create an instance for OpenNeuro dataset ``{dataset_id}``.
+
+        {markdown_table(row_series)}
+
+        Parameters
+        ----------
+        cache_dir : str
+            Local cache directory.
+        query : dict | None
+            Extra Mongo query merged with ``{{'dataset': '{dataset_id}'}}``.
+        s3_bucket : str | None
+            Optional S3 bucket name.
+        **kwargs
+            Passed through to {base_class.__name__}.
+        """
+
+        init.__doc__ = doc
+
+        cls = type(
+            class_name,
+            (base_class,),
+            {
+                "_dataset": dataset_id,
+                "__init__": init,
+                "__doc__": doc,
+                "__module__": module_name,  #
+            },
+        )
+
+        namespace[class_name] = cls
+        registered[class_name] = cls
+
+        if add_to_all:
+            ns_all = namespace.setdefault("__all__", [])
+            if isinstance(ns_all, list) and class_name not in ns_all:
+                ns_all.append(class_name)
+
+    return registered
+
+
+def markdown_table(row_series: pd.Series) -> str:
+    """Create a reStructuredText grid table from a pandas Series."""
+    if row_series.empty:
+        return ""
+
+    # Prepare the dataframe with user's suggested logic
+    df = (
+        row_series.to_frame()
+        .T.rename(
+            columns={
+                "n_subjects": "#Subj",
+                "nchans_set": "#Chan",
+                "n_tasks": "#Classes",
+                "sampling_freqs": "Freq(Hz)",
+                "duration_hours_total": "Duration(H)",
+            }
+        )
+        .reindex(
+            columns=[
+                "dataset",
+                "#Subj",
+                "#Chan",
+                "#Classes",
+                "Freq(Hz)",
+                "Duration(H)",
+            ]
+        )
+        .infer_objects(copy=False)
+        .fillna("")
+    )
+
+    # Use tabulate for the final rst formatting
+    table = tabulate(df, headers="keys", tablefmt="rst", showindex=False)
+
+    # Indent the table to fit within the admonition block
+    indented_table = "\n".join("    " + line for line in table.split("\n"))
+    return f"\n\n{indented_table}"

{eegdash-0.3.4.dev69 → eegdash-0.3.4.dev70/eegdash.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.4.dev69
+Version: 0.3.4.dev70
 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-Expression: GPL-3.0-only
@@ -38,6 +38,7 @@ Requires-Dist: tqdm
 Requires-Dist: xarray
 Requires-Dist: h5io>=0.2.4
 Requires-Dist: pymatreader
+Requires-Dist: tabulate
 Provides-Extra: tests
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"

{eegdash-0.3.4.dev69 → eegdash-0.3.4.dev70}/eegdash.egg-info/requires.txt

@@ -12,6 +12,7 @@ tqdm
 xarray
 h5io>=0.2.4
 pymatreader
+tabulate
 
 [all]
 pre-commit

{eegdash-0.3.4.dev69 → eegdash-0.3.4.dev70}/pyproject.toml

@@ -49,6 +49,7 @@ dependencies = [
   "xarray",
   "h5io >= 0.2.4",
   "pymatreader",
+  "tabulate",
 ]
 
 [project.urls]

{eegdash-0.3.4.dev69 → eegdash-0.3.4.dev70}/tests/test_dataset_registration.py

@@ -16,6 +16,7 @@ def test_register_openneuro_datasets(tmp_path: Path):
     summary.write_text(
         "\n".join(
             [
+                "dataset_id,num_subjects,num_sessions,num_runs,num_channels,sampling_rate,duration",
                 "ds002718,18,18,1,74,250,14.844",
                 "ds000001,1,1,1,1,1,1",
             ]

eegdash-0.3.4.dev69/eegdash/registry.py

@@ -1,72 +0,0 @@
-from __future__ import annotations
-
-import csv
-from pathlib import Path
-from typing import Any, Dict
-
-
-def register_openneuro_datasets(
-    summary_file: str | Path,
-    *,
-    base_class=None,
-    namespace: Dict[str, Any] | None = None,
-) -> Dict[str, type]:
-    """Dynamically create dataset classes from a summary file.
-
-    Parameters
-    ----------
-    summary_file : str | Path
-        Path to a CSV file where each line starts with the dataset identifier.
-    base_class : type | None
-        Base class for the generated datasets. If ``None``, defaults to
-        :class:`eegdash.api.EEGDashDataset`.
-    namespace : dict | None
-        Mapping where the new classes will be registered. Defaults to the
-        module's global namespace.
-
-    Returns
-    -------
-    dict
-        Mapping from class names to the generated classes.
-
-    """
-    if base_class is None:
-        from .api import EEGDashDataset as base_class  # lazy import
-
-    summary_path = Path(summary_file)
-    namespace = namespace if namespace is not None else globals()
-    registered: Dict[str, type] = {}
-
-    with summary_path.open() as f:
-        reader = csv.reader(f)
-        for row in reader:
-            if not row:
-                continue
-            dataset_id = row[0].strip()
-            if not dataset_id or dataset_id.startswith("#"):
-                continue
-            class_name = dataset_id.upper()
-
-            def __init__(
-                self,
-                cache_dir: str,
-                query: dict | None = None,
-                s3_bucket: str | None = None,
-                **kwargs,
-            ):
-                q = {"dataset": self._dataset}
-                if query:
-                    q.update(query)
-                super().__init__(
-                    query=q, cache_dir=cache_dir, s3_bucket=s3_bucket, **kwargs
-                )
-
-            cls = type(
-                class_name,
-                (base_class,),
-                {"_dataset": dataset_id, "__init__": __init__},
-            )
-            namespace[class_name] = cls
-            registered[class_name] = cls
-
-    return registered