eegdash 0.3.5.dev87__py3-none-any.whl → 0.3.5.dev92__py3-none-any.whl

eegdash/__init__.py

@@ -7,4 +7,4 @@ __init__mongo_client()
 
 __all__ = ["EEGDash", "EEGDashDataset", "EEGChallengeDataset"]
 
-__version__ = "0.3.5.dev87"
+__version__ = "0.3.5.dev92"

eegdash/api.py

@@ -90,12 +90,16 @@ class EEGDash:
     ) -> list[Mapping[str, Any]]:
         """Find records in the MongoDB collection.
 
-        This method can be called in two ways:
+        This method supports four usage patterns:
         1. With a pre-built MongoDB query dictionary (positional argument):
            >>> eegdash.find({"dataset": "ds002718", "subject": {"$in": ["012", "013"]}})
         2. With user-friendly keyword arguments for simple and multi-value queries:
            >>> eegdash.find(dataset="ds002718", subject="012")
            >>> eegdash.find(dataset="ds002718", subject=["012", "013"])
+        3. With an explicit empty query to return all documents:
+           >>> eegdash.find({})  # fetches all records (use with care)
+        4. By combining a raw query with kwargs (merged via logical AND):
+           >>> eegdash.find({"dataset": "ds002718"}, subject=["012", "013"])  # yields {"$and":[{"dataset":"ds002718"}, {"subject":{"$in":["012","013"]}}]}
 
         Parameters
         ----------
@@ -110,26 +114,34 @@ class EEGDash:
         list:
             A list of DB records (string-keyed dictionaries) that match the query.
 
-        Raises
-        ------
-        ValueError
-            If both a `query` dictionary and keyword arguments are provided.
-
         """
-        if query is not None and kwargs:
-            raise ValueError(
-                "Provide either a positional 'query' dictionary or keyword arguments, not both."
-            )
-
-        final_query = {}
-        if query is not None:
-            final_query = query
-        elif kwargs:
-            final_query = self._build_query_from_kwargs(**kwargs)
+        final_query: dict[str, Any] | None = None
+
+        # Accept explicit empty dict {} to mean "match all"
+        raw_query = query if isinstance(query, dict) else None
+        kwargs_query = self._build_query_from_kwargs(**kwargs) if kwargs else None
+
+        # Determine presence, treating {} as a valid raw query
+        has_raw = isinstance(raw_query, dict)
+        has_kwargs = kwargs_query is not None
+
+        if has_raw and has_kwargs:
+            # Detect conflicting constraints on the same field (e.g., task specified
+            # differently in both places) and raise a clear error instead of silently
+            # producing an empty result.
+            self._raise_if_conflicting_constraints(raw_query, kwargs_query)
+            # Merge with logical AND so both constraints apply
+            if raw_query:  # non-empty dict adds constraints
+                final_query = {"$and": [raw_query, kwargs_query]}
+            else:  # {} adds nothing; use kwargs_query only
+                final_query = kwargs_query
+        elif has_raw:
+            # May be {} meaning match-all, or a non-empty dict
+            final_query = raw_query
+        elif has_kwargs:
+            final_query = kwargs_query
         else:
-            # By default, an empty query {} returns all documents.
-            # This can be dangerous, so we can either allow it or raise an error.
-            # Let's require an explicit query for safety.
+            # Avoid accidental full scans
             raise ValueError(
                 "find() requires a query dictionary or at least one keyword argument. "
                 "To find all documents, use find({})."
@@ -224,9 +236,12 @@ class EEGDash:
         return record
 
     def _build_query_from_kwargs(self, **kwargs) -> dict[str, Any]:
-        """Builds and validates a MongoDB query from user-friendly keyword arguments.
+        """Build and validate a MongoDB query from user-friendly keyword arguments.
 
-        Translates list values into MongoDB's `$in` operator.
+        Improvements:
+        - Reject None values and empty/whitespace-only strings
+        - For list/tuple/set values: strip strings, drop None/empties, deduplicate, and use `$in`
+        - Preserve scalars as exact matches
         """
         # 1. Validate that all provided keys are allowed for querying
         unknown_fields = set(kwargs.keys()) - self._ALLOWED_QUERY_FIELDS
@@ -239,19 +254,108 @@ class EEGDash:
         # 2. Construct the query dictionary
         query = {}
         for key, value in kwargs.items():
-            if isinstance(value, (list, tuple)):
-                if not value:
+            # None is not a valid constraint
+            if value is None:
+                raise ValueError(
+                    f"Received None for query parameter '{key}'. Provide a concrete value."
+                )
+
+            # Handle list-like values as multi-constraints
+            if isinstance(value, (list, tuple, set)):
+                cleaned: list[Any] = []
+                for item in value:
+                    if item is None:
+                        continue
+                    if isinstance(item, str):
+                        item = item.strip()
+                        if not item:
+                            continue
+                    cleaned.append(item)
+                # Deduplicate while preserving order
+                cleaned = list(dict.fromkeys(cleaned))
+                if not cleaned:
                     raise ValueError(
                         f"Received an empty list for query parameter '{key}'. This is not supported."
                     )
-                # If the value is a list, use the `$in` operator for multi-search
-                query[key] = {"$in": value}
+                query[key] = {"$in": cleaned}
             else:
-                # Otherwise, it's a direct match
+                # Scalars: trim strings and validate
+                if isinstance(value, str):
+                    value = value.strip()
+                    if not value:
+                        raise ValueError(
+                            f"Received an empty string for query parameter '{key}'."
+                        )
                 query[key] = value
 
         return query
 
+    # --- Query merging and conflict detection helpers ---
+    def _extract_simple_constraint(self, query: dict[str, Any], key: str):
+        """Extract a simple constraint for a given key from a query dict.
+
+        Supports only top-level equality (key: value) and $in (key: {"$in": [...]})
+        constraints. Returns a tuple (kind, value) where kind is "eq" or "in". If the
+        key is not present or uses other operators, returns None.
+        """
+        if not isinstance(query, dict) or key not in query:
+            return None
+        val = query[key]
+        if isinstance(val, dict):
+            if "$in" in val and isinstance(val["$in"], (list, tuple)):
+                return ("in", list(val["$in"]))
+            return None  # unsupported operator shape for conflict checking
+        else:
+            return ("eq", val)
+
+    def _raise_if_conflicting_constraints(
+        self, raw_query: dict[str, Any], kwargs_query: dict[str, Any]
+    ) -> None:
+        """Raise ValueError if both query sources define incompatible constraints.
+
+        We conservatively check only top-level fields with simple equality or $in
+        constraints. If a field appears in both queries and constraints are mutually
+        exclusive, raise an explicit error to avoid silent empty result sets.
+        """
+        if not raw_query or not kwargs_query:
+            return
+
+        # Only consider fields we generally allow; skip meta operators like $and
+        raw_keys = set(raw_query.keys()) & self._ALLOWED_QUERY_FIELDS
+        kw_keys = set(kwargs_query.keys()) & self._ALLOWED_QUERY_FIELDS
+        dup_keys = raw_keys & kw_keys
+        for key in dup_keys:
+            rc = self._extract_simple_constraint(raw_query, key)
+            kc = self._extract_simple_constraint(kwargs_query, key)
+            if rc is None or kc is None:
+                # If either side is non-simple, skip conflict detection for this key
+                continue
+
+            r_kind, r_val = rc
+            k_kind, k_val = kc
+
+            # Normalize to sets when appropriate for simpler checks
+            if r_kind == "eq" and k_kind == "eq":
+                if r_val != k_val:
+                    raise ValueError(
+                        f"Conflicting constraints for '{key}': query={r_val!r} vs kwargs={k_val!r}"
+                    )
+            elif r_kind == "in" and k_kind == "eq":
+                if k_val not in r_val:
+                    raise ValueError(
+                        f"Conflicting constraints for '{key}': query in {r_val!r} vs kwargs={k_val!r}"
+                    )
+            elif r_kind == "eq" and k_kind == "in":
+                if r_val not in k_val:
+                    raise ValueError(
+                        f"Conflicting constraints for '{key}': query={r_val!r} vs kwargs in {k_val!r}"
+                    )
+            elif r_kind == "in" and k_kind == "in":
+                if len(set(r_val).intersection(k_val)) == 0:
+                    raise ValueError(
+                        f"Conflicting constraints for '{key}': disjoint sets {r_val!r} and {k_val!r}"
+                    )
+
     def load_eeg_data_from_s3(self, s3path: str) -> xr.DataArray:
         """Load an EEGLAB .set file from an AWS S3 URI and return it as an xarray DataArray.
 
@@ -591,7 +695,7 @@ class EEGDashDataset(BaseConcatDataset):
         self,
         query: dict | None = None,
         cache_dir: str = "~/eegdash_cache",
-        dataset: str | None = None,
+        dataset: str | list[str] | None = None,
         description_fields: list[str] = [
             "subject",
             "session",
@@ -669,10 +773,15 @@ class EEGDashDataset(BaseConcatDataset):
         }
         base_dataset_kwargs = {k: v for k, v in kwargs.items() if k not in query_kwargs}
 
-        if query and query_kwargs:
-            raise ValueError(
-                "Provide either a 'query' dictionary or keyword arguments for filtering, not both."
-            )
+        # If user provided a dataset name via the dedicated parameter (and we're not
+        # loading from a local directory), treat it as a query filter. Accept str or list.
+        if data_dir is None and dataset is not None:
+            # Allow callers to pass a single dataset id (str) or a list of them.
+            # If list is provided, let _build_query_from_kwargs turn it into $in later.
+            query_kwargs.setdefault("dataset", dataset)
+
+        # Allow mixing raw DB query with additional keyword filters. Both will be
+        # merged by EEGDash.find() (logical AND), so we do not raise here.
 
         try:
             if records is not None:
@@ -688,15 +797,20 @@ class EEGDashDataset(BaseConcatDataset):
                 ]
             elif data_dir:
                 # This path loads from a local directory and is not affected by DB query logic
-                if isinstance(data_dir, str) or isinstance(data_dir, Path):
+                if isinstance(data_dir, (str, Path)):
                     datasets = self.load_bids_dataset(
-                        dataset=dataset,
+                        dataset=dataset
+                        if isinstance(dataset, str)
+                        else (dataset[0] if dataset else None),
                         data_dir=data_dir,
                         description_fields=description_fields,
                         s3_bucket=s3_bucket,
                         **base_dataset_kwargs,
                     )
                 else:
+                    assert dataset is not None, (
+                        "dataset must be provided when passing multiple data_dir"
+                    )
                     assert len(data_dir) == len(dataset), (
                         "Number of datasets and directories must match"
                     )
@@ -711,7 +825,7 @@ class EEGDashDataset(BaseConcatDataset):
                                 **base_dataset_kwargs,
                             )
                         )
-            elif query or query_kwargs:
+            elif query is not None or query_kwargs:
                 # This is the DB query path that we are improving
                 datasets = self.find_datasets(
                     query=query,
@@ -748,7 +862,7 @@ class EEGDashDataset(BaseConcatDataset):
 
     def find_datasets(
         self,
-        query: dict[str, Any],
+        query: dict[str, Any] | None,
         description_fields: list[str],
         query_kwargs: dict,
         base_dataset_kwargs: dict,
@@ -774,6 +888,10 @@ class EEGDashDataset(BaseConcatDataset):
         """
         datasets: list[EEGDashBaseDataset] = []
 
+        # Build records using either a raw query OR keyword filters, but not both.
+        # Note: callers may accidentally pass an empty dict for `query` along with
+        # kwargs. In that case, treat it as if no query was provided and rely on kwargs.
+        # Always delegate merging of raw query + kwargs to EEGDash.find
         self.records = self.eeg_dash.find(query, **query_kwargs)
 
         for record in self.records:

eegdash/data_utils.py

@@ -2,6 +2,7 @@ import json
 import logging
 import os
 import re
+import traceback
 import warnings
 from pathlib import Path
 from typing import Any
@@ -66,9 +67,7 @@ class EEGDashBaseDataset(BaseDataset):
             self.s3_open_neuro = True
 
         self.filecache = self.cache_dir / record["bidspath"]
-
         self.bids_root = self.cache_dir / record["dataset"]
-
         self.bidspath = BIDSPath(
             root=self.bids_root,
             datatype="eeg",
@@ -99,6 +98,9 @@ class EEGDashBaseDataset(BaseDataset):
         )
         if not self.s3_open_neuro:
             self.s3file = re.sub(r"(^|/)ds\d{6}/", r"\1", self.s3file, count=1)
+            if self.s3file.endswith(".set"):
+                self.s3file = self.s3file[:-4] + ".bdf"
+                self.filecache = self.filecache.with_suffix(".bdf")
 
         self.filecache.parent.mkdir(parents=True, exist_ok=True)
         info = filesystem.info(self.s3file)
@@ -132,11 +134,21 @@ class EEGDashBaseDataset(BaseDataset):
             anon=True, client_kwargs={"region_name": "us-east-2"}
         )
         for i, dep in enumerate(self.bids_dependencies):
+            if not self.s3_open_neuro:
+                # fix this when our bucket is integrated into the
+                # mongodb
+                # if the file have ".set" replace to ".bdf"
+                if dep.endswith(".set"):
+                    dep = dep[:-4] + ".bdf"
+
             s3path = self.get_s3path(dep)
             if not self.s3_open_neuro:
                 dep = self.bids_dependencies_original[i]
 
             filepath = self.cache_dir / dep
+            if not self.s3_open_neuro:
+                if self.filecache.suffix == ".set":
+                    self.filecache = self.filecache.with_suffix(".bdf")
             # here, we download the dependency and it is fine
             # in the case of the competition.
             if not filepath.exists():
@@ -179,9 +191,23 @@ class EEGDashBaseDataset(BaseDataset):
             # capturing any warnings
             # to-do: remove this once is fixed on the mne-bids side.
             with warnings.catch_warnings(record=True) as w:
-                self._raw = mne_bids.read_raw_bids(
-                    bids_path=self.bidspath, verbose="ERROR"
-                )
+                try:
+                    # TO-DO: remove this once is fixed on the our side
+                    if not self.s3_open_neuro:
+                        self.bidspath = self.bidspath.update(extension=".bdf")
+
+                    self._raw = mne_bids.read_raw_bids(
+                        bids_path=self.bidspath, verbose="ERROR"
+                    )
+                except Exception as e:
+                    logger.error(
+                        f"Error while reading BIDS file: {self.bidspath}\n"
+                        "This may be due to a missing or corrupted file.\n"
+                        "Please check the file and try again."
+                    )
+                    logger.error(f"Exception: {e}")
+                    logger.error(traceback.format_exc())
+                    raise e
                 for warning in w:
                     logger.warning(
                         f"Warning while reading BIDS file: {warning.message}"
@@ -292,7 +318,6 @@ 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) -> None:
@@ -513,7 +538,6 @@ class EEGBIDSDataset:
         with os.scandir(directory) as entries:
             for entry in entries:
                 if entry.is_file() and entry.name.endswith(extension):
-                    print("Adding ", entry.path)
                     result_files.append(entry.path)
                 elif entry.is_dir():
                     # check that entry path doesn't contain any name in ignore list

eegdash/dataset.py

@@ -17,12 +17,258 @@ RELEASE_TO_OPENNEURO_DATASET_MAP = {
     "R1": "ds005505",
 }
 
+SUBJECT_MINI_RELEASE_MAP = {
+    "R11": [
+        "NDARAB678VYW",
+        "NDARAG788YV9",
+        "NDARAM946HJE",
+        "NDARAY977BZT",
+        "NDARAZ532KK0",
+        "NDARCE912ZXW",
+        "NDARCM214WFE",
+        "NDARDL033XRG",
+        "NDARDT889RT9",
+        "NDARDZ794ZVP",
+        "NDAREV869CPW",
+        "NDARFN221WW5",
+        "NDARFV289RKB",
+        "NDARFY623ZTE",
+        "NDARGA890MKA",
+        "NDARHN206XY3",
+        "NDARHP518FUR",
+        "NDARJL292RYV",
+        "NDARKM199DXW",
+        "NDARKW236TN7",
+    ],
+    "R10": [
+        "NDARAR935TGZ",
+        "NDARAV474ADJ",
+        "NDARCB869VM8",
+        "NDARCJ667UPL",
+        "NDARCM677TC1",
+        "NDARET671FTC",
+        "NDARKM061NHZ",
+        "NDARLD501HDK",
+        "NDARLL176DJR",
+        "NDARMT791WDH",
+        "NDARMW299ZAB",
+        "NDARNC405WJA",
+        "NDARNP962TJK",
+        "NDARPB967KU7",
+        "NDARRU560AGK",
+        "NDARTB173LY2",
+        "NDARUW377KAE",
+        "NDARVH565FX9",
+        "NDARVP799KGY",
+        "NDARVY962GB5",
+    ],
+    "R9": [
+        "NDARAC589YMB",
+        "NDARAC853CR6",
+        "NDARAH239PGG",
+        "NDARAL897CYV",
+        "NDARAN160GUF",
+        "NDARAP049KXJ",
+        "NDARAP457WB5",
+        "NDARAW216PM7",
+        "NDARBA004KBT",
+        "NDARBD328NUQ",
+        "NDARBF042LDM",
+        "NDARBH019KPD",
+        "NDARBH728DFK",
+        "NDARBM370JCB",
+        "NDARBU183TDJ",
+        "NDARBW971DCW",
+        "NDARBZ444ZHK",
+        "NDARCC620ZFT",
+        "NDARCD182XT1",
+        "NDARCK113CJM",
+    ],
+    "R8": [
+        "NDARAB514MAJ",
+        "NDARAD571FLB",
+        "NDARAF003VCL",
+        "NDARAG191AE8",
+        "NDARAJ977PRJ",
+        "NDARAP912JK3",
+        "NDARAV454VF0",
+        "NDARAY298THW",
+        "NDARBJ375VP4",
+        "NDARBT436PMT",
+        "NDARBV630BK6",
+        "NDARCB627KDN",
+        "NDARCC059WTH",
+        "NDARCM953HKD",
+        "NDARCN681CXW",
+        "NDARCT889DMB",
+        "NDARDJ204EPU",
+        "NDARDJ544BU5",
+        "NDARDP292DVC",
+        "NDARDW178AC6",
+    ],
+    "R7": [
+        "NDARAY475AKD",
+        "NDARBW026UGE",
+        "NDARCK162REX",
+        "NDARCK481KRH",
+        "NDARCV378MMX",
+        "NDARCX462NVA",
+        "NDARDJ970ELG",
+        "NDARDU617ZW1",
+        "NDAREM609ZXW",
+        "NDAREW074ZM2",
+        "NDARFE555KXB",
+        "NDARFT176NJP",
+        "NDARGK442YHH",
+        "NDARGM439FZD",
+        "NDARGT634DUJ",
+        "NDARHE283KZN",
+        "NDARHG260BM9",
+        "NDARHL684WYU",
+        "NDARHN224TPA",
+        "NDARHP841RMR",
+    ],
+    "R6": [
+        "NDARAD224CRB",
+        "NDARAE301XTM",
+        "NDARAT680GJA",
+        "NDARCA578CEB",
+        "NDARDZ147ETZ",
+        "NDARFL793LDE",
+        "NDARFX710UZA",
+        "NDARGE994BMX",
+        "NDARGP191YHN",
+        "NDARGV436PFT",
+        "NDARHF545HFW",
+        "NDARHP039DBU",
+        "NDARHT774ZK1",
+        "NDARJA830BYV",
+        "NDARKB614KGY",
+        "NDARKM250ET5",
+        "NDARKZ085UKQ",
+        "NDARLB581AXF",
+        "NDARNJ899HW7",
+        "NDARRZ606EDP",
+    ],
+    "R4": [
+        "NDARAC350BZ0",
+        "NDARAD615WLJ",
+        "NDARAG584XLU",
+        "NDARAH503YG1",
+        "NDARAX272ZJL",
+        "NDARAY461TZZ",
+        "NDARBC734UVY",
+        "NDARBL444FBA",
+        "NDARBT640EBN",
+        "NDARBU098PJT",
+        "NDARBU928LV0",
+        "NDARBV059CGE",
+        "NDARCG037CX4",
+        "NDARCG947ZC0",
+        "NDARCH001CN2",
+        "NDARCU001ZN7",
+        "NDARCW497XW2",
+        "NDARCX053GU5",
+        "NDARDF568GL5",
+        "NDARDJ092YKH",
+    ],
+    "R5": [
+        "NDARAH793FBF",
+        "NDARAJ689BVN",
+        "NDARAP785CTE",
+        "NDARAU708TL8",
+        "NDARBE091BGD",
+        "NDARBE103DHM",
+        "NDARBF851NH6",
+        "NDARBH228RDW",
+        "NDARBJ674TVU",
+        "NDARBM433VER",
+        "NDARCA740UC8",
+        "NDARCU633GCZ",
+        "NDARCU736GZ1",
+        "NDARCU744XWL",
+        "NDARDC843HHM",
+        "NDARDH086ZKK",
+        "NDARDL305BT8",
+        "NDARDU853XZ6",
+        "NDARDV245WJG",
+        "NDAREC480KFA",
+    ],
+    "R3": [
+        "NDARAA948VFH",
+        "NDARAD774HAZ",
+        "NDARAE828CML",
+        "NDARAG340ERT",
+        "NDARBA839HLG",
+        "NDARBE641DGZ",
+        "NDARBG574KF4",
+        "NDARBM642JFT",
+        "NDARCL016NHB",
+        "NDARCV944JA6",
+        "NDARCY178KJP",
+        "NDARDY150ZP9",
+        "NDAREC542MH3",
+        "NDAREK549XUQ",
+        "NDAREM887YY8",
+        "NDARFA815FXE",
+        "NDARFF644ZGD",
+        "NDARFV557XAA",
+        "NDARFV780ABD",
+        "NDARGB102NWJ",
+    ],
+    "R2": [
+        "NDARAB793GL3",
+        "NDARAM675UR8",
+        "NDARBM839WR5",
+        "NDARBU730PN8",
+        "NDARCT974NAJ",
+        "NDARCW933FD5",
+        "NDARCZ770BRG",
+        "NDARDW741HCF",
+        "NDARDZ058NZN",
+        "NDAREC377AU2",
+        "NDAREM500WWH",
+        "NDAREV527ZRF",
+        "NDAREV601CE7",
+        "NDARFF070XHV",
+        "NDARFR108JNB",
+        "NDARFT305CG1",
+        "NDARGA056TMW",
+        "NDARGH775KF5",
+        "NDARGJ878ZP4",
+        "NDARHA387FPM",
+    ],
+    "R1": [
+        "NDARAC904DMU",
+        "NDARAM704GKZ",
+        "NDARAP359UM6",
+        "NDARBD879MBX",
+        "NDARBH024NH2",
+        "NDARBK082PDD",
+        "NDARCA153NKE",
+        "NDARCE721YB5",
+        "NDARCJ594BWQ",
+        "NDARCN669XPR",
+        "NDARCW094JCG",
+        "NDARCZ947WU5",
+        "NDARDH670PXH",
+        "NDARDL511UND",
+        "NDARDU986RBM",
+        "NDAREM731BYM",
+        "NDAREN519BLJ",
+        "NDARFK610GY5",
+        "NDARFT581ZW5",
+        "NDARFW972KFQ",
+    ],
+}
+
 
 class EEGChallengeDataset(EEGDashDataset):
     def __init__(
         self,
         release: str,
         cache_dir: str,
+        mini: bool = True,
         query: dict | None = None,
         s3_bucket: str | None = "s3://nmdatasets/NeurIPS25",
         **kwargs,
@@ -35,6 +281,9 @@ class EEGChallengeDataset(EEGDashDataset):
         ----------
         release: str
             Release name. Can be one of ["R1", ..., "R11"]
+        mini: bool, default True
+            Whether to use the mini-release version of the dataset. It is recommended
+            to use the mini version for faster training and evaluation.
         query : dict | None
             Optionally a dictionary that specifies a query to be executed,
             in addition to the dataset (automatically inferred from the release argument).
@@ -50,24 +299,46 @@ class EEGChallengeDataset(EEGDashDataset):
 
         """
         self.release = release
+        self.mini = mini
+
         if release not in RELEASE_TO_OPENNEURO_DATASET_MAP:
-            raise ValueError(f"Unknown release: {release}")
-
-        dataset = RELEASE_TO_OPENNEURO_DATASET_MAP[release]
-        if query is None:
-            query = {"dataset": dataset}
-        elif "dataset" not in query:
-            query["dataset"] = dataset
-        elif query["dataset"] != dataset:
             raise ValueError(
-                f"Query dataset {query['dataset']} does not match the release {release} "
-                f"which corresponds to dataset {dataset}."
+                f"Unknown release: {release}, expected one of {list(RELEASE_TO_OPENNEURO_DATASET_MAP.keys())}"
+            )
+
+        dataset_parameters = []
+        if isinstance(release, str):
+            dataset_parameters.append(RELEASE_TO_OPENNEURO_DATASET_MAP[release])
+        else:
+            raise ValueError(
+                f"Unknown release type: {type(release)}, the expected type is str."
             )
 
+        if query and "dataset" in query:
+            raise ValueError(
+                "Query using the parameters `dataset` with the class EEGChallengeDataset is not possible."
+                "Please use the release argument instead, or the object EEGDashDataset instead."
+            )
+
+        if self.mini:
+            # Disallow mixing subject selection with mini=True since mini already
+            # applies a predefined subject subset.
+            if (query and "subject" in query) or ("subject" in kwargs):
+                raise ValueError(
+                    "Query using the parameters `subject` with the class EEGChallengeDataset and `mini==True` is not possible."
+                    "Please don't use the `subject` selection twice."
+                    "Set `mini=False` to use the `subject` selection."
+                )
+            kwargs["subject"] = SUBJECT_MINI_RELEASE_MAP[release]
+            s3_bucket = f"{s3_bucket}/{release}_mini_L100_bdf"
+        else:
+            s3_bucket = f"{s3_bucket}/{release}_L100_bdf"
+
         super().__init__(
+            dataset=dataset_parameters,
             query=query,
             cache_dir=cache_dir,
-            s3_bucket=f"{s3_bucket}/{release}_L100",
+            s3_bucket=s3_bucket,
             **kwargs,
         )
 

{eegdash-0.3.5.dev87.dist-info → eegdash-0.3.5.dev92.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: eegdash
-Version: 0.3.5.dev87
+Version: 0.3.5.dev92
 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
@@ -60,22 +60,9 @@ Requires-Dist: memory_profiler; extra == "docs"
 Requires-Dist: ipython; extra == "docs"
 Requires-Dist: lightgbm; extra == "docs"
 Provides-Extra: all
-Requires-Dist: pre-commit; extra == "all"
-Requires-Dist: pytest; extra == "all"
-Requires-Dist: pytest-cov; extra == "all"
-Requires-Dist: codecov; extra == "all"
-Requires-Dist: pytest_cases; extra == "all"
-Requires-Dist: pytest-benchmark; extra == "all"
-Requires-Dist: sphinx; extra == "all"
-Requires-Dist: sphinx_design; extra == "all"
-Requires-Dist: sphinx_gallery; extra == "all"
-Requires-Dist: sphinx_rtd_theme; extra == "all"
-Requires-Dist: pydata-sphinx-theme; extra == "all"
-Requires-Dist: sphinx-autobuild; extra == "all"
-Requires-Dist: numpydoc; extra == "all"
-Requires-Dist: memory_profiler; extra == "all"
-Requires-Dist: ipython; extra == "all"
-Requires-Dist: lightgbm; extra == "all"
+Requires-Dist: eegdash[docs]; extra == "all"
+Requires-Dist: eegdash[dev]; extra == "all"
+Requires-Dist: eegdash[tests]; extra == "all"
 Dynamic: license-file
 
 # EEG-Dash

{eegdash-0.3.5.dev87.dist-info → eegdash-0.3.5.dev92.dist-info}/RECORD

@@ -1,8 +1,8 @@
-eegdash/__init__.py,sha256=VuKtyUq59YapSDPTr_g71JTGfHqjbtJUilFQ-hrOTzc,240
-eegdash/api.py,sha256=KjmEVkfltLR5EwRnmnPp5rEDS5Oa6_dnprif9EVpeQs,32351
+eegdash/__init__.py,sha256=ao48gkXYHPAJnu73RWcBgDLvEE3uNWOScbioW4nbEn4,240
+eegdash/api.py,sha256=yotN4vqurZAxVA4q_DK4z0mhh9P8sbpxKzvyxuRSkcQ,38538
 eegdash/data_config.py,sha256=OS6ERO-jHrnEOfMJUehY7ieABdsRw_qWzOKJ4pzSfqw,1323
-eegdash/data_utils.py,sha256=_dycnPmGfTbYs7bc6edHxUn_m01dLYtp92_k44ffEoY,26475
-eegdash/dataset.py,sha256=ooLoxMFy2I8BY9gJl6ncTp_Gz-Rq0Z-o4NJyyomxLcU,2670
+eegdash/data_utils.py,sha256=mi9pscui-BPpRH9ovRtGWiSwHG5QN6K_IvJdYaING2I,27679
+eegdash/dataset.py,sha256=iGi7m2FNhLgJxxwSsB9JIy01p4tmdlJIPzdL5CDAJU4,9446
 eegdash/dataset_summary.csv,sha256=EfnPciglkf4Vgc8dDq_1x7Woeeze1II8vOhx60g4yhc,8670
 eegdash/mongodb.py,sha256=GD3WgA253oFgpzOHrYaj4P1mRjNtDMT5Oj4kVvHswjI,2006
 eegdash/preprocessing.py,sha256=7S_TTRKPKEk47tTnh2D6WExBt4cctAMxUxGDjJqq5lU,2221
@@ -23,8 +23,8 @@ 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-0.3.5.dev87.dist-info/licenses/LICENSE,sha256=asisR-xupy_NrQBFXnx6yqXeZcYWLvbAaiETl25iXT0,931
-eegdash-0.3.5.dev87.dist-info/METADATA,sha256=pyOun6m8eRMa6tsrwGoP4yPTgvDrQuKYGJOZmFd2azs,10485
-eegdash-0.3.5.dev87.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-eegdash-0.3.5.dev87.dist-info/top_level.txt,sha256=zavO69HQ6MyZM0aQMR2zUS6TAFc7bnN5GEpDpOpFZzU,8
-eegdash-0.3.5.dev87.dist-info/RECORD,,
+eegdash-0.3.5.dev92.dist-info/licenses/LICENSE,sha256=asisR-xupy_NrQBFXnx6yqXeZcYWLvbAaiETl25iXT0,931
+eegdash-0.3.5.dev92.dist-info/METADATA,sha256=ThukZMsprgai1PZFYVbURPOmzV3xTMmCPJi-j_sQZps,9925
+eegdash-0.3.5.dev92.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+eegdash-0.3.5.dev92.dist-info/top_level.txt,sha256=zavO69HQ6MyZM0aQMR2zUS6TAFc7bnN5GEpDpOpFZzU,8
+eegdash-0.3.5.dev92.dist-info/RECORD,,