🔨 adding -sub flag to select subjects from a big dataset

.gitignore

@@ -30,6 +30,7 @@ docs
 
 # Local environment
 .venv
+venv
 
 # Jupyter
 .ipynb_checkpoints

bids2table/__main__.py

@@ -60,7 +60,14 @@ def main():
         default=None,
         help="List of directory names or glob patterns to exclude from indexing.",
     )
-
+    parser.add_argument(
+        "--subject",
+        "-sub",
+        nargs="+",
+        type=str,
+        help="List of subject labels to index (default: None)",
+        default=None,
+    )
     args = parser.parse_args()
 
     log_level = ["ERROR", "WARNING", "INFO"][min(args.verbose, 2)]
@@ -75,6 +82,7 @@ def main():
         workers=args.workers,
         worker_id=args.worker_id,
         exclude=args.exclude,
+        subject=args.subject,
         return_table=False,
     )
 

bids2table/_b2t.py

@@ -25,6 +25,7 @@ def bids2table(
     workers: Optional[int] = None,
     worker_id: Optional[int] = None,
     return_table: bool = True,
+    subject: Optional[List[str]] = None,
 ) -> Optional[BIDSTable]:
     """
     Index a BIDS dataset directory and load as a pandas DataFrame.
@@ -47,6 +48,7 @@ def bids2table(
             overwrite.
         return_table: whether to return the BIDS table or just build the persistent
             index.
+        subject: optional subject label to index only a specific subject directory
 
     Returns:
         A `BIDSTable` representing the indexed dataset(s), or `None` if `return_table`
@@ -62,13 +64,29 @@ def bids2table(
     if exclude is None:
         exclude = []
 
-    source = Crawler(
-        root=root,
-        include=["sub-*"],  # find subject dirs
-        skip=["sub-*"] + exclude,  # but don't crawl into subject dirs
-        dirs_only=True,
-        follow_links=True,
-    )
+    if subject is not None:
+        subjects = [sub.lstrip("sub-") if sub.startswith("sub-") else sub for sub in subject]
+        logger.info(f"Indexing only subjects: {', '.join([f'sub-{sub}' for sub in subjects])}")
+        all_subjects = [d.name for d in root.iterdir() if d.is_dir() and d.name.startswith("sub-")]
+        exclude += [f"{sub}" for sub in all_subjects if sub not in [f"sub-{s}" for s in subjects]]
+        logger.info(f"Excluding subjects: {exclude}")
+        include_patterns = [f"sub-{sub}" for sub in subjects]
+        source = Crawler(
+            root=root,
+            include=include_patterns,
+            exclude=exclude,
+            dirs_only=True,
+            follow_links=True,
+        )
+    else:
+        logger.info("Indexing all subjects")
+        source = Crawler(
+            root=root,
+            include=["sub-*"],  # find subject dirs
+            skip=["sub-*"] + exclude,  # exclude specified patterns
+            dirs_only=True,
+            follow_links=True,
+        )
     extract = partial(extract_bids_subdir, exclude=exclude, with_meta=with_meta)
 
     if index_path is None:
@@ -110,4 +128,4 @@ def bids2table(
         mtime_column="file__mod_time",
     )
     tab = BIDSTable.from_parquet(index_path) if return_table else None
-    return tab
+    return tab