opensportslib 0.1.2.dev2__tar.gz → 0.1.2.dev4__tar.gz

{opensportslib-0.1.2.dev2/opensportslib.egg-info → opensportslib-0.1.2.dev4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opensportslib
-Version: 0.1.2.dev2
+Version: 0.1.2.dev4
 Summary: OpenSportsLib is the professional library, designed for advanced video understanding in sports. It provides state-of-the-art tools for action recognition, spotting, retrieval, and captioning, making it ideal for researchers, analysts, and developers working with sports video data.
 Author: Jeet Vora
 Requires-Python: >=3.12
@@ -9,7 +9,7 @@ License-File: LICENSE
 License-File: LICENSE-COMMERCIAL
 Requires-Dist: SoccerNet
 Requires-Dist: av
-Requires-Dist: decord; platform_system != "Darwin" and platform_machine != "arm64"
+Requires-Dist: decord; platform_system != "Darwin" and platform_machine != "arm64" and platform_machine != "aarch64"
 Requires-Dist: evaluate
 Requires-Dist: scikit-learn
 Requires-Dist: torch
@@ -196,6 +196,32 @@ metrics_from_file = my_model.evaluate(
 )
 ```
 
+
+---
+
+## Hugging Face Dataset Transfer
+
+OpenSportsLib provides APIs and scripts for downloading and uploading OSL datasets with Hugging Face.
+
+### Python API
+
+```python
+from opensportslib.tools import (
+    download_dataset_split_from_hf,
+    upload_dataset_inputs_from_json_to_hf,
+    upload_dataset_as_parquet_to_hf,
+)
+```
+
+### Scripts
+
+```bash
+python tools/download_osl_hf.py --repo-id <org/repo> --revision main --split test --format parquet --output-dir downloaded_data
+python tools/upload_osl_hf.py --repo-id <org/repo> --json-path <local_dataset.json> --split test --revision main
+```
+
+Downloads are placed under `<output-dir>/<revision>/<split>`.
+
 ---
 
 ## What you can do with OpenSportsLib

{opensportslib-0.1.2.dev2 → opensportslib-0.1.2.dev4}/README.md

@@ -165,6 +165,32 @@ metrics_from_file = my_model.evaluate(
 )
 ```
 
+
+---
+
+## Hugging Face Dataset Transfer
+
+OpenSportsLib provides APIs and scripts for downloading and uploading OSL datasets with Hugging Face.
+
+### Python API
+
+```python
+from opensportslib.tools import (
+    download_dataset_split_from_hf,
+    upload_dataset_inputs_from_json_to_hf,
+    upload_dataset_as_parquet_to_hf,
+)
+```
+
+### Scripts
+
+```bash
+python tools/download_osl_hf.py --repo-id <org/repo> --revision main --split test --format parquet --output-dir downloaded_data
+python tools/upload_osl_hf.py --repo-id <org/repo> --json-path <local_dataset.json> --split test --revision main
+```
+
+Downloads are placed under `<output-dir>/<revision>/<split>`.
+
 ---
 
 ## What you can do with OpenSportsLib

{opensportslib-0.1.2.dev2 → opensportslib-0.1.2.dev4}/opensportslib/__init__.py

@@ -1,8 +1,5 @@
 import importlib
-# from . import apis as model
-# from . import metrics
-# from . import datasets
-# from . import core
+
 
 def __getattr__(name):
     if name == "model":
@@ -13,6 +10,9 @@ def __getattr__(name):
         return importlib.import_module("opensportslib.datasets")
     if name == "core":
         return importlib.import_module("opensportslib.core")
+    if name == "tools":
+        return importlib.import_module("opensportslib.tools")
     raise AttributeError(f"module 'opensportslib' has no attribute '{name}'")
 
-__all__ = ["model", "metrics", "datasets", "core"]
+
+__all__ = ["model", "metrics", "datasets", "core", "tools"]

opensportslib-0.1.2.dev4/opensportslib/cli.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+
+import argparse
+from typing import Optional
+
+from opensportslib.setup.setup import setup
+
+
+def main(argv: Optional[list[str]] = None) -> int:
+    parser = argparse.ArgumentParser(prog="opensportslib")
+    parser.add_argument("command", choices=["setup"])
+    parser.add_argument("--pyg", action="store_true")
+    parser.add_argument("--dali", action="store_true")
+
+    args = parser.parse_args(argv)
+
+    if args.command == "setup":
+        setup(
+            pyg=args.pyg,
+            dali=args.dali,
+        )
+        return 0
+
+    return 2
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

{opensportslib-0.1.2.dev2 → opensportslib-0.1.2.dev4}/opensportslib/core/utils/load_annotations.py

@@ -220,7 +220,7 @@ def annotationstoe2eformat(
 
         for video in tqdm.tqdm(videos):
             # ---- Video path & metadata ----
-            video_path = video["inputs"][0]["path"].replace(" ", "_")
+            video_path = video["inputs"][0]["path"] #.replace(" ", "_")
             #game_dir  = os.path.dirname(video_path)
             #game_name = os.path.basename(video_path)
             full_video_path = os.path.join(video_dir, video_path)

opensportslib-0.1.2.dev4/opensportslib/tools/__init__.py

@@ -0,0 +1,49 @@
+"""OpenSportsLib dataset conversion and Hugging Face transfer tools."""
+
+from .hf_transfer import (
+    HF_BRANCH_KEY,
+    HF_REPO_ID_KEY,
+    HF_SPLIT_KEY,
+    HfTransferCancelled,
+    create_dataset_branch_on_hf,
+    create_dataset_repo_on_hf,
+    dataset_repo_exists_on_hf,
+    download_dataset_split_from_hf,
+    extract_local_input_upload_entries_from_json,
+    extract_repo_paths_from_json,
+    get_json_repo_folder,
+    is_hf_download_url_not_found_error,
+    is_hf_repo_not_found_error,
+    is_hf_revision_not_found_error,
+    read_hf_source_metadata_from_dataset,
+    upload_dataset_as_parquet_to_hf,
+    upload_dataset_inputs_from_json_to_hf,
+    write_hf_source_metadata_to_dataset_json,
+)
+from .osl_json_to_parquet import DEFAULT_SHARD_SIZE, convert_json_to_parquet, parse_shard_size
+from .parquet_to_osl_json import convert_parquet_to_json
+
+__all__ = [
+    "convert_json_to_parquet",
+    "DEFAULT_SHARD_SIZE",
+    "parse_shard_size",
+    "convert_parquet_to_json",
+    "HfTransferCancelled",
+    "HF_REPO_ID_KEY",
+    "HF_BRANCH_KEY",
+    "HF_SPLIT_KEY",
+    "download_dataset_split_from_hf",
+    "upload_dataset_inputs_from_json_to_hf",
+    "upload_dataset_as_parquet_to_hf",
+    "create_dataset_repo_on_hf",
+    "dataset_repo_exists_on_hf",
+    "create_dataset_branch_on_hf",
+    "read_hf_source_metadata_from_dataset",
+    "write_hf_source_metadata_to_dataset_json",
+    "is_hf_repo_not_found_error",
+    "is_hf_revision_not_found_error",
+    "is_hf_download_url_not_found_error",
+    "get_json_repo_folder",
+    "extract_repo_paths_from_json",
+    "extract_local_input_upload_entries_from_json",
+]

opensportslib-0.1.2.dev4/opensportslib/tools/_common.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+
+import json
+from typing import Any
+
+import pandas as pd
+
+
+def json_dumps_compact(obj: Any) -> str:
+    return json.dumps(obj, ensure_ascii=False, separators=(",", ":"))
+
+
+def maybe_json_loads(value: Any, default: Any) -> Any:
+    if value is None:
+        return default
+    if isinstance(value, float) and pd.isna(value):
+        return default
+    if isinstance(value, (dict, list)):
+        return value
+    if isinstance(value, str):
+        value = value.strip()
+        if not value:
+            return default
+        try:
+            return json.loads(value)
+        except Exception:
+            return default
+    return default