[JOSS review] Can't load open game

[felixchenier]

In this page:

https://databallpy.readthedocs.io/en/latest/getting_started/visualizations_page.html

This line:

game = get_open_game()

fails with this traceback:

In [3]: game = get_open_game()
---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
Cell In[3], line 1
----> 1 game = get_open_game()

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/databallpy/utils/logging.py:26, in logging_wrapper.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
     22 except Exception as e:
     23     logger.error(
     24         f"Error in the function `{func.__name__}`: {e}\n{traceback.format_exc()}"
     25     )
---> 26     raise e

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/databallpy/utils/logging.py:19, in logging_wrapper.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
     17 try:
     18     logger.info(f"Trying to run the function `{func.__name__}`")
---> 19     result = func(*args, **kwargs)
     20     logger.info(f"Successfully ran the function `{func.__name__}`")
     21     return result

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/databallpy/utils/get_game.py:556, in get_open_game(provider, game_id, verbose, use_cache)
    554 save_path = os.path.join("datasets", "IDSSE", game_id)
    555 if use_cache and os.path.exists(save_path):
--> 556     return get_saved_game(save_path)
    558 tracking_data, metadata = load_sportec_open_tracking_data(
    559     game_id=game_id,
    560     verbose=verbose,
    561 )
    562 event_data, ed_metadata, databallpy_events = load_sportec_open_event_data(
    563     game_id=game_id
    564 )

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/databallpy/utils/logging.py:26, in logging_wrapper.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
     22 except Exception as e:
     23     logger.error(
     24         f"Error in the function `{func.__name__}`: {e}\n{traceback.format_exc()}"
     25     )
---> 26     raise e

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/databallpy/utils/logging.py:19, in logging_wrapper.<locals>.decorator.<locals>.wrapper(*args, **kwargs)
     17 try:
     18     logger.info(f"Trying to run the function `{func.__name__}`")
---> 19     result = func(*args, **kwargs)
     20     logger.info(f"Successfully ran the function `{func.__name__}`")
     21     return result

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/databallpy/utils/get_game.py:364, in get_saved_game(name, path)
    361 if not os.path.isdir(full_path):
    362     raise ValueError(f"Directory {full_path} does not exist")
--> 364 with open(os.path.join(full_path, "metadata.json"), "rb") as f:
    365     metadata = json.load(f)
    367 return Game(
    368     tracking_data=TrackingData(
    369         pd.read_parquet(os.path.join(full_path, "tracking_data.parquet")),
   (...)
    404     _check_inputs_=False,
    405 )

FileNotFoundError: [Errno 2] No such file or directory: '/Users/felix/datasets/IDSSE/J03WMX/metadata.json'

I would have expected this to download an open game like it did with provider="metrica" on this page: https://databallpy.readthedocs.io/en/latest/getting_started/loading_in_a_game_page.html

As a consequence, I could not continue this tutorial, because the game opened with provider="metrica" fails:

game = get_open_game(provider="metrica")

from databallpy.visualize import plot_tracking_data
import numpy as np

game.tracking_data.add_velocity(
    column_ids=game.get_column_ids(),
    filter_type="savitzky_golay",
    max_velocity=13.0,
    allow_overwrite=True
    )

second_pass_id = game.event_data.loc[game.event_data["databallpy_event"]=="pass", "event_id"].iloc[1]
idx = game.tracking_data[game.tracking_data["event_id"]==second_pass_id].index[0]

x_grid, _ = np.meshgrid(np.linspace(0, 1, 15), np.linspace(0, 1, 10))

fig, ax = plot_soccer_pitch(field_dimen=game.pitch_dimensions, pitch_color="white")
fig, ax = plot_tracking_data(
    game, 
    idx, 
    fig=fig, 
    ax=ax, 
    events=["pass"],
    title="First pass after the kick-off",
    add_velocities=True,
    variable_of_interest=game.tracking_data.loc[idx, "frame"],
    heatmap_overlay=x_grid,
    overlay_cmap="coolwarm",
    )

with the following traceback:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/pandas/core/indexes/base.py:3812, in Index.get_loc(self, key)
   3811 try:
-> 3812     return self._engine.get_loc(casted_key)
   3813 except KeyError as err:

File pandas/_libs/index.pyx:167, in pandas._libs.index.IndexEngine.get_loc()

File pandas/_libs/index.pyx:196, in pandas._libs.index.IndexEngine.get_loc()

File pandas/_libs/hashtable_class_helper.pxi:7088, in pandas._libs.hashtable.PyObjectHashTable.get_item()

File pandas/_libs/hashtable_class_helper.pxi:7096, in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'event_id'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
Cell In[8], line 12
      4 game.tracking_data.add_velocity(
      5     column_ids=game.get_column_ids(),
      6     filter_type="savitzky_golay",
      7     max_velocity=13.0,
      8     allow_overwrite=True
      9     )
     11 second_pass_id = game.event_data.loc[game.event_data["databallpy_event"]=="pass", "event_id"].iloc[1]
---> 12 idx = game.tracking_data[game.tracking_data["event_id"]==second_pass_id].index[0]
     14 x_grid, _ = np.meshgrid(np.linspace(0, 1, 15), np.linspace(0, 1, 10))
     16 fig, ax = plot_soccer_pitch(field_dimen=game.pitch_dimensions, pitch_color="white")

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/pandas/core/frame.py:4113, in DataFrame.__getitem__(self, key)
   4111 if self.columns.nlevels > 1:
   4112     return self._getitem_multilevel(key)
-> 4113 indexer = self.columns.get_loc(key)
   4114 if is_integer(indexer):
   4115     indexer = [indexer]

File /opt/miniconda3/envs/databallpy/lib/python3.10/site-packages/pandas/core/indexes/base.py:3819, in Index.get_loc(self, key)
   3814     if isinstance(casted_key, slice) or (
   3815         isinstance(casted_key, abc.Iterable)
   3816         and any(isinstance(x, slice) for x in casted_key)
   3817     ):
   3818         raise InvalidIndexError(key)
-> 3819     raise KeyError(key) from err
   3820 except TypeError:
   3821     # If we have a listlike key, _check_indexing_error will raise
   3822     #  InvalidIndexError. Otherwise we fall through and re-raise
   3823     #  the TypeError.
   3824     self._check_indexing_error(key)

KeyError: 'event_id'

[felixchenier]

As a complementary issue, it seems that the documentation may not be up to date at some places, at least here where the default (non-working) value is provider="sportec" while the parameters section indicates "dfl".

https://databallpy.readthedocs.io/en/latest/api_docs/game_api.html#databallpy.get_open_game

get_open_game(provider: str = 'sportec', game_id: str = 'J03WMX', verbose: bool = True, use_cache: bool = True) → Game
[[source]](https://databallpy.readthedocs.io/en/latest/_modules/databallpy/utils/get_game.html#get_open_game)

    Function to load a game object from an open datasource

    Parameters:

            provider (str, optional) – What provider to get the open data from. Defaults to “dfl”. Options are [“metrica”, “dfl”, “sportec”, “tracab”]

            game_id (str, optional) – The Game id of the open game. Defaults to ‘J03WMX’,

            verbose (bool, optional) – Whether or not to print info about progress

            terminal (in the)

            True. (Defaults to)

            use_cache (bool, optional) – Use cached version of match if available.

    Returns:

        All information about the game
    Return type:

        Game

[felixchenier]

openjournals/joss-reviews#10223