Statsbomb¶

Load local files¶

In [1]:

Copied!





from kloppy import statsbomb

dataset = statsbomb.load(
    event_data="../../kloppy/tests/files/statsbomb_3788741_event.json",
    lineup_data="../../kloppy/tests/files/statsbomb_3788741_lineup.json",
    
    # 360 file is optional
    three_sixty_data="../../kloppy/tests/files/statsbomb_3788741_360.json",
    
    # Optional arguments
    coordinates="statsbomb",
    event_types=["pass", "shot"]
)

dataset.to_df().head()
from kloppy import statsbomb

dataset = statsbomb.load(
    event_data="../../kloppy/tests/files/statsbomb_3788741_event.json",
    lineup_data="../../kloppy/tests/files/statsbomb_3788741_lineup.json",
    
    # 360 file is optional
    three_sixty_data="../../kloppy/tests/files/statsbomb_3788741_360.json",
    
    # Optional arguments
    coordinates="statsbomb",
    event_types=["pass", "shot"]
)

dataset.to_df().head()

Out[1]:

	event_id	event_type	result	success	period_id	timestamp	end_timestamp	ball_state	ball_owning_team	team_id	player_id	coordinates_x	coordinates_y	end_coordinates_x	end_coordinates_y	receiver_player_id	set_piece_type	body_part_type	pass_type
0	bbc398f7-c784-4958-a504-37b583caf97a	PASS	COMPLETE	True	1	0.878	2.788504	alive	909	909	11086	59.95	39.95	32.45	28.75	8963	KICK_OFF	RIGHT_FOOT	NaN
1	5c210f79-9714-44a6-b2ec-387f6a117b37	PASS	COMPLETE	True	1	4.288	6.764772	alive	909	909	8963	36.15	30.35	70.65	75.75	8541	NaN	LEFT_FOOT	LONG_BALL
2	8a3e6668-9680-4417-987e-8db0c6ce6a8b	PASS	COMPLETE	True	1	12.163	14.093230	alive	914	914	8286	43.05	0.05	15.75	7.45	6954	THROW_IN	NaN	NaN
3	f8e61bb0-b618-4695-9ff9-eaa0584bdbfa	PASS	COMPLETE	True	1	16.420	18.242108	alive	914	914	6954	3.25	12.65	7.85	36.15	7036	NaN	RIGHT_FOOT	NaN
4	1d72ce76-31fd-43e0-a6b2-1f78c8a57a77	PASS	COMPLETE	True	1	20.025	21.071484	alive	914	914	7036	9.05	38.85	19.65	47.85	7173	NaN	RIGHT_FOOT	NaN

Load remote files¶

You can also directly read files from urls (http or https) by passing a url instead of a local path.

In [2]:

Copied!





from kloppy import statsbomb

dataset = statsbomb.load(
    event_data="https://raw.githubusercontent.com/statsbomb/open-data/master/data/events/15946.json",
    lineup_data="https://raw.githubusercontent.com/statsbomb/open-data/master/data/lineups/15946.json",
    
    # Optional arguments
    coordinates="statsbomb",
    event_types=["pass", "shot"]
)

dataset.to_df().head()
from kloppy import statsbomb

dataset = statsbomb.load(
    event_data="https://raw.githubusercontent.com/statsbomb/open-data/master/data/events/15946.json",
    lineup_data="https://raw.githubusercontent.com/statsbomb/open-data/master/data/lineups/15946.json",
    
    # Optional arguments
    coordinates="statsbomb",
    event_types=["pass", "shot"]
)

dataset.to_df().head()

Out[2]:

	event_id	event_type	result	success	period_id	timestamp	end_timestamp	ball_state	ball_owning_team	team_id	player_id	coordinates_x	coordinates_y	end_coordinates_x	end_coordinates_y	receiver_player_id	set_piece_type	body_part_type	pass_type
0	34208ade-2af4-45c3-970e-655937cad938	PASS	COMPLETE	True	1	0.098	2.007	alive	206	206	6581	60.5	40.5	35.5	25.5	6855	KICK_OFF	LEFT_FOOT	NaN
1	d1cccb73-c7ef-4b02-8267-ebd7f149904b	PASS	INCOMPLETE	False	1	3.497	6.785	alive	206	206	6855	35.5	28.5	85.5	72.5	None	NaN	RIGHT_FOOT	LONG_BALL
2	f1cc47d6-4b19-45a6-beb9-33d67fc83f4b	PASS	COMPLETE	True	1	6.785	8.431	alive	217	217	5203	34.5	7.5	34.5	20.5	5470	NaN	HEAD	HEAD_PASS
3	f774571f-4b65-43a0-9bfc-6384948d1b82	PASS	COMPLETE	True	1	8.431	9.576	alive	217	217	5470	35.5	20.5	35.5	1.5	5477	NaN	HEAD	HEAD_PASS
4	46f0e871-3e72-4817-9a53-af27583ba6c1	PASS	COMPLETE	True	1	10.433	11.150	alive	217	217	5477	33.5	2.5	25.5	1.5	5211	NaN	RIGHT_FOOT	NaN

Load open data¶

For loading Statsbomb open data you can also use statsbomb.load_open_data. The api is very simular but you don't have to pass the urls.

In [3]:

Copied!





from kloppy import statsbomb

dataset = statsbomb.load_open_data(
    match_id=15946,
    
    # Optional arguments
    coordinates="statsbomb",
    event_types=["pass", "shot"]
)

dataset.to_df().head()
from kloppy import statsbomb

dataset = statsbomb.load_open_data(
    match_id=15946,
    
    # Optional arguments
    coordinates="statsbomb",
    event_types=["pass", "shot"]
)

dataset.to_df().head()

/Users/koen/Developer/Projects/PySport/kloppy/.venv/lib/python3.10/site-packages/kloppy-3.7.1-py3.10.egg/kloppy/_providers/statsbomb.py:67: UserWarning: 

You are about to use StatsBomb public data.
By using this data, you are agreeing to the user agreement. 
The user agreement can be found here: https://github.com/statsbomb/open-data/blob/master/LICENSE.pdf

  warnings.warn(

Out[3]:

	event_id	event_type	result	success	period_id	timestamp	end_timestamp	ball_state	ball_owning_team	team_id	player_id	coordinates_x	coordinates_y	end_coordinates_x	end_coordinates_y	receiver_player_id	set_piece_type	body_part_type	pass_type
0	34208ade-2af4-45c3-970e-655937cad938	PASS	COMPLETE	True	1	0.098	2.007	alive	206	206	6581	60.5	40.5	35.5	25.5	6855	KICK_OFF	LEFT_FOOT	NaN
1	d1cccb73-c7ef-4b02-8267-ebd7f149904b	PASS	INCOMPLETE	False	1	3.497	6.785	alive	206	206	6855	35.5	28.5	85.5	72.5	None	NaN	RIGHT_FOOT	LONG_BALL
2	f1cc47d6-4b19-45a6-beb9-33d67fc83f4b	PASS	COMPLETE	True	1	6.785	8.431	alive	217	217	5203	34.5	7.5	34.5	20.5	5470	NaN	HEAD	HEAD_PASS
3	f774571f-4b65-43a0-9bfc-6384948d1b82	PASS	COMPLETE	True	1	8.431	9.576	alive	217	217	5470	35.5	20.5	35.5	1.5	5477	NaN	HEAD	HEAD_PASS
4	46f0e871-3e72-4817-9a53-af27583ba6c1	PASS	COMPLETE	True	1	10.433	11.150	alive	217	217	5477	33.5	2.5	25.5	1.5	5211	NaN	RIGHT_FOOT	NaN