[Football Analysis]02.이벤트 위치 시각화

 

작성일자 : 2023-08-27
Ver. 0.1.1

import os
import pandas as pd
import matplotlib.pyplot as plt
import plotly.graph_objects as go

Change directory

current_dir = os.getcwd()
print(current_dir)

/Users/limjongjun/Desktop/JayJay/Growth/Python/soccer-analytics

new_dir = '/Users/limjongjun/Desktop/JayJay/Growth/Python/soccer-analytics'
os.chdir(new_dir)

print(current_dir)

/Users/limjongjun/Desktop/JayJay/Growth/Python/soccer-analytics/Excercise

User scr.plot_utils

from src.plot_utils import * #plot_uitils.py  <- 경기장 이미지를 그리는 코드 

17/18 시즌 18Round Mancity vs Tottenham

match_id = 2499895
match_events = pd.read_pickle(f'data/refined_events/England/2499895.pkl') #pkl 파일을 Dataframe으로 불러오기
match_events

	match_id	event_id	period	time	team_id	team_name	player_id	player_name	event_type	sub_event_type	tags	start_x	start_y	end_x	end_y
0	2499895	215108367	1H	1.784	1625	Manchester City	8325	S. Agüero	Pass	Simple pass	[Accurate]	52.00	34.68	40.56	34.68
1	2499895	215108368	1H	3.324	1625	Manchester City	105339	Fernandinho	Pass	Simple pass	[Accurate]	40.56	34.68	29.12	8.16
2	2499895	215108369	1H	6.406	1625	Manchester City	8277	K. Walker	Pass	Simple pass	[Accurate]	29.12	8.16	44.72	10.20
3	2499895	215108370	1H	7.124	1625	Manchester City	38021	K. De Bruyne	Pass	Simple pass	[Accurate]	44.72	10.20	69.68	6.12
4	2499895	215108371	1H	8.676	1625	Manchester City	11066	R. Sterling	Pass	Simple pass	[Accurate]	69.68	6.12	58.24	12.24
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1607	2499895	215110122	2H	2875.703	1624	Tottenham Hotspur	210044	E. Dier	Pass	Simple pass	[Accurate]	36.40	26.52	48.88	29.92
1608	2499895	215110123	2H	2876.142	1624	Tottenham Hotspur	240070	H. Winks	Duel	Ground attacking duel	[Anticipation, Lost, Not accurate]	48.88	29.92	43.68	24.48
1609	2499895	215109959	2H	2876.768	1625	Manchester City	447205	P. Foden	Duel	Ground defending duel	[Anticipated, Won, Accurate]	55.12	38.08	60.32	43.52
1610	2499895	215109960	2H	2878.046	1625	Manchester City	11066	R. Sterling	Duel	Ground attacking duel	[Free space right, Lost, Not accurate]	60.32	43.52	60.32	43.52
1611	2499895	215110124	2H	2878.216	1624	Tottenham Hotspur	240070	H. Winks	Duel	Ground defending duel	[Free space left, Lost, Not accurate]	43.68	24.48	NaN	NaN

1612 rows × 15 columns

match_pass = match_events[match_events['event_type'] == 'Pass']
match_pass.head()

	match_id	event_id	period	time	team_id	team_name	player_id	player_name	event_type	sub_event_type	tags	start_x	start_y	end_x	end_y
0	2499895	215108367	1H	1.784	1625	Manchester City	8325	S. Agüero	Pass	Simple pass	[Accurate]	52.00	34.68	40.56	34.68
1	2499895	215108368	1H	3.324	1625	Manchester City	105339	Fernandinho	Pass	Simple pass	[Accurate]	40.56	34.68	29.12	8.16
2	2499895	215108369	1H	6.406	1625	Manchester City	8277	K. Walker	Pass	Simple pass	[Accurate]	29.12	8.16	44.72	10.20
3	2499895	215108370	1H	7.124	1625	Manchester City	38021	K. De Bruyne	Pass	Simple pass	[Accurate]	44.72	10.20	69.68	6.12
4	2499895	215108371	1H	8.676	1625	Manchester City	11066	R. Sterling	Pass	Simple pass	[Accurate]	69.68	6.12	58.24	12.24

match_pass.info()

<class 'pandas.core.frame.DataFrame'>
Index: 796 entries, 0 to 1607
Data columns (total 15 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   match_id        796 non-null    object 
 1   event_id        796 non-null    object 
 2   period          796 non-null    object 
 3   time            796 non-null    object 
 4   team_id         796 non-null    object 
 5   team_name       796 non-null    object 
 6   player_id       796 non-null    object 
 7   player_name     796 non-null    object 
 8   event_type      796 non-null    object 
 9   sub_event_type  796 non-null    object 
 10  tags            796 non-null    object 
 11  start_x         796 non-null    float64
 12  start_y         796 non-null    float64
 13  end_x           795 non-null    float64
 14  end_y           795 non-null    float64
dtypes: float64(4), object(11)
memory usage: 99.5+ KB

team1_name, team2_name = match_pass['team_name'].unique()

team1_pass = match_pass[match_pass['team_name'] == team1_name]
team2_pass = match_pass[match_pass['team_name'] == team2_name]

team1_name, team2_name

('Manchester City', 'Tottenham Hotspur')

team1_pass

	match_id	event_id	period	time	team_id	team_name	player_id	player_name	event_type	sub_event_type	tags	start_x	start_y	end_x	end_y
0	2499895	215108367	1H	1.784	1625	Manchester City	8325	S. Agüero	Pass	Simple pass	[Accurate]	52.00	34.68	40.56	34.68
1	2499895	215108368	1H	3.324	1625	Manchester City	105339	Fernandinho	Pass	Simple pass	[Accurate]	40.56	34.68	29.12	8.16
2	2499895	215108369	1H	6.406	1625	Manchester City	8277	K. Walker	Pass	Simple pass	[Accurate]	29.12	8.16	44.72	10.20
3	2499895	215108370	1H	7.124	1625	Manchester City	38021	K. De Bruyne	Pass	Simple pass	[Accurate]	44.72	10.20	69.68	6.12
4	2499895	215108371	1H	8.676	1625	Manchester City	11066	R. Sterling	Pass	Simple pass	[Accurate]	69.68	6.12	58.24	12.24
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1594	2499895	215109949	2H	2815.542	1625	Manchester City	8464	F. Delph	Pass	Simple pass	[Accurate]	10.40	63.92	5.20	40.12
1595	2499895	215109951	2H	2818.302	1625	Manchester City	71654	Ederson	Pass	Launch	[Not accurate]	5.20	40.12	42.64	53.72
1597	2499895	215109953	2H	2821.927	1625	Manchester City	105339	Fernandinho	Pass	Simple pass	[Not accurate]	28.08	42.84	23.92	33.32
1602	2499895	215109957	2H	2864.952	1625	Manchester City	105339	Fernandinho	Pass	Simple pass	[Not accurate]	41.60	17.00	64.48	19.04
1606	2499895	215109958	2H	2873.567	1625	Manchester City	105339	Fernandinho	Pass	High pass	[Not accurate]	45.76	19.72	67.60	41.48

422 rows × 15 columns

plt.scatter(team1_pass['start_x'], team1_pass['start_y'], c = 'blue')
plt.scatter(team2_pass['start_x'], team2_pass['start_y'], c = 'black')
plt.show()

draw_pitch(pitch='#440F48', line='white')
plt.savefig('img/pitch_ver2.png', bbox_inches='tight')

team2_pass[['start_x', 'end_x']].head()

	start_x	end_x
7	47.84	55.12
13	78.00	85.28
20	30.16	10.40
21	10.40	13.52
22	13.52	22.88

team2_pass[['start_y', 'end_y']].head()

	start_y	end_y
7	61.20	47.60
13	63.92	57.80
20	37.40	36.04
21	36.04	63.24
22	63.24	65.96

#데이터는 한방향으로 데이터가 쌓이고 있기에, team2의 위치 반전 필요
# x축 0~ 104 / y 축 0 ~ 68
team2_pass[['start_x', 'end_x']] = 104 - team2_pass[['start_x', 'end_x']]
team2_pass[['start_y', 'end_y']] = 68 - team2_pass[['start_y', 'end_y']]

/var/folders/_b/znjp14gd02d8lg63thqc7bm40000gn/T/ipykernel_2729/1796384401.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  team2_pass[['start_x', 'end_x']] = 104 - team2_pass[['start_x', 'end_x']]
/var/folders/_b/znjp14gd02d8lg63thqc7bm40000gn/T/ipykernel_2729/1796384401.py:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  team2_pass[['start_y', 'end_y']] = 68 - team2_pass[['start_y', 'end_y']]

draw_pitch('darkgreen','white')

plt.scatter (
    team1_pass['start_x'], team1_pass['start_y'], c = 'blue' , edgecolors= 'k' , alpha= 0.4, label = f'{team1_name} : {len(team1_pass)} pass'
)
plt.scatter (
    team2_pass['start_x'], team2_pass['start_y'], c = 'black' , edgecolors= 'k' , alpha= 0.4, label = f'{team2_name} : {len(team2_pass)} pass'
)

plt.legend(fontsize = 15, bbox_to_anchor = (1,1))
plt.show()