ium_478839/IUM03.ipynb

1. Pobieranie bazy

!kaggle datasets download -d slehkyi/extended-football-stats-for-european-leagues-xg

Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 /home/osboxes/.kaggle/kaggle.json'
Downloading extended-football-stats-for-european-leagues-xg.zip to /home/osboxes/jupyter_dir/notebooks/IUM03
 73%|███████████████████████████▋          | 1.00M/1.37M [00:00<00:00, 5.12MB/s]
100%|██████████████████████████████████████| 1.37M/1.37M [00:00<00:00, 3.95MB/s]

!unzip -o extended-football-stats-for-european-leagues-xg.zip

Archive:  extended-football-stats-for-european-leagues-xg.zip
  inflating: understat.com.csv       
  inflating: understat_per_game.csv  

2. Zmiana nazwy plikow

mv understat.com.csv understat.csv

3. Zmiana nazwy kolumn

import pandas as pd
understat = pd.read_csv('understat.csv')
understat_per_game = pd.read_csv('understat_per_game.csv')

understat.rename( columns={'Unnamed: 0':'league'}, inplace=True)
understat.rename( columns={'Unnamed: 1':'year'}, inplace=True)

understat.head()

	league	year	position	team	matches	wins	draws	loses	scored	missed	...	xGA	xGA_diff	npxGA	npxGD	ppda_coef	oppda_coef	deep	deep_allowed	xpts	xpts_diff
0	La_liga	2014	1	Barcelona	38	30	4	4	110	21	...	28.444293	7.444293	24.727907	73.049305	5.683535	16.367593	489	114	94.0813	0.0813
1	La_liga	2014	2	Real Madrid	38	30	2	6	118	38	...	42.607198	4.607198	38.890805	47.213090	10.209085	12.929510	351	153	81.7489	-10.2511
2	La_liga	2014	3	Atletico Madrid	38	23	9	6	67	29	...	29.069107	0.069107	26.839271	25.748737	8.982028	9.237091	197	123	73.1353	-4.8647
3	La_liga	2014	4	Valencia	38	22	11	5	70	32	...	39.392572	7.392572	33.446477	16.257501	8.709827	7.870225	203	172	63.7068	-13.2932
4	La_liga	2014	5	Sevilla	38	23	7	8	71	45	...	47.862742	2.862742	41.916529	20.178070	8.276148	9.477805	305	168	67.3867	-8.6133

5 rows × 24 columns

understat_per_game.head()

	league	year	h_a	xG	xGA	npxG	npxGA	deep	deep_allowed	scored	...	ppda_coef	ppda_att	ppda_def	oppda_coef	oppda_att	oppda_def	team	xG_diff	xGA_diff	xpts_diff
0	Bundesliga	2014	h	2.57012	1.198420	2.57012	1.198420	5	4	2	...	9.625000	231	24	21.850000	437	20	Bayern Munich	0.57012	0.198420	-0.6514
1	Bundesliga	2014	a	1.50328	1.307950	1.50328	1.307950	10	1	1	...	4.756098	195	41	17.695652	407	23	Bayern Munich	0.50328	0.307950	0.5143
2	Bundesliga	2014	h	1.22987	0.310166	1.22987	0.310166	13	3	2	...	5.060606	167	33	16.961538	441	26	Bayern Munich	-0.77013	0.310166	-0.8412
3	Bundesliga	2014	a	1.03519	0.203118	1.03519	0.203118	6	2	0	...	4.423077	115	26	9.446809	444	47	Bayern Munich	1.03519	0.203118	1.1367
4	Bundesliga	2014	h	3.48286	0.402844	3.48286	0.402844	23	2	4	...	4.250000	170	40	44.800000	448	10	Bayern Munich	-0.51714	0.402844	-0.0713

5 rows × 29 columns