football-data.co.uk

[1]:

import sys
sys.path.append("../")

import penaltyblog as pb

[2]:

pb.__version__

[2]:

'0.4.0'

List the available countries to download data for

[3]:

pb.scrapers.FootballData.list_competitions()

[3]:

['DEU Bundesliga 1',
 'DEU Bundesliga 2',
 'ENG Premier League',
 'ENG Championship',
 'ENG League 1',
 'ENG League 2',
 'ENG Conference',
 'FRA Ligue 1',
 'FRA Ligue 2',
 'GRC Super League',
 'ITA Serie A',
 'ITA Serie B',
 'NLD Eredivisie',
 'PRT Liga 1',
 'SCO Premier League',
 'SCO Division 1',
 'SCO Division 2',
 'SCO Division 3',
 'TUR Super Lig']

Download the data for the English Premier League

[4]:

fb = pb.scrapers.FootballData("ENG Premier League", "2021-2022")
df = fb.get_fixtures()

df.head()

[4]:

	competition	season	datetime	div	date	time	team_home	team_away	fthg	ftag	...	avg_c<2.5	ah_ch	b365_cahh	b365_caha	pcahh	pcaha	max_cahh	max_caha	avg_cahh	avg_caha
id
1628812800---brentford---arsenal	ENG Premier League	2021-2022	2021-08-13 20:00:00	E0	2021-08-13	20:00	Brentford	Arsenal	2	0	...	1.62	0.50	1.75	2.05	1.81	2.13	2.05	2.17	1.80	2.09
1628899200---burnley---brighton	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Burnley	Brighton	1	2	...	1.62	0.25	1.79	2.15	1.81	2.14	1.82	2.19	1.79	2.12
1628899200---chelsea---crystal_palace	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Chelsea	Crystal Palace	3	0	...	1.94	-1.50	2.05	1.75	2.12	1.81	2.16	1.93	2.06	1.82
1628899200---everton---southampton	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Everton	Southampton	3	1	...	1.67	-0.50	2.05	1.88	2.05	1.88	2.08	1.90	2.03	1.86
1628899200---leicester---wolves	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Leicester	Wolves	1	0	...	1.79	-0.75	2.02	1.91	2.01	1.92	2.05	1.95	1.99	1.89

5 rows × 109 columns

Download the data for the English Premier League and map team names

[8]:

team_mappings = pb.scrapers.get_example_team_name_mappings()

fb = pb.scrapers.FootballData("ENG Premier League", "2021-2022", team_mappings)
df = fb.get_fixtures()

df.head()

[8]:

	competition	season	datetime	div	date	time	team_home	team_away	fthg	ftag	...	avg_c<2.5	ah_ch	b365_cahh	b365_caha	pcahh	pcaha	max_cahh	max_caha	avg_cahh	avg_caha
id
1628812800---brentford---arsenal	ENG Premier League	2021-2022	2021-08-13 20:00:00	E0	2021-08-13	20:00	Brentford	Arsenal	2	0	...	1.62	0.50	1.75	2.05	1.81	2.13	2.05	2.17	1.80	2.09
1628899200---burnley---brighton	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Burnley	Brighton	1	2	...	1.62	0.25	1.79	2.15	1.81	2.14	1.82	2.19	1.79	2.12
1628899200---chelsea---crystal_palace	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Chelsea	Crystal Palace	3	0	...	1.94	-1.50	2.05	1.75	2.12	1.81	2.16	1.93	2.06	1.82
1628899200---everton---southampton	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Everton	Southampton	3	1	...	1.67	-0.50	2.05	1.88	2.05	1.88	2.08	1.90	2.03	1.86
1628899200---leicester_city---wolverhampton_wanderers	ENG Premier League	2021-2022	2021-08-14 15:00:00	E0	2021-08-14	15:00	Leicester City	Wolverhampton Wanderers	1	0	...	1.79	-0.75	2.02	1.91	2.01	1.92	2.05	1.95	1.99	1.89

5 rows × 109 columns

[10]:

"Wolverhampton Wanderers" in df["team_home"].unique()

[10]:

True

[9]:

df["team_home"].unique()

[9]:

array(['Brentford', 'Burnley', 'Chelsea', 'Everton', 'Leicester City',
       'Manchester United', 'Norwich City', 'Watford', 'Newcastle United',
       'Tottenham Hotspur', 'Aston Villa', 'Brighton', 'Crystal Palace',
       'Leeds United', 'Liverpool', 'Manchester City', 'Arsenal',
       'Southampton', 'Wolverhampton Wanderers', 'West Ham'], dtype=object)

[ ]: