Note
Click here to download the full example code
Sample soccer data
This example shows SampleSoccerStats and SampleSoccerOdds, the sample data that ships with the library.
# Author: Georgios Douzas <gdouzas@icloud.com>
# Licence: MIT
import matplotlib.pyplot as plt
from sportsbet.dataloaders import DataLoader
from sportsbet.sources import SampleSoccerOdds, SampleSoccerStats
What the sample carries
It is a real season of the English and Spanish first divisions, taken from football-data.co.uk and frozen. It needs no key and reaches no network. That is why the examples and the tests use it.
stats = SampleSoccerStats()
stats.name, stats.kind, stats.sport
Out:
('sample_soccer', 'stats', 'soccer')
It ships with the library, so it knows what it publishes without reading anything.
stats.list_available_params()
Out:
[{'division': 1, 'league': 'England', 'year': 2024}, {'division': 1, 'league': 'Spain', 'year': 2024}]
Extracting the data
It is an ordinary source, so you use it like any other. Give it to a dataloader beside an odds source. Extracting reads the bundled files off your disk. That costs nothing and touches no network.
dataloader = DataLoader(param_grid={'league': ['England']}, stats=stats, odds=SampleSoccerOdds())
X_train, Y_train, O_train = dataloader.extract_train_data(odds_type='market_average')
The input data:
X_train
Out:
league division ... away_points_avg home_points_avg
date ...
2023-08-11 19:00:00+00:00 England 1 ... NaN NaN
2023-08-12 11:30:00+00:00 England 1 ... NaN NaN
2023-08-12 14:00:00+00:00 England 1 ... NaN NaN
2023-08-12 14:00:00+00:00 England 1 ... NaN NaN
2023-08-12 14:00:00+00:00 England 1 ... NaN NaN
... ... ... ... ... ...
2024-05-19 15:00:00+00:00 England 1 ... 1.837838 1.243243
2024-05-19 15:00:00+00:00 England 1 ... 1.243243 2.135135
2024-05-19 15:00:00+00:00 England 1 ... 1.189189 0.702703
2024-05-19 15:00:00+00:00 England 1 ... 1.405405 2.378378
2024-05-19 15:00:00+00:00 England 1 ... 1.702703 0.432432
[380 rows x 7 columns]
The multi-output targets:
Y_train
Out:
home_win__postplay__0min ... under_2.5__postplay__0min
date ...
2023-08-11 19:00:00+00:00 0.0 ... 0.0
2023-08-12 11:30:00+00:00 1.0 ... 0.0
2023-08-12 14:00:00+00:00 0.0 ... 1.0
2023-08-12 14:00:00+00:00 1.0 ... 0.0
2023-08-12 14:00:00+00:00 0.0 ... 1.0
... ... ... ...
2024-05-19 15:00:00+00:00 1.0 ... 0.0
2024-05-19 15:00:00+00:00 1.0 ... 1.0
2024-05-19 15:00:00+00:00 0.0 ... 0.0
2024-05-19 15:00:00+00:00 1.0 ... 0.0
2024-05-19 15:00:00+00:00 0.0 ... 0.0
[380 rows x 5 columns]
The odds:
O_train
Out:
market_average__away_win__preplay__0min ... market_average__under_2.5__preplay__0min
date ...
2023-08-11 19:00:00+00:00 1.35 ... 2.27
2023-08-12 11:30:00+00:00 15.67 ... 2.85
2023-08-12 14:00:00+00:00 2.64 ... 1.94
2023-08-12 14:00:00+00:00 9.61 ... 2.34
2023-08-12 14:00:00+00:00 3.30 ... 1.86
... ... ... ...
2024-05-19 15:00:00+00:00 3.67 ... 2.96
2024-05-19 15:00:00+00:00 14.55 ... 4.23
2024-05-19 15:00:00+00:00 2.23 ... 2.76
2024-05-19 15:00:00+00:00 21.81 ... 4.45
2024-05-19 15:00:00+00:00 1.35 ... 4.14
[380 rows x 5 columns]
It has no fixtures
The season is finished, so every match in it has been played. A fixture is a match that has not been played. The
sample has none, so extract_fixtures_data returns an empty frame with the training columns.
To bet on something, you need a source that is still publishing matches. See Football-Data. The sample is for learning the interface, not for betting.
X_fix, _, O_fix = dataloader.extract_fixtures_data()
len(X_fix)
Out:
0
A picture of it
This shows how the season ended. Home wins lead. That lead is the home advantage the odds always price in.
outcomes = Y_train.sum()
outcomes.index = outcomes.index.str.split('__').str[0]
fig, ax = plt.subplots()
ax.bar(outcomes.index, outcomes.to_numpy(), color=['tab:green', 'tab:grey', 'tab:red'])
ax.set_title('How the sample season ended, by outcome')
ax.set_ylabel('matches')
Out:
Text(37.722222222222214, 0.5, 'matches')
Total running time of the script: ( 0 minutes 0.794 seconds)
Download Python source code: plot_sample_soccer.py