Soccer analysis example

This tutorial uses data extracted from video footage of a soccer game that was published in https://github.com/Friends-of-Tracking-Data-FoTD/Last-Row

import numpy as np
import pandas as pd
import geopandas as gpd
import movingpandas as mpd
import shapely as shp
import holoviews as hv
import hvplot.pandas 
import matplotlib.pyplot as plt

from geopandas import GeoDataFrame, read_file
from shapely.geometry import Point, LineString, Polygon
from datetime import datetime, timedelta
from holoviews import opts, dim
from os.path import exists
from urllib.request import urlretrieve

import warnings
warnings.filterwarnings('ignore')

hvplot_defaults = {'line_width':5, 'frame_height':350, 'frame_width':700, 'colorbar':True, 'tiles':None, 'geo':False,}

mpd.show_versions()

MovingPandas 0.17.0

SYSTEM INFO
-----------
python     : 3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]
executable : H:\miniconda3\envs\mpd-ex\python.exe
machine    : Windows-10-10.0.19045-SP0

GEOS, GDAL, PROJ INFO
---------------------
GEOS       : None
GEOS lib   : None
GDAL       : 3.7.0
GDAL data dir: None
PROJ       : 9.2.1
PROJ data dir: H:\miniconda3\pkgs\proj-9.0.0-h1cfcee9_1\Library\share\proj

PYTHON DEPENDENCIES
-------------------
geopandas  : 0.13.2
pandas     : 2.0.3
fiona      : 1.9.4
numpy      : 1.24.4
shapely    : 2.0.1
rtree      : 1.0.1
pyproj     : 3.6.0
matplotlib : 3.7.2
mapclassify: 2.5.0
geopy      : 2.3.0
holoviews  : 1.17.0
hvplot     : 0.8.3
geoviews   : 1.9.6
stonesoup  : 1.0

Loading soccer dataset from Github

def get_file_from_url(url):
    file = url.split('/')[-1]
    if not exists(file):
        urlretrieve(url, file)
    return file     

def get_df_from_gh_url(url):
    file = get_file_from_url(url)
    return pd.read_csv(file)

input_file = "https://raw.githubusercontent.com/Friends-of-Tracking-Data-FoTD/Last-Row/master/datasets/positional_data/liverpool_2019.csv"
df = get_df_from_gh_url(input_file)
df.drop(columns=['Unnamed: 0'], inplace=True)
print(f'Number of records: {len(df)}')

Number of records: 74936

df.head()

	bgcolor	dx	dy	edgecolor	frame	play	player	player_num	team	x	y	z
0	NaN	0.000000	0.000000	NaN	0	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	46.394558	11.134454	0.0
1	NaN	0.185745	1.217580	NaN	1	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	46.580302	12.352034	0.0
2	NaN	0.178659	1.171133	NaN	2	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	46.758961	13.523166	0.0
3	NaN	0.171573	1.124685	NaN	3	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	46.930535	14.647852	0.0
4	NaN	0.164488	1.078238	NaN	4	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	47.095022	15.726090	0.0

From the metadata:

• play: the scoreline after the goal. The team who scored the goal is the one next to the brackets.
• frame: the frame number for the current location. Data provided has 20 frames per second.
• player: the id of the player. The id is consistent within a play but not between plays.
• player_num: the player jersey number. This number is the official one, and did not change for Liverpool in 2019. You can check the corresponding names at this wikipedia link.
• x, y: coordinates for the player/ball. Pitch coordinates go from 0 to 100 on each axis.
• dx, dx: change in (x,y) coordinates from last frame to current frame
• z: height, from 0 to 1.5 (only filled for the ball)
• bgcolor: the main color for the team (used as background color)
• edgecolor the secondary color (used as edge color)

And accoring to https://en.wikipedia.org/wiki/Football_pitch

the preferred size for many professional teams' stadiums is 105 by 68 metres

plays = list(df.play.unique())

def to_timestamp(row):
    # plays to date
    day = plays.index(row.play)+1
    start_time = datetime(2019,1,day,12,0,0)
    # frames to time
    td = timedelta(milliseconds=1000/20*row.frame)
    return start_time + td

# frame: the frame number for the current location. Data provided has 20 frames per second
df['time'] = df.apply(to_timestamp, axis=1)
df.set_index('time', inplace=True)

# the preferred size for many professional teams' stadiums is 105 by 68 metres, accoring to https://en.wikipedia.org/wiki/Football_pitch
pitch_length = 105
pitch_width = 68
df.x = df.x / 100 * pitch_length 
df.y = df.y / 100 * pitch_width

df

	bgcolor	dx	dy	edgecolor	frame	play	player	player_num	team	x	y	z
time
2019-01-01 12:00:00.000	NaN	0.000000	0.000000	NaN	0	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	48.714286	7.571429	0.0
2019-01-01 12:00:00.050	NaN	0.185745	1.217580	NaN	1	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	48.909318	8.399383	0.0
2019-01-01 12:00:00.100	NaN	0.178659	1.171133	NaN	2	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	49.096909	9.195753	0.0
2019-01-01 12:00:00.150	NaN	0.171573	1.124685	NaN	3	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	49.277061	9.960539	0.0
2019-01-01 12:00:00.200	NaN	0.164488	1.078238	NaN	4	Liverpool [3] - 0 Bournemouth	0	NaN	NaN	49.449774	10.693741	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...
2019-01-19 12:00:06.000	blue	0.000000	0.000000	white	120	Leicester 0 - [3] Liverpool	10267	NaN	defense	103.661067	36.529840	0.0
2019-01-19 12:00:06.050	blue	0.000000	0.000000	white	121	Leicester 0 - [3] Liverpool	10267	NaN	defense	103.661067	36.529840	0.0
2019-01-19 12:00:06.100	blue	0.000000	0.000000	white	122	Leicester 0 - [3] Liverpool	10267	NaN	defense	103.661067	36.529840	0.0
2019-01-19 12:00:06.150	blue	0.000000	0.000000	white	123	Leicester 0 - [3] Liverpool	10267	NaN	defense	103.661067	36.529840	0.0
2019-01-19 12:00:06.200	blue	0.000000	0.000000	white	124	Leicester 0 - [3] Liverpool	10267	NaN	defense	103.661067	36.529840	0.0

74936 rows × 12 columns

df['team'].value_counts().plot(title='team', kind='bar', figsize=(15,3))

<Axes: title={'center': 'team'}, xlabel='team'>

df['player_num'].value_counts().plot(title='player_num', kind='bar', figsize=(15,3))

<Axes: title={'center': 'player_num'}, xlabel='player_num'>

df['team'] = df['team'].astype('category').cat.as_ordered()
df['player'] = df['player'].astype('category').cat.as_ordered()
df['player_num'] = df['player_num'].astype('category').cat.as_ordered()

Finally, let's create trajectories:

Trajectories

%%time
CRS = None
tc = mpd.TrajectoryCollection(df, 'player', x='x', y='y', crs=CRS)
mpd.TemporalSplitter(tc).split(mode="day")
print(f"Finished creating {len(tc)} trajectories")

Finished creating 364 trajectories
CPU times: total: 10.2 s
Wall time: 10.5 s

pitch = Polygon([(0, 0), (0, pitch_width), (pitch_length, pitch_width), (pitch_length, 0), (0, 0)])
plotted_pitch = GeoDataFrame(pd.DataFrame([{'geometry': pitch, 'id': 1}]), crs=CRS).hvplot(color='white', alpha=0.5)

plotted_pitch * tc.filter('player_num', 20).hvplot(**hvplot_defaults)

Plays

PLAY = 2
title = f'Play {PLAY} {plays[PLAY]}'
play_trajs = tc.filter('play', plays[PLAY])
play_trajs

TrajectoryCollection with 20 trajectories

play_trajs.plot(column='team', colormap={'attack':'hotpink', 'defense':'turquoise'})

<Axes: >

generalized = mpd.MinTimeDeltaGeneralizer(play_trajs).generalize(tolerance=timedelta(seconds=0.5))

generalized.add_speed()

generalized.hvplot(title=title,  c='speed', hover_cols=['player', 'team'], **hvplot_defaults)

(
    plotted_pitch * 
    generalized.hvplot(title=title,  c='speed', hover_cols=['player'], cmap='Viridis', **hvplot_defaults)
)

get_file_from_url('https://github.com/movingpandas/movingpandas/raw/main/tutorials/data/soccer_field.png')

pitch_img = hv.RGB.load_image('soccer_field.png', bounds=(0,0,pitch_length,pitch_width)) 
(
    pitch_img * 
    generalized.hvplot(title=title, c='team', colormap={'attack':'limegreen', 'defense':'purple'}, hover_cols=['team'], **hvplot_defaults) * 
    generalized.get_start_locations().hvplot(label='start', color='orange')
)