floodlight.io

Collection of file parsing functionalities for different data providers as well as loaders for public datasets.

Submodule Reference

• floodlight.io.datasets
• floodlight.io.dfl
• floodlight.io.kinexon
• floodlight.io.opta
• floodlight.io.secondspectrum
• floodlight.io.sportradar
• floodlight.io.statsbomb
• floodlight.io.statsperform
• floodlight.io.tracab
• floodlight.io.utils

Datasets

EIGDDataset	This dataset loads the EIGD-H data from the A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games paper.
StatsBombOpenDataset	This dataset loads the StatsBomb open data provided by the official data repository.
ToyDataset	This dataset loads synthetic data for a (very) short artificial football match.

DFL

read_position_data_xml	Parse DFL files and extract position data, possession and ballstatus codes as well as pitch information and teamsheets.
read_event_data_xml	Parses a DFL Match Event XML file and extracts the event data as well as teamsheets.
read_pitch_from_mat_info_xml	Reads match_information XML file and returns the playing Pitch.
read_teamsheets_from_mat_info_xml	Reads match_information XML file and returns two teamsheet objects for the home and the away team.

Kinexon

read_position_data_csv	Parses a Kinexon csv file and extracts position data.
create_links_from_meta_data	Creates a dictionary from the pID_dict linking the identifier to the xID.
get_meta_data	Reads Kinexon's position data file and extracts meta-data about groups, sensors, length and framerate.
get_column_names_from_csv	Reads first line of a Kinexon.csv-file and extracts the column names.

Opta

read_event_data_xml	Parse Opta's f24 feed (containing match events) and extract event data and pitch information.
get_opta_feedtype	Tries to extract the feed type from Opta's XML feed.

Second Spectrum

read_position_data_jsonl	Parse Second Spectrum files and extract position data, possession and ballstatus codes, as well as pitch information.
read_event_data_jsonl	Parse Second Spectrums's Insight file (containing match events) and extract event data and pitch information.
read_teamsheets_from_meta_json	Parses the Second Spectrum meta.json-file and creates respective teamsheets for the home and the away team.

Sportradar

read_event_data_json

Parses the Sportradar timeline files in json format and extracts the event data.

StatsBomb

read_open_event_data_json	Parses files for a single match from the StatsBomb open dataset and extracts the event data and teamsheets.
read_teamsheets_from_open_event_data_json	Reads open events and match files and returns Teamsheet objects for the home and the away team.

StatsPerform

read_position_data_txt	Parses a StatsPerform TXT file and extracts position data and teamsheets.
read_open_position_data_csv	Parses an open StatsPerform CSV file and extract position data and possession codes as well as teamsheets and pitch information.
read_position_data_from_url	Reads a URL from the StatsPerform API (StatsEdgeViewer) containing a position data TXT file and extracts position data and teamsheets.
read_event_data_xml	Parses a StatsPerform XML file and extracts event data and pitch information.
read_open_event_data_csv	Parses an open StatsPerform Match Event CSV file and extracts the event data and teamsheets.
read_event_data_from_url	Reads a URL containing a StatsPerform events CSV file and extracts the stored event data, pitch information, and teamsheets.
read_teamsheets_from_position_data_txt	Parses the StatsPerform position file and returns two simple Teamsheet-objects containing only two columns "player" and "jID" for the home and the away team.
read_teamsheets_from_event_data_xml	Parses the StatsPerform event file and returns two Teamsheet-objects with detailed player information for the home and the away team.
read_teamsheets_from_open_data_csv	Parses the entire open StatsPerform position data CSV file for unique jIDs (jerseynumbers) and creates teamsheets for both teams.

Tracab (ChyronHego)

read_position_data_dat	Parse TRACAB .dat-files (ASCII) and metadata (xml or json) and extract position data, possession and ballstatus codes, teamsheets as well as pitch information.
read_teamsheets_from_dat	Parses the entire TRACAB .dat file for unique jIDs (jerseynumbers) and creates respective teamsheets for the home and the away team.
read_teamsheets_from_meta_json	Reads TRACAB's metadata file (json format) and creates respective teamsheets for the home and the away team.