The whole pipeline in one call

Extraction, team/player counts, second-phase detection, retention, added value, the report, and the rating are normally five-plus function calls chained together. wa_setpieces.run_workflow() runs that whole chain for one set-piece type and hands back every table at once – this example runs it, then plots straight off the result.

from pathlib import Path

from wa_setpieces import load_matches, run_workflow
from wa_setpieces.core.xt import XTModel
from wa_setpieces.viz.plots import plot_dashboard, plot_rating_benchmark

try:
    _here = Path(__file__).resolve().parent
except NameError:
    _here = Path.cwd()
DATA = _here.parent / "tests" / "data" / "sample_match.json"

events = load_matches(DATA)
model = XTModel.fit(events, x_bins=8, y_bins=6)

One call gets everything – summary through rating:

result = run_workflow(events, "corner", model=model, min_deliveries=1, min_shots=1)
result.report

	contestantId	attempts	successful	success_rate	second_phases	second_phase_goals	second_phase_rate	retention_rate	total_added_value	avg_added_value	goals
0	cxb4hqite921i36gwrezdts7c	2	1	0.500	0	0	0.000	0.500	-0.0192	-0.0096	0
1	f2yd0yzt0om6qhks9gbowu1d6	7	1	0.143	2	0	0.286	0.429	0.0000	0.0000	0

Straight into a plot, no intermediate wiring:

team_id = result.report["contestantId"].iloc[0]
fig = plot_dashboard(events, team_id, set_piece_type="corner")

fig, ax = plot_rating_benchmark(result.team_rating, title="Corner rating — by team")