def main():
"""
This example shows the use of Metrica datasets, and how we can pass argument
to the dataset loader.
"""
logging.basicConfig(
stream=sys.stdout,
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
)
# The metrica dataset loader loads by default the 'game1' dataset
dataset = datasets.load("metrica_tracking",
options={
"sample_rate": 1.0 / 12,
"limit": 10
})
print(len(dataset.frames))
# We can pass additional keyword arguments to the loaders to specify a different dataset
dataset = datasets.load("metrica_tracking",
options={"limit": 1000},
game="game2")
data_frame = to_pandas(dataset)
print(data_frame)
def main():
"""
This example shows the use of Statsbomb datasets, and how we can pass argument
to the dataset loader.
"""
logging.basicConfig(
stream=sys.stdout,
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)
dataset = datasets.load(
"statsbomb", {"event_types": ["pass", "take_on", "carry", "shot"]})
with performance_logging("transform", logger=logger):
# convert to TRACAB coordinates
dataset = transform(dataset,
to_orientation="FIXED_HOME_AWAY",
to_pitch_dimensions=[(-5500, 5500), (-3300, 3300)])
with performance_logging("to pandas", logger=logger):
dataframe = to_pandas(dataset)
print(dataframe[:50].to_string())
def main():
"""
This example shows how to determine playing time
"""
logging.basicConfig(
stream=sys.stdout,
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
)
dataset = datasets.load("metrica_tracking",
options={"sample_rate": 1.0 / 25})
playing_seconds_per_player = Counter()
for frame in dataset.frames:
playing_seconds_per_player.update([
player.jersey_no for player in frame.players_coordinates.keys()
if player.team.ground == Ground.HOME
])
x = range(len(playing_seconds_per_player))
jersey_numbers, playing_seconds = zip(
*sorted(playing_seconds_per_player.items()))
playing_minutes = [seconds / 60 for seconds in playing_seconds]
plt.bar(x, playing_minutes, align="center", alpha=0.5)
plt.xticks(x, jersey_numbers)
plt.ylabel("Minutes")
plt.title("Playing time per player")
plt.show()
def main():
"""
This example shows how to determine playing time
"""
data_set = datasets.load("metrica_tracking",
options={'sample_rate': 1. / 25})
playing_seconds_per_player = Counter()
for frame in data_set.frames:
playing_seconds_per_player.update([
int(jersey_no)
for jersey_no in frame.home_team_player_positions.keys()
])
x = range(len(playing_seconds_per_player))
jersey_numbers, playing_seconds = zip(
*sorted(playing_seconds_per_player.items()))
playing_minutes = [seconds / 60 for seconds in playing_seconds]
plt.bar(x, playing_minutes, align='center', alpha=0.5)
plt.xticks(x, jersey_numbers)
plt.ylabel('Minutes')
plt.title('Playing time per player')
plt.show()
def main():
"""
This example shows the use of Metrica datasets, and how we can pass argument
to the dataset loader.
"""
# The metrica dataset loader loads by default the 'game1' dataset
data_set = datasets.load("metrica_tracking",
options={
'sample_rate': 1. / 12,
'limit': 10
})
print(len(data_set.frames))
# We can pass additional keyword arguments to the loaders to specify a different dataset
data_set = datasets.load("metrica_tracking",
options={'limit': 1000},
game='game2')
data_frame = to_pandas(data_set)
print(data_frame)
def main():
import pandas as pd
pd.set_option("display.max_colwidth", None)
pd.set_option("display.max_columns", None)
pd.set_option("display.max_rows", None)
pd.set_option("display.width", 2000)
matcher = Matcher(encoder)
dataset = datasets.load("statsbomb",
options={"event_types": ["shot", "pass"]})
with performance_logging("search"):
matches = matcher.search(dataset, r"PPS")
df = to_pandas(
dataset,
additional_columns={
"player_name": lambda event: event.player.full_name,
"team_name": lambda event: str(event.team),
},
)
print(df[["timestamp", "team_name", "player_name", "event_type",
"result"]][:100])
return
for i, match in enumerate(matches):
df = to_pandas(
dataset,
additional_columns={
"player_name": lambda event: event.player.full_name,
"team_name": lambda event: str(event.team),
},
)
print(df[[
"period_id",
"timestamp",
"team_name",
"player_name",
"event_type",
]])
def main():
logging.basicConfig(
stream=sys.stdout,
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)
dataset = datasets.load(
"statsbomb", {"event_types": ["pass", "take_on", "carry", "shot"]})
with performance_logging("transform", logger=logger):
dataset = transform(dataset,
to_orientation="FIXED_HOME_AWAY",
to_pitch_dimensions=[(-5500, 5500), (-3300, 3300)])
with performance_logging("to pandas", logger=logger):
dataframe = to_pandas(dataset)
print(dataframe[:50].to_string())
def _load_match(provider: str, match_id: str) -> List[pyspark.Row]:
dataset = datasets.load(provider, match_id=match_id)
pdf = kh.fix_kloppy_dataframe(dataset.to_pandas(all_passes=True))
return [pyspark.Row(match=match_id, **row) for row in pdf.to_dict(orient="records")]