def _fix_clearances(actions: DataFrame) -> DataFrame:
next_actions = actions.shift(-1)
next_actions[-1:] = actions[-1:]
clearance_idx = actions.type_id == spadlconfig.actiontypes.index(
'clearance')
actions.loc[clearance_idx,
'end_x'] = next_actions[clearance_idx].start_x.values
actions.loc[clearance_idx,
'end_y'] = next_actions[clearance_idx].start_y.values
return actions
def _extra_from_shots(actions: DataFrame) -> DataFrame:
next_actions = actions.shift(-1)
shotlike = ['shot', 'shot_freekick', 'shot_penalty']
shot_ids = list(_spadl.actiontypes.index(ty) for ty in shotlike)
samegame = actions.game_id == next_actions.game_id
sameperiod = actions.period_id == next_actions.period_id
shot = actions.type_id.isin(shot_ids)
goal = shot & (actions.result_id == _spadl.results.index('success'))
owngoal = shot & (actions.result_id == _spadl.results.index('owngoal'))
next_corner_goalkick = next_actions.type_id.isin([
actiontypes.index('corner_crossed'),
actiontypes.index('corner_short'),
actiontypes.index('goalkick'),
])
out = shot & next_corner_goalkick & samegame & sameperiod
extra_idx = goal | owngoal | out
prev = actions[extra_idx]
# nex = next_actions[extra_idx]
extra = pd.DataFrame()
extra['game_id'] = prev.game_id
extra['original_event_id'] = prev.original_event_id
extra['period_id'] = prev.period_id
extra['action_id'] = prev.action_id + 0.1
extra['time_seconds'] = prev.time_seconds # + nex.time_seconds) / 2
extra['start_x'] = prev.end_x
extra['start_y'] = prev.end_y
extra['end_x'] = prev.end_x
extra['end_y'] = prev.end_y
extra['bodypart_id'] = prev.bodypart_id
extra['result_id'] = -1
extra['team_id'] = prev.team_id
extra['player_id'] = prev.player_id
ar = actiontypes
extra['type_id'] = -1
extra['type_id'] = (extra.type_id.mask(goal, ar.index('goal')).mask(
owngoal, ar.index('owngoal')).mask(out, ar.index('out')))
actions = pd.concat([actions, extra], ignore_index=True, sort=False)
actions = actions.sort_values(['game_id', 'period_id',
'action_id']).reset_index(drop=True)
actions['action_id'] = range(len(actions))
return actions
def _add_dribbles(actions: DataFrame) -> DataFrame:
next_actions = actions.shift(-1)
same_team = actions.team_id == next_actions.team_id
# not_clearance = actions.type_id != actiontypes.index("clearance")
dx = actions.end_x - next_actions.start_x
dy = actions.end_y - next_actions.start_y
far_enough = dx**2 + dy**2 >= min_dribble_length**2
not_too_far = dx**2 + dy**2 <= max_dribble_length**2
dt = next_actions.time_seconds - actions.time_seconds
same_phase = dt < max_dribble_duration
same_period = actions.period_id == next_actions.period_id
dribble_idx = same_team & far_enough & not_too_far & same_phase & same_period
dribbles = pd.DataFrame()
prev = actions[dribble_idx]
nex = next_actions[dribble_idx]
dribbles['game_id'] = nex.game_id
dribbles['period_id'] = nex.period_id
dribbles['action_id'] = prev.action_id + 0.1
dribbles['time_seconds'] = (prev.time_seconds + nex.time_seconds) / 2
if 'timestamp' in actions.columns:
dribbles['timestamp'] = nex.timestamp
dribbles['team_id'] = nex.team_id
dribbles['player_id'] = nex.player_id
dribbles['start_x'] = prev.end_x
dribbles['start_y'] = prev.end_y
dribbles['end_x'] = nex.start_x
dribbles['end_y'] = nex.start_y
dribbles['bodypart_id'] = spadlconfig.bodyparts.index('foot')
dribbles['type_id'] = spadlconfig.actiontypes.index('dribble')
dribbles['result_id'] = spadlconfig.results.index('success')
actions = pd.concat([actions, dribbles], ignore_index=True, sort=False)
actions = actions.sort_values(['game_id', 'period_id',
'action_id']).reset_index(drop=True)
actions['action_id'] = range(len(actions))
return actions
def _extra_from_passes(actions: DataFrame) -> DataFrame:
next_actions = actions.shift(-1)
same_team = actions.team_id == next_actions.team_id
passlike = [
'pass',
'cross',
'throw_in',
'freekick_short',
'freekick_crossed',
'corner_crossed',
'corner_short',
'clearance',
'goalkick',
]
pass_ids = list(_spadl.actiontypes.index(ty) for ty in passlike)
interceptionlike = [
'interception',
'tackle',
'keeper_punch',
'keeper_save',
'keeper_claim',
'keeper_pick_up',
]
interception_ids = list(
_spadl.actiontypes.index(ty) for ty in interceptionlike)
samegame = actions.game_id == next_actions.game_id
sameperiod = actions.period_id == next_actions.period_id
# samephase = next_actions.time_seconds - actions.time_seconds < max_pass_duration
extra_idx = (
actions.type_id.isin(pass_ids)
& samegame
& sameperiod # & samephase
& ~next_actions.type_id.isin(interception_ids))
prev = actions[extra_idx]
nex = next_actions[extra_idx]
extra = pd.DataFrame()
extra['game_id'] = prev.game_id
extra['original_event_id'] = prev.original_event_id
extra['period_id'] = prev.period_id
extra['action_id'] = prev.action_id + 0.1
extra['time_seconds'] = (prev.time_seconds + nex.time_seconds) / 2
extra['start_x'] = prev.end_x
extra['start_y'] = prev.end_y
extra['end_x'] = prev.end_x
extra['end_y'] = prev.end_y
extra['bodypart_id'] = bodyparts.index('foot')
extra['result_id'] = -1
offside = prev.result_id == _spadl.results.index('offside')
out = ((nex.type_id == actiontypes.index('goalkick')) &
(~same_team)) | (nex.type_id == actiontypes.index('throw_in'))
ar = actiontypes
extra['type_id'] = -1
extra['type_id'] = (extra.type_id.mask(
same_team,
ar.index('receival')).mask(~same_team, ar.index('interception')).mask(
out, ar.index('out')).mask(offside, ar.index('offside')))
is_interception = extra['type_id'] == ar.index('interception')
extra['team_id'] = prev.team_id.mask(is_interception, nex.team_id)
extra['player_id'] = nex.player_id.mask(out | offside, prev.player_id)
actions = pd.concat([actions, extra], ignore_index=True, sort=False)
actions = actions.sort_values(['game_id', 'period_id',
'action_id']).reset_index(drop=True)
actions['action_id'] = range(len(actions))
return actions