def fit_one(self, data, model_y, model_stereo):
event_ids = numpy.unique(data.EventID.values)
if self.train_size != None:
event_ids_train, event_ids_test= train_test_split(event_ids, train_size=self.train_size, random_state=42)
else:
event_ids_test = event_ids
# fit train tracks
if self.train_size != None:
tracks_train = {}
p = Pool(self.processes)
results_train = p.map(tracks_reconstruction, zip(event_ids_train,
[data]*len(event_ids_train),
[model_y]*len(event_ids_train),
[model_stereo]*len(event_ids_train)))
tracks_train = merge_dicts(results_train)
# train clf
if self.train_size != None:
sc = SuperCombinator()
combination_data = sc.data_collection(tracks_train, data)
X_data = combination_data[combination_data.columns[:-1]].values
y_data = combination_data.label.values
xgb_base = XGBoostClassifier(n_estimators=1000, colsample=0.7, eta=0.01, nthreads=1,
subsample=0.7, max_depth=8)
folding = FoldingClassifier(xgb_base, n_folds=10, random_state=11)
folding.fit(X_data, y_data)
clf = folding.estimators[0]
else:
clf = None
# fit test tracks
tracks_test = {}
p = Pool(self.processes)
results_test = p.map(tracks_reconstruction, zip(event_ids_test,
[data]*len(event_ids_test),
[model_y]*len(event_ids_test),
[model_stereo]*len(event_ids_test)))
tracks_test = merge_dicts(results_test)
# quality
p = Pool(self.processes)
effs = p.map(get_eff_value, zip(event_ids_test,
[data]*len(event_ids_test),
[tracks_test]*len(event_ids_test),
[clf]*len(event_ids_test)))
eff = 100. * numpy.array(effs).sum() / len(effs)
return eff
def fit_one(self, data, model_y, model_stereo):
event_ids = numpy.unique(data.EventID.values)
if self.train_size != None:
event_ids_train, event_ids_test = train_test_split(
event_ids, train_size=self.train_size, random_state=42)
else:
event_ids_test = event_ids
# fit train tracks
if self.train_size != None:
tracks_train = {}
p = Pool(self.processes)
results_train = p.map(
tracks_reconstruction,
zip(event_ids_train, [data] * len(event_ids_train),
[model_y] * len(event_ids_train),
[model_stereo] * len(event_ids_train)))
tracks_train = merge_dicts(results_train)
# train clf
if self.train_size != None:
sc = SuperCombinator()
combination_data = sc.data_collection(tracks_train, data)
X_data = combination_data[combination_data.columns[:-1]].values
y_data = combination_data.label.values
xgb_base = XGBoostClassifier(n_estimators=1000,
colsample=0.7,
eta=0.01,
nthreads=1,
subsample=0.7,
max_depth=8)
folding = FoldingClassifier(xgb_base, n_folds=10, random_state=11)
folding.fit(X_data, y_data)
clf = folding.estimators[0]
else:
clf = None
# fit test tracks
tracks_test = {}
p = Pool(self.processes)
results_test = p.map(
tracks_reconstruction,
zip(event_ids_test, [data] * len(event_ids_test),
[model_y] * len(event_ids_test),
[model_stereo] * len(event_ids_test)))
tracks_test = merge_dicts(results_test)
# quality
p = Pool(self.processes)
effs = p.map(
get_eff_value,
zip(event_ids_test, [data] * len(event_ids_test),
[tracks_test] * len(event_ids_test),
[clf] * len(event_ids_test)))
eff = 100. * numpy.array(effs).sum() / len(effs)
return eff
