def create_data():
training_files = _get_training_files()
series_training_files = _get_series_of_files(training_files)
for series in series_training_files:
data = Data(False, False)
data.training = TrainingSet(False, False, *series)
yield data
def _run(self):
data = Data()
data.training = self.training
system = System(data)
system.use_best_feature_set()
system.create_features()
system.train()
system.eval(quiet=True)
self.result_event_event = system.evaluation_accuracy_event_event
self.result_event_timex = system.evaluation_accuracy_event_timex
def _run_systems(self):
for k in range(1, self.max_len+1):
features = list(set(self._feature_series(k, self.features_event_event) + self._feature_series(k, self.features_event_timex)))
print features
data = Data()
data.training = TrainingSet(False, False, "data/training/TBAQ-cleaned/TimeBank/")
system = System(data, features)
system.create_features()
system.cross_validation()
now = list(set(self._feature_series(k, self.features_event_event)))
if k > 1:
prev = list(set(self._feature_series(k-1, self.features_event_event)))
if k > 1:
if now != prev:
self.accuracies_event_event.append(system.crossval_accuracy_event_event)
print system.crossval_accuracy_event_event
else:
self.accuracies_event_event.append(system.crossval_accuracy_event_event)
print system.crossval_accuracy_event_event
now = list(set(self._feature_series(k, self.features_event_timex)))
if k > 1:
prev = list(set(self._feature_series(k-1, self.features_event_timex)))
if k > 1:
if now != prev:
self.accuracies_event_timex.append(system.crossval_accuracy_event_timex)
print system.crossval_accuracy_event_timex
else:
self.accuracies_event_timex.append(system.crossval_accuracy_event_timex)
print system.crossval_accuracy_event_timex
print
# Leave out i for testing
train_X, test_X = leave_out(pieces_X, i)
train_y, test_y = leave_out(pieces_y, i)
# Transform back to sparse
train_X = transform_to_sparse_matrix(train_X)
test_X = transform_to_sparse_matrix(test_X)
clf.fit(train_X, train_y)
predicted = clf.predict(test_X)
accs.append(accuracy_score(test_y, predicted))
return np.mean(accs)
data = Data()
data.training = TrainingSet(False, False, "data/training/TBAQ-cleaned/TimeBank/")
system = System(data, ["lemma", "token"])
system.create_features()
X_event_event, y_event_event = system.training_event_event
X_event_timex, y_event_timex = system.training_event_timex
X_event_event = transform_to_list(X_event_event)
X_event_timex = transform_to_list(X_event_timex)
print kfold(X_event_event, y_event_event, 5)
print kfold(X_event_timex, y_event_timex, 5)
