def predict(self):
"""
Predicts tags in the given data
It reports the accuracy if the data is fully labeled
@type data_test: SequenceData
@param data_test: the test data set
@return: the predicted labels, the accuracy, the f1_score
"""
# keep starting timestamp
start_time = time.time()
assert (not self.feature_extractor.is_training), "In order to predict, is_training should be False"
# Extract features on all instances (labeled or unlabeled) of the test set
# pass them to liblinearutil for prediction
pred_labels, (acc, _, _), _ = liblinearutil.predict(self.label_list_test, self.features_list_test,
self.__liblinear_model, "-q")
# print some useful information
if not self.quiet:
num_seconds = int(math.ceil(time.time() - start_time))
# estimate prediction time
print("Prediction time: {0}".format(str(datetime.timedelta(seconds=num_seconds))))
# convert predicted labels from integer IDs to strings.
pred_labels = self.convert_prediction(pred_labels, self.data_test)
# for i, label in enumerate(pred_labels):
# pred_labels[i] = self.feature_extractor.get_label_string(label)
self.__save_prediction_to_file(self.data_test, pred_labels)
return pred_labels, acc
def model_training(x,y,x_test,y_test):
prob = liblinearutil.problem(y, x)
start = time.process_time()
# sklearn.svm.libsvm.cross_validation(x,y)
# sklearn.svm.libsvm.fit(x,y)
param = liblinearutil.parameter('-q')
m = liblinearutil.train(prob, param)
train_time = time.process_time() - start
start2 = time.process_time()
pred_labels, (acc, MSE, SCC), pred_values = liblinearutil.predict(y_test, x_test, m)
predict_time = time.process_time() - start2
# print(time.process_time() - start)
return train_time,predict_time
def model_training(n, i):
meth = method[i]
y, x = liblinearutil.svm_read_problem("other_method/kmeans_linear/%s/train_%s" % (
name, meth))
y_test, x_test = liblinearutil.svm_read_problem("other_method/kmeans_linear/%s/test_%s" % (
name, meth))
prob = liblinearutil.problem(y, x)
temp_result = np.empty((14))
for idx, val in enumerate(cost):
param = liblinearutil.parameter(' -q -c %f' % (val))
m = liblinearutil.train(prob, param)
pred_labels, (temp_result[idx], MSE, SCC), pred_values = liblinearutil.predict(y_test, x_test, m)
return (i, f_idx, n, temp_result)
def model_training():
meth = method[0]
y, x = liblinearutil.svm_read_problem("other_method/kmeans_linear/%s/train_%s" % (
name, meth))
y_test, x_test = liblinearutil.svm_read_problem("other_method/kmeans_linear/%s/test_%s" % (
name, meth))
prob = liblinearutil.problem(y, x)
temp_result = np.zeros((12))
# print(x.shape(1))
for idx, val in enumerate(cost):
start = time.time()
param = liblinearutil.parameter(' -q -c %f' % (val))
m = liblinearutil.train(prob, param)
pred_labels, (temp_result[idx], MSE, SCC), pred_values = liblinearutil.predict(y_test, x_test, m)
# print(temp_result)
t2 = time.time()-start
return np.max(temp_result),t2
def model_training():
x, y = load_svmlight_file("svm/BudgetedSVM/original/%s/train" % (name))
x_test, y_test = load_svmlight_file("svm/BudgetedSVM/original/%s/test" %
(name))
# x = np.asarray(x)
# x_test = np.asarray(x_test)
# scaler = StandardScaler().fit(x)
#
# x = scaler.transform(x)
prob = liblinearutil.problem(y, x)
temp_result = np.empty((14))
# x_test = scaler.transform(x_test)
param = liblinearutil.parameter(' -q ')
start = time.process_time()
m = liblinearutil.train(prob, param)
print(time.process_time() - start)
start2 = time.process_time()
pred_labels, (acc, MSE,
SCC), pred_values = liblinearutil.predict(y_test, x_test, m)
print(time.process_time() - start2, acc)
exit()