def second_classifier_trainonall(data, virtual_labels, vl_ind):
print("\nTARGET CLASSIFIER")
Xdata = copy.deepcopy(data.Xtarget[data.tar_train_index])
Xdata_aux = copy.deepcopy(data.Xtarget[data.tar_train_index])
for i in range(10*4):
Xdata = np.append(Xdata, Xdata_aux, 1)
X_target_test = data.Xtarget[data.tar_test_index]
X_target_test = np.squeeze(X_target_test)
Xdata = np.squeeze(Xdata)
Xdata = np.append(Xdata, X_target_test[vl_ind], 0)
for s in range(len(data.Xsource)):
Xdata = np.append(Xdata, data.Xsource[s], 0)
labels = copy.deepcopy(data.ytarget[data.tar_train_index])
labels_aux = copy.deepcopy(data.ytarget[data.tar_train_index])
for i in range(10*4):
labels = np.append(labels, labels_aux, 0)
labels = np.append(labels, virtual_labels[vl_ind])
for s in range(len(data.Xsource)):
labels = np.append(labels, data.ysource[s], 0)
forest = RandomForestClassifier(n_estimators=NUM_ESTIMATORS, n_jobs=-1, max_depth=MAX_DEPTH, max_features=MAX_FEATURES, min_samples_split=MIN_SAMPLES_SPLIT)
forest = forest.fit(Xdata, labels)
Xtest = np.squeeze(data.Xtarget[data.tar_test_index])
ytest = np.squeeze(data.ytarget[data.tar_test_index])
predictions = forest.predict(Xtest)
print("Final accuracy: ", ut.accuracy_test(predictions, ytest))
def main_random_forest():
for i in range(NUM_ITERATIONS):
print("************ RANDOM FOREST METHOD:",i+1,"************")
data = utrf.load_data_from_files()
results = rf.base_rf(data, utrf.Results())
results = rf.determine_relevance(results)
print("\n--- Virtual labels ---")
virtual_labels, indices = rf.get_virtual_vote(results)
ytarget = np.squeeze(data.ytarget[data.tar_test_index])
print("\nVirtual label accuracy:", utrf.accuracy_test(virtual_labels[indices], ytarget[indices]))
rf.second_classifier_trainonall(data, virtual_labels, indices)
def main_random_forest():
for i in range(NUM_ITERATIONS):
print("************ RANDOM FOREST METHOD:", i + 1, "************")
data = utrf.load_data_from_files()
results = rf.base_rf(data, utrf.Results())
results = rf.determine_relevance(results)
print("\n--- Virtual labels ---")
virtual_labels, indices = rf.get_virtual_vote(results)
ytarget = np.squeeze(data.ytarget[data.tar_test_index])
print("\nVirtual label accuracy:",
utrf.accuracy_test(virtual_labels[indices], ytarget[indices]))
rf.second_classifier_trainonall(data, virtual_labels, indices)
