def svm(data):
#create results file if it doesn't already exist
results_directory_name = "results"
result_file = os.path.join(results_directory_name, str(data.currentY), "svm_fr", "result_main_svm_fr.txt")
# crée le répertoire "results" et le sous-répertoire "svm_fr"
if not (os.path.exists(results_directory_name)):
os.mkdir(results_directory_name)
if not (os.path.exists(os.path.join(results_directory_name, str(data.currentY)))):
os.mkdir(os.path.join(results_directory_name, str(data.currentY)))
if not (os.path.exists(os.path.join(results_directory_name, str(data.currentY), 'svm_fr'))):
os.mkdir(os.path.join(results_directory_name, str(data.currentY), 'svm_fr'))
ut.log_print(result_file,
'<========== BEGIN @ ' + datetime.datetime.now().strftime("%I:%M%p on %B %d, %Y") + ' ============>\n')
best_params = []
for s in range(len(data.Xsource)):
print("\n--- Domain:",s,"---\n")
# création de répertoires results/svm_fr/decision_values/...
dv_dir = os.path.join(results_directory_name, str(data.currentY), 'svm_fr', 'decision_values', data.domain_names[s])
if not (os.path.exists(results_directory_name)):
os.mkdir(results_directory_name)
if not (os.path.exists(os.path.join(results_directory_name, str(data.currentY)))):
os.mkdir(os.path.join(results_directory_name, str(data.currentY)))
if not (os.path.exists(os.path.join(results_directory_name, str(data.currentY), 'svm_fr'))):
os.mkdir(os.path.join(results_directory_name, str(data.currentY), 'svm_fr'))
if not (os.path.exists(os.path.join(results_directory_name, str(data.currentY), 'svm_fr', 'decision_values'))):
os.mkdir(os.path.join(results_directory_name, str(data.currentY), 'svm_fr', 'decision_values'))
if not (os.path.exists(dv_dir)):
os.mkdir(dv_dir)
#for the s-th source domain...
Xsource = data.Xsource[s]
ysource = data.ysource[s]
#glue together the labelled data from the source and target domains
Xsparse = sp.sparse.vstack([data.Xtarget, csc_matrix(Xsource)])
Xdata = Xsparse.todense()
#get the associated labels for all training points
y = np.concatenate((data.ytarget, ysource))
src_index = [i + data.Xtarget.shape[0] for i in range(Xsource.shape[0])]
tar_index = [i for i in range(data.Xtarget.shape[0])]
for r in range(data.nRound):
tar_train_index = data.tar_train_index[r]
tar_test_index = data.tar_test_index[r]
train_index = np.concatenate((src_index, tar_train_index))
dv_file = os.path.join(dv_dir, "dv_round=" + str(r) + ".mat")
if os.path.exists(dv_file):
decision_values = io.loadmat(dv_file)['decision_values']
else:
Ymatrix = np.asarray(np.squeeze(y[train_index]), dtype=float)
Xmatrix = np.asarray(Xdata[train_index])
classifier = prepare_svm(Xmatrix, Ymatrix, False)
classifier_params = classifier.get_params()
best_params.append(classifier_params)
decision_values = classifier.decision_function(Xdata[tar_index])
decision_values = np.array(decision_values)
training_predictions = classifier.predict(Xmatrix)
print("Training Accuracy", ut.final_accuracy(training_predictions, y[train_index]))
predictions = classifier.predict(Xdata[tar_index])
print("Test Accuracy", ut.final_accuracy(predictions, y[tar_index]))
io.savemat(dv_file, {'decision_values': decision_values})
ut.save_mmd_fr(data, best_params, s)
def second_phase(data, results):
result_directory_name = 'results'
result_filename = os.path.join(result_directory_name, 'secondPhase',
'results_main_secondPhase.txt')
if not (os.path.exists(result_directory_name)):
os.mkdir(result_directory_name)
if not (os.path.exists(os.path.join(result_directory_name,
'secondPhase'))):
os.mkdir(os.path.join(result_directory_name, 'secondPhase'))
Xdata = copy.deepcopy(data.Xtarget)
K = Xdata.dot(Xdata.T)
tar_train_index = data.tar_train_index
tar_test_index = data.tar_test_index
all_test_dv = []
mmd_values = []
for r in range(data.nRound):
#loading DVs and MMD values
for s in range(len(data.Xsource)):
dv_dir = os.path.join(result_directory_name, str(data.currentY),
'svm_fr', 'decision_values',
data.domain_names[s])
mmd_dir = os.path.join(result_directory_name, str(data.currentY),
'mmd_values_fr', data.domain_names[s])
dv_file = os.path.join(dv_dir, "dv_round=" + str(r) + ".mat")
if os.path.exists(dv_file):
decision_values = io.loadmat(dv_file)['decision_values']
else:
print(
'You need to run the required baseline algorithms to obtain the decision values required by algorithm'
)
return -1
mmd_file = os.path.join(mmd_dir, 'mmd.mat')
if os.path.exists(mmd_file):
mmd_value = (io.loadmat(mmd_file))['mmd_value']
else:
print(
'please run the proper save_mmd first to prepare the mmd values required by this algorithm'
)
return -1
mmd_values.extend(mmd_value)
all_test_dv.extend([decision_values])
y = copy.deepcopy(data.ytarget)
y[tar_test_index] = 0
f_s = np.squeeze(np.array(all_test_dv))
print("mmds", mmd_values)
gamma_s = np.zeros((len(mmd_values)), dtype=float)
mmd_aux = np.reshape(
np.asarray(mmd_values).flatten(), (len(mmd_values), 1))
mmd_aux = np.power(mmd_aux, 2).flatten()
gamma_s = gamma_s + np.exp((-1 * BETA) * mmd_aux)
gamma_s = gamma_s / np.sum(gamma_s)
print("gamma", gamma_s)
theta1 = LAMBDA_L
theta2 = LAMBDA_D
dv = train_fast_dam(K, y, f_s, gamma_s, theta1, theta2, np.array([]),
np.array([]))
formatted_results = []
for item in dv[tar_test_index]:
formatted_results.extend(item)
formatted_results = np.asarray(formatted_results).reshape(
(len(formatted_results), 1))
results = np.hstack((results, formatted_results))
print("DV", dv[tar_test_index])
accuracy = ut.final_accuracy(np.squeeze(dv[tar_test_index]),
np.squeeze(data.ytarget[tar_test_index]))
print("Accuracy?!", accuracy, "\n")
return results
def second_phase(data, results):
result_directory_name = 'results'
result_filename = os.path.join(result_directory_name, 'secondPhase', 'results_main_secondPhase.txt')
if not (os.path.exists(result_directory_name)):
os.mkdir(result_directory_name)
if not (os.path.exists(os.path.join(result_directory_name, 'secondPhase'))):
os.mkdir(os.path.join(result_directory_name, 'secondPhase'))
Xdata = copy.deepcopy(data.Xtarget)
K = Xdata.dot(Xdata.T)
tar_train_index = data.tar_train_index
tar_test_index = data.tar_test_index
all_test_dv = []
mmd_values = []
for r in range(data.nRound):
#loading DVs and MMD values
for s in range(len(data.Xsource)):
dv_dir = os.path.join(result_directory_name, str(data.currentY), 'svm_fr', 'decision_values', data.domain_names[s])
mmd_dir = os.path.join(result_directory_name, str(data.currentY), 'mmd_values_fr', data.domain_names[s])
dv_file = os.path.join(dv_dir, "dv_round="+str(r)+".mat")
if os.path.exists(dv_file):
decision_values = io.loadmat(dv_file)['decision_values']
else:
print('You need to run the required baseline algorithms to obtain the decision values required by algorithm')
return -1
mmd_file = os.path.join(mmd_dir, 'mmd.mat')
if os.path.exists(mmd_file):
mmd_value = (io.loadmat(mmd_file))['mmd_value']
else:
print('please run the proper save_mmd first to prepare the mmd values required by this algorithm')
return -1
mmd_values.extend(mmd_value)
all_test_dv.extend([decision_values])
y = copy.deepcopy(data.ytarget)
y[tar_test_index] = 0
f_s = np.squeeze(np.array(all_test_dv))
print("mmds", mmd_values)
gamma_s = np.zeros((len(mmd_values)), dtype=float)
mmd_aux = np.reshape(np.asarray(mmd_values).flatten(), (len(mmd_values), 1))
mmd_aux = np.power(mmd_aux, 2).flatten()
gamma_s = gamma_s + np.exp((-1*BETA)*mmd_aux)
gamma_s = gamma_s/np.sum(gamma_s)
print("gamma", gamma_s)
theta1 = LAMBDA_L
theta2 = LAMBDA_D
dv = train_fast_dam(K, y, f_s, gamma_s, theta1, theta2, np.array([]), np.array([]))
formatted_results = []
for item in dv[tar_test_index]:
formatted_results.extend(item)
formatted_results = np.asarray(formatted_results).reshape((len(formatted_results),1))
results = np.hstack((results, formatted_results))
print("DV", dv[tar_test_index])
accuracy = ut.final_accuracy(np.squeeze(dv[tar_test_index]), np.squeeze(data.ytarget[tar_test_index]))
print("Accuracy?!", accuracy, "\n")
return results