def main():
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
DATASET_DIRECTORY = '../data_part1'
X, y, X_hidden = dataset_manip.load_dataset(DATASET_DIRECTORY)
num_classes = len(set(y))
print('X.shape = ' + str(X.shape))
print('X_hidden.shape = ' + str(X_hidden.shape))
ens = Ensemble(input_shape=(77, 71, 1),
num_classes=10,
num_models=11,
batch_size=512,
path='./ensemble_files',
load=False)
ens.train(X=X, y=y, epochs_per_model=300, split_rate=0.9)
print(ens.measure_accuracy(X, y))
return
X_train, X_validation, y_train, y_validation = dataset_manip.split_dataset(
X, y, rate=0.5)
model = Model(image_shape=X.shape[1:],
num_classes=num_classes,
model_path='./model_files/model',
batch_size=512,
first_run=True) # 1250
model.train(X_train, y_train, X_validation, y_validation, 500)
model.train_unsupervised(X_hidden, X_validation, y_validation, 200)
print('Final Accuracy: {}'.format(
model.measure_accuracy(X_validation, y_validation)))
def worker(fold, n_users, n_items, dataset_dir):
traFilePath = dataset_dir + 'ratings__' + str(fold + 1) + '_tra.txt'
trasR = lil_matrix(
matBinarize(loadSparseR(n_users, n_items, traFilePath),
binarize_threshold))
print(
dataset_dir.split('/')[-2] + '@%d:' % (fold + 1), trasR.shape,
trasR.nnz, '%.2f' % (trasR.nnz / float(trasR.shape[0])))
tstFilePath = dataset_dir + 'ratings__' + str(fold + 1) + '_tst.txt'
tstsR = lil_matrix(
matBinarize(loadSparseR(n_users, n_items, tstFilePath),
binarize_threshold))
sampler = Sampler(trasR=trasR, batch_size=batch_size)
en = Ensemble(n_users, n_items, kensemble, topN, split_method,
eval_metrics, reg, n_factors, batch_size)
scores = en.train(fold + 1, trasR, tstsR, sampler)
print(
dataset_dir.split('/')[-2] + '@%d:' % (fold + 1),
','.join(['%s' % eval_metric for eval_metric in eval_metrics]) +
'@%d=' % (topN) + ','.join(['%.6f' % (score) for score in scores]))
en.close()
return scores
def main():
# Dataset path
dataset_name = ['credit_card_clients_balanced', 'credit_card_clients']
for data_name in dataset_name:
dataset_path = os.getcwd() + "\\dataset\\" + data_name + ".csv"
dataset = pd.read_csv(dataset_path, encoding='utf-8')
# Datasets columns
data_x = dataset[[
'X1', 'X2', 'X3', 'X4', 'X5', 'X6', 'X7', 'X8', 'X9', 'X10', 'X11',
'X12', 'X13', 'X14', 'X15', 'X16', 'X17', 'X18', 'X19', 'X20',
'X21', 'X22', 'X23'
]]
data_y = dataset['Y']
# Preprocessing data
min_max_scaler = preprocessing.MinMaxScaler()
X_normalized = min_max_scaler.fit_transform(data_x)
acc_rate = []
reject_rate = []
# Runs to test the model
for i in range(20):
print('---------------- Ensemble -----------------')
print('--- MLP - SVM - KNN - GMM - Naive Bayes ---')
print(i + 1, 'of 20 iterations')
X_train, X_test, y_train, y_test = train_test_split(X_normalized,
data_y,
test_size=0.2)
y_train = np.array(y_train)
y_test = np.array(y_test)
model = Ensemble()
model.train(X_train, y_train, gridSearch=False)
y_hat = model.predict(X_test)
error, reject = model.evaluate(y_hat, y_test)
acc_rate.append(1 - error)
reject_rate.append(reject)
graphics(acc_rate, reject_rate, data_name)
