def get_all_data():
print("reading data...")
# Load training and eval data
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data_rq2(training_data_path, eval_data_path, OUT_FOLDER, "rq2_cnn1d_" + smell,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples=5000)
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data, eval_labels, max_input_length)
def get_all_data(data_path, smell):
print("reading data...")
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data(data_path, OUT_FOLDER, "rq1_rnn_" + smell,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples= 5000)
train_data = train_data.reshape((len(train_labels), max_input_length))
eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data,
eval_labels, max_input_length)
def get_all_data(training_data_path, eval_data_path, smell):
print("reading data...")
if smell in ["ComplexConditional", "ComplexMethod"]:
max_eval_samples = 150000 # for impl smells (methods)
else:
max_eval_samples = 50000 # for design smells (classes)
training_data, training_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data_rq2(training_data_path, eval_data_path, OUT_FOLDER, "rq2_rnn_" + smell,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples=5000,
max_eval_samples=max_eval_samples)
training_data = training_data.reshape((len(training_labels), max_input_length))
eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("reading data... done.")
return input_data.Input_data(training_data, training_labels, eval_data, eval_labels, max_input_length)
def get_all_data(data_path):
print("reading data...")
# Load training and eval data
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data(data_path, OUT_FOLDER, "rq1_cnn1d_" + smell,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples= 5000)
# train_data = train_data.reshape((len(train_labels), max_input_length))
# eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("train_data: " + str(len(train_data)))
print("train_labels: " + str(len(train_labels)))
print("eval_data: " + str(len(eval_data)))
print("eval_labels: " + str(len(eval_labels)))
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data,
eval_labels, max_input_length)
def get_all_data(data_path, smell):
print("reading data...")
max_eval_samples = 150000
if smell in ["MultifacetedAbstraction", "FeatureEnvy"]:
max_eval_samples = 50000
train_data, eval_data, eval_labels, max_input_length = \
inputs.get_data_autoencoder(data_path,
train_validate_ratio=TRAIN_VALIDATE_RATIO,
max_training_samples=5000,
max_eval_samples=max_eval_samples,
)
print("nan count: " + str(np.count_nonzero(np.isnan(train_data))))
print("train_data: " + str(len(train_data)))
print("train_data shape: " + str(train_data.shape))
print("eval_data: " + str(len(eval_data)))
print("eval_labels: " + str(len(eval_labels)))
print("reading data... done.")
return input_data.Input_data(train_data, None, eval_data, eval_labels, max_input_length)
def get_all_data(data_path, smell):
print("reading data...")
if smell in ["ComplexConditional", "ComplexMethod"]:
max_eval_samples = 150000 # for impl smells (methods)
else:
max_eval_samples = 50000 #for design smells (classes)
# Load training and eval data
train_data, train_labels, eval_data, eval_labels, max_input_length = \
inputs.get_data(data_path,
train_validate_ratio=TRAIN_VALIDATE_RATIO, max_training_samples=5000,
max_eval_samples=max_eval_samples, is_c2v = C2V)
# train_data = train_data.reshape((len(train_labels), max_input_length))
# eval_data = eval_data.reshape((len(eval_labels), max_input_length))
print("train_data: " + str(len(train_data)))
print("train_labels: " + str(len(train_labels)))
print("eval_data: " + str(len(eval_data)))
print("eval_labels: " + str(len(eval_labels)))
print("reading data... done.")
return input_data.Input_data(train_data, train_labels, eval_data,
eval_labels, max_input_length)