def create_and_visualize(param):
print(f"{dt()} :: Create And Visualize Initialize")
datasets = loader.create_loader(param)
for nb_comb in range(1, 6):
print(f"{dt()} :: --Create Combine Number : {nb_comb}")
dc = dict()
for key, files in datasets.items():
files = sorted(files)
param.key = key
class_collect = list()
for file in files:
output = create_configuration(param, file, nb_comb)
class_collect.append(output)
dc[key] = class_collect
print(f"{dt()} :: --Combine Number : {nb_comb} Save Initialize")
cc.save_datasets(param, dc, nb_comb)
print(f"{dt()} :: --Done")
if nb_comb == 1:
print(f"{dt()} :: Visualize Initialize")
visdat = loader.viz_loader(param)
print(f"{dt()} :: --Visualize Dataset Path Load")
visualizer.chosen_viz(param, visdat)
print(f"{dt()} :: --Done")
def vector_to_img(param):
print(f"{dt()} :: Create Initialize")
datasets = loader.create_loader(param)
nb_comb = 1
pn_collect = list()
cn_collect = list()
data_collect = list()
dc = dict()
for key, files in datasets.items():
files = sorted(files)
param.key = key
for file in files:
# class_collect.append(output)
if param.model_name == 'create':
pressure, acc, gyro, peo_nb, class_nb = vti_configuration(
param, file, nb_comb)
cc.save_vti(pressure, 'pressure', peo_nb, class_nb, param)
cc.save_dataset_with_vti(acc, 'acc', peo_nb, class_nb, param)
cc.save_dataset_with_vti(gyro, 'gyro', peo_nb, class_nb, param)
else:
pressure, acc, gyro, peo_nb, class_nb = vti_configuration(
param, file, nb_comb)
pn_collect.append(int(peo_nb))
cn_collect.append(int(class_nb))
dataset = [pressure, acc, gyro]
data_collect.append(dataset)
preprocessing.vti_preprocess(param, pn_collect, cn_collect, data_collect)
def cropping(param):
print(f"{dt()} :: Cropping Network Initialize")
datasets = loader.create_loader(param)
data_list = preprocessing.normalize_all_of_length(param, datasets)
for i, data in enumerate(data_list):
data[:, -2] = data[:, -2] - 1
data_list[i] = data[data[:, -2].argsort()]
param.nb_modal = 3
train, test, nb_class, nb_people = preprocessing.chosen_method(param=param, comb=1, datasets=data_list)
nb_repeat = len(train)
for repeat in range(nb_repeat):
model = model_compactor.model_setting(param, train[repeat], test[repeat], [nb_class, nb_people])
print('Done?')
def create(param):
print(f"{dt()} :: Create Initialize")
datasets = loader.create_loader(param)
for nb_comb in range(1, 6):
print(f"{dt()} :: Combine Number : {nb_comb}")
dc = dict()
for key, files in datasets.items():
files = sorted(files)
param.key = key
class_collect = list()
for file in files:
output = create_configuration(param, file, nb_comb)
class_collect.append(output)
dc[key] = class_collect
print(f"{dt()} :: --Combine Number : {nb_comb} Save Initialize")
cc.save_datasets(param, dc, nb_comb)
print(f"{dt()} :: --Done")
def create_v2(param):
print(f"{dt()} :: Create Initialize")
datasets = loader.create_loader(param)
for nb_comb in range(1, 6):
print(f"{dt()} :: Combine Number : {nb_comb}")
dc = dict()
for key, files in datasets.items():
files = sorted(files)
param.key = key
class_collect = list()
for file in files:
if file.split('/')[-1] == '13_04.csv' or file.split('/')[-1] == '14_05.csv' and \
(param.datatype == 'disease' or param.datatype == 'disease_add'):
continue
print(file)
output = create_configuration_v2(param, file, nb_comb)
class_collect.append(output)
dc[key] = class_collect
print(f"{dt()} :: --Combine Number : {nb_comb} Save Initialize")
cc.save_datasets(param, dc, nb_comb)
print(f"{dt()} :: --Done")