def load(self):
datasetAlreadyExists = self.__create_folders()
# clone file sources if dataset doesn't already exists
if not datasetAlreadyExists:
self.__cloneFilesSources()
if not os.path.exists(FileManager.getDatasetCopyFileUrl()):
# load dataset in memory
self.__loadInMemory()
# generate 'filtered' version
self.__filterSources()
# save dataset copy
datasetCopy: dict = {'training': self.Dataset.training, 'testing': self.Dataset.testing}
FileManager.writeFile(FileManager.getDatasetCopyFileUrl(), json.dumps(datasetCopy))
else:
datasetCopy = json.loads(FileManager.readFile(FileManager.getDatasetCopyFileUrl()))
self.Dataset.training = datasetCopy['training']
self.Dataset.testing = datasetCopy['testing']
return self
