def get_all():
return data.get_json_data('SELECT * FROM PROVEEDOR')
def get_all():
return data.get_json_data('SELECT * FROM CLIENTE')
def get_all():
return data.get_json_data('SELECT * FROM MOVIMIENTO')
# do pca on datasets
pca = PCA(n_components=2)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
## set seed
np.random.seed(args.seed)
torch.backends.cudnn.deterministic = True
torch.manual_seed(args.seed)
## get data
# 1. vocabulary
print('Getting vocabulary ...')
data_file = os.path.join(args.data_path, 'min_df_{}'.format(args.min_df))
data_file = args.data_path
# vocab, train, valid, test = data.get_data(data_file, temporal=True)
vocab, train, valid, test = data.get_json_data(data_file)
vocab_size = len(vocab)
args.vocab_size = vocab_size
# 1. training data
print('Getting training data ...')
train_tokens = train['tokens']
train_counts = train['counts']
train_times = train['times']
args.num_times = 25 # len(np.unique(train_times))
args.num_docs_train = len(train_tokens)
train_rnn_inp = data.get_rnn_input(
train_tokens, train_counts, train_times, args.num_times, args.vocab_size, args.num_docs_train)
# 2. dev set
print('Getting validation data ...')
def get_all_json_data(self):
all_json_data = data.get_json_data('SELECT * FROM {0}'.format(self.table_name))
return all_json_data