def train(param, x, y):
dim_in = x.shape[1]
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print(device)
dataloader = DataLoader(torch.from_numpy(x.astype(np.float32)),
batch_size=param.batch_size,
shuffle=True,
num_workers=2)
flow = RealNVP(dim_in, device)
flow.to(device)
flow.train()
optimizer = torch.optim.Adam(
[p for p in flow.parameters() if p.requires_grad == True], lr=param.lr)
it, print_cnt = 0, 0
while it < param.total_it:
for i, data in enumerate(dataloader):
loss = -flow.log_prob(data.to(device)).mean()
optimizer.zero_grad()
loss.backward(retain_graph=True)
optimizer.step()
it += data.shape[0]
print_cnt += data.shape[0]
if print_cnt > PRINT_FREQ:
print('it {:d} -- loss {:.03f}'.format(it, loss))
print_cnt = 0
torch.save(flow.state_dict(), 'flow_model.pytorch')
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print(device)
x, y, scaler = load_data('lendingclub',
is_tree=False,
scaler_type='standardize')
x = np.concatenate([x, np.zeros((x.shape[0], 1))],
axis=1).astype(np.float32)
flow = RealNVP(x.shape[1], device)
if device.type == 'cpu':
flow.load_state_dict(torch.load(args.model, map_location='cpu'))
else:
flow.load_state_dict(torch.load(args.model))
flow.to(device)
flow.eval()
# produce samples
x_gen = flow.g(flow.prior.sample(
(args.n_samples, ))).detach().cpu().numpy()[:, :-1]
np.save('samples.npy', x_gen)
df_x = scaler.as_dataframe(x[:, :-1])
df_gen = fix_df(x_gen, scaler)
df_gen.to_csv('real.csv')
# reconstruction quality ---------------------
if args.quality:
quality_test(df_x, df_gen, scaler)
