def _prepocess_training_data(self, x, t, e, vsize, random_state):
"""RNNs require different preprocessing for variable length sequences"""
idx = list(range(x.shape[0]))
np.random.seed(random_state)
np.random.shuffle(idx)
x = _get_padded_features(x)
t = _get_padded_targets(t)
e = _get_padded_targets(e)
x_train, t_train, e_train = x[idx], t[idx], e[idx]
x_train = torch.from_numpy(x_train).double()
t_train = torch.from_numpy(t_train).double()
e_train = torch.from_numpy(e_train).double()
vsize = int(vsize * x_train.shape[0])
x_val, t_val, e_val = x_train[-vsize:], t_train[-vsize:], e_train[
-vsize:]
x_train = x_train[:-vsize]
t_train = t_train[:-vsize]
e_train = e_train[:-vsize]
return (x_train, t_train, e_train, x_val, t_val, e_val)
def _prepocess_training_data(self, x, t, e, vsize, val_data, random_state):
"""RNNs require different preprocessing for variable length sequences"""
idx = list(range(x.shape[0]))
np.random.seed(random_state)
np.random.shuffle(idx)
x = _get_padded_features(x)
x_train, t_train, e_train = x[idx], t[idx], e[idx]
x_train = torch.from_numpy(x_train).double()
t_train = torch.from_numpy(t_train).double()
e_train = torch.from_numpy(e_train).double()
if val_data is None:
vsize = int(vsize*x_train.shape[0])
x_val, t_val, e_val = x_train[-vsize:], t_train[-vsize:], e_train[-vsize:]
x_train = x_train[:-vsize]
t_train = t_train[:-vsize]
e_train = e_train[:-vsize]
else:
x_val, t_val, e_val = val_data
x_val = _get_padded_features(x_val)
t_val, _ = self.discretize(t_val, self.split, self.split_time)
x_val = torch.from_numpy(x_val).double()
t_val = torch.from_numpy(last(t_val)).double()
e_val = torch.from_numpy(last(e_val)).double()
return (x_train, t_train, e_train,
x_val, t_val, e_val)
def _prepocess_test_data(self, x):
return torch.from_numpy(_get_padded_features(x))
def _prepocess_test_data(self, x): data = torch.from_numpy(_get_padded_features(x)) if self.cuda: data = data.cuda() return data