Dataloader

class TSDataLoader[source]

TSDataLoader(dataset, horizon, lookback=72, step=1, min_seq_len=None, max_std=2, bs=64, shuffle=False, num_workers=None, verbose=False, do_setup=True, pin_memory=False, timeout=0, batch_size=None, drop_last=False, indexed=None, n=None, device=None, wif=None, before_iter=None, after_item=None, before_batch=None, after_batch=None, after_iter=None, create_batches=None, create_item=None, create_batch=None, retain=None, get_idxs=None, sample=None, shuffle_fn=None, do_batch=None) :: TfmdDL

Transformed DataLoader

horizon,lookback = 2,5
ints = L(np.arange(9.)[None,:],np.arange(9.,14)[None,:]).map(tensor)
ints

(#2) [tensor([[0., 1., 2., 3., 4., 5., 6., 7., 8.]]),tensor([[ 9., 10., 11., 12., 13.]])]

dl = TSDataLoader(ints, horizon, lookback, step=2, norm=False)
list(dl)

Need to pad 1/2 time series due to length.

[(TSTensorSeq([[[ 0.,  1.,  2.,  3.,  4.]],
  
          [[ 2.,  3.,  4.,  5.,  6.]],
  
          [[10., 10.,  9., 10., 11.]]]),
  TSTensorSeqy([[[ 0.,  1.,  2.,  3.,  4.,  5.,  6.]],
  
          [[ 2.,  3.,  4.,  5.,  6.,  7.,  8.]],
  
          [[10., 10., 10., 10., 11., 12., 13.]]]))]

The first sequence (0 to 7) is transformed in to two items. One with x from 0 to 4 and y from 0 to 6. The next one is shifted just two, because step == 2. The second sequence (and third resulting item) is not long enough and is therefore padded with the mean of x (10). Note both x and y are padded with the mean of x

Showing

Intergration Example

from fastseq.core import *
from fastai2.basics import *

path = untar_data(URLs.m4_daily)
df_train = pd.read_csv(path/'train.csv',nrows=300)
df_test = pd.read_csv(path/'val.csv')
df_test.head()

	V1	V2	V3	V4	V5	V6	V7	V8	V9	V10	V11	V12	V13	V14	V15
0	D1	2039.20	2035.00	2051.80	2061.8	2063.50	2069.5	2054.00	2057.00	2062.80	2066.40	2067.40	2071.40	2083.80	2080.60
1	D2	2986.00	3001.20	2975.90	2996.1	2981.90	2985.5	2975.80	2956.20	2964.70	2989.00	2991.40	3024.90	3070.80	3076.90
2	D3	1120.70	1117.90	1115.10	1112.3	1109.50	1106.7	1103.90	1101.10	1098.30	1095.50	1092.70	1089.90	1087.10	1084.30
3	D4	1190.00	1162.00	1134.00	1106.0	1078.00	1050.0	1022.00	994.00	966.00	938.00	910.00	1428.00	1400.00	1372.00
4	D5	5904.67	5917.05	5922.58	5928.8	5935.29	6002.8	6009.47	6014.82	6020.19	6072.49	6077.72	6080.23	6082.75	6108.07

horizon = 14
lookback = 14*3

items = ts_lists(df_train.iloc[:,1:].values)
splits = RandomSplitter()(items)

dl = TSDataLoader(items, horizon = horizon, lookback = lookback, step=5)
dl.show_batch()