Spaces:
No application file
No application file
File size: 3,037 Bytes
2bc420d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
from gluonts.dataset.multivariate_grouper import MultivariateGrouper
from gluonts.time_feature import time_features_from_frequency_str
from datasets import load_dataset
from functools import lru_cache
import pandas as pd
import numpy as np
from functools import partial
from transformers import InformerConfig, InformerForPrediction
freq = "1H"
prediction_length = 48
def get_train_test_datasets():
@lru_cache(10_000)
def convert_to_pandas_period(date, freq):
return pd.Period(date, freq)
def transform_start_field(batch, freq):
batch["start"] = [convert_to_pandas_period(date, freq) for date in batch["start"]]
return batch
dataset = load_dataset("monash_tsf", "traffic_hourly")
train_dataset = dataset["train"]
test_dataset = dataset["test"]
train_dataset.set_transform(partial(transform_start_field, freq=freq))
test_dataset.set_transform(partial(transform_start_field, freq=freq))
return train_dataset, test_dataset
def get_train_test_multivariate_grouper(train_dataset, test_dataset):
num_of_variates = len(train_dataset)
train_grouper = MultivariateGrouper(max_target_dim=num_of_variates)
test_grouper = MultivariateGrouper(
max_target_dim=num_of_variates,
num_test_dates=len(test_dataset) // num_of_variates, # number of rolling test windows
)
return train_grouper, test_grouper
def get_informer_model(num_of_variates, time_features):
config = InformerConfig(
# in the multivariate setting, input_size is the number of variates in the time series per time step
input_size=num_of_variates,
# prediction length:
prediction_length=prediction_length,
# context length:
context_length=prediction_length * 2,
# lags value copied from 1 week before:
lags_sequence=[1, 24 * 7],
# we'll add 5 time features ("hour_of_day", ..., and "age"):
num_time_features=len(time_features) + 1,
# informer params:
dropout=0.1,
encoder_layers=6,
decoder_layers=4,
# project input from num_of_variates*len(lags_sequence)+num_time_features to:
d_model=64,
)
model = InformerForPrediction(config)
return model
def main():
train_dataset, test_dataset = get_train_test_datasets()
train_grouper, test_grouper = get_train_test_multivariate_grouper(train_dataset, test_dataset)
multi_variate_train_dataset = train_grouper(train_dataset)
multi_variate_test_dataset = test_grouper(test_dataset)
multi_variate_train_example = multi_variate_train_dataset[0]
train_example = train_dataset[0]
print('train_example["target"].shape =', len(train_example["target"]))
print('multi_variate_train_example["target"].shape =', multi_variate_train_example["target"].shape)
time_features = time_features_from_frequency_str(freq)
print(time_features)
informer = get_informer_model(num_of_variates=62, time_features=time_features)
if __name__ == '__main__':
main()
|