v1.0

scripts/variate_generalization/ECL/iTransformer.sh

+export CUDA_VISIBLE_DEVICES=3
+
+model_name=Transformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/electricity/ \
+#  --data_path electricity.csv \
+#  --model_id ECL_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 321 \
+#  --dec_in 321 \
+#  --c_out 321 \
+#  --des 'Exp' \
+#  --itr 1
+
+# 20% partial variates, enc_in: 64 = 321 // 5
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/electricity/ \
+  --data_path electricity.csv \
+  --model_id ECL_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 64 \
+  --dec_in 64 \
+  --c_out 64 \
+  --des 'Exp' \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 8 \
+  --d_model 32 \
+  --d_ff 64 \
+  --itr 1
+
+model_name=iTransformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/electricity/ \
+#  --data_path electricity.csv \
+#  --model_id ECL_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 321 \
+#  --dec_in 321 \
+#  --c_out 321 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/electricity/ \
+  --data_path electricity.csv \
+  --model_id ECL_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 64 \
+  --dec_in 64 \
+  --c_out 64 \
+  --des 'Exp' \
+  --exp_name partial_train \
+  --itr 1
\ No newline at end of file

scripts/variate_generalization/README.md

+# iTransformer for Variate Generalization
+
+This folder contains the implementation of the iTransformer to generalize on unseen variates. If you are new to this repo, we recommend you to read this [README](../multivariate_forecasting/README.md) first.
+
+By inverting vanilla Transformers, the model is empowered with the generalization capability on unseen variates. Firstly, benefiting from the flexibility of the number of input tokens, the amount of variate channels is no longer restricted and thus feasible to vary from training and inference. Second, feed-forward networks are identically applied on independent variate tokens to learn transferable representations of time series.
+
+## Scripts
+
+```
+# Train models with only 20% of variates from Traffic and test the model on all variates without finetuning
+
+bash ./scripts/variate_generalization/Traffic/iTransformer.sh
+```
+
+> During Training
+<p align="center">
+<img src="../../figures/pt.png" alt="" align=center />
+</p>
+
+> During Inference
+<p align="center">
+<img src="../../figures/pi.png" alt="" align=center />
+</p>
+
+In each folder named after the dataset, we provide two strategies to enable Transformers to generalize on unseen variate.
+
+* **CI-Transformers**: Channel Independence regards each variate of time series as independent channels, and uses a shared backbone to forecast all variates. Therefore, the model can predict variates one by one, but the training and inference procedure can be time-consuming.
+
+* **iTransformers**: benefiting from the flexibility of attention that the number of input tokens can be dynamically changeable, the amount of variates as tokens is no longer restricted, and can even allow the model to be trained on arbitrary variables.
+
+## Results
+
+<p align="center">
+<img src="../../figures/generability.png" alt="" align=center />
+</p>
+
+ iTransformers can be naturally trained with 20% variates and accomplish forecast on all variates with the ability to learn transferable representations.
\ No newline at end of file

scripts/variate_generalization/SolarEnergy/iFlowformer.sh

+export CUDA_VISIBLE_DEVICES=0
+
+model_name=Flowformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --d_model 32 \
+  --d_ff 64 \
+  --learning_rate 0.0005 \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 8 \
+  --itr 1
+
+model_name=iFlowformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --learning_rate 0.0005 \
+  --exp_name partial_train \
+  --itr 1
\ No newline at end of file

scripts/variate_generalization/SolarEnergy/iInformer.sh

+export CUDA_VISIBLE_DEVICES=1
+
+model_name=Informer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --d_model 32 \
+  --d_ff 64 \
+  --learning_rate 0.0005 \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 8 \
+  --itr 1
+
+model_name=iInformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --learning_rate 0.0005 \
+  --exp_name partial_train \
+  --itr 1
\ No newline at end of file

scripts/variate_generalization/SolarEnergy/iReformer.sh

+export CUDA_VISIBLE_DEVICES=2
+
+model_name=Reformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --d_model 32 \
+  --d_ff 64 \
+  --learning_rate 0.0005 \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 8 \
+  --itr 1
+
+model_name=iReformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --learning_rate 0.0005 \
+  --exp_name partial_train \
+  --itr 1
\ No newline at end of file

scripts/variate_generalization/SolarEnergy/iTransformer.sh

+export CUDA_VISIBLE_DEVICES=3
+
+model_name=Transformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+# 20% partial variates: 27 = 137 // 5
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \     
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --d_model 32 \
+  --d_ff 64 \
+  --learning_rate 0.0005 \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 8 \
+  --itr 1
+
+model_name=iTransformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/Solar/ \
+#  --data_path solar_AL.txt \
+#  --model_id solar_96_96 \
+#  --model $model_name \
+#  --data Solar \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 137 \
+#  --dec_in 137 \
+#  --c_out 137 \
+#  --des 'Exp' \
+#  --learning_rate 0.0005 \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/Solar/ \
+  --data_path solar_AL.txt \
+  --model_id solar_96_96 \
+  --model $model_name \
+  --data Solar \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 27 \
+  --dec_in 27 \
+  --c_out 27 \
+  --des 'Exp' \
+  --learning_rate 0.0005 \
+  --exp_name partial_train \
+  --itr 1
\ No newline at end of file

scripts/variate_generalization/Traffic/iFlowformer.sh

+export CUDA_VISIBLE_DEVICES=0
+
+model_name=Flowformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 4 \
+  --d_model 32 \
+  --d_ff 64 \
+  --itr 1
+
+model_name=iFlowformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --exp_name partial_train \
+  --itr 1

scripts/variate_generalization/Traffic/iInformer.sh

+export CUDA_VISIBLE_DEVICES=1
+
+model_name=Informer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 4 \
+  --d_model 32 \
+  --d_ff 64 \
+  --itr 1
+
+model_name=iInformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --exp_name partial_train \
+  --itr 1

scripts/variate_generalization/Traffic/iReformer.sh

+export CUDA_VISIBLE_DEVICES=2
+
+model_name=Reformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 4 \
+  --d_model 32 \
+  --d_ff 64 \
+  --itr 1
+
+model_name=iReformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --exp_name partial_train \
+  --itr 1
\ No newline at end of file

scripts/variate_generalization/Traffic/iTransformer.sh

+export CUDA_VISIBLE_DEVICES=3
+
+model_name=Transformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+# 20% partial variates, enc_in: 172 = 862 // 5
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --channel_independence true \
+  --exp_name partial_train \
+  --batch_size 8 \
+  --d_model 32 \
+  --d_ff 64 \
+  --itr 1
+
+model_name=iTransformer
+
+#python -u run.py \
+##  --is_training 1 \
+#  --root_path ./dataset/traffic/ \
+#  --data_path traffic.csv \
+#  --model_id traffic_96_96 \
+#  --model $model_name \
+#  --data custom \
+#  --features M \
+#  --seq_len 96 \
+#  --label_len 48 \
+#  --pred_len 96 \
+#  --e_layers 2 \
+#  --d_layers 1 \
+#  --factor 3 \
+#  --enc_in 862 \
+#  --dec_in 862 \
+#  --c_out 862 \
+#  --des 'Exp' \
+#  --itr 1
+
+python -u run.py \
+  --is_training 1 \
+  --root_path ./dataset/traffic/ \
+  --data_path traffic.csv \
+  --model_id traffic_96_96 \
+  --model $model_name \
+  --data custom \
+  --features M \
+  --seq_len 96 \
+  --label_len 48 \
+  --pred_len 96 \
+  --e_layers 2 \
+  --d_layers 1 \
+  --factor 3 \
+  --enc_in 172 \
+  --dec_in 172 \
+  --c_out 172 \
+  --des 'Exp' \
+  --exp_name partial_train \
+  --itr 1

utils/masking.py

+import torch
+
+
+class TriangularCausalMask():
+    def __init__(self, B, L, device="cpu"):
+        mask_shape = [B, 1, L, L]
+        with torch.no_grad():
+            self._mask = torch.triu(torch.ones(mask_shape, dtype=torch.bool), diagonal=1).to(device)
+
+    @property
+    def mask(self):
+        return self._mask
+
+
+class ProbMask():
+    def __init__(self, B, H, L, index, scores, device="cpu"):
+        _mask = torch.ones(L, scores.shape[-1], dtype=torch.bool).to(device).triu(1)
+        _mask_ex = _mask[None, None, :].expand(B, H, L, scores.shape[-1])
+        indicator = _mask_ex[torch.arange(B)[:, None, None],
+                    torch.arange(H)[None, :, None],
+                    index, :].to(device)
+        self._mask = indicator.view(scores.shape).to(device)
+
+    @property
+    def mask(self):
+        return self._mask

utils/metrics.py

+import numpy as np
+
+
+def RSE(pred, true):
+    return np.sqrt(np.sum((true - pred) ** 2)) / np.sqrt(np.sum((true - true.mean()) ** 2))
+
+
+def CORR(pred, true):
+    u = ((true - true.mean(0)) * (pred - pred.mean(0))).sum(0)
+    d = np.sqrt(((true - true.mean(0)) ** 2 * (pred - pred.mean(0)) ** 2).sum(0))
+    return (u / d).mean(-1)
+
+
+def MAE(pred, true):
+    return np.mean(np.abs(pred - true))
+
+
+def MSE(pred, true):
+    return np.mean((pred - true) ** 2)
+
+
+def RMSE(pred, true):
+    return np.sqrt(MSE(pred, true))
+
+
+def MAPE(pred, true):
+    return np.mean(np.abs((pred - true) / true))
+
+
+def MSPE(pred, true):
+    return np.mean(np.square((pred - true) / true))
+
+
+def metric(pred, true):
+    mae = MAE(pred, true)
+    mse = MSE(pred, true)
+    rmse = RMSE(pred, true)
+    mape = MAPE(pred, true)
+    mspe = MSPE(pred, true)
+
+    return mae, mse, rmse, mape, mspe

utils/timefeatures.py

+# From: gluonts/src/gluonts/time_feature/_base.py
+# Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License").
+# You may not use this file except in compliance with the License.
+# A copy of the License is located at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the "license" file accompanying this file. This file is distributed
+# on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
+# express or implied. See the License for the specific language governing
+# permissions and limitations under the License.
+
+from typing import List
+
+import numpy as np
+import pandas as pd
+from pandas.tseries import offsets
+from pandas.tseries.frequencies import to_offset
+
+
+class TimeFeature:
+    def __init__(self):
+        pass
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        pass
+
+    def __repr__(self):
+        return self.__class__.__name__ + "()"
+
+
+class SecondOfMinute(TimeFeature):
+    """Minute of hour encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return index.second / 59.0 - 0.5
+
+
+class MinuteOfHour(TimeFeature):
+    """Minute of hour encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return index.minute / 59.0 - 0.5
+
+
+class HourOfDay(TimeFeature):
+    """Hour of day encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return index.hour / 23.0 - 0.5
+
+
+class DayOfWeek(TimeFeature):
+    """Hour of day encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return index.dayofweek / 6.0 - 0.5
+
+
+class DayOfMonth(TimeFeature):
+    """Day of month encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return (index.day - 1) / 30.0 - 0.5
+
+
+class DayOfYear(TimeFeature):
+    """Day of year encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return (index.dayofyear - 1) / 365.0 - 0.5
+
+
+class MonthOfYear(TimeFeature):
+    """Month of year encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return (index.month - 1) / 11.0 - 0.5
+
+
+class WeekOfYear(TimeFeature):
+    """Week of year encoded as value between [-0.5, 0.5]"""
+
+    def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
+        return (index.isocalendar().week - 1) / 52.0 - 0.5
+
+
+def time_features_from_frequency_str(freq_str: str) -> List[TimeFeature]:
+    """
+    Returns a list of time features that will be appropriate for the given frequency string.
+    Parameters
+    ----------
+    freq_str
+        Frequency string of the form [multiple][granularity] such as "12H", "5min", "1D" etc.
+    """
+
+    features_by_offsets = {
+        offsets.YearEnd: [],
+        offsets.QuarterEnd: [MonthOfYear],
+        offsets.MonthEnd: [MonthOfYear],
+        offsets.Week: [DayOfMonth, WeekOfYear],
+        offsets.Day: [DayOfWeek, DayOfMonth, DayOfYear],
+        offsets.BusinessDay: [DayOfWeek, DayOfMonth, DayOfYear],
+        offsets.Hour: [HourOfDay, DayOfWeek, DayOfMonth, DayOfYear],
+        offsets.Minute: [
+            MinuteOfHour,
+            HourOfDay,
+            DayOfWeek,
+            DayOfMonth,
+            DayOfYear,
+        ],
+        offsets.Second: [
+            SecondOfMinute,
+            MinuteOfHour,
+            HourOfDay,
+            DayOfWeek,
+            DayOfMonth,
+            DayOfYear,
+        ],
+    }
+
+    offset = to_offset(freq_str)
+
+    for offset_type, feature_classes in features_by_offsets.items():
+        if isinstance(offset, offset_type):
+            return [cls() for cls in feature_classes]
+
+    supported_freq_msg = f"""
+    Unsupported frequency {freq_str}
+    The following frequencies are supported:
+        Y   - yearly
+            alias: A
+        M   - monthly
+        W   - weekly
+        D   - daily
+        B   - business days
+        H   - hourly
+        T   - minutely
+            alias: min
+        S   - secondly
+    """
+    raise RuntimeError(supported_freq_msg)
+
+
+def time_features(dates, freq='h'):
+    return np.vstack([feat(dates) for feat in time_features_from_frequency_str(freq)])

utils/tools.py

+import os
+
+import numpy as np
+import torch
+import matplotlib.pyplot as plt
+import pandas as pd
+
+plt.switch_backend('agg')
+
+
+def adjust_learning_rate(optimizer, epoch, args):
+    # lr = args.learning_rate * (0.2 ** (epoch // 2))
+    if args.lradj == 'type1':
+        lr_adjust = {epoch: args.learning_rate * (0.5 ** ((epoch - 1) // 1))}
+    elif args.lradj == 'type2':
+        lr_adjust = {
+            2: 5e-5, 4: 1e-5, 6: 5e-6, 8: 1e-6,
+            10: 5e-7, 15: 1e-7, 20: 5e-8
+        }
+    if epoch in lr_adjust.keys():
+        lr = lr_adjust[epoch]
+        for param_group in optimizer.param_groups:
+            param_group['lr'] = lr
+        print('Updating learning rate to {}'.format(lr))
+
+
+class EarlyStopping:
+    def __init__(self, patience=7, verbose=False, delta=0):
+        self.patience = patience
+        self.verbose = verbose
+        self.counter = 0
+        self.best_score = None
+        self.early_stop = False
+        self.val_loss_min = np.Inf
+        self.delta = delta
+
+    def __call__(self, val_loss, model, path):
+        score = -val_loss
+        if self.best_score is None:
+            self.best_score = score
+            self.save_checkpoint(val_loss, model, path)
+        elif score < self.best_score + self.delta:
+            self.counter += 1
+            print(f'EarlyStopping counter: {self.counter} out of {self.patience}')
+            if self.counter >= self.patience:
+                self.early_stop = True
+        else:
+            self.best_score = score
+            self.save_checkpoint(val_loss, model, path)
+            self.counter = 0
+
+    def save_checkpoint(self, val_loss, model, path):
+        if self.verbose:
+            print(f'Validation loss decreased ({self.val_loss_min:.6f} --> {val_loss:.6f}).  Saving model ...')
+        torch.save(model.state_dict(), path + '/' + 'checkpoint.pth')
+        self.val_loss_min = val_loss
+
+
+class dotdict(dict):
+    """dot.notation access to dictionary attributes"""
+    __getattr__ = dict.get
+    __setattr__ = dict.__setitem__
+    __delattr__ = dict.__delitem__
+
+
+class StandardScaler():
+    def __init__(self, mean, std):
+        self.mean = mean
+        self.std = std
+
+    def transform(self, data):
+        return (data - self.mean) / self.std
+
+    def inverse_transform(self, data):
+        return (data * self.std) + self.mean
+
+
+def visual(true, preds=None, name='./pic/test.pdf'):
+    """
+    Results visualization
+    """
+    plt.figure()
+    plt.plot(true, label='GroundTruth', linewidth=2)
+    if preds is not None:
+        plt.plot(preds, label='Prediction', linewidth=2)
+    plt.legend()
+    plt.savefig(name, bbox_inches='tight')
+
+
+def adjustment(gt, pred):
+    anomaly_state = False
+    for i in range(len(gt)):
+        if gt[i] == 1 and pred[i] == 1 and not anomaly_state:
+            anomaly_state = True
+            for j in range(i, 0, -1):
+                if gt[j] == 0:
+                    break
+                else:
+                    if pred[j] == 0:
+                        pred[j] = 1
+            for j in range(i, len(gt)):
+                if gt[j] == 0:
+                    break
+                else:
+                    if pred[j] == 0:
+                        pred[j] = 1
+        elif gt[i] == 0:
+            anomaly_state = False
+        if anomaly_state:
+            pred[i] = 1
+    return gt, pred
+
+
+def cal_accuracy(y_pred, y_true):
+    return np.mean(y_pred == y_true)