feat: add mamba and dynamic chunking related code and test code

scripts/short_term_forecast/vanillaMamba_M4.sh

@@ -0,0 +1,165 @@
+#!/bin/bash
+
+model_name=vanillaMamba
+
+# M4 Monthly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Monthly' \
+  --model_id m4_Monthly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --expand 2 \
+  --d_conv 4 \
+  --d_state 64 \
+  --headdim 64 \
+  --ngroups 1 \
+  --chunk_size 256 \
+  --dropout 0.1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Yearly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Yearly' \
+  --model_id m4_Yearly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --expand 2 \
+  --d_conv 4 \
+  --d_state 64 \
+  --headdim 64 \
+  --ngroups 1 \
+  --chunk_size 256 \
+  --dropout 0.1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Quarterly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Quarterly' \
+  --model_id m4_Quarterly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --expand 2 \
+  --d_conv 4 \
+  --d_state 64 \
+  --headdim 64 \
+  --ngroups 1 \
+  --chunk_size 256 \
+  --dropout 0.1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Weekly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Weekly' \
+  --model_id m4_Weekly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --expand 2 \
+  --d_conv 4 \
+  --d_state 64 \
+  --headdim 64 \
+  --ngroups 1 \
+  --chunk_size 256 \
+  --dropout 0.1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Daily
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Daily' \
+  --model_id m4_Daily \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --expand 2 \
+  --d_conv 4 \
+  --d_state 64 \
+  --headdim 64 \
+  --ngroups 1 \
+  --chunk_size 256 \
+  --dropout 0.1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Hourly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Hourly' \
+  --model_id m4_Hourly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --expand 2 \
+  --d_conv 4 \
+  --d_state 64 \
+  --headdim 64 \
+  --ngroups 1 \
+  --chunk_size 256 \
+  --dropout 0.1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'

scripts/short_term_forecast/xPatch_SparseChannel_M4.sh

@@ -0,0 +1,165 @@
+#!/bin/bash
+
+model_name=xPatch_SparseChannel
+
+# M4 Monthly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Monthly' \
+  --model_id m4_Monthly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --d_ff 256 \
+  --n_heads 16 \
+  --patch_len 16 \
+  --stride 8 \
+  --k_graph 1 \
+  --dropout 0.1 \
+  --revin 1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Yearly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Yearly' \
+  --model_id m4_Yearly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --d_ff 256 \
+  --n_heads 16 \
+  --patch_len 16 \
+  --stride 8 \
+  --k_graph 1 \
+  --dropout 0.1 \
+  --revin 1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Quarterly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Quarterly' \
+  --model_id m4_Quarterly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --d_ff 256 \
+  --n_heads 16 \
+  --patch_len 16 \
+  --stride 8 \
+  --k_graph 1 \
+  --dropout 0.1 \
+  --revin 1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Weekly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Weekly' \
+  --model_id m4_Weekly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --d_ff 256 \
+  --n_heads 16 \
+  --patch_len 16 \
+  --stride 8 \
+  --k_graph 1 \
+  --dropout 0.1 \
+  --revin 1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Daily
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Daily' \
+  --model_id m4_Daily \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --d_ff 256 \
+  --n_heads 16 \
+  --patch_len 16 \
+  --stride 8 \
+  --k_graph 1 \
+  --dropout 0.1 \
+  --revin 1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'
+
+# M4 Hourly
+python -u run.py \
+  --task_name short_term_forecast \
+  --is_training 1 \
+  --root_path ./dataset/m4 \
+  --seasonal_patterns 'Hourly' \
+  --model_id m4_Hourly \
+  --model $model_name \
+  --data m4 \
+  --features M \
+  --e_layers 2 \
+  --enc_in 1 \
+  --c_out 1 \
+  --batch_size 16 \
+  --d_model 128 \
+  --d_ff 256 \
+  --n_heads 16 \
+  --patch_len 16 \
+  --stride 8 \
+  --k_graph 1 \
+  --dropout 0.1 \
+  --revin 1 \
+  --des 'Exp' \
+  --itr 1 \
+  --learning_rate 0.001 \
+  --loss 'SMAPE'