shaido987 / kdd_wind_power_forecast

KDD Cup 2022 spatial dynamic wind power forecast challenge solution.

🎓 I'm a Senior Research Engineer at Noah's Ark Lab at Huawei in Hong Kong.
🔆 My work has mainly been on time series, including anomaly detection, forecasting, root cause analysis/localization, and spatio-temporal graphs. These days I'm getting more involved with robotics.
🌱 As my previous work alludes, my research interests are quite broad. My focus right now is specifically on LLMs and dexterous manipulation.

kdd_wind_power_forecast's Issues

FileNotFoundError

hello！ here are some question. when I python train_xtgn.py ,It goes rong . the rong messages are following:

Traceback (most recent call last):
File "train_xtgn.py", line 180, in
main(args, model_dir)
File "train_xtgn.py", line 34, in main
data_loader, _ = load_wp_dataset_mask(model_dir, args['ratio'], args['batch_size'], args['batch_size'],
File "/csg/shzhou/bingcheng_KDD/KDD_wind_power_forecast-main/KDD_wind_power_forecast-main/methods/xtgn/data_process/util.py", line 154, in load_wp_dataset_mask
cat_data = np.load(os.path.join(dataset_dir, category + f"_{ratio}_new_mask.npz"))
File "/csg/shzhou/anaconda3/envs/pytorch/lib/python3.8/site-packages/numpy/lib/npyio.py", line 407, in load
fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: 'methods/checkpoints/xtgn-2/train_9_new_mask.npz'

wish you best!!! hope receiving your answer！！！

detailed performance for model

Dear @shaido987 ,

Thanks for sharing such nice solution.

I noticed you use 2 models here, DLinear and GraphWavenet. Both of them sounds interesting. Do you mind to share each model's performance respectively, I just want to know which model performs better.