buaabigscity / kddcup2022 Goto Github PK

[KDD CUP 2022] 11th place solution of Spatial-Temporal Graph Neural Network for Wind Power Forecasting in Baidu KDD CUP 2022

Home Page: https://aistudio.baidu.com/aistudio/competition/detail/152/0/introduction

License: MIT License

Python 100.00%

deep-learning spatio-temporal-prediction wind-power-forecasting agcrn kddcup2022 mtgnn

kddcup2022's People

Contributors

Stargazers

Watchers

Forkers

phoenixes94 miachelgu jun2hou liuweishuo xhfei1224 songpeixu mojeedoyedeji lee-liew ch468087977 noinget kaminoteto yiliangw am94ghiassi lyzl2010 illegalargumentexception-oss qimingguicai

kddcup2022's Issues

visualize

Hi @aptx1231 , how to visualize the results of wind power forecasting？I hope you can take some time out of your busy schedule to reply to this question, preferably with the code, thank you very much, it's really important to me!

data Z-score normalization

hi @aptx1231 :
In wpf_dataset.py, why are the mean and variance of node features calculated for all features of the node rather than for each feature of the node

self.data_mean = np.expand_dims( # (1, 134, 1, 1)

np.mean(

data[:, border1s[0]:border2s[0], 2:],

axis=(1, 2),

keepdims=True),

self.data_scale = np.expand_dims( # (1, 134, 1, 1)

np.std(data[:, border1s[0]:border2s[0], 2:],

axis=(1, 2),

keepdims=True),

Recommend Projects