Skip to content

user00144/dacon_seoul_hack

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 

Repository files navigation

Seoul Average Temperature Forecasting


DACON competition : Seoul Average Temperature Forecasting

Competition , Dec. 2023 ~ Jan. 2024


Software Stacks

PyTorch Pandas


Competition Topic

Time Series Forecasting

Forecasting Seoul's average temperature from previous time series(temperature) data.


Implementation

1. Dataset

  • Seoul Temperatures : Average daily temperature data from 1960 to 2022

2. Data preprocessing

  • Process "NULL" values
  • Drop unusal features 캡처

3. Model Selection

  • Time Series Forecasting Model
  • Tried method : ARIMA Model, Prophet ...
  • Patch Mixer :: Gong, Zeying, Yujin Tang, and Junwei Liang. "Patchmixer: A patch-mixing architecture for long-term time series forecasting." arXiv preprint arXiv:2310.00655 (2023).
  • code reference : tsf-new-paper-taste : github

4. Hyperparameter

  • SEQ_LEN = 716
  • PATCH_LEN = 1
  • STRIDE = 2
  • EPOCHS = 100

Result

  • Top 4% , Mean absolute error 2.6186 (in private data) 다운로드

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published