informer_ChineseNotes has added Chinese annotations and some visual additions to the informer2020 project.
- 时间序列预测
- 股票预测
- 市场预测
- 电力预测
- 天气预测
- ....
- torch_lts
- pyecharts
- Python 3.7
- matplotlib
- numpy == 1.19.4
- pandas
- scikit_learn
- xlrd
- ....
You can install it directly from the environment pack version file:
pip install -r requirements.txt
or
conda env create -f torch_lts.yaml
Create a virtual environment in Anaconda Powershell Prompt (Anaconda3) :
conda create -n torch_lts python=3.7
Then enter the virtual environment:
activate torch_lts
Finally, install the environment dependency package using the requirements. TXT file:
pip install -r requirements.txt
Create virtual environments and install dependencies using conda and YAMl files directly from Anaconda Powershell Prompt (Anaconda3) :
conda env create -f torch_lts.yaml
Execute the following commands directly in your environment to install:
conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch-lts -c conda-forge
pip install numpy == 1.19.4
pip install pyecharts
pip install xlrd
pip install openpyxl
pip install matplotlib
pip install pandas
When selecting the interpreter, do not create a new virtual environment and use the virtual environment you already created:
If you run into a problem like RuntimeError: The size of tensor a (98) must match the size of tensor b (96) at non-singleton dimension 1
, you can check torch version or modify code about Conv1d
of TokenEmbedding
in models/embed.py
as the way of circular padding mode in Conv1d changed in different torch versions.
- Thanks to @zhouhaoyi open source algorithm paper and code repository.
- Original repository: informer2020
- Zhouhaoyi paper: Informer:Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (AAAI'21 Best Paper)
数据是网上找来的,已做脱敏处理,如有冒犯到您的请联系e-mail或者从Tony's blog中私聊我侵删。
- e-mail:[email protected]