Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
lvlvhao 7d637f85c1 | 2 years ago | |
---|---|---|
experiments | 2 years ago | |
model | 2 years ago | |
.DS_Store | 2 years ago | |
DeepAR_pipline.ipynb | 2 years ago | |
README.md | 2 years ago | |
dataloader.py | 2 years ago | |
evaluate.py | 2 years ago | |
param_search.log | 2 years ago | |
preprocess_elect.py | 2 years ago | |
requirements.txt | 2 years ago | |
search_hyperparams.py | 2 years ago | |
train.py | 2 years ago | |
utils.py | 2 years ago |
在命令行运行下面命令!
安装requirements.txt依赖包:
pip install requirements.txt
获取数据并预处理:
python preprocess_sale_data.py
开始训练:
python train.py
如果想进行祖先采样,请运行下面的命令训练:
python train.py --sampling
如果不想在评估期间做规范化处理,请运行下面的命令训练:
python train.py --relative-metrics
评估一组保存的模型权重:
python evaluate.py
进行超参数搜索:
python search_hyperparams.py
时间序列的不确定性预测,不确定预测是为了配合供应链场景中补货等场景中不同用户需求而研发的,目前亚马逊、lokad等公司都在进行这方面研究,本项目是实现了亚马逊公布的Deepar深度学习概率预测模型
Jupyter Notebook Python
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》