Awesome
Reproduce performance of NBeats in M4 Dataset
Link to [paper].
Steps to reproduce
- Download M4 Dataset at Mcompetitions/M4-methods
- Placed it at somewhere and modifiled global variable
DATA_PATH
indata.py
properly, the directory structure is:Dataset ├── M4-info.csv ├── Test │ ├── Daily-test.csv │ ├── Hourly-test.csv │ ├── Monthly-test.csv │ ├── Quarterly-test.csv │ ├── Weekly-test.csv │ └── Yearly-test.csv └── Train ├── Daily-train.csv ├── Hourly-train.csv ├── Monthly-train.csv ├── Quarterly-train.csv ├── Weekly-train.csv └── Yearly-train.csv
- Install missing packages like
tensorflow_io
- Run the .ipynb file.
Results
There is only results for Yearly dataset and interpretable model at the moment. Check author's results here