/NBeats-M4

Reproduce performance of NBeats in M4 Dataset

Primary LanguagePython

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 in data.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

Credit: