Time-series-prediction

Time-series-prediction copied to clipboard

[build-image]: https://github.com/LongxingTan/Time-series-prediction/actions/workflows/test.yml/badge.svg?branch=master

Documentation | Tutorials | Release Notes | 中文

TFTS (TensorFlow Time Series) is a python package for time series prediction, supporting the common deep learning methods in TensorFlow.

Usage

1. Install the required library

$ pip install -r requirements.txt

2. Download the data, if necessary

$ sh ./data/download_passenger.sh

3. Train the model
   set custom_model_params if you want (refer to params in ./tfts/models/*.py), and pay attention to feature engineering.

$ cd examples
$ python run_train.py --use_model seq2seq
$ cd ..
$ tensorboard --logdir=./data/logs

4. Predict new data

$ cd examples
$ python run_test.py

Documentation

Visit https to read the documentation with detailed tutorials

Examples

• I use the seq2seq model from this lib to win 4th/2849 in Tianchi ENSO prediction, code is here

Further reading

• https://github.com/awslabs/gluon-ts/
• https://github.com/Azure/DeepLearningForTimeSeriesForecasting
• https://github.com/microsoft/forecasting
• https://github.com/jdb78/pytorch-forecasting
• https://github.com/timeseriesAI/tsai
• https://github.com/facebookresearch/Kats