Documentation | Tutorials | Release Notes | 中文

TFTS (TensorFlow Time Series) is a python package for time series task, supporting the classical and SOTA deep learning methods in TensorFlow.

• Flexible and powerful design for time series task
• Advanced deep learning models
• Documentation lives at time-series-prediction.readthedocs.io

Tutorial

Installation

• python >= 3.7
• tensorflow >= 2.1

$ pip install tfts

Usage

import matplotlib.pyplot as plt
import tfts
from tfts import AutoModel, KerasTrainer, Trainer

train_length = 24
predict_length = 8

# train is a tuple of (x_train, y_train), valid is (x_valid, y_valid)
train, valid = tfts.get_data('sine', train_length, predict_length, test_size=0.2)
model = AutoModel('seq2seq', predict_length)

trainer = KerasTrainer(model)
trainer.train(train, valid)

pred = trainer.predict(valid[0])
trainer.plot(history=valid[0], true=valid[1], pred=pred)
plt.show()

Examples

• TFTS-prediction for basic usage
• TFTS-Bert model wins the 3rd place in KDD Cup 2022 Baidu-wind power forecasting
• TFTS-Seq2seq model wins the 4th place in Alibaba Tianchi-ENSO prediction 2021

if you prefer to use PyTorch, please try pytorch-forecasting

Citation

If you find tfts project useful in your research, please consider cite:

@misc{tfts2020,
  author = {Longxing Tan},
  title = {Time series prediction},
  year = {2020},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/longxingtan/time-series-prediction}},
}