tsts 0.3.0

toolset for time series forecasting

(Docs)(Benchmark)

Introduction

tsts is an open-source easy-to-use toolset for time series forecasting.

Installation

pip install tsts

Time Series Forecasting?

Time series forecasting is the task to predict the values of the time series on Horizon given the values of the time series on Lookback Period. Note that data can be multivariate.

Available Modules

Following modules are supported.

Architectures	Losses	Metrics	Optimizers	Scalers	Schedulers
Informer NBeats Seq2Seq	DILATE MAPE MSE	MAE MSE RMSE MAPE	Adam SGD	MinMaxScaler StandardScaler	CosineAnnealing StepScheduler

Getting Started

Following example shows how to train a model on sine curve dataset. See Docs for the details.

Training

Without a log directory path provided by config, it automatically generates a random log directory.

import torch
from tsts.solvers import TimeSeriesForecaster

sin_dataset = torch.sin(torch.arange(0, 100, 0.1))
sin_dataset = sin_dataset.unsqueeze(-1)
forecaster = TimeSeriesForecaster()
forecaster.fit([sin_dataset])

Inference

For inference, it needs to load parameters from a log directory generated in training.

# inference.yml
LOGGER:
  LOG_DIR: "log directory generated in training"

import torch
from tsts.solvers import TimeSeriesForecaster

X = torch.sin(torch.arange(0.0, 10.0, 0.1)).unsqueeze(1)
forecaster = TimeSeriesForecaster("inference.yml")
forecaster.predict(X)

Examples

See Benchmark for advanced usage.