Metadata-Version: 2.1
Name: DSTS
Version: 2.1.2
Summary: Official Python package implementation of the paper Doubly Structured Data Synthesis for Time-series Energy Use Data
Author-email: Changwook Lee <changwook1410@gmail.com>
Project-URL: Homepage, https://github.com/chomgid/DSTS
Project-URL: Source, https://github.com/chomgid/DSTS
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: <3.10,>=3.6
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pandas>=2.0.0
Requires-Dist: scikit-learn>=1.2.0
Requires-Dist: tensorflow<=2.13.1
Requires-Dist: tqdm>=4.64.1
Requires-Dist: torch>=2.0.1
Requires-Dist: seaborn>=0.12.2

# Doubly Structured Time-series Synthesis (DSTS)

This repository contains the official Python package implementation of **Doubly Structured Time-series Synthesis (DSTS)**.

## Installation

You can install the package via `pip`. Run the following command in your terminal:

```bash
pip install DSTS
```

## Usage

Below is a simple example to help you get started with the `DSTS` package.

### Import the package

```python
from DSTS import dsts
```

### Load your dataset

```python
data = ...  # Your dataset here
```

### Construct a DSTS model

```python
mixup_model = dsts(sort=True, centering='double')
```

### Fit the model to your data

```python
mixup_model.fit(train_data)
```

### Generate synthetic data

```python
generated_data = mixup_model.generate(aug=1)
```

---

## License

This project is licensed under the terms of the [MIT License](LICENSE).
