Metadata-Version: 2.1
Name: mlpforecast
Version: 0.1.2
Summary: Multilayer Perceptron Learning Models for Time Series Forecasting
Author: sambaiga
Author-email: sambaiga@gmail.com
Requires-Python: >=3.11,<3.12
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Requires-Dist: altair (>=5.3.0)
Requires-Dist: arviz (>=0.18.0,<0.19.0)
Requires-Dist: astral (>=3.2,<4.0)
Requires-Dist: coreforecast (>=0.0.6,<0.0.7)
Requires-Dist: lightning (>=2.0.8,<3.0.0)
Requires-Dist: matplotlib (>=3.8.4,<4.0.0)
Requires-Dist: matplotlib_inline (>=0.1.6)
Requires-Dist: numpy (>=1.24.3,<2.0.0)
Requires-Dist: optuna (>=3.2.0,<4.0.0)
Requires-Dist: optuna-integration (>=3.6.0,<4.0.0)
Requires-Dist: pandas (==1.5.3)
Requires-Dist: pmdarima (>=2.0.4,<3.0.0)
Requires-Dist: ppscore (>=1.3.0,<2.0.0)
Requires-Dist: pyarrow (>=13.0.0,<14.0.0)
Requires-Dist: pytimetk (>=0.4.0,<0.5.0)
Requires-Dist: rich (>=13.7.1,<14.0.0)
Requires-Dist: scikit-learn (==1.5.1)
Requires-Dist: seaborn (>=0.13.2)
Requires-Dist: statsmodels (>=0.14.0)
Requires-Dist: tensorboard (>=2.1.5,<3.0.0)
Requires-Dist: torch (>=2.0.1,<3.0.0)
Requires-Dist: torchmetrics (>=1.4.0,<2.0.0)
Requires-Dist: tqdm (>=4.66.4,<5.0.0)
Requires-Dist: utilsforecast (>=0.0.25,<0.0.26)
Requires-Dist: vl-convert-python (>1.4.0)
Requires-Dist: wandb (>=0.17.4,<0.18.0)
Description-Content-Type: text/markdown

# mlpForecaster(MLPF)

<div align="center">

<!-- [![Python](https://img.shields.io/pypi/pyversions/mlpforecast)](https://pypi.org/project/mlpforecast/)
[![PyPi](https://img.shields.io/pypi/v/mlpforecast?color=blue)](https://pypi.org/project/mlpforecast/)
[![All Contributors](https://img.shields.io/badge/all_contributors-3-orange.svg?style=flat-square)](#contributors-) -->
<a href="https://pypi.org/project/mlpforecast" target="_blank">
    <img src="https://img.shields.io/pypi/pyversions/mlpforecast" alt="Python version">
</a>
<a href="https://pypi.org/project/mlpforecast" target="_blank">
    <img src="https://img.shields.io/pypi/v/mlpforecast?color=%2334D058&label=pypi%20package" alt="Package version">
</a>
<a href="#contributors-" target="_blank">
    <img src="https://img.shields.io/badge/all_contributors-3-orange.svg?style=flat-square" alt="All Contributors">
</a>

</div>

**MLPF** is a simple and efficient architecture for providing point and probabilistic forecasting. The architecture has been designed to minimize model complexity while improving forecasting performance.

## Table of Contents
- [mlpForecaster(MLPF)](#mlpforecastermlpf)
  - [Table of Contents](#table-of-contents)
  - [Installation](#installation)
  - [Usage](#usage)
  - [Features](#features)
  - [Examples](#examples)
  - [Contributing](#contributing)
  - [License](#license)
  - [Contributors](#contributors)
  - [References](#references)

## Installation

You can install the `mlpForecaster` via pip:

```bash
pip install mlpforecaster
```

## Usage

```python
from mlpforecast.forecaster.mlp import MLPForecast

model = MLPForecast(exp_name='test', model_type="MLPF", hparams=model_hparams)

model.fit(train_data)
out=model.predict(test_data)

```
## Features
- **Point Forecasting**: Generate accurate single-point predictions for your time series data, ensuring precise future estimates.
  ![alt text](https://raw.githubusercontent.com/sambaiga/mlpforecast/main/images/prediction.png)

- **Low Model Complexity**: Benefit from a design focused on minimizing complexity while maintaining high performance and accuracy, making it easier to deploy and maintain.

- **Hyperparameter Optimization**: Automatically optimize hyperparameters using the Optuna library, enhancing model performance and reducing manual tuning efforts.

- **Recursive Forecasting**: Achieve any desired forecast length by leveraging recursive forecasting techniques, which extend predictions iteratively over time.

## Examples

You can find more examples and detailed usage in the [examples directory](https://github.com/sambaiga/mlpforecast/blob/main/example/).

## Contributing

We welcome contributions! Please see our [CONTRIBUTING](CONTRIBUTING.md) guide for more details.

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## Contributors

Thanks goes to these wonderful people:
<!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->
<!-- prettier-ignore-start -->
<!-- markdownlint-disable -->
<table>
  <tbody>
    <tr>
      <td align="center" valign="top" width="14.28%"><a href="https://github.com/sambaiga"><img src="https://avatars.githubusercontent.com/u/338440?v=4?s=100" width="100px;" alt="Sambaiga"/><br /><sub><b>Anthony</b></sub></a><br /><a href="https://github.com/sambaiga/MLPF/commits?author=sambaiga" title="Code">💻</a> <a href="#maintenance-sambaiga" title="Maintenance">🚧</a></td>
      <td align="center" valign="top" width="14.28%"><a href="https://github.com/fred-apina"><img src="https://avatars.githubusercontent.com/u/39369908?v=4?s=100" width="100px;" alt="fred-apina"/><br /><sub><b>Frederick</b></sub></a><br /><a href="https://github.com/sambaiga/MLPF/commits?author=fred-apina" title="Code">💻</a> <a href="#maintenance-fred-apina" title="Maintenance">🚧</a></td>
      <td align="center" valign="top" width="14.28%"><a href="https://github.com/fred-apina"><img src="https://avatars.githubusercontent.com/u/7491890?v=4?s=100" width="100px;" alt="alspereira"/><br /><sub><b>Lucas</b></sub></a><br /><a href="https://github.com/sambaiga/MLPF/commits?author=alspereira" title="Code">💻</a> <a href="#maintenance-alspereira" title="Maintenance">🚧</a></td>
    </tr>
  </tbody>
</table>



## References

This work is inspired by the research from the following publication:

1. A. Faustine, N. J. Nunes and L. Pereira, "Efficiency through Simplicity: MLP-based Approach for Net-Load Forecasting with Uncertainty Estimates in Low-Voltage Distribution Networks," in IEEE Transactions on Power Systems, doi: [10.1109/TPWRS.2024.3400123](https://ieeexplore.ieee.org/document/10529636).
2.  A. Faustine and L. Pereira, "FPSeq2Q: Fully Parameterized Sequence to Quantile Regression for Net-Load Forecasting With Uncertainty Estimates," in IEEE Transactions on Smart Grid, vol. 13, no. 3, pp. 2440-2451, May 2022, doi: [10.1109/TSG.2022.3148699](https://ieeexplore.ieee.org/document/9701598).

<!-- markdownlint-restore -->

