README

A simple and extensible library for forecasting missing data points using different regression models: Linear, Power, Logarithmic, and Exponential. Designed for PHP 8.1+.

✨ Features

• 📊 Supports Linear, Power, Logarithmic, and Exponential regression.
• 🔍 Optional interpolation-only mode to avoid extrapolation.
• 🧩 Pluggable architecture via RegressionInterface.
• ⚡️ Fast, simple, and stateless static prediction:
  ForecastService::predict($data, $method)
• ✅ Thoroughly unit-tested.

📂 Source Code

The complete source code is available on GitHub.

🛠 Installation

    composer require mykolavuy/forecast-regressions

🚀 Usage

use MykolaVuy\Forecast\ForecastService;

$data = [
    1 => 10,
    2 => null,
    3 => 30,
    4 => null,
    5 => 50,
    6 => null,
];

$service = new ForecastService();

// Linear regression forecast
$result = $service->forecast($data, method: 'linear');

// Power regression with interpolation only
$interpolated = $service->forecast($data, method: 'power', interpolateOnly: true);

// 🔹 Static call (no instance needed)
$static = ForecastService::predict($data, method: 'exponential');

🔧 Regression Methods

✅ Requirements

• PHP 8.1 or higher
• Composer

🧪 Running Tests

    ./vendor/bin/phpunit

Test files are located in the tests/ directory.

📄 License

This project is licensed under the MIT License.

🌐 Projects by the Author

intester.com

InTester is a secure and transparent online knowledge assessment platform. It offers time-limited tests, anti-cheating measures, instant results with PDF certificates, and public test records — making it ideal for job seekers and recruiters alike.

dctsign.com

DCT Sign is a blockchain-backed electronic signature platform that prioritizes privacy and data integrity. Users can securely sign documents without storing the original files, ensuring confidentiality and compliance with advanced e-signature standards.

Thank you for using ForecastRegressions! Contributions and feedback are welcome.