PHPackages sphamster/classification-metrics - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. [Utility & Helpers](/categories/utility) 4. / 5. sphamster/classification-metrics ActiveLibrary[Utility & Helpers](/categories/utility) sphamster/classification-metrics ================================ PHP package to compute confusion matrices and classification metrics v1.0.0(10mo ago)02MITPHPPHP ^8.1CI passing Since Jul 19Pushed 10mo agoCompare [ Source](https://github.com/sphamster/classification-metrics)[ Packagist](https://packagist.org/packages/sphamster/classification-metrics)[ RSS](/packages/sphamster-classification-metrics/feed)WikiDiscussions master Synced 1mo ago READMEChangelog (1)Dependencies (7)Versions (2)Used By (0) Classification Metrics for PHP ============================== [](#classification-metrics-for-php) [![Latest Version on Packagist](https://camo.githubusercontent.com/1c7157fe46bdf922a09e03296b61db07f418da2812b18e9ea30f85e34e24c61d/68747470733a2f2f696d672e736869656c64732e696f2f7061636b61676973742f762f737068616d737465722f636c617373696669636174696f6e2d6d6574726963732e7376673f7374796c653d666c61742d737175617265)](https://packagist.org/packages/sphamster/classification-metrics)[![GitHub Tests Action Status](https://camo.githubusercontent.com/7bc894790ec073d4764a0a2829e95652db7aa5afb3812b9c1a4ef17ed386a8d7/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f616374696f6e732f776f726b666c6f772f7374617475732f737068616d737465722f636c617373696669636174696f6e2d6d6574726963732f70756c6c2d726571756573742e796d6c3f6272616e63683d6d6173746572266c6162656c3d7465737473267374796c653d666c61742d737175617265)](https://github.com/sphamster/classification-metrics/actions?query=workflow%3Arun-tests+branch%3Amain)[![MIT Licensed](https://camo.githubusercontent.com/55c0218c8f8009f06ad4ddae837ddd05301481fcf0dff8e0ed9dadda8780713e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6c6963656e73652d4d49542d627269676874677265656e2e7376673f7374796c653d666c61742d737175617265)](LICENSE)[![PHP Version](https://camo.githubusercontent.com/4c37146ddaf0c22a728307816e2491aecd7a7a07926a9c2ee8385ae8f9990951/68747470733a2f2f696d672e736869656c64732e696f2f7061636b61676973742f646570656e64656e63792d762f737068616d737465722f636c617373696669636174696f6e2d6d6574726963732f7068702e7376673f7374796c653d666c61742d737175617265)](composer.json)[![PHPStan Level](https://camo.githubusercontent.com/fa7d257d0c5c1cf237ac3490ef3a5561626b17fcb0a8547c01b0bb8746554e60/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f5048505374616e2d6c6576656c253230392d627269676874677265656e2e7376673f7374796c653d666c61742d737175617265)](https://phpstan.org/)[![Code Coverage](https://camo.githubusercontent.com/8b94d24cafb5a4f63f51139f87b8a264ab2702ef64b2a25abb42272951457d86/68747470733a2f2f696d672e736869656c64732e696f2f636f6465636f762f632f6769746875622f737068616d737465722f636c617373696669636174696f6e2d6d6574726963733f7374796c653d666c61742d737175617265)](https://codecov.io/gh/sphamster/classification-metrics) A PHP package for computing confusion matrices and classification metrics for machine learning models. Installation ------------ [](#installation) You can install the package via composer: ``` composer require sphamster/classification-metrics ``` Requirements ------------ [](#requirements) - PHP 8.1 or higher Usage ----- [](#usage) ### Creating a Confusion Matrix [](#creating-a-confusion-matrix) You can create a confusion matrix directly from predictions: ``` use Sphamster\ClassificationMetrics\ConfusionMatrix; // Your ground truth labels $true_labels = ['cat', 'dog', 'cat', 'bird', 'dog', 'bird']; // Your model's predictions $predicted_labels = ['cat', 'dog', 'dog', 'bird', 'cat', 'bird']; // Optional: specify the order of labels (if omitted, will use unique values from true_labels) $labels = ['cat', 'dog', 'bird']; // Create the confusion matrix $confusion_matrix = ConfusionMatrix::fromPredictions($true_labels, $predicted_labels, $labels); ``` Or you can create it directly from a matrix: ``` $labels = ['cat', 'dog', 'bird']; $matrix = [ [5, 1, 0], // cat: 5 correct, 1 as dog, 0 as bird [2, 8, 1], // dog: 2 as cat, 8 correct, 1 as bird [0, 0, 6] // bird: 0 as cat, 0 as dog, 6 correct ]; $confusion_matrix = new ConfusionMatrix($labels, $matrix); ``` ### Extracting Basic Metrics [](#extracting-basic-metrics) The confusion matrix provides methods to extract basic metrics: ``` // Get true positives for all classes $tp = $confusion_matrix->truePositives(); // Or for a specific class $tp_cat = $confusion_matrix->truePositives('cat'); // Similarly for false positives, false negatives, and true negatives $fp = $confusion_matrix->falsePositives(); $fn = $confusion_matrix->falseNegatives(); $tn = $confusion_matrix->trueNegatives(); ``` ### Computing Classification Metrics [](#computing-classification-metrics) The package provides implementations for common classification metrics: #### Precision [](#precision) ``` use Sphamster\ClassificationMetrics\Metrics\Precision; use Sphamster\ClassificationMetrics\Enums\AverageStrategy; // Get precision for each class $precision = new Precision(); $class_precision = $precision->measure($confusion_matrix); // Get macro-averaged precision $macro_precision = (new Precision(AverageStrategy::MACRO))->measure($confusion_matrix); // Get micro-averaged precision $micro_precision = (new Precision(AverageStrategy::MICRO))->measure($confusion_matrix); // Get weighted-averaged precision $weighted_precision = (new Precision(AverageStrategy::WEIGHTED))->measure($confusion_matrix); ``` #### Recall [](#recall) ``` use Sphamster\ClassificationMetrics\Metrics\Recall; // Get recall for each class $recall = new Recall(); $class_recall = $recall->measure($confusion_matrix); // Similarly, you can use AverageStrategy for macro, micro, and weighted averaging ``` #### F1 Score [](#f1-score) ``` use Sphamster\ClassificationMetrics\Metrics\F1Score; // Get F1 score for each class $f1 = new F1Score(); $class_f1 = $f1->measure($confusion_matrix); // Similarly, you can use AverageStrategy for macro, micro, and weighted averaging ``` Averaging Strategies -------------------- [](#averaging-strategies) The package supports three averaging strategies for multi-class metrics: - **Macro**: Calculate metrics for each label and find their unweighted mean. This does not take label imbalance into account. - **Micro**: Calculate metrics globally by counting the total true positives, false negatives, and false positives. - **Weighted**: Calculate metrics for each label and find their average weighted by support (the number of true instances for each label). Testing ------- [](#testing) ``` composer test ``` Code Quality ------------ [](#code-quality) The package includes tools for maintaining code quality: ``` # Run code style fixer composer lint # Run static analysis composer test:types # Run refactoring tool composer refactor # Run all checks composer test ``` License ------- [](#license) The MIT License (MIT). Please see [License File](LICENSE) for more information. Author ------ [](#author) - [Andrea Civita](https://github.com/andreacivita) ### Health Score 29 — LowBetter than 59% of packages Maintenance54 Moderate activity, may be stable Popularity2 Limited adoption so far Community6 Small or concentrated contributor base Maturity45 Maturing project, gaining track record Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Release Activity Cadence Unknown Total 1 Last Release 304d ago ### Community Maintainers ![](https://www.gravatar.com/avatar/3ca8ae45c81288c22836f584e70c2e3dd2ac2ef2a22bea404d5eb91b4f669649?d=identicon)[andreacivita](/maintainers/andreacivita) --- Top Contributors [![andreacivita](https://avatars.githubusercontent.com/u/4959092?v=4)](https://github.com/andreacivita "andreacivita (5 commits)") ### Code Quality TestsPest Static AnalysisPHPStan, Rector Code StyleLaravel Pint Type Coverage Yes ### Embed Badge ![Health badge](/badges/sphamster-classification-metrics/health.svg) ``` [![Health](https://phpackages.com/badges/sphamster-classification-metrics/health.svg)](https://phpackages.com/packages/sphamster-classification-metrics) ``` PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)