about.md

layout	manual
title	About

About us

SmartCore is developed and maintained by Smartcore developers. Our goal is to build an open library that has accurate, numerically stable, and well-documented implementations of the most well-known and widely used machine learning algorithms.

Contributors

{% for contributor in site.data.contributors %}

{% avatar user=contributor.id size=60 %}

{{contributor.name}}

{% endfor %}

## Release Notes

Version 0.6.x (current)

• Edition 2024 port (MSRV 1.85), no unsafe in library code
• ndarray upgraded to 0.17; nalgebra bindings dropped
• New preprocessing module (one-hot encoding, standard scaling, series encoder)
• New AgglomerativeClustering and ExtraTreesRegressor
• New Cosine and Jaccard distance metrics
• DenseMatrix moved to linalg::basic::matrix (constructors now fallible)
• Trait rework: SupervisedEstimatorBorrow/PredictorBorrow for borrow-style estimators (SVC, SVR)
• train_test_split takes an optional RNG seed
• cross_validate takes an estimator instance, not a fit fn pointer
• Model persistence moved from bincode to postcard
• default feature set is now empty; datasets, ndarray-bindings, serde are opt-in

Version 0.2.0

• DBSCAN
• Epsilon-SVR, SVC
• Ridge, Lasso, ElasticNet
• Bernoulli, Gaussian, Categorical and Multinomial Naive Bayes
• K-fold Cross Validation
• Singular value decomposition
• New api module
• Integration with Clippy
• smartcore::error:FailedError is now non-exhaustive
• ndarray upgraded to 0.14
• Cholesky decomposition
• API changed in: K-Means, PCA, Random Forest, Linear and Logistic Regression, KNN, Decision Tree

Version 0.1.0

This is our first realease, enjoy! In this version you'll find:

• KNN + distance metrics (Euclidian, Minkowski, Manhattan, Hamming, Mahalanobis)
• Linear Regression (OLS)
• Logistic Regression
• Random Forest Classifier
• Decision Tree Classifier
• PCA
• K-Means
• Integrated with ndarray
• Abstract linear algebra methods
• RandomForest Regressor
• Decision Tree Regressor
• Serde integration
• LU, QR, SVD, EVD
• Evaluation Metrics

Please let us know if you found a problem. The best way to report it is to open an issue on GitHub.