Expand description
Classification and regression evaluation metrics.
This crate provides functions for evaluating machine learning model
performance, including classification metrics (accuracy_score,
precision_score, recall_score, f1_score_avg,
confusion_matrix) and regression metrics (mse, mae,
r2_score).
§Examples
use ndarray::array;
use anofox_ml_metrics::{accuracy_score, mse};
// Classification: compute accuracy
let y_true = array![0.0, 1.0, 1.0, 0.0];
let y_pred = array![0.0, 1.0, 0.0, 0.0];
let acc: f64 = accuracy_score(&y_true, &y_pred).unwrap();
assert!((acc - 0.75).abs() < 1e-10);
// Regression: compute mean squared error
let actual = array![1.0, 2.0, 3.0];
let predicted = array![1.5, 2.5, 3.5];
let error: f64 = mse(&actual, &predicted).unwrap();
assert!((error - 0.25).abs() < 1e-10);Re-exports§
pub use classification::accuracy_score;pub use classification::confusion_matrix;pub use classification::f1_score;pub use classification::f1_score_avg;pub use classification::precision;pub use classification::precision_score;pub use classification::recall;pub use classification::recall_score;pub use classification::Average;pub use classification_extended::average_precision_score;pub use classification_extended::matthews_corrcoef;pub use classification_extended::roc_auc_score;pub use classification_extra::balanced_accuracy_score;pub use classification_extra::cohen_kappa_score;pub use classification_extra::log_loss;pub use clustering::silhouette_score;pub use clustering_extra::adjusted_rand_score;pub use clustering_extra::normalized_mutual_info_score;pub use curves::brier_score_loss;pub use curves::precision_recall_curve;pub use curves::roc_curve;pub use regression::mae;pub use regression::mse;pub use regression::r2_score;pub use regression_extended::explained_variance_score;pub use regression_extended::max_error;pub use regression_extended::mean_absolute_percentage_error;pub use regression_extra::mean_squared_log_error;pub use regression_extra::median_absolute_error;