work/smartcore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix precision and recall calculations (#338)

Browse Source 
* fix precision and recall calculations
This commit is contained in:
Charlie Martin
2025-11-23 20:46:56 -05:00
committed by GitHub
parent 0e42a97514
commit 70d8a0f34b
2 changed files with 152 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/metrics/precision.rs
+88 -23
View File
@@ -4,7 +4,9 @@
//!
//! \\[precision = \frac{tp}{tp + fp}\\]
//!
//! where tp (true positive) - correct result, fp (false positive) - unexpected result
//! where tp (true positive) - correct result, fp (false positive) - unexpected result.
//! For binary classification, this is precision for the positive class (assumed to be 1.0).
//! For multiclass, this is macro-averaged precision (average of per-class precisions).
//!
//! Example:
//!
@@ -19,7 +21,8 @@
//!
//! <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>
//! <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
use std::collections::HashSet;
use std::collections::{HashMap, HashSet};
use std::marker::PhantomData;
#[cfg(feature = "serde")]
@@ -61,33 +64,63 @@ impl<T: RealNumber> Metrics<T> for Precision<T> {
);
}
let mut classes = HashSet::new();
for i in 0..y_true.shape() {
classes.insert(y_true.get(i).to_f64_bits());
}
let classes = classes.len();
let n = y_true.shape();
let mut tp = 0;
let mut fp = 0;
for i in 0..y_true.shape() {
if y_pred.get(i) == y_true.get(i) {
if classes == 2 {
if *y_true.get(i) == T::one() {
let mut classes_set: HashSet<u64> = HashSet::new();
for i in 0..n {
classes_set.insert(y_true.get(i).to_f64_bits());
}
let classes: usize = classes_set.len();
if classes == 2 {
// Binary case: precision for positive class (assumed T::one())
let positive = T::one();
let mut tp: usize = 0;
let mut fp_count: usize = 0;
for i in 0..n {
let t = *y_true.get(i);
let p = *y_pred.get(i);
if p == t {
if t == positive {
tp += 1;
}
} else {
tp += 1;
}
} else if classes == 2 {
if *y_true.get(i) == T::one() {
fp += 1;
} else if t != positive {
fp_count += 1;
}
}
if tp + fp_count == 0 {
0.0
} else {
fp += 1;
tp as f64 / (tp + fp_count) as f64
}
} else {
// Multiclass case: macro-averaged precision
let mut predicted: HashMap<u64, usize> = HashMap::new();
let mut tp_map: HashMap<u64, usize> = HashMap::new();
for i in 0..n {
let p_bits = y_pred.get(i).to_f64_bits();
*predicted.entry(p_bits).or_insert(0) += 1;
if *y_true.get(i) == *y_pred.get(i) {
*tp_map.entry(p_bits).or_insert(0) += 1;
}
}
let mut precision_sum = 0.0;
for &bits in &classes_set {
let pred_count = *predicted.get(&bits).unwrap_or(&0);
let tp = *tp_map.get(&bits).unwrap_or(&0);
let prec = if pred_count > 0 {
tp as f64 / pred_count as f64
} else {
0.0
};
precision_sum += prec;
}
if classes == 0 {
0.0
} else {
precision_sum / classes as f64
}
}
tp as f64 / (tp as f64 + fp as f64)
}
}
@@ -114,7 +147,7 @@ mod tests {
let y_pred: Vec<f64> = vec![0., 0., 1., 1., 1., 1.];
let score3: f64 = Precision::new().get_score(&y_true, &y_pred);
assert!((score3 - 0.6666666666).abs() < 1e-8);
assert!((score3 - 0.5).abs() < 1e-8);
}
#[cfg_attr(
@@ -132,4 +165,36 @@ mod tests {
assert!((score1 - 0.333333333).abs() < 1e-8);
assert!((score2 - 1.0).abs() < 1e-8);
}
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test
)]
#[test]
fn precision_multiclass_imbalanced() {
let y_true: Vec<f64> = vec![0., 0., 1., 2., 2., 2.];
let y_pred: Vec<f64> = vec![0., 1., 1., 2., 0., 2.];
let score: f64 = Precision::new().get_score(&y_true, &y_pred);
let expected = (0.5 + 0.5 + 1.0) / 3.0;
assert!((score - expected).abs() < 1e-8);
}
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test
)]
#[test]
fn precision_multiclass_unpredicted_class() {
let y_true: Vec<f64> = vec![0., 0., 1., 2., 2., 2., 3.];
let y_pred: Vec<f64> = vec![0., 1., 1., 2., 0., 2., 0.];
let score: f64 = Precision::new().get_score(&y_true, &y_pred);
// Class 0: pred=3, tp=1 -> 1/3 ≈0.333
// Class 1: pred=2, tp=1 -> 0.5
// Class 2: pred=2, tp=2 -> 1.0
// Class 3: pred=0, tp=0 -> 0.0
let expected = (1.0 / 3.0 + 0.5 + 1.0 + 0.0) / 4.0;
assert!((score - expected).abs() < 1e-8);
}
}
src/metrics/recall.rs
+64 -24
View File
@@ -4,7 +4,9 @@
//!
//! \\[recall = \frac{tp}{tp + fn}\\]
//!
//! where tp (true positive) - correct result, fn (false negative) - missing result
//! where tp (true positive) - correct result, fn (false negative) - missing result.
//! For binary classification, this is recall for the positive class (assumed to be 1.0).
//! For multiclass, this is macro-averaged recall (average of per-class recalls).
//!
//! Example:
//!
@@ -20,8 +22,7 @@
//! <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>
//! <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
use std::collections::HashSet;
use std::convert::TryInto;
use std::collections::{HashMap, HashSet};
use std::marker::PhantomData;
#[cfg(feature = "serde")]
@@ -52,7 +53,7 @@ impl<T: RealNumber> Metrics<T> for Recall<T> {
}
}
/// Calculated recall score
/// * `y_true` - cround truth (correct) labels.
/// * `y_true` - ground truth (correct) labels.
/// * `y_pred` - predicted labels, as returned by a classifier.
fn get_score(&self, y_true: &dyn ArrayView1<T>, y_pred: &dyn ArrayView1<T>) -> f64 {
if y_true.shape() != y_pred.shape() {
@@ -63,32 +64,57 @@ impl<T: RealNumber> Metrics<T> for Recall<T> {
);
}
let mut classes = HashSet::new();
for i in 0..y_true.shape() {
classes.insert(y_true.get(i).to_f64_bits());
}
let classes: i64 = classes.len().try_into().unwrap();
let n = y_true.shape();
let mut tp = 0;
let mut fne = 0;
for i in 0..y_true.shape() {
if y_pred.get(i) == y_true.get(i) {
if classes == 2 {
if *y_true.get(i) == T::one() {
let mut classes_set = HashSet::new();
for i in 0..n {
classes_set.insert(y_true.get(i).to_f64_bits());
}
let classes: usize = classes_set.len();
if classes == 2 {
// Binary case: recall for positive class (assumed T::one())
let positive = T::one();
let mut tp: usize = 0;
let mut fn_count: usize = 0;
for i in 0..n {
let t = *y_true.get(i);
let p = *y_pred.get(i);
if p == t {
if t == positive {
tp += 1;
}
} else {
tp += 1;
}
} else if classes == 2 {
if *y_true.get(i) != T::one() {
fne += 1;
} else if t == positive {
fn_count += 1;
}
}
if tp + fn_count == 0 {
0.0
} else {
fne += 1;
tp as f64 / (tp + fn_count) as f64
}
} else {
// Multiclass case: macro-averaged recall
let mut support: HashMap<u64, usize> = HashMap::new();
let mut tp_map: HashMap<u64, usize> = HashMap::new();
for i in 0..n {
let t_bits = y_true.get(i).to_f64_bits();
*support.entry(t_bits).or_insert(0) += 1;
if *y_true.get(i) == *y_pred.get(i) {
*tp_map.entry(t_bits).or_insert(0) += 1;
}
}
let mut recall_sum = 0.0;
for (&bits, &sup) in &support {
let tp = *tp_map.get(&bits).unwrap_or(&0);
recall_sum += tp as f64 / sup as f64;
}
if support.is_empty() {
0.0
} else {
recall_sum / support.len() as f64
}
}
tp as f64 / (tp as f64 + fne as f64)
}
}
@@ -115,7 +141,7 @@ mod tests {
let y_pred: Vec<f64> = vec![0., 0., 1., 1., 1., 1.];
let score3: f64 = Recall::new().get_score(&y_true, &y_pred);
assert!((score3 - 0.5).abs() < 1e-8);
assert!((score3 - (2.0 / 3.0)).abs() < 1e-8);
}
#[cfg_attr(
@@ -133,4 +159,18 @@ mod tests {
assert!((score1 - 0.333333333).abs() < 1e-8);
assert!((score2 - 1.0).abs() < 1e-8);
}
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test
)]
#[test]
fn recall_multiclass_imbalanced() {
let y_true: Vec<f64> = vec![0., 0., 1., 2., 2., 2.];
let y_pred: Vec<f64> = vec![0., 1., 1., 2., 0., 2.];
let score: f64 = Recall::new().get_score(&y_true, &y_pred);
let expected = (0.5 + 1.0 + (2.0 / 3.0)) / 3.0;
assert!((score - expected).abs() < 1e-8);
}
}