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

Implement predict_proba for DecisionTreeClassifier (#287)

Browse Source 
* Implement predict_proba for DecisionTreeClassifier
* Some automated fixes suggested by cargo clippy --fix
This commit is contained in:
Lorenzo
2025-01-20 18:50:00 +00:00
committed by GitHub
parent 4523ac73ff
commit 3da433f757
13 changed files with 166 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/algorithm/neighbour/fastpair.rs
+3 -1
View File
@@ -212,7 +212,9 @@ mod tests_fastpair {
use crate::linalg::basic::{arrays::Array, matrix::DenseMatrix};
/// Brute force algorithm, used only for comparison and testing
pub fn closest_pair_brute(fastpair: &FastPair<f64, DenseMatrix<f64>>) -> PairwiseDistance<f64> {
pub fn closest_pair_brute(
fastpair: &FastPair<'_, f64, DenseMatrix<f64>>,
) -> PairwiseDistance<f64> {
use itertools::Itertools;
let m = fastpair.samples.shape().0;
src/linalg/basic/matrix.rs
+12 -13
View File
@@ -91,7 +91,7 @@ impl<'a, T: Debug + Display + Copy + Sized> DenseMatrixView<'a, T> {
}
}
impl<'a, T: Debug + Display + Copy + Sized> fmt::Display for DenseMatrixView<'a, T> {
impl<T: Debug + Display + Copy + Sized> fmt::Display for DenseMatrixView<'_, T> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(
f,
@@ -142,7 +142,7 @@ impl<'a, T: Debug + Display + Copy + Sized> DenseMatrixMutView<'a, T> {
}
}
fn iter_mut<'b>(&'b mut self, axis: u8) -> Box<dyn Iterator<Item = &mut T> + 'b> {
fn iter_mut<'b>(&'b mut self, axis: u8) -> Box<dyn Iterator<Item = &'b mut T> + 'b> {
let column_major = self.column_major;
let stride = self.stride;
let ptr = self.values.as_mut_ptr();
@@ -169,7 +169,7 @@ impl<'a, T: Debug + Display + Copy + Sized> DenseMatrixMutView<'a, T> {
}
}
impl<'a, T: Debug + Display + Copy + Sized> fmt::Display for DenseMatrixMutView<'a, T> {
impl<T: Debug + Display + Copy + Sized> fmt::Display for DenseMatrixMutView<'_, T> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(
f,
@@ -493,7 +493,7 @@ impl<T: Number + RealNumber> EVDDecomposable<T> for DenseMatrix<T> {}
impl<T: Number + RealNumber> LUDecomposable<T> for DenseMatrix<T> {}
impl<T: Number + RealNumber> SVDDecomposable<T> for DenseMatrix<T> {}
impl<'a, T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMatrixView<'a, T> {
impl<T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMatrixView<'_, T> {
fn get(&self, pos: (usize, usize)) -> &T {
if self.column_major {
&self.values[pos.0 + pos.1 * self.stride]
@@ -515,7 +515,7 @@ impl<'a, T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMa
}
}
impl<'a, T: Debug + Display + Copy + Sized> Array<T, usize> for DenseMatrixView<'a, T> {
impl<T: Debug + Display + Copy + Sized> Array<T, usize> for DenseMatrixView<'_, T> {
fn get(&self, i: usize) -> &T {
if self.nrows == 1 {
if self.column_major {
@@ -553,11 +553,11 @@ impl<'a, T: Debug + Display + Copy + Sized> Array<T, usize> for DenseMatrixView<
}
}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView2<T> for DenseMatrixView<'a, T> {}
impl<T: Debug + Display + Copy + Sized> ArrayView2<T> for DenseMatrixView<'_, T> {}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView1<T> for DenseMatrixView<'a, T> {}
impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for DenseMatrixView<'_, T> {}
impl<'a, T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMatrixMutView<'a, T> {
impl<T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMatrixMutView<'_, T> {
fn get(&self, pos: (usize, usize)) -> &T {
if self.column_major {
&self.values[pos.0 + pos.1 * self.stride]
@@ -579,9 +579,7 @@ impl<'a, T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMa
}
}
impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)>
for DenseMatrixMutView<'a, T>
{
impl<T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)> for DenseMatrixMutView<'_, T> {
fn set(&mut self, pos: (usize, usize), x: T) {
if self.column_major {
self.values[pos.0 + pos.1 * self.stride] = x;
@@ -595,15 +593,16 @@ impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)>
}
}
impl<'a, T: Debug + Display + Copy + Sized> MutArrayView2<T> for DenseMatrixMutView<'a, T> {}
impl<T: Debug + Display + Copy + Sized> MutArrayView2<T> for DenseMatrixMutView<'_, T> {}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView2<T> for DenseMatrixMutView<'a, T> {}
impl<T: Debug + Display + Copy + Sized> ArrayView2<T> for DenseMatrixMutView<'_, T> {}
impl<T: RealNumber> MatrixStats<T> for DenseMatrix<T> {}
impl<T: RealNumber> MatrixPreprocessing<T> for DenseMatrix<T> {}
#[cfg(test)]
#[warn(clippy::reversed_empty_ranges)]
mod tests {
use super::*;
use approx::relative_eq;
src/linalg/basic/vector.rs
+6 -6
View File
@@ -119,7 +119,7 @@ impl<T: Debug + Display + Copy + Sized> Array1<T> for Vec<T> {
}
}
impl<'a, T: Debug + Display + Copy + Sized> Array<T, usize> for VecMutView<'a, T> {
impl<T: Debug + Display + Copy + Sized> Array<T, usize> for VecMutView<'_, T> {
fn get(&self, i: usize) -> &T {
&self.ptr[i]
}
@@ -138,7 +138,7 @@ impl<'a, T: Debug + Display + Copy + Sized> Array<T, usize> for VecMutView<'a, T
}
}
impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, usize> for VecMutView<'a, T> {
impl<T: Debug + Display + Copy + Sized> MutArray<T, usize> for VecMutView<'_, T> {
fn set(&mut self, i: usize, x: T) {
self.ptr[i] = x;
}
@@ -149,10 +149,10 @@ impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, usize> for VecMutView<'a
}
}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView1<T> for VecMutView<'a, T> {}
impl<'a, T: Debug + Display + Copy + Sized> MutArrayView1<T> for VecMutView<'a, T> {}
impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for VecMutView<'_, T> {}
impl<T: Debug + Display + Copy + Sized> MutArrayView1<T> for VecMutView<'_, T> {}
impl<'a, T: Debug + Display + Copy + Sized> Array<T, usize> for VecView<'a, T> {
impl<T: Debug + Display + Copy + Sized> Array<T, usize> for VecView<'_, T> {
fn get(&self, i: usize) -> &T {
&self.ptr[i]
}
@@ -171,7 +171,7 @@ impl<'a, T: Debug + Display + Copy + Sized> Array<T, usize> for VecView<'a, T> {
}
}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView1<T> for VecView<'a, T> {}
impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for VecView<'_, T> {}
#[cfg(test)]
mod tests {
src/linalg/ndarray/matrix.rs
+6 -10
View File
@@ -68,7 +68,7 @@ impl<T: Debug + Display + Copy + Sized> ArrayView2<T> for ArrayBase<OwnedRepr<T>
impl<T: Debug + Display + Copy + Sized> MutArrayView2<T> for ArrayBase<OwnedRepr<T>, Ix2> {}
impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, (usize, usize)> for ArrayView<'a, T, Ix2> {
impl<T: Debug + Display + Copy + Sized> BaseArray<T, (usize, usize)> for ArrayView<'_, T, Ix2> {
fn get(&self, pos: (usize, usize)) -> &T {
&self[[pos.0, pos.1]]
}
@@ -144,11 +144,9 @@ impl<T: Number + RealNumber> EVDDecomposable<T> for ArrayBase<OwnedRepr<T>, Ix2>
impl<T: Number + RealNumber> LUDecomposable<T> for ArrayBase<OwnedRepr<T>, Ix2> {}
impl<T: Number + RealNumber> SVDDecomposable<T> for ArrayBase<OwnedRepr<T>, Ix2> {}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView2<T> for ArrayView<'a, T, Ix2> {}
impl<T: Debug + Display + Copy + Sized> ArrayView2<T> for ArrayView<'_, T, Ix2> {}
impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, (usize, usize)>
for ArrayViewMut<'a, T, Ix2>
{
impl<T: Debug + Display + Copy + Sized> BaseArray<T, (usize, usize)> for ArrayViewMut<'_, T, Ix2> {
fn get(&self, pos: (usize, usize)) -> &T {
&self[[pos.0, pos.1]]
}
@@ -175,9 +173,7 @@ impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, (usize, usize)>
}
}
impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)>
for ArrayViewMut<'a, T, Ix2>
{
impl<T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)> for ArrayViewMut<'_, T, Ix2> {
fn set(&mut self, pos: (usize, usize), x: T) {
self[[pos.0, pos.1]] = x
}
@@ -195,9 +191,9 @@ impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)>
}
}
impl<'a, T: Debug + Display + Copy + Sized> MutArrayView2<T> for ArrayViewMut<'a, T, Ix2> {}
impl<T: Debug + Display + Copy + Sized> MutArrayView2<T> for ArrayViewMut<'_, T, Ix2> {}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView2<T> for ArrayViewMut<'a, T, Ix2> {}
impl<T: Debug + Display + Copy + Sized> ArrayView2<T> for ArrayViewMut<'_, T, Ix2> {}
#[cfg(test)]
mod tests {
src/linalg/ndarray/vector.rs
+6 -6
View File
@@ -41,7 +41,7 @@ impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for ArrayBase<OwnedRepr<T>
impl<T: Debug + Display + Copy + Sized> MutArrayView1<T> for ArrayBase<OwnedRepr<T>, Ix1> {}
impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, usize> for ArrayView<'a, T, Ix1> {
impl<T: Debug + Display + Copy + Sized> BaseArray<T, usize> for ArrayView<'_, T, Ix1> {
fn get(&self, i: usize) -> &T {
&self[i]
}
@@ -60,9 +60,9 @@ impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, usize> for ArrayView<'a
}
}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView1<T> for ArrayView<'a, T, Ix1> {}
impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for ArrayView<'_, T, Ix1> {}
impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, usize> for ArrayViewMut<'a, T, Ix1> {
impl<T: Debug + Display + Copy + Sized> BaseArray<T, usize> for ArrayViewMut<'_, T, Ix1> {
fn get(&self, i: usize) -> &T {
&self[i]
}
@@ -81,7 +81,7 @@ impl<'a, T: Debug + Display + Copy + Sized> BaseArray<T, usize> for ArrayViewMut
}
}
impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, usize> for ArrayViewMut<'a, T, Ix1> {
impl<T: Debug + Display + Copy + Sized> MutArray<T, usize> for ArrayViewMut<'_, T, Ix1> {
fn set(&mut self, i: usize, x: T) {
self[i] = x;
}
@@ -92,8 +92,8 @@ impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, usize> for ArrayViewMut<
}
}
impl<'a, T: Debug + Display + Copy + Sized> ArrayView1<T> for ArrayViewMut<'a, T, Ix1> {}
impl<'a, T: Debug + Display + Copy + Sized> MutArrayView1<T> for ArrayViewMut<'a, T, Ix1> {}
impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for ArrayViewMut<'_, T, Ix1> {}
impl<T: Debug + Display + Copy + Sized> MutArrayView1<T> for ArrayViewMut<'_, T, Ix1> {}
impl<T: Debug + Display + Copy + Sized> Array1<T> for ArrayBase<OwnedRepr<T>, Ix1> {
fn slice<'a>(&'a self, range: Range<usize>) -> Box<dyn ArrayView1<T> + 'a> {
src/linalg/traits/stats.rs
-1
View File
@@ -142,7 +142,6 @@ pub trait MatrixPreprocessing<T: RealNumber>: MutArrayView2<T> + Clone {
///
/// assert_eq!(a, expected);
/// ```
fn binarize_mut(&mut self, threshold: T) {
let (nrows, ncols) = self.shape();
for row in 0..nrows {
src/linear/logistic_regression.rs
+4 -4
View File
@@ -258,8 +258,8 @@ impl<TX: Number + FloatNumber + RealNumber, TY: Number + Ord, X: Array2<TX>, Y:
}
}
impl<'a, T: Number + FloatNumber, X: Array2<T>> ObjectiveFunction<T, X>
for BinaryObjectiveFunction<'a, T, X>
impl<T: Number + FloatNumber, X: Array2<T>> ObjectiveFunction<T, X>
for BinaryObjectiveFunction<'_, T, X>
{
fn f(&self, w_bias: &[T]) -> T {
let mut f = T::zero();
@@ -313,8 +313,8 @@ struct MultiClassObjectiveFunction<'a, T: Number + FloatNumber, X: Array2<T>> {
_phantom_t: PhantomData<T>,
}
impl<'a, T: Number + FloatNumber + RealNumber, X: Array2<T>> ObjectiveFunction<T, X>
for MultiClassObjectiveFunction<'a, T, X>
impl<T: Number + FloatNumber + RealNumber, X: Array2<T>> ObjectiveFunction<T, X>
for MultiClassObjectiveFunction<'_, T, X>
{
fn f(&self, w_bias: &[T]) -> T {
let mut f = T::zero();
src/naive_bayes/mod.rs
+1 -1
View File
@@ -147,7 +147,7 @@ mod tests {
#[derive(Debug, PartialEq, Clone)]
struct TestDistribution<'d>(&'d Vec<i32>);
impl<'d> NBDistribution<i32, i32> for TestDistribution<'d> {
impl NBDistribution<i32, i32> for TestDistribution<'_> {
fn prior(&self, _class_index: usize) -> f64 {
1.
}
src/preprocessing/numerical.rs
+8 -12
View File
@@ -172,18 +172,14 @@ where
T: Number + RealNumber,
M: Array2<T>,
{
if let Some(output_matrix) = columns.first().cloned() {
return Some(
columns
.iter()
.skip(1)
.fold(output_matrix, |current_matrix, new_colum| {
current_matrix.h_stack(new_colum)
}),
);
} else {
None
}
columns.first().cloned().map(|output_matrix| {
columns
.iter()
.skip(1)
.fold(output_matrix, |current_matrix, new_colum| {
current_matrix.h_stack(new_colum)
})
})
}
#[cfg(test)]
src/readers/csv.rs
+1 -1
View File
@@ -30,7 +30,7 @@ pub struct CSVDefinition<'a> {
/// What seperates the fields in your csv-file?
field_seperator: &'a str,
}
impl<'a> Default for CSVDefinition<'a> {
impl Default for CSVDefinition<'_> {
fn default() -> Self {
Self {
n_rows_header: 1,
src/svm/svc.rs
+3 -3
View File
@@ -360,8 +360,8 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX> + 'a, Y: Array
}
}
impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>> PartialEq
for SVC<'a, TX, TY, X, Y>
impl<TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>> PartialEq
for SVC<'_, TX, TY, X, Y>
{
fn eq(&self, other: &Self) -> bool {
if (self.b.unwrap().sub(other.b.unwrap())).abs() > TX::epsilon() * TX::two()
@@ -1110,7 +1110,7 @@ mod tests {
let svc = SVC::fit(&x, &y, &params).unwrap();
// serialization
let deserialized_svc: SVC<f64, i32, _, _> =
let deserialized_svc: SVC<'_, f64, i32, _, _> =
serde_json::from_str(&serde_json::to_string(&svc).unwrap()).unwrap();
assert_eq!(svc, deserialized_svc);
src/svm/svr.rs
+3 -3
View File
@@ -281,8 +281,8 @@ impl<'a, T: Number + FloatNumber + PartialOrd, X: Array2<T>, Y: Array1<T>> SVR<'
}
}
impl<'a, T: Number + FloatNumber + PartialOrd, X: Array2<T>, Y: Array1<T>> PartialEq
for SVR<'a, T, X, Y>
impl<T: Number + FloatNumber + PartialOrd, X: Array2<T>, Y: Array1<T>> PartialEq
for SVR<'_, T, X, Y>
{
fn eq(&self, other: &Self) -> bool {
if (self.b - other.b).abs() > T::epsilon() * T::two()
@@ -702,7 +702,7 @@ mod tests {
let svr = SVR::fit(&x, &y, &params).unwrap();
let deserialized_svr: SVR<f64, DenseMatrix<f64>, _> =
let deserialized_svr: SVR<'_, f64, DenseMatrix<f64>, _> =
serde_json::from_str(&serde_json::to_string(&svr).unwrap()).unwrap();
assert_eq!(svr, deserialized_svr);
src/tree/decision_tree_classifier.rs
+113
View File
@@ -77,7 +77,9 @@ use serde::{Deserialize, Serialize};
use crate::api::{Predictor, SupervisedEstimator};
use crate::error::Failed;
use crate::linalg::basic::arrays::MutArray;
use crate::linalg::basic::arrays::{Array1, Array2, MutArrayView1};
use crate::linalg::basic::matrix::DenseMatrix;
use crate::numbers::basenum::Number;
use crate::rand_custom::get_rng_impl;
@@ -887,11 +889,77 @@ impl<TX: Number + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>>
}
importances
}
/// Predict class probabilities for the input samples.
///
/// # Arguments
///
/// * `x` - The input samples as a matrix where each row is a sample and each column is a feature.
///
/// # Returns
///
/// A `Result` containing a `DenseMatrix<f64>` where each row corresponds to a sample and each column
/// corresponds to a class. The values represent the probability of the sample belonging to each class.
///
/// # Errors
///
/// Returns an error if at least one row prediction process fails.
pub fn predict_proba(&self, x: &X) -> Result<DenseMatrix<f64>, Failed> {
let (n_samples, _) = x.shape();
let n_classes = self.classes().len();
let mut result = DenseMatrix::<f64>::zeros(n_samples, n_classes);
for i in 0..n_samples {
let probs = self.predict_proba_for_row(x, i)?;
for (j, &prob) in probs.iter().enumerate() {
result.set((i, j), prob);
}
}
Ok(result)
}
/// Predict class probabilities for a single input sample.
///
/// # Arguments
///
/// * `x` - The input matrix containing all samples.
/// * `row` - The index of the row in `x` for which to predict probabilities.
///
/// # Returns
///
/// A vector of probabilities, one for each class, representing the probability
/// of the input sample belonging to each class.
fn predict_proba_for_row(&self, x: &X, row: usize) -> Result<Vec<f64>, Failed> {
let mut node = 0;
while let Some(current_node) = self.nodes().get(node) {
if current_node.true_child.is_none() && current_node.false_child.is_none() {
// Leaf node reached
let mut probs = vec![0.0; self.classes().len()];
probs[current_node.output] = 1.0;
return Ok(probs);
}
let split_feature = current_node.split_feature;
let split_value = current_node.split_value.unwrap_or(f64::NAN);
if x.get((row, split_feature)).to_f64().unwrap() <= split_value {
node = current_node.true_child.unwrap();
} else {
node = current_node.false_child.unwrap();
}
}
// This should never happen if the tree is properly constructed
Err(Failed::predict("Nodes iteration did not reach leaf"))
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::linalg::basic::arrays::Array;
use crate::linalg::basic::matrix::DenseMatrix;
#[test]
@@ -934,6 +1002,51 @@ mod tests {
);
}
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test
)]
#[test]
fn test_predict_proba() {
let x: DenseMatrix<f64> = DenseMatrix::from_2d_array(&[
&[5.1, 3.5, 1.4, 0.2],
&[4.9, 3.0, 1.4, 0.2],
&[4.7, 3.2, 1.3, 0.2],
&[4.6, 3.1, 1.5, 0.2],
&[5.0, 3.6, 1.4, 0.2],
&[7.0, 3.2, 4.7, 1.4],
&[6.4, 3.2, 4.5, 1.5],
&[6.9, 3.1, 4.9, 1.5],
&[5.5, 2.3, 4.0, 1.3],
&[6.5, 2.8, 4.6, 1.5],
])
.unwrap();
let y: Vec<usize> = vec![0, 0, 0, 0, 0, 1, 1, 1, 1, 1];
let tree = DecisionTreeClassifier::fit(&x, &y, Default::default()).unwrap();
let probabilities = tree.predict_proba(&x).unwrap();
assert_eq!(probabilities.shape(), (10, 2));
for row in 0..10 {
let row_sum: f64 = probabilities.get_row(row).sum();
assert!(
(row_sum - 1.0).abs() < 1e-6,
"Row probabilities should sum to 1"
);
}
// Check if the first 5 samples have higher probability for class 0
for i in 0..5 {
assert!(probabilities.get((i, 0)) > probabilities.get((i, 1)));
}
// Check if the last 5 samples have higher probability for class 1
for i in 5..10 {
assert!(probabilities.get((i, 1)) > probabilities.get((i, 0)));
}
}
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test