Merge branch 'development' into kmeans-with-fastpair

.github/CONTRIBUTING.md

@@ -37,6 +37,8 @@ $ rust-code-analysis-cli -p src/algorithm/neighbour/fastpair.rs --ls 22 --le 213
 ```
 * find more information about what happens in your binary with [`twiggy`](https://rustwasm.github.io/twiggy/install.html). This need a compiled binary so create a brief `main {}` function using `smartcore` and then point `twiggy` to that file.
 
+* Please take a look to the output of a profiler to spot most evident performance problems, see [this guide about using a profiler](http://www.codeofview.com/fix-rs/2017/01/24/how-to-optimize-rust-programs-on-linux/).
+
 ## Issue Report Process
 
 1. Go to the project's issues.

Cargo.toml

@@ -2,7 +2,7 @@
 name = "smartcore"
 description = "Machine Learning in Rust."
 homepage = "https://smartcorelib.org"
-version = "0.3.1"
+version = "0.3.2"
 authors = ["smartcore Developers"]
 edition = "2021"
 license = "Apache-2.0"

src/linalg/basic/matrix.rs

@@ -431,9 +431,9 @@ impl<T: Number + RealNumber> SVDDecomposable<T> for DenseMatrix<T> {}
 impl<'a, T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMatrixView<'a, T> {
     fn get(&self, pos: (usize, usize)) -> &T {
         if self.column_major {
-            &self.values[(pos.0 + pos.1 * self.stride)]
+            &self.values[pos.0 + pos.1 * self.stride]
         } else {
-            &self.values[(pos.0 * self.stride + pos.1)]
+            &self.values[pos.0 * self.stride + pos.1]
         }
     }
 
@@ -495,9 +495,9 @@ impl<'a, T: Debug + Display + Copy + Sized> ArrayView1<T> for DenseMatrixView<'a
 impl<'a, T: Debug + Display + Copy + Sized> Array<T, (usize, usize)> for DenseMatrixMutView<'a, T> {
     fn get(&self, pos: (usize, usize)) -> &T {
         if self.column_major {
-            &self.values[(pos.0 + pos.1 * self.stride)]
+            &self.values[pos.0 + pos.1 * self.stride]
         } else {
-            &self.values[(pos.0 * self.stride + pos.1)]
+            &self.values[pos.0 * self.stride + pos.1]
         }
     }
 
@@ -519,9 +519,9 @@ impl<'a, T: Debug + Display + Copy + Sized> MutArray<T, (usize, usize)>
 {
     fn set(&mut self, pos: (usize, usize), x: T) {
         if self.column_major {
-            self.values[(pos.0 + pos.1 * self.stride)] = x;
+            self.values[pos.0 + pos.1 * self.stride] = x;
         } else {
-            self.values[(pos.0 * self.stride + pos.1)] = x;
+            self.values[pos.0 * self.stride + pos.1] = x;
         }
     }
 

src/linalg/basic/vector.rs

@@ -15,6 +15,25 @@ pub struct VecView<'a, T: Debug + Display + Copy + Sized> {
     ptr: &'a [T],
 }
 
+impl<T: Debug + Display + Copy + Sized> Array<T, usize> for &[T] {
+    fn get(&self, i: usize) -> &T {
+        &self[i]
+    }
+
+    fn shape(&self) -> usize {
+        self.len()
+    }
+
+    fn is_empty(&self) -> bool {
+        self.len() > 0
+    }
+
+    fn iterator<'b>(&'b self, axis: u8) -> Box<dyn Iterator<Item = &'b T> + 'b> {
+        assert!(axis == 0, "For one dimensional array `axis` should == 0");
+        Box::new(self.iter())
+    }
+}
+
 impl<T: Debug + Display + Copy + Sized> Array<T, usize> for Vec<T> {
     fn get(&self, i: usize) -> &T {
         &self[i]
@@ -46,6 +65,7 @@ impl<T: Debug + Display + Copy + Sized> MutArray<T, usize> for Vec<T> {
 }
 
 impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for Vec<T> {}
+impl<T: Debug + Display + Copy + Sized> ArrayView1<T> for &[T] {}
 
 impl<T: Debug + Display + Copy + Sized> MutArrayView1<T> for Vec<T> {}
 

src/model_selection/kfold.rs

@@ -283,9 +283,7 @@ mod tests {
             (vec![0, 1, 2, 3, 7, 8, 9], vec![4, 5, 6]),
             (vec![0, 1, 2, 3, 4, 5, 6], vec![7, 8, 9]),
         ];
-        for ((train, test), (expected_train, expected_test)) in
+        for ((train, test), (expected_train, expected_test)) in k.split(&x).zip(expected) {
-            k.split(&x).into_iter().zip(expected)
-        {
             assert_eq!(test, expected_test);
             assert_eq!(train, expected_train);
         }
@@ -307,9 +305,7 @@ mod tests {
             (vec![0, 1, 2, 3, 7, 8, 9], vec![4, 5, 6]),
             (vec![0, 1, 2, 3, 4, 5, 6], vec![7, 8, 9]),
         ];
-        for ((train, test), (expected_train, expected_test)) in
+        for ((train, test), (expected_train, expected_test)) in k.split(&x).zip(expected) {
-            k.split(&x).into_iter().zip(expected)
-        {
             assert_eq!(test.len(), expected_test.len());
             assert_eq!(train.len(), expected_train.len());
         }

src/readers/csv.rs

@@ -83,7 +83,7 @@ where
     Matrix: Array2<T>,
 {
     let csv_text = read_string_from_source(source)?;
-    let rows: Vec<Vec<T>> = extract_row_vectors_from_csv_text::<T, RowVector, Matrix>(
+    let rows: Vec<Vec<T>> = extract_row_vectors_from_csv_text(
         &csv_text,
         &definition,
         detect_row_format(&csv_text, &definition)?,
@@ -103,12 +103,7 @@ where
 
 /// Given a string containing the contents of a csv file, extract its value
 /// into row-vectors.
-fn extract_row_vectors_from_csv_text<
+fn extract_row_vectors_from_csv_text<'a, T: Number + RealNumber + std::str::FromStr>(
-    'a,
-    T: Number + RealNumber + std::str::FromStr,
-    RowVector: Array1<T>,
-    Matrix: Array2<T>,
->(
     csv_text: &'a str,
     definition: &'a CSVDefinition<'_>,
     row_format: CSVRowFormat<'_>,
@@ -305,12 +300,11 @@ mod tests {
     }
     mod extract_row_vectors_from_csv_text {
         use super::super::{extract_row_vectors_from_csv_text, CSVDefinition, CSVRowFormat};
-        use crate::linalg::basic::matrix::DenseMatrix;
 
         #[test]
         fn read_default_csv() {
             assert_eq!(
-                extract_row_vectors_from_csv_text::<f64, Vec<_>, DenseMatrix<_>>(
+                extract_row_vectors_from_csv_text::<f64>(
                     "column 1, column 2, column3\n1.0,2.0,3.0\n4.0,5.0,6.0",
                     &CSVDefinition::default(),
                     CSVRowFormat {

src/svm/svc.rs

@@ -322,19 +322,26 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX> + 'a, Y: Array
         let (n, _) = x.shape();
         let mut y_hat: Vec<TX> = Array1::zeros(n);
 
+        let mut row = Vec::with_capacity(n);
         for i in 0..n {
-            let row_pred: TX =
+            row.clear();
-                self.predict_for_row(Vec::from_iterator(x.get_row(i).iterator(0).copied(), n));
+            row.extend(x.get_row(i).iterator(0).copied());
+            let row_pred: TX = self.predict_for_row(&row);
             y_hat.set(i, row_pred);
         }
 
         Ok(y_hat)
     }
 
-    fn predict_for_row(&self, x: Vec<TX>) -> TX {
+    fn predict_for_row(&self, x: &[TX]) -> TX {
         let mut f = self.b.unwrap();
 
+        let xi: Vec<_> = x.iter().map(|e| e.to_f64().unwrap()).collect();
         for i in 0..self.instances.as_ref().unwrap().len() {
+            let xj: Vec<_> = self.instances.as_ref().unwrap()[i]
+                .iter()
+                .map(|e| e.to_f64().unwrap())
+                .collect();
             f += self.w.as_ref().unwrap()[i]
                 * TX::from(
                     self.parameters
@@ -343,13 +350,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX> + 'a, Y: Array
                         .kernel
                         .as_ref()
                         .unwrap()
-                        .apply(
+                        .apply(&xi, &xj)
-                            &x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                            &self.instances.as_ref().unwrap()[i]
-                                .iter()
-                                .map(|e| e.to_f64().unwrap())
-                                .collect(),
-                        )
                         .unwrap(),
                 )
                 .unwrap();
@@ -472,14 +473,12 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
         let tol = self.parameters.tol;
         let good_enough = TX::from_i32(1000).unwrap();
 
+        let mut x = Vec::with_capacity(n);
         for _ in 0..self.parameters.epoch {
             for i in self.permutate(n) {
-                self.process(
+                x.clear();
-                    i,
+                x.extend(self.x.get_row(i).iterator(0).take(n).copied());
-                    Vec::from_iterator(self.x.get_row(i).iterator(0).copied(), n),
+                self.process(i, &x, *self.y.get(i), &mut cache);
-                    *self.y.get(i),
-                    &mut cache,
-                );
                 loop {
                     self.reprocess(tol, &mut cache);
                     self.find_min_max_gradient();
@@ -511,24 +510,17 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
         let mut cp = 0;
         let mut cn = 0;
 
+        let mut x = Vec::with_capacity(n);
         for i in self.permutate(n) {
+            x.clear();
+            x.extend(self.x.get_row(i).iterator(0).take(n).copied());
             if *self.y.get(i) == TY::one() && cp < few {
-                if self.process(
+                if self.process(i, &x, *self.y.get(i), cache) {
-                    i,
-                    Vec::from_iterator(self.x.get_row(i).iterator(0).copied(), n),
-                    *self.y.get(i),
-                    cache,
-                ) {
                     cp += 1;
                 }
             } else if *self.y.get(i) == TY::from(-1).unwrap()
                 && cn < few
-                && self.process(
+                && self.process(i, &x, *self.y.get(i), cache)
-                    i,
-                    Vec::from_iterator(self.x.get_row(i).iterator(0).copied(), n),
-                    *self.y.get(i),
-                    cache,
-                )
             {
                 cn += 1;
             }
@@ -539,7 +531,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
         }
     }
 
-    fn process(&mut self, i: usize, x: Vec<TX>, y: TY, cache: &mut Cache<TX, TY, X, Y>) -> bool {
+    fn process(&mut self, i: usize, x: &[TX], y: TY, cache: &mut Cache<TX, TY, X, Y>) -> bool {
         for j in 0..self.sv.len() {
             if self.sv[j].index == i {
                 return true;
@@ -551,15 +543,14 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
         let mut cache_values: Vec<((usize, usize), TX)> = Vec::new();
 
         for v in self.sv.iter() {
+            let xi: Vec<_> = v.x.iter().map(|e| e.to_f64().unwrap()).collect();
+            let xj: Vec<_> = x.iter().map(|e| e.to_f64().unwrap()).collect();
             let k = self
                 .parameters
                 .kernel
                 .as_ref()
                 .unwrap()
-                .apply(
+                .apply(&xi, &xj)
-                    &v.x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                    &x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                )
                 .unwrap();
             cache_values.push(((i, v.index), TX::from(k).unwrap()));
             g -= v.alpha * k;
@@ -578,7 +569,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
             cache.insert(v.0, v.1.to_f64().unwrap());
         }
 
-        let x_f64 = x.iter().map(|e| e.to_f64().unwrap()).collect();
+        let x_f64: Vec<_> = x.iter().map(|e| e.to_f64().unwrap()).collect();
         let k_v = self
             .parameters
             .kernel
@@ -701,8 +692,10 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                 let km = sv1.k;
                 let gm = sv1.grad;
                 let mut best = 0f64;
+                let xi: Vec<_> = sv1.x.iter().map(|e| e.to_f64().unwrap()).collect();
                 for i in 0..self.sv.len() {
                     let v = &self.sv[i];
+                    let xj: Vec<_> = v.x.iter().map(|e| e.to_f64().unwrap()).collect();
                     let z = v.grad - gm;
                     let k = cache.get(
                         sv1,
@@ -711,10 +704,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                             .kernel
                             .as_ref()
                             .unwrap()
-                            .apply(
+                            .apply(&xi, &xj)
-                                &sv1.x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                                &v.x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                            )
                             .unwrap(),
                     );
                     let mut curv = km + v.k - 2f64 * k;
@@ -732,6 +722,12 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                     }
                 }
 
+                let xi: Vec<_> = self.sv[idx_1]
+                    .x
+                    .iter()
+                    .map(|e| e.to_f64().unwrap())
+                    .collect::<Vec<_>>();
+
                 idx_2.map(|idx_2| {
                     (
                         idx_1,
@@ -742,16 +738,12 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                                 .as_ref()
                                 .unwrap()
                                 .apply(
-                                    &self.sv[idx_1]
+                                    &xi,
-                                        .x
-                                        .iter()
-                                        .map(|e| e.to_f64().unwrap())
-                                        .collect(),
                                     &self.sv[idx_2]
                                         .x
                                         .iter()
                                         .map(|e| e.to_f64().unwrap())
-                                        .collect(),
+                                        .collect::<Vec<_>>(),
                                 )
                                 .unwrap()
                         }),
@@ -765,8 +757,11 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                 let km = sv2.k;
                 let gm = sv2.grad;
                 let mut best = 0f64;
+
+                let xi: Vec<_> = sv2.x.iter().map(|e| e.to_f64().unwrap()).collect();
                 for i in 0..self.sv.len() {
                     let v = &self.sv[i];
+                    let xj: Vec<_> = v.x.iter().map(|e| e.to_f64().unwrap()).collect();
                     let z = gm - v.grad;
                     let k = cache.get(
                         sv2,
@@ -775,10 +770,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                             .kernel
                             .as_ref()
                             .unwrap()
-                            .apply(
+                            .apply(&xi, &xj)
-                                &sv2.x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                                &v.x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                            )
                             .unwrap(),
                     );
                     let mut curv = km + v.k - 2f64 * k;
@@ -797,6 +789,12 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                     }
                 }
 
+                let xj: Vec<_> = self.sv[idx_2]
+                    .x
+                    .iter()
+                    .map(|e| e.to_f64().unwrap())
+                    .collect();
+
                 idx_1.map(|idx_1| {
                     (
                         idx_1,
@@ -811,12 +809,8 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                                         .x
                                         .iter()
                                         .map(|e| e.to_f64().unwrap())
-                                        .collect(),
+                                        .collect::<Vec<_>>(),
-                                    &self.sv[idx_2]
+                                    &xj,
-                                        .x
-                                        .iter()
-                                        .map(|e| e.to_f64().unwrap())
-                                        .collect(),
                                 )
                                 .unwrap()
                         }),
@@ -835,12 +829,12 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                             .x
                             .iter()
                             .map(|e| e.to_f64().unwrap())
-                            .collect(),
+                            .collect::<Vec<_>>(),
                         &self.sv[idx_2]
                             .x
                             .iter()
                             .map(|e| e.to_f64().unwrap())
-                            .collect(),
+                            .collect::<Vec<_>>(),
                     )
                     .unwrap(),
             )),
@@ -895,7 +889,10 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
         self.sv[v1].alpha -= step.to_f64().unwrap();
         self.sv[v2].alpha += step.to_f64().unwrap();
 
+        let xi_v1: Vec<_> = self.sv[v1].x.iter().map(|e| e.to_f64().unwrap()).collect();
+        let xi_v2: Vec<_> = self.sv[v2].x.iter().map(|e| e.to_f64().unwrap()).collect();
         for i in 0..self.sv.len() {
+            let xj: Vec<_> = self.sv[i].x.iter().map(|e| e.to_f64().unwrap()).collect();
             let k2 = cache.get(
                 &self.sv[v2],
                 &self.sv[i],
@@ -903,10 +900,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                     .kernel
                     .as_ref()
                     .unwrap()
-                    .apply(
+                    .apply(&xi_v2, &xj)
-                        &self.sv[v2].x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                        &self.sv[i].x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                    )
                     .unwrap(),
             );
             let k1 = cache.get(
@@ -916,10 +910,7 @@ impl<'a, TX: Number + RealNumber, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>
                     .kernel
                     .as_ref()
                     .unwrap()
-                    .apply(
+                    .apply(&xi_v1, &xj)
-                        &self.sv[v1].x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                        &self.sv[i].x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                    )
                     .unwrap(),
             );
             self.sv[i].grad -= step.to_f64().unwrap() * (k2 - k1);

src/svm/svr.rs

@@ -248,19 +248,20 @@ impl<'a, T: Number + FloatNumber + PartialOrd, X: Array2<T>, Y: Array1<T>> SVR<'
 
         let mut y_hat: Vec<T> = Vec::<T>::zeros(n);
 
+        let mut x_i = Vec::with_capacity(n);
         for i in 0..n {
-            y_hat.set(
+            x_i.clear();
-                i,
+            x_i.extend(x.get_row(i).iterator(0).copied());
-                self.predict_for_row(Vec::from_iterator(x.get_row(i).iterator(0).copied(), n)),
+            y_hat.set(i, self.predict_for_row(&x_i));
-            );
         }
 
         Ok(y_hat)
     }
 
-    pub(crate) fn predict_for_row(&self, x: Vec<T>) -> T {
+    pub(crate) fn predict_for_row(&self, x: &[T]) -> T {
         let mut f = self.b;
 
+        let xi: Vec<_> = x.iter().map(|e| e.to_f64().unwrap()).collect();
         for i in 0..self.instances.as_ref().unwrap().len() {
             f += self.w.as_ref().unwrap()[i]
                 * T::from(
@@ -270,10 +271,7 @@ impl<'a, T: Number + FloatNumber + PartialOrd, X: Array2<T>, Y: Array1<T>> SVR<'
                         .kernel
                         .as_ref()
                         .unwrap()
-                        .apply(
+                        .apply(&xi, &self.instances.as_ref().unwrap()[i])
-                            &x.iter().map(|e| e.to_f64().unwrap()).collect(),
-                            &self.instances.as_ref().unwrap()[i],
-                        )
                         .unwrap(),
                 )
                 .unwrap()