feat: pre-release

Cargo.toml

@@ -1,8 +1,16 @@
 [package]
 name = "smartcore"
+description = "The most advanced machine learning library in rust."
+homepage = "https://smartcorelib.org"
 version = "0.1.0"
 authors = ["SmartCore Developers"]
 edition = "2018"
+license = "Apache-2.0"
+documentation = "https://docs.rs/smartcore"
+repository = "https://github.com/smartcorelib/smartcore"
+readme = "README.md"
+keywords = ["machine learning", "statistical", "modeling", "machine", "learning", "ai", "optimization", "linear algebra"]
+categories = ["science"]
 
 [features]
 default = ["datasets"]

src/algorithm/neighbour/bbd_tree.rs

@@ -101,7 +101,6 @@ impl<T: RealNumber> BBDTree<T> {
     ) -> T {
         let d = centroids[0].len();
 
-        // Determine which mean the node mean is closest to
         let mut min_dist =
             Euclidian::squared_distance(&self.nodes[node].center, &centroids[candidates[0]]);
         let mut closest = candidates[0];
@@ -114,9 +113,7 @@ impl<T: RealNumber> BBDTree<T> {
             }
         }
 
-        // If this is a non-leaf node, recurse if necessary
         if !self.nodes[node].lower.is_none() {
-            // Build the new list of candidates
             let mut new_candidates = vec![0; k];
             let mut newk = 0;
 
@@ -133,7 +130,6 @@ impl<T: RealNumber> BBDTree<T> {
                 }
             }
 
-            // Recurse if there's at least two
             if newk > 1 {
                 return self.filter(
                     self.nodes[node].lower.unwrap(),
@@ -155,7 +151,6 @@ impl<T: RealNumber> BBDTree<T> {
             }
         }
 
-        // Assigns all data within this node to a single mean
         for i in 0..d {
             sums[closest][i] = sums[closest][i] + self.nodes[node].sum[i];
         }
@@ -203,14 +198,11 @@ impl<T: RealNumber> BBDTree<T> {
     fn build_node<M: Matrix<T>>(&mut self, data: &M, begin: usize, end: usize) -> usize {
         let (_, d) = data.shape();
 
-        // Allocate the node
         let mut node = BBDTreeNode::new(d);
 
-        // Fill in basic info
         node.count = end - begin;
         node.index = begin;
 
-        // Calculate the bounding box
         let mut lower_bound = vec![T::zero(); d];
         let mut upper_bound = vec![T::zero(); d];
 
@@ -231,7 +223,6 @@ impl<T: RealNumber> BBDTree<T> {
             }
         }
 
-        // Calculate bounding box stats
         let mut max_radius = T::from(-1.).unwrap();
         let mut split_index = 0;
         for i in 0..d {
@@ -243,7 +234,6 @@ impl<T: RealNumber> BBDTree<T> {
             }
         }
 
-        // If the max spread is 0, make this a leaf node
         if max_radius < T::from(1E-10).unwrap() {
             node.lower = Option::None;
             node.upper = Option::None;
@@ -262,9 +252,6 @@ impl<T: RealNumber> BBDTree<T> {
             return self.add_node(node);
         }
 
-        // Partition the data around the midpoint in this dimension. The
-        // partitioning is done in-place by iterating from left-to-right and
-        // right-to-left in the same way that partioning is done in quicksort.
         let split_cutoff = node.center[split_index];
         let mut i1 = begin;
         let mut i2 = end - 1;
@@ -291,11 +278,9 @@ impl<T: RealNumber> BBDTree<T> {
             }
         }
 
-        // Create the child nodes
         node.lower = Option::Some(self.build_node(data, begin, begin + size));
         node.upper = Option::Some(self.build_node(data, begin + size, end));
 
-        // Calculate the new sum and opt cost
         for i in 0..d {
             node.sum[i] =
                 self.nodes[node.lower.unwrap()].sum[i] + self.nodes[node.upper.unwrap()].sum[i];

src/cluster/kmeans.rs

@@ -222,12 +222,8 @@ impl<T: RealNumber + Sum> KMeans<T> {
 
         let mut row = vec![T::zero(); m];
 
-        // pick the next center
         for j in 1..k {
-            // Loop over the samples and compare them to the most recent center.  Store
-            // the distance from each sample to its closest center in scores.
             for i in 0..n {
-                // compute the distance between this sample and the current center
                 data.copy_row_as_vec(i, &mut row);
                 let dist = Euclidian::squared_distance(&row, &centroid);
 
@@ -257,7 +253,6 @@ impl<T: RealNumber + Sum> KMeans<T> {
 
         for i in 0..n {
             data.copy_row_as_vec(i, &mut row);
-            // compute the distance between this sample and the current center
             let dist = Euclidian::squared_distance(&row, &centroid);
 
             if dist < d[i] {

src/linalg/evd.rs

@@ -103,9 +103,7 @@ fn tred2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec
         d[i] = V.get(n - 1, i);
     }
 
-    // Householder reduction to tridiagonal form.
     for i in (1..n).rev() {
-        // Scale to avoid under/overflow.
         let mut scale = T::zero();
         let mut h = T::zero();
         for k in 0..i {
@@ -119,7 +117,6 @@ fn tred2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec
                 V.set(j, i, T::zero());
             }
         } else {
-            // Generate Householder vector.
             for k in 0..i {
                 d[k] = d[k] / scale;
                 h = h + d[k] * d[k];
@@ -136,7 +133,6 @@ fn tred2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec
                 e[j] = T::zero();
             }
 
-            // Apply similarity transformation to remaining columns.
             for j in 0..i {
                 f = d[j];
                 V.set(j, i, f);
@@ -169,7 +165,6 @@ fn tred2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec
         d[i] = h;
     }
 
-    // Accumulate transformations.
     for i in 0..n - 1 {
         V.set(n - 1, i, V.get(i, i));
         V.set(i, i, T::one());
@@ -210,7 +205,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
     let mut f = T::zero();
     let mut tst1 = T::zero();
     for l in 0..n {
-        // Find small subdiagonal element
         tst1 = T::max(tst1, d[l].abs() + e[l].abs());
 
         let mut m = l;
@@ -226,8 +220,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
             }
         }
 
-        // If m == l, d[l] is an eigenvalue,
-        // otherwise, iterate.
         if m > l {
             let mut iter = 0;
             loop {
@@ -236,7 +228,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
                     panic!("Too many iterations");
                 }
 
-                // Compute implicit shift
                 let mut g = d[l];
                 let mut p = (d[l + 1] - g) / (T::two() * e[l]);
                 let mut r = p.hypot(T::one());
@@ -252,7 +243,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
                 }
                 f = f + h;
 
-                // Implicit QL transformation.
                 p = d[m];
                 let mut c = T::one();
                 let mut c2 = c;
@@ -273,7 +263,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
                     p = c * d[i] - s * g;
                     d[i + 1] = h + s * (c * g + s * d[i]);
 
-                    // Accumulate transformation.
                     for k in 0..n {
                         h = V.get(k, i + 1);
                         V.set(k, i + 1, s * V.get(k, i) + c * h);
@@ -284,7 +273,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
                 e[l] = s * p;
                 d[l] = c * p;
 
-                // Check for convergence.
                 if e[l].abs() <= tst1 * T::epsilon() {
                     break;
                 }
@@ -294,7 +282,6 @@ fn tql2<T: RealNumber, M: BaseMatrix<T>>(V: &mut M, d: &mut Vec<T>, e: &mut Vec<
         e[l] = T::zero();
     }
 
-    // Sort eigenvalues and corresponding vectors.
     for i in 0..n - 1 {
         let mut k = i;
         let mut p = d[i];