Patch to version 0.4.0 (#257)

* uncomment test * Add random test for logistic regression * linting * Bump version * Add test for logistic regression * linting * initial commit * final * final-clean * Bump to 0.4.0 * Fix linter * cleanup * Update CHANDELOG with breaking changes * Update CHANDELOG date * Add functional methods to DenseMatrix implementation * linting * add type declaration in test * Fix Wasm tests failing * linting * fix tests * linting * Add type annotations on BBDTree constructor * fix clippy * fix clippy * fix tests * bump version * run fmt. fix changelog --------- Co-authored-by: Edmund Cape <edmund@Edmunds-MacBook-Pro.local>
smartcorelib · Mar 4, 2024 · 239c004 · 239c004
1 parent 80a93c1
commit 239c004
Show file tree

Hide file tree

Showing 45 changed files with 763 additions and 410 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.0] - 2023-04-05
+
+## Added
+- WARNING: Breaking changes!
+- `DenseMatrix` constructor now returns `Result` to avoid user instantiating inconsistent rows/cols count. Their return values need to be unwrapped with `unwrap()`, see tests
+
 ## [0.3.0] - 2022-11-09 
 
 ## Added

diff --git a/Cargo.toml b/Cargo.toml
@@ -2,7 +2,7 @@
 name = "smartcore"
 description = "Machine Learning in Rust."
 homepage = "https://smartcorelib.org"
-version = "0.3.2"
+version = "0.4.0"
 authors = ["smartcore Developers"]
 edition = "2021"
 license = "Apache-2.0"

diff --git a/src/algorithm/neighbour/bbd_tree.rs b/src/algorithm/neighbour/bbd_tree.rs
@@ -40,11 +40,11 @@ impl BBDTreeNode {
 
 impl BBDTree {
     pub fn new<T: Number, M: Array2<T>>(data: &M) -> BBDTree {
-        let nodes = Vec::new();
+        let nodes: Vec<BBDTreeNode> = Vec::new();
 
         let (n, _) = data.shape();
 
-        let index = (0..n).collect::<Vec<_>>();
+        let index = (0..n).collect::<Vec<usize>>();
 
         let mut tree = BBDTree {
             nodes,
@@ -343,7 +343,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
 
         let tree = BBDTree::new(&data);
 

diff --git a/src/algorithm/neighbour/fastpair.rs b/src/algorithm/neighbour/fastpair.rs
@@ -17,7 +17,7 @@
 ///     &[4.6, 3.1, 1.5, 0.2],
 ///     &[5.0, 3.6, 1.4, 0.2],
 ///     &[5.4, 3.9, 1.7, 0.4],
-/// ]);
+/// ]).unwrap();
 /// let fastpair = FastPair::new(&x);
 /// let closest_pair: PairwiseDistance<f64> = fastpair.unwrap().closest_pair();
 /// ```
@@ -271,7 +271,7 @@ mod tests_fastpair {
     fn dataset_has_at_least_three_points() {
         // Create a dataset which consists of only two points:
         // A(0.0, 0.0) and B(1.0, 1.0).
-        let dataset = DenseMatrix::<f64>::from_2d_array(&[&[0.0, 0.0], &[1.0, 1.0]]);
+        let dataset = DenseMatrix::<f64>::from_2d_array(&[&[0.0, 0.0], &[1.0, 1.0]]).unwrap();
 
         // We expect an error when we run `FastPair` on this dataset,
         // becuase `FastPair` currently only works on a minimum of 3
@@ -288,7 +288,7 @@ mod tests_fastpair {
 
     #[test]
     fn one_dimensional_dataset_minimal() {
-        let dataset = DenseMatrix::<f64>::from_2d_array(&[&[0.0], &[2.0], &[9.0]]);
+        let dataset = DenseMatrix::<f64>::from_2d_array(&[&[0.0], &[2.0], &[9.0]]).unwrap();
 
         let result = FastPair::new(&dataset);
         assert!(result.is_ok());
@@ -308,7 +308,8 @@ mod tests_fastpair {
 
     #[test]
     fn one_dimensional_dataset_2() {
-        let dataset = DenseMatrix::<f64>::from_2d_array(&[&[27.0], &[0.0], &[9.0], &[2.0]]);
+        let dataset =
+            DenseMatrix::<f64>::from_2d_array(&[&[27.0], &[0.0], &[9.0], &[2.0]]).unwrap();
 
         let result = FastPair::new(&dataset);
         assert!(result.is_ok());
@@ -343,7 +344,8 @@ mod tests_fastpair {
             &[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 fastpair = FastPair::new(&x);
         assert!(fastpair.is_ok());
 
@@ -516,7 +518,8 @@ mod tests_fastpair {
             &[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();
         // compute
         let fastpair = FastPair::new(&x);
         assert!(fastpair.is_ok());
@@ -564,7 +567,8 @@ mod tests_fastpair {
             &[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();
         // compute
         let fastpair = FastPair::new(&x);
         assert!(fastpair.is_ok());

diff --git a/src/cluster/dbscan.rs b/src/cluster/dbscan.rs
@@ -442,7 +442,8 @@ mod tests {
             &[2.2, 1.2],
             &[1.8, 0.8],
             &[3.0, 5.0],
-        ]);
+        ])
+        .unwrap();
 
         let expected_labels = vec![1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 0];
 
@@ -487,7 +488,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
 
         let dbscan = DBSCAN::fit(&x, Default::default()).unwrap();
 

diff --git a/src/cluster/kmeans.rs b/src/cluster/kmeans.rs
@@ -41,7 +41,7 @@
 //!            &[4.9, 2.4, 3.3, 1.0],
 //!            &[6.6, 2.9, 4.6, 1.3],
 //!            &[5.2, 2.7, 3.9, 1.4],
-//!            ]);
+//!            ]).unwrap();
 //!
 //! let kmeans = KMeans::fit(&x, KMeansParameters::default().with_k(2)).unwrap(); // Fit to data, 2 clusters
 //! let y_hat: Vec<u8> = kmeans.predict(&x).unwrap(); // use the same points for prediction
@@ -249,7 +249,7 @@ impl<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>> Predictor<X, Y>
 
 impl<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>> KMeans<TX, TY, X, Y> {
     /// Fit algorithm to _NxM_ matrix where _N_ is number of samples and _M_ is number of features.
-    /// * `data` - training instances to cluster    
+    /// * `data` - training instances to cluster
     /// * `parameters` - cluster parameters
     pub fn fit(data: &X, parameters: KMeansParameters) -> Result<KMeans<TX, TY, X, Y>, Failed> {
         let bbd = BBDTree::new(data);
@@ -424,7 +424,7 @@ mod tests {
     )]
     #[test]
     fn invalid_k() {
-        let x = DenseMatrix::from_2d_array(&[&[1, 2, 3], &[4, 5, 6]]);
+        let x = DenseMatrix::from_2d_array(&[&[1, 2, 3], &[4, 5, 6]]).unwrap();
 
         assert!(KMeans::<i32, i32, DenseMatrix<i32>, Vec<i32>>::fit(
             &x,
@@ -492,7 +492,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
 
         let kmeans = KMeans::fit(&x, Default::default()).unwrap();
 
@@ -531,7 +532,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
 
         let kmeans: KMeans<f32, f32, DenseMatrix<f32>, Vec<f32>> =
             KMeans::fit(&x, Default::default()).unwrap();

diff --git a/src/decomposition/pca.rs b/src/decomposition/pca.rs
@@ -35,7 +35,7 @@
 //!                     &[4.9, 2.4, 3.3, 1.0],
 //!                     &[6.6, 2.9, 4.6, 1.3],
 //!                     &[5.2, 2.7, 3.9, 1.4],
-//!                     ]);
+//!                     ]).unwrap();
 //!
 //! let pca = PCA::fit(&iris, PCAParameters::default().with_n_components(2)).unwrap(); // Reduce number of features to 2
 //!
@@ -443,6 +443,7 @@ mod tests {
             &[2.6, 53.0, 66.0, 10.8],
             &[6.8, 161.0, 60.0, 15.6],
         ])
+        .unwrap()
     }
     #[cfg_attr(
         all(target_arch = "wasm32", not(target_os = "wasi")),
@@ -457,7 +458,8 @@ mod tests {
             &[0.9952, 0.0588],
             &[0.0463, 0.9769],
             &[0.0752, 0.2007],
-        ]);
+        ])
+        .unwrap();
 
         let pca = PCA::fit(&us_arrests, Default::default()).unwrap();
 
@@ -500,7 +502,8 @@ mod tests {
                 -0.974080592182491,
                 0.0723250196376097,
             ],
-        ]);
+        ])
+        .unwrap();
 
         let expected_projection = DenseMatrix::from_2d_array(&[
             &[-64.8022, -11.448, 2.4949, -2.4079],
@@ -553,7 +556,8 @@ mod tests {
             &[91.5446, -22.9529, 0.402, -0.7369],
             &[118.1763, 5.5076, 2.7113, -0.205],
             &[10.4345, -5.9245, 3.7944, 0.5179],
-        ]);
+        ])
+        .unwrap();
 
         let expected_eigenvalues: Vec<f64> = vec![
             343544.6277001563,
@@ -616,7 +620,8 @@ mod tests {
                 -0.0881962972508558,
                 -0.0096011588898465,
             ],
-        ]);
+        ])
+        .unwrap();
 
         let expected_projection = DenseMatrix::from_2d_array(&[
             &[0.9856, -1.1334, 0.4443, -0.1563],
@@ -669,7 +674,8 @@ mod tests {
             &[-2.1086, -1.4248, -0.1048, -0.1319],
             &[-2.0797, 0.6113, 0.1389, -0.1841],
             &[-0.6294, -0.321, 0.2407, 0.1667],
-        ]);
+        ])
+        .unwrap();
 
         let expected_eigenvalues: Vec<f64> = vec![
             2.480241579149493,
@@ -732,7 +738,7 @@ mod tests {
     //         &[4.9, 2.4, 3.3, 1.0],
     //         &[6.6, 2.9, 4.6, 1.3],
     //         &[5.2, 2.7, 3.9, 1.4],
-    //     ]);
+    //     ]).unwrap();
 
     //     let pca = PCA::fit(&iris, Default::default()).unwrap();
 

diff --git a/src/decomposition/svd.rs b/src/decomposition/svd.rs
@@ -32,7 +32,7 @@
 //!                     &[4.9, 2.4, 3.3, 1.0],
 //!                     &[6.6, 2.9, 4.6, 1.3],
 //!                     &[5.2, 2.7, 3.9, 1.4],
-//!                     ]);
+//!                     ]).unwrap();
 //!
 //! let svd = SVD::fit(&iris, SVDParameters::default().
 //!         with_n_components(2)).unwrap(); // Reduce number of features to 2
@@ -292,15 +292,17 @@ mod tests {
             &[5.7, 81.0, 39.0, 9.3],
             &[2.6, 53.0, 66.0, 10.8],
             &[6.8, 161.0, 60.0, 15.6],
-        ]);
+        ])
+        .unwrap();
 
         let expected = DenseMatrix::from_2d_array(&[
             &[243.54655757, -18.76673788],
             &[268.36802004, -33.79304302],
             &[305.93972467, -15.39087376],
             &[197.28420365, -11.66808306],
             &[293.43187394, 1.91163633],
-        ]);
+        ])
+        .unwrap();
         let svd = SVD::fit(&x, Default::default()).unwrap();
 
         let x_transformed = svd.transform(&x).unwrap();
@@ -341,7 +343,7 @@ mod tests {
     //         &[4.9, 2.4, 3.3, 1.0],
     //         &[6.6, 2.9, 4.6, 1.3],
     //         &[5.2, 2.7, 3.9, 1.4],
-    //     ]);
+    //     ]).unwrap();
 
     //     let svd = SVD::fit(&iris, Default::default()).unwrap();
 

diff --git a/src/ensemble/random_forest_classifier.rs b/src/ensemble/random_forest_classifier.rs
@@ -33,7 +33,7 @@
 //!              &[4.9, 2.4, 3.3, 1.0],
 //!              &[6.6, 2.9, 4.6, 1.3],
 //!              &[5.2, 2.7, 3.9, 1.4],
-//!         ]);
+//!         ]).unwrap();
 //! let y = vec![
 //!              0, 0, 0, 0, 0, 0, 0, 0,
 //!              1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
@@ -660,7 +660,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
         let y = vec![0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1];
 
         let classifier = RandomForestClassifier::fit(
@@ -733,7 +734,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
         let y = vec![0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1];
 
         let classifier = RandomForestClassifier::fit(
@@ -786,7 +788,8 @@ mod tests {
             &[4.9, 2.4, 3.3, 1.0],
             &[6.6, 2.9, 4.6, 1.3],
             &[5.2, 2.7, 3.9, 1.4],
-        ]);
+        ])
+        .unwrap();
         let y = vec![0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1];
 
         let forest = RandomForestClassifier::fit(&x, &y, Default::default()).unwrap();

diff --git a/src/ensemble/random_forest_regressor.rs b/src/ensemble/random_forest_regressor.rs
@@ -29,7 +29,7 @@
 //!             &[502.601, 393.1, 251.4, 125.368, 1960., 69.564],
 //!             &[518.173, 480.6, 257.2, 127.852, 1961., 69.331],
 //!             &[554.894, 400.7, 282.7, 130.081, 1962., 70.551],
-//!         ]);
+//!         ]).unwrap();
 //! let y = vec![
 //!             83.0, 88.5, 88.2, 89.5, 96.2, 98.1, 99.0, 100.0, 101.2,
 //!             104.6, 108.4, 110.8, 112.6, 114.2, 115.7, 116.9
@@ -574,7 +574,8 @@ mod tests {
             &[502.601, 393.1, 251.4, 125.368, 1960., 69.564],
             &[518.173, 480.6, 257.2, 127.852, 1961., 69.331],
             &[554.894, 400.7, 282.7, 130.081, 1962., 70.551],
-        ]);
+        ])
+        .unwrap();
         let y = vec![
             83.0, 88.5, 88.2, 89.5, 96.2, 98.1, 99.0, 100.0, 101.2, 104.6, 108.4, 110.8, 112.6,
             114.2, 115.7, 116.9,
@@ -648,7 +649,8 @@ mod tests {
             &[502.601, 393.1, 251.4, 125.368, 1960., 69.564],
             &[518.173, 480.6, 257.2, 127.852, 1961., 69.331],
             &[554.894, 400.7, 282.7, 130.081, 1962., 70.551],
-        ]);
+        ])
+        .unwrap();
         let y = vec![
             83.0, 88.5, 88.2, 89.5, 96.2, 98.1, 99.0, 100.0, 101.2, 104.6, 108.4, 110.8, 112.6,
             114.2, 115.7, 116.9,
@@ -702,7 +704,8 @@ mod tests {
             &[502.601, 393.1, 251.4, 125.368, 1960., 69.564],
             &[518.173, 480.6, 257.2, 127.852, 1961., 69.331],
             &[554.894, 400.7, 282.7, 130.081, 1962., 70.551],
-        ]);
+        ])
+        .unwrap();
         let y = vec![
             83.0, 88.5, 88.2, 89.5, 96.2, 98.1, 99.0, 100.0, 101.2, 104.6, 108.4, 110.8, 112.6,
             114.2, 115.7, 116.9,