merge development

Author: Montana Low

.github/workflows/ci.yml

@@ -2,23 +2,24 @@ name: CI
 
 on:
   push:
-    branches: [ main, development ]
+    branches: [main, development]
   pull_request:
-    branches: [ development ]
+    branches: [development]
 
 jobs:
   tests:
     runs-on: "${{ matrix.platform.os }}-latest"
     strategy:
       matrix:
-        platform: [
-          { os: "windows", target: "x86_64-pc-windows-msvc" },
-          { os: "windows", target: "i686-pc-windows-msvc" },
-          { os: "ubuntu", target: "x86_64-unknown-linux-gnu" },
-          { os: "ubuntu", target: "i686-unknown-linux-gnu" },
-          { os: "ubuntu", target: "wasm32-unknown-unknown" },
-          { os: "macos", target: "aarch64-apple-darwin" },
-        ]    
+        platform:
+          [
+            { os: "windows", target: "x86_64-pc-windows-msvc" },
+            { os: "windows", target: "i686-pc-windows-msvc" },
+            { os: "ubuntu", target: "x86_64-unknown-linux-gnu" },
+            { os: "ubuntu", target: "i686-unknown-linux-gnu" },
+            { os: "ubuntu", target: "wasm32-unknown-unknown" },
+            { os: "macos", target: "aarch64-apple-darwin" },
+          ]
     env:
       TZ: "/usr/share/zoneinfo/your/location"
     steps:
@@ -40,7 +41,7 @@ jobs:
           default: true
       - name: Install test runner for wasm
         if: matrix.platform.target == 'wasm32-unknown-unknown'
-        run:  curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
+        run: curl https://rustwasm.github.io/wasm-pack/installer/init.sh -sSf | sh
       - name: Stable Build
         uses: actions-rs/cargo@v1
         with:

CHANGELOG.md

@@ -6,6 +6,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## Added
+- Seeds to multiple algorithims that depend on random number generation.
+- Added feature `js` to use WASM in browser
+
+## BREAKING CHANGE
+- Added a new parameter to `train_test_split` to define the seed.
+
+## [0.2.1] - 2022-05-10
+
 ## Added
 - L2 regularization penalty to the Logistic Regression
 - Getters for the naive bayes structs

Cargo.toml

@@ -16,21 +16,26 @@ categories = ["science"]
 default = ["datasets", "serde"]
 ndarray-bindings = ["ndarray"]
 nalgebra-bindings = ["nalgebra"]
-datasets = ["rand_distr"]
+datasets = ["rand_distr", "std"]
 fp_bench = ["itertools"]
+std = ["rand/std", "rand/std_rng"]
+# wasm32 only
+js = ["getrandom/js"]
 
 [dependencies]
 approx = "0.5.1"
+cfg-if = "1.0.0"
 itertools = { version = "0.10.3", optional = true }
 ndarray = { version = "0.15", optional = true }
 nalgebra = { version = "0.31", optional = true }
 num-traits = "0.2.12"
 num = "0.4"
-rand = "0.8.3"
+rand = { version = "0.8", default-features = false, features = ["small_rng"] }
 rand_distr = { version = "0.4", optional = true }
 serde = { version = "1", features = ["derive"], optional = true }
+
 [target.'cfg(target_arch = "wasm32")'.dependencies]
-getrandom = { version = "0.2", features = ["js"] }
+getrandom = { version = "0.2", optional = true }
 
 [dev-dependencies]
 smartcore = { path = ".", features = ["fp_bench"] }

src/algorithm/neighbour/mod.rs

@@ -59,6 +59,12 @@ pub enum KNNAlgorithmName {
     CoverTree,
 }
 
+impl Default for KNNAlgorithmName {
+    fn default() -> Self {
+        KNNAlgorithmName::CoverTree
+    }
+}
+
 #[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
 #[derive(Debug)]
 pub(crate) enum KNNAlgorithm<T: Number, D: Distance<Vec<T>>> {

src/cluster/dbscan.rs

@@ -69,19 +69,25 @@ pub struct DBSCAN<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>, D: Dista
     _phantom_y: PhantomData<Y>,
 }
 
+#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
 #[derive(Debug, Clone)]
 /// DBSCAN clustering algorithm parameters
 pub struct DBSCANParameters<T: Number, D: Distance<Vec<T>>> {
+    #[cfg_attr(feature = "serde", serde(default))]
     /// a function that defines a distance between each pair of point in training data.
     /// This function should extend [`Distance`](../../math/distance/trait.Distance.html) trait.
     /// See [`Distances`](../../math/distance/struct.Distances.html) for a list of available functions.
     pub distance: D,
+    #[cfg_attr(feature = "serde", serde(default))]
     /// The number of samples (or total weight) in a neighborhood for a point to be considered as a core point.
     pub min_samples: usize,
+    #[cfg_attr(feature = "serde", serde(default))]
     /// The maximum distance between two samples for one to be considered as in the neighborhood of the other.
     pub eps: f64,
+    #[cfg_attr(feature = "serde", serde(default))]
     /// KNN algorithm to use.
     pub algorithm: KNNAlgorithmName,
+    #[cfg_attr(feature = "serde", serde(default))]
     _phantom_t: PhantomData<T>,
 }
 
@@ -115,6 +121,110 @@ impl<T: Number, D: Distance<Vec<T>>> DBSCANParameters<T, D> {
     }
 }
 
+/// DBSCAN grid search parameters
+#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
+#[derive(Debug, Clone)]
+pub struct DBSCANSearchParameters<T: Number, D: Distance<Vec<T>>> {
+    #[cfg_attr(feature = "serde", serde(default))]
+    /// a function that defines a distance between each pair of point in training data.
+    /// This function should extend [`Distance`](../../math/distance/trait.Distance.html) trait.
+    /// See [`Distances`](../../math/distance/struct.Distances.html) for a list of available functions.
+    pub distance: Vec<D>,
+    #[cfg_attr(feature = "serde", serde(default))]
+    /// The number of samples (or total weight) in a neighborhood for a point to be considered as a core point.
+    pub min_samples: Vec<usize>,
+    #[cfg_attr(feature = "serde", serde(default))]
+    /// The maximum distance between two samples for one to be considered as in the neighborhood of the other.
+    pub eps: Vec<f64>,
+    #[cfg_attr(feature = "serde", serde(default))]
+    /// KNN algorithm to use.
+    pub algorithm: Vec<KNNAlgorithmName>,
+    _phantom_t: PhantomData<T>,
+}
+
+/// DBSCAN grid search iterator
+pub struct DBSCANSearchParametersIterator<T: Number, D: Distance<Vec<T>>> {
+    dbscan_search_parameters: DBSCANSearchParameters<T, D>,
+    current_distance: usize,
+    current_min_samples: usize,
+    current_eps: usize,
+    current_algorithm: usize,
+}
+
+impl<T: Number, D: Distance<Vec<T>>> IntoIterator for DBSCANSearchParameters<T, D> {
+    type Item = DBSCANParameters<T, D>;
+    type IntoIter = DBSCANSearchParametersIterator<T, D>;
+
+    fn into_iter(self) -> Self::IntoIter {
+        DBSCANSearchParametersIterator {
+            dbscan_search_parameters: self,
+            current_distance: 0,
+            current_min_samples: 0,
+            current_eps: 0,
+            current_algorithm: 0,
+        }
+    }
+}
+
+impl<T: Number, D: Distance<Vec<T>>> Iterator for DBSCANSearchParametersIterator<T, D> {
+    type Item = DBSCANParameters<T, D>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        if self.current_distance == self.dbscan_search_parameters.distance.len()
+            && self.current_min_samples == self.dbscan_search_parameters.min_samples.len()
+            && self.current_eps == self.dbscan_search_parameters.eps.len()
+            && self.current_algorithm == self.dbscan_search_parameters.algorithm.len()
+        {
+            return None;
+        }
+
+        let next = DBSCANParameters {
+            distance: self.dbscan_search_parameters.distance[self.current_distance].clone(),
+            min_samples: self.dbscan_search_parameters.min_samples[self.current_min_samples],
+            eps: self.dbscan_search_parameters.eps[self.current_eps],
+            algorithm: self.dbscan_search_parameters.algorithm[self.current_algorithm].clone(),
+            _phantom_t: PhantomData,
+        };
+
+        if self.current_distance + 1 < self.dbscan_search_parameters.distance.len() {
+            self.current_distance += 1;
+        } else if self.current_min_samples + 1 < self.dbscan_search_parameters.min_samples.len() {
+            self.current_distance = 0;
+            self.current_min_samples += 1;
+        } else if self.current_eps + 1 < self.dbscan_search_parameters.eps.len() {
+            self.current_distance = 0;
+            self.current_min_samples = 0;
+            self.current_eps += 1;
+        } else if self.current_algorithm + 1 < self.dbscan_search_parameters.algorithm.len() {
+            self.current_distance = 0;
+            self.current_min_samples = 0;
+            self.current_eps = 0;
+            self.current_algorithm += 1;
+        } else {
+            self.current_distance += 1;
+            self.current_min_samples += 1;
+            self.current_eps += 1;
+            self.current_algorithm += 1;
+        }
+
+        Some(next)
+    }
+}
+
+impl<T: Number> Default for DBSCANSearchParameters<T, Euclidian<T>> {
+    fn default() -> Self {
+        let default_params = DBSCANParameters::default();
+
+        DBSCANSearchParameters {
+            distance: vec![default_params.distance],
+            min_samples: vec![default_params.min_samples],
+            eps: vec![default_params.eps],
+            algorithm: vec![default_params.algorithm],
+            _phantom_t: PhantomData,
+        }
+    }
+}
+
 impl<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>, D: Distance<Vec<TX>>> PartialEq
     for DBSCAN<TX, TY, X, Y, D>
 {
@@ -132,7 +242,7 @@ impl<T: Number> Default for DBSCANParameters<T, Euclidian<T>> {
             distance: Distances::euclidian(),
             min_samples: 5,
             eps: 0.5f64,
-            algorithm: KNNAlgorithmName::CoverTree,
+            algorithm: KNNAlgorithmName::default(),
             _phantom_t: PhantomData,
         }
     }
@@ -292,6 +402,29 @@ mod tests {
     #[cfg(feature = "serde")]
     use crate::metrics::distance::euclidian::Euclidian;
 
+    #[test]
+    fn search_parameters() {
+        let parameters = DBSCANSearchParameters {
+            min_samples: vec![10, 100],
+            eps: vec![1., 2.],
+            ..Default::default()
+        };
+        let mut iter = parameters.into_iter();
+        let next = iter.next().unwrap();
+        assert_eq!(next.min_samples, 10);
+        assert_eq!(next.eps, 1.);
+        let next = iter.next().unwrap();
+        assert_eq!(next.min_samples, 100);
+        assert_eq!(next.eps, 1.);
+        let next = iter.next().unwrap();
+        assert_eq!(next.min_samples, 10);
+        assert_eq!(next.eps, 2.);
+        let next = iter.next().unwrap();
+        assert_eq!(next.min_samples, 100);
+        assert_eq!(next.eps, 2.);
+        assert!(iter.next().is_none());
+    }
+
     #[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
     #[test]
     fn fit_predict_dbscan() {