feat: + cross_validate, trait Predictor, refactoring

Author: Volodymyr Orlov

src/algorithm/neighbour/cover_tree.rs

@@ -6,6 +6,7 @@
 //! use smartcore::algorithm::neighbour::cover_tree::*;
 //! use smartcore::math::distance::Distance;
 //!
+//! #[derive(Clone)]
 //! struct SimpleDistance {} // Our distance function
 //!
 //! impl Distance<i32, f64> for SimpleDistance {
@@ -453,7 +454,7 @@ mod tests {
     use super::*;
     use crate::math::distance::Distances;
 
-    #[derive(Debug, Serialize, Deserialize)]
+    #[derive(Debug, Serialize, Deserialize, Clone)]
     struct SimpleDistance {}
 
     impl Distance<i32, f64> for SimpleDistance {

src/algorithm/neighbour/linear_search.rs

@@ -5,6 +5,7 @@
 //! use smartcore::algorithm::neighbour::linear_search::*;
 //! use smartcore::math::distance::Distance;
 //!
+//! #[derive(Clone)]
 //! struct SimpleDistance {} // Our distance function
 //!
 //! impl Distance<i32, f64> for SimpleDistance {
@@ -137,6 +138,7 @@ mod tests {
     use super::*;
     use crate::math::distance::Distances;
 
+    #[derive(Debug, Serialize, Deserialize, Clone)]
     struct SimpleDistance {}
 
     impl Distance<i32, f64> for SimpleDistance {

src/base.rs

@@ -0,0 +1,10 @@
+//! # Common Interfaces and methods
+//!
+//! This module consolidates interfaces and uniform basic API that is used elsewhere in the code.
+
+use crate::error::Failed;
+
+/// Implements method predict that offers a way to estimate target value from new data
+pub trait Predictor<X, Y> {
+    fn predict(&self, x: &X) -> Result<Y, Failed>;
+}

src/ensemble/random_forest_classifier.rs

@@ -9,7 +9,7 @@
 //!
 //! ```
 //! use smartcore::linalg::naive::dense_matrix::*;
-//! use smartcore::ensemble::random_forest_classifier::*;
+//! use smartcore::ensemble::random_forest_classifier::RandomForestClassifier;
 //!
 //! // Iris dataset
 //! let x = DenseMatrix::from_2d_array(&[
@@ -51,6 +51,7 @@ use std::fmt::Debug;
 use rand::Rng;
 use serde::{Deserialize, Serialize};
 
+use crate::base::Predictor;
 use crate::error::Failed;
 use crate::linalg::Matrix;
 use crate::math::num::RealNumber;
@@ -117,6 +118,12 @@ impl Default for RandomForestClassifierParameters {
     }
 }
 
+impl<T: RealNumber, M: Matrix<T>> Predictor<M, M::RowVector> for RandomForestClassifier<T> {
+    fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
+        self.predict(x)
+    }
+}
+
 impl<T: RealNumber> RandomForestClassifier<T> {
     /// Build a forest of trees from the training set.
     /// * `x` - _NxM_ matrix with _N_ observations and _M_ features in each observation.

src/ensemble/random_forest_regressor.rs

@@ -49,6 +49,7 @@ use std::fmt::Debug;
 use rand::Rng;
 use serde::{Deserialize, Serialize};
 
+use crate::base::Predictor;
 use crate::error::Failed;
 use crate::linalg::Matrix;
 use crate::math::num::RealNumber;
@@ -106,6 +107,12 @@ impl<T: RealNumber> PartialEq for RandomForestRegressor<T> {
     }
 }
 
+impl<T: RealNumber, M: Matrix<T>> Predictor<M, M::RowVector> for RandomForestRegressor<T> {
+    fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
+        self.predict(x)
+    }
+}
+
 impl<T: RealNumber> RandomForestRegressor<T> {
     /// Build a forest of trees from the training set.
     /// * `x` - _NxM_ matrix with _N_ observations and _M_ features in each observation.

src/lib.rs

@@ -63,14 +63,15 @@
 //! let y = vec![2., 2., 2., 3., 3.];
 //!
 //! // Train classifier
-//! let knn = KNNClassifier::fit(&x, &y, Distances::euclidian(), Default::default()).unwrap();
+//! let knn = KNNClassifier::fit(&x, &y, Default::default()).unwrap();
 //!
 //! // Predict classes
 //! let y_hat = knn.predict(&x).unwrap();
 //! ```
 
 /// Various algorithms and helper methods that are used elsewhere in SmartCore
 pub mod algorithm;
+pub(crate) mod base;
 /// Algorithms for clustering of unlabeled data
 pub mod cluster;
 /// Various datasets

src/linalg/mod.rs

@@ -274,6 +274,19 @@ pub trait BaseVector<T: RealNumber>: Clone + Debug {
 
     /// Copies content of `other` vector.
     fn copy_from(&mut self, other: &Self);
+
+    /// Take elements from an array.
+    fn take(&self, index: &[usize]) -> Self {
+        let n = index.len();
+
+        let mut result = Self::zeros(n);
+
+        for i in 0..n {
+            result.set(i, self.get(index[i]));
+        }
+
+        result
+    }
 }
 
 /// Generic matrix type.
@@ -611,6 +624,32 @@ pub trait BaseMatrix<T: RealNumber>: Clone + Debug {
 
     /// Calculates the covariance matrix
     fn cov(&self) -> Self;
+
+    /// Take elements from an array along an axis.
+    fn take(&self, index: &[usize], axis: u8) -> Self {
+        let (n, p) = self.shape();
+
+        let k = match axis {
+            0 => p,
+            _ => n,
+        };
+
+        let mut result = match axis {
+            0 => Self::zeros(index.len(), p),
+            _ => Self::zeros(n, index.len()),
+        };
+
+        for i in 0..index.len() {
+            for j in 0..k {
+                match axis {
+                    0 => result.set(i, j, self.get(index[i], j)),
+                    _ => result.set(j, i, self.get(j, index[i])),
+                };
+            }
+        }
+
+        result
+    }
 }
 
 /// Generic matrix with additional mixins like various factorization methods.
@@ -662,6 +701,8 @@ impl<'a, T: RealNumber, M: BaseMatrix<T>> Iterator for RowIter<'a, T, M> {
 
 #[cfg(test)]
 mod tests {
+    use crate::linalg::naive::dense_matrix::DenseMatrix;
+    use crate::linalg::BaseMatrix;
     use crate::linalg::BaseVector;
 
     #[test]
@@ -684,4 +725,35 @@ mod tests {
 
         assert!((m.var() - 1.25f64).abs() < std::f64::EPSILON);
     }
+
+    #[test]
+    fn vec_take() {
+        let m = vec![1., 2., 3., 4., 5.];
+
+        assert_eq!(m.take(&vec!(0, 0, 4, 4)), vec![1., 1., 5., 5.]);
+    }
+
+    #[test]
+    fn take() {
+        let m = DenseMatrix::from_2d_array(&[
+            &[1.0, 2.0],
+            &[3.0, 4.0],
+            &[5.0, 6.0],
+            &[7.0, 8.0],
+            &[9.0, 10.0],
+        ]);
+
+        let expected_0 = DenseMatrix::from_2d_array(&[&[3.0, 4.0], &[3.0, 4.0], &[7.0, 8.0]]);
+
+        let expected_1 = DenseMatrix::from_2d_array(&[
+            &[2.0, 1.0],
+            &[4.0, 3.0],
+            &[6.0, 5.0],
+            &[8.0, 7.0],
+            &[10.0, 9.0],
+        ]);
+
+        assert_eq!(m.take(&vec!(1, 1, 3), 0), expected_0);
+        assert_eq!(m.take(&vec!(1, 0), 1), expected_1);
+    }
 }

src/linalg/ndarray_bindings.rs

@@ -36,7 +36,7 @@
 //!             1., 1., 1., 1., 1., 1., 1., 1., 1., 1.
 //!         ]);
 //!
-//! let lr = LogisticRegression::fit(&x, &y).unwrap();
+//! let lr = LogisticRegression::fit(&x, &y, Default::default()).unwrap();
 //! let y_hat = lr.predict(&x).unwrap();
 //! ```
 use std::iter::Sum;
@@ -917,7 +917,7 @@ mod tests {
             0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,
         ]);
 
-        let lr = LogisticRegression::fit(&x, &y).unwrap();
+        let lr = LogisticRegression::fit(&x, &y, Default::default()).unwrap();
 
         let y_hat = lr.predict(&x).unwrap();
 

src/linear/elastic_net.rs

@@ -58,6 +58,7 @@ use std::fmt::Debug;
 
 use serde::{Deserialize, Serialize};
 
+use crate::base::Predictor;
 use crate::error::Failed;
 use crate::linalg::BaseVector;
 use crate::linalg::Matrix;
@@ -66,7 +67,7 @@ use crate::math::num::RealNumber;
 use crate::linear::lasso_optimizer::InteriorPointOptimizer;
 
 /// Elastic net parameters
-#[derive(Serialize, Deserialize, Debug)]
+#[derive(Serialize, Deserialize, Debug, Clone)]
 pub struct ElasticNetParameters<T: RealNumber> {
     /// Regularization parameter.
     pub alpha: T,
@@ -108,6 +109,12 @@ impl<T: RealNumber, M: Matrix<T>> PartialEq for ElasticNet<T, M> {
     }
 }
 
+impl<T: RealNumber, M: Matrix<T>> Predictor<M, M::RowVector> for ElasticNet<T, M> {
+    fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
+        self.predict(x)
+    }
+}
+
 impl<T: RealNumber, M: Matrix<T>> ElasticNet<T, M> {
     /// Fits elastic net regression to your data.
     /// * `x` - _NxM_ matrix with _N_ observations and _M_ features in each observation.

src/linear/lasso.rs

@@ -26,14 +26,15 @@ use std::fmt::Debug;
 
 use serde::{Deserialize, Serialize};
 
+use crate::base::Predictor;
 use crate::error::Failed;
 use crate::linalg::BaseVector;
 use crate::linalg::Matrix;
 use crate::linear::lasso_optimizer::InteriorPointOptimizer;
 use crate::math::num::RealNumber;
 
 /// Lasso regression parameters
-#[derive(Serialize, Deserialize, Debug)]
+#[derive(Serialize, Deserialize, Debug, Clone)]
 pub struct LassoParameters<T: RealNumber> {
     /// Controls the strength of the penalty to the loss function.
     pub alpha: T,
@@ -71,6 +72,12 @@ impl<T: RealNumber, M: Matrix<T>> PartialEq for Lasso<T, M> {
     }
 }
 
+impl<T: RealNumber, M: Matrix<T>> Predictor<M, M::RowVector> for Lasso<T, M> {
+    fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
+        self.predict(x)
+    }
+}
+
 impl<T: RealNumber, M: Matrix<T>> Lasso<T, M> {
     /// Fits Lasso regression to your data.
     /// * `x` - _NxM_ matrix with _N_ observations and _M_ features in each observation.