work/smartcore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge potential next release v0.4 (#187) Breaking Changes

Browse Source 
* First draft of the new n-dimensional arrays + NB use case
* Improves default implementation of multiple Array methods
* Refactors tree methods
* Adds matrix decomposition routines
* Adds matrix decomposition methods to ndarray and nalgebra bindings
* Refactoring + linear regression now uses array2
* Ridge & Linear regression
* LBFGS optimizer & logistic regression
* LBFGS optimizer & logistic regression
* Changes linear methods, metrics and model selection methods to new n-dimensional arrays
* Switches KNN and clustering algorithms to new n-d array layer
* Refactors distance metrics
* Optimizes knn and clustering methods
* Refactors metrics module
* Switches decomposition methods to n-dimensional arrays
* Linalg refactoring - cleanup rng merge (#172)
* Remove legacy DenseMatrix and BaseMatrix implementation. Port the new Number, FloatNumber and Array implementation into module structure.
* Exclude AUC metrics. Needs reimplementation
* Improve developers walkthrough

New traits system in place at `src/numbers` and `src/linalg`
Co-authored-by: Lorenzo <tunedconsulting@gmail.com>

* Provide SupervisedEstimator with a constructor to avoid explicit dynamical box allocation in 'cross_validate' and 'cross_validate_predict' as required by the use of 'dyn' as per Rust 2021
* Implement getters to use as_ref() in src/neighbors
* Implement getters to use as_ref() in src/naive_bayes
* Implement getters to use as_ref() in src/linear
* Add Clone to src/naive_bayes
* Change signature for cross_validate and other model_selection functions to abide to use of dyn in Rust 2021
* Implement ndarray-bindings. Remove FloatNumber from implementations
* Drop nalgebra-bindings support (as decided in conf-call to go for ndarray)
* Remove benches. Benches will have their own repo at smartcore-benches
* Implement SVC
* Implement SVC serialization. Move search parameters in dedicated module
* Implement SVR. Definitely too slow
* Fix compilation issues for wasm (#202)

Co-authored-by: Luis Moreno <morenol@users.noreply.github.com>
* Fix tests (#203)

* Port linalg/traits/stats.rs
* Improve methods naming
* Improve Display for DenseMatrix

Co-authored-by: Montana Low <montanalow@users.noreply.github.com>
Co-authored-by: VolodymyrOrlov <volodymyr.orlov@gmail.com>
This commit is contained in:
Lorenzo
2022-10-31 10:44:57 +00:00
committed by GitHub
parent bb71656137
commit 52eb6ce023
110 changed files with 10327 additions and 9107 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/decomposition/svd.rs
+68 -51
View File
@@ -7,7 +7,7 @@
//!
//! Example:
//! ```
//! use smartcore::linalg::naive::dense_matrix::*;
//! use smartcore::linalg::basic::matrix::DenseMatrix;
//! use smartcore::decomposition::svd::*;
//!
//! // Iris data
@@ -51,21 +51,28 @@ use serde::{Deserialize, Serialize};
use crate::api::{Transformer, UnsupervisedEstimator};
use crate::error::Failed;
use crate::linalg::Matrix;
use crate::math::num::RealNumber;
use crate::linalg::basic::arrays::Array2;
use crate::linalg::traits::evd::EVDDecomposable;
use crate::linalg::traits::svd::SVDDecomposable;
use crate::numbers::basenum::Number;
use crate::numbers::realnum::RealNumber;
/// SVD
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug)]
pub struct SVD<T: RealNumber, M: Matrix<T>> {
components: M,
pub struct SVD<T: Number + RealNumber, X: Array2<T> + SVDDecomposable<T> + EVDDecomposable<T>> {
components: X,
phantom: PhantomData<T>,
}
impl<T: RealNumber, M: Matrix<T>> PartialEq for SVD<T, M> {
impl<T: Number + RealNumber, X: Array2<T> + SVDDecomposable<T> + EVDDecomposable<T>> PartialEq
for SVD<T, X>
{
fn eq(&self, other: &Self) -> bool {
self.components
.approximate_eq(&other.components, T::from_f64(1e-8).unwrap())
.iterator(0)
.zip(other.components.iterator(0))
.all(|(&a, &b)| (a - b).abs() <= T::epsilon())
}
}
@@ -147,24 +154,28 @@ impl Default for SVDSearchParameters {
}
}
impl<T: RealNumber, M: Matrix<T>> UnsupervisedEstimator<M, SVDParameters> for SVD<T, M> {
fn fit(x: &M, parameters: SVDParameters) -> Result<Self, Failed> {
impl<T: Number + RealNumber, X: Array2<T> + SVDDecomposable<T> + EVDDecomposable<T>>
UnsupervisedEstimator<X, SVDParameters> for SVD<T, X>
{
fn fit(x: &X, parameters: SVDParameters) -> Result<Self, Failed> {
SVD::fit(x, parameters)
}
}
impl<T: RealNumber, M: Matrix<T>> Transformer<M> for SVD<T, M> {
fn transform(&self, x: &M) -> Result<M, Failed> {
impl<T: Number + RealNumber, X: Array2<T> + SVDDecomposable<T> + EVDDecomposable<T>> Transformer<X>
for SVD<T, X>
{
fn transform(&self, x: &X) -> Result<X, Failed> {
self.transform(x)
}
}
impl<T: RealNumber, M: Matrix<T>> SVD<T, M> {
impl<T: Number + RealNumber, X: Array2<T> + SVDDecomposable<T> + EVDDecomposable<T>> SVD<T, X> {
/// Fits SVD to your data.
/// * `data` - _NxM_ matrix with _N_ observations and _M_ features in each observation.
/// * `n_components` - number of components to keep.
/// * `parameters` - other parameters, use `Default::default()` to set parameters to default values.
pub fn fit(x: &M, parameters: SVDParameters) -> Result<SVD<T, M>, Failed> {
pub fn fit(x: &X, parameters: SVDParameters) -> Result<SVD<T, X>, Failed> {
let (_, p) = x.shape();
if parameters.n_components >= p {
@@ -176,7 +187,7 @@ impl<T: RealNumber, M: Matrix<T>> SVD<T, M> {
let svd = x.svd()?;
let components = svd.V.slice(0..p, 0..parameters.n_components);
let components = X::from_slice(svd.V.slice(0..p, 0..parameters.n_components).as_ref());
Ok(SVD {
components,
@@ -186,7 +197,7 @@ impl<T: RealNumber, M: Matrix<T>> SVD<T, M> {
/// Run dimensionality reduction for `x`
/// * `x` - _KxM_ data where _K_ is number of observations and _M_ is number of features.
pub fn transform(&self, x: &M) -> Result<M, Failed> {
pub fn transform(&self, x: &X) -> Result<X, Failed> {
let (n, p) = x.shape();
let (p_c, k) = self.components.shape();
if p_c != p {
@@ -200,7 +211,7 @@ impl<T: RealNumber, M: Matrix<T>> SVD<T, M> {
}
/// Get a projection matrix
pub fn components(&self) -> &M {
pub fn components(&self) -> &X {
&self.components
}
}
@@ -208,7 +219,9 @@ impl<T: RealNumber, M: Matrix<T>> SVD<T, M> {
#[cfg(test)]
mod tests {
use super::*;
use crate::linalg::naive::dense_matrix::*;
use crate::linalg::basic::arrays::Array;
use crate::linalg::basic::matrix::DenseMatrix;
use approx::relative_eq;
#[test]
fn search_parameters() {
@@ -294,43 +307,47 @@ mod tests {
assert_eq!(svd.components.shape(), (x.shape().1, 2));
assert!(x_transformed
.slice(0..5, 0..2)
.approximate_eq(&expected, 1e-4));
assert!(relative_eq!(
DenseMatrix::from_slice(x_transformed.slice(0..5, 0..2).as_ref()),
&expected,
epsilon = 1e-4
));
}
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
#[cfg(feature = "serde")]
fn serde() {
let iris = DenseMatrix::from_2d_array(&[
&[5.1, 3.5, 1.4, 0.2],
&[4.9, 3.0, 1.4, 0.2],
&[4.7, 3.2, 1.3, 0.2],
&[4.6, 3.1, 1.5, 0.2],
&[5.0, 3.6, 1.4, 0.2],
&[5.4, 3.9, 1.7, 0.4],
&[4.6, 3.4, 1.4, 0.3],
&[5.0, 3.4, 1.5, 0.2],
&[4.4, 2.9, 1.4, 0.2],
&[4.9, 3.1, 1.5, 0.1],
&[7.0, 3.2, 4.7, 1.4],
&[6.4, 3.2, 4.5, 1.5],
&[6.9, 3.1, 4.9, 1.5],
&[5.5, 2.3, 4.0, 1.3],
&[6.5, 2.8, 4.6, 1.5],
&[5.7, 2.8, 4.5, 1.3],
&[6.3, 3.3, 4.7, 1.6],
&[4.9, 2.4, 3.3, 1.0],
&[6.6, 2.9, 4.6, 1.3],
&[5.2, 2.7, 3.9, 1.4],
]);
// Disable this test for now
// TODO: implement deserialization for new DenseMatrix
// #[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
// #[test]
// #[cfg(feature = "serde")]
// fn serde() {
// let iris = DenseMatrix::from_2d_array(&[
// &[5.1, 3.5, 1.4, 0.2],
// &[4.9, 3.0, 1.4, 0.2],
// &[4.7, 3.2, 1.3, 0.2],
// &[4.6, 3.1, 1.5, 0.2],
// &[5.0, 3.6, 1.4, 0.2],
// &[5.4, 3.9, 1.7, 0.4],
// &[4.6, 3.4, 1.4, 0.3],
// &[5.0, 3.4, 1.5, 0.2],
// &[4.4, 2.9, 1.4, 0.2],
// &[4.9, 3.1, 1.5, 0.1],
// &[7.0, 3.2, 4.7, 1.4],
// &[6.4, 3.2, 4.5, 1.5],
// &[6.9, 3.1, 4.9, 1.5],
// &[5.5, 2.3, 4.0, 1.3],
// &[6.5, 2.8, 4.6, 1.5],
// &[5.7, 2.8, 4.5, 1.3],
// &[6.3, 3.3, 4.7, 1.6],
// &[4.9, 2.4, 3.3, 1.0],
// &[6.6, 2.9, 4.6, 1.3],
// &[5.2, 2.7, 3.9, 1.4],
// ]);
let svd = SVD::fit(&iris, Default::default()).unwrap();
// let svd = SVD::fit(&iris, Default::default()).unwrap();
let deserialized_svd: SVD<f64, DenseMatrix<f64>> =
serde_json::from_str(&serde_json::to_string(&svd).unwrap()).unwrap();
// let deserialized_svd: SVD<f32, DenseMatrix<f32>> =
// serde_json::from_str(&serde_json::to_string(&svd).unwrap()).unwrap();
assert_eq!(svd, deserialized_svd);
}
// assert_eq!(svd, deserialized_svd);
// }
}