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

* 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>
2022-10-31 10:44:57 +00:00
parent bb71656137
commit 52eb6ce023
110 changed files with 10327 additions and 9107 deletions
@@ -0,0 +1,51 @@
+use num_traits::{Bounded, FromPrimitive, Num, NumCast, ToPrimitive};
+use std::fmt::{Debug, Display};
+use std::iter::{Product, Sum};
+use std::ops::{AddAssign, DivAssign, MulAssign, SubAssign};
+
+/// Define a `Number` set that acquires traits from `num_traits` to make available a base trait  
+/// to be used by other usable sets like `FloatNumber`.
+pub trait Number:
+    Num
+    + FromPrimitive
+    + ToPrimitive
+    + Debug
+    + Display
+    + Copy
+    + Sum
+    + Product
+    + AddAssign
+    + SubAssign
+    + MulAssign
+    + DivAssign
+    + Bounded
+    + NumCast
+{
+}
+
+impl Number for f64 {}
+impl Number for f32 {}
+impl Number for i8 {}
+impl Number for i16 {}
+impl Number for i32 {}
+impl Number for i64 {}
+impl Number for u8 {}
+impl Number for u16 {}
+impl Number for u32 {}
+impl Number for u64 {}
+impl Number for usize {}
+
+#[cfg(test)]
+mod tests {
+    use std::str::FromStr;
+
+    #[test]
+    fn i32_from_string() {
+        assert_eq!(i32::from_str("1").unwrap(), 1)
+    }
+
+    #[test]
+    fn i8_from_string() {
+        assert_eq!(i8::from_str("1").unwrap(), 1)
+    }
+}
@@ -0,0 +1,117 @@
+use rand::Rng;
+
+use num_traits::{Float, Signed};
+
+use crate::numbers::basenum::Number;
+
+/// Defines float number
+/// <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS_CHTML"></script>
+pub trait FloatNumber: Number + Float + Signed {
+    /// Copy sign from `sign` - another real number
+    fn copysign(self, sign: Self) -> Self;
+
+    /// Calculates natural \\( \ln(1+e^x) \\) without overflow.
+    fn ln_1pe(self) -> Self;
+
+    /// Efficient implementation of Sigmoid function, \\( S(x) = \frac{1}{1 + e^{-x}} \\), see [Sigmoid function](https://en.wikipedia.org/wiki/Sigmoid_function)
+    fn sigmoid(self) -> Self;
+
+    /// Returns pseudorandom number between 0 and 1
+    fn rand() -> Self;
+
+    /// Returns 2
+    fn two() -> Self;
+
+    /// Returns .5
+    fn half() -> Self;
+
+    /// Returns \\( x^2 \\)
+    fn square(self) -> Self {
+        self * self
+    }
+
+    /// Raw transmutation to u64
+    fn to_f32_bits(self) -> u32;
+}
+
+impl FloatNumber for f64 {
+    fn copysign(self, sign: Self) -> Self {
+        self.copysign(sign)
+    }
+
+    fn ln_1pe(self) -> f64 {
+        if self > 15. {
+            self
+        } else {
+            self.exp().ln_1p()
+        }
+    }
+
+    fn sigmoid(self) -> f64 {
+        if self < -40. {
+            0.
+        } else if self > 40. {
+            1.
+        } else {
+            1. / (1. + f64::exp(-self))
+        }
+    }
+
+    fn rand() -> f64 {
+        let mut rng = rand::thread_rng();
+        rng.gen()
+    }
+
+    fn two() -> Self {
+        2f64
+    }
+
+    fn half() -> Self {
+        0.5f64
+    }
+
+    fn to_f32_bits(self) -> u32 {
+        self.to_bits() as u32
+    }
+}
+
+impl FloatNumber for f32 {
+    fn copysign(self, sign: Self) -> Self {
+        self.copysign(sign)
+    }
+
+    fn ln_1pe(self) -> f32 {
+        if self > 15. {
+            self
+        } else {
+            self.exp().ln_1p()
+        }
+    }
+
+    fn sigmoid(self) -> f32 {
+        if self < -40. {
+            0.
+        } else if self > 40. {
+            1.
+        } else {
+            1. / (1. + f32::exp(-self))
+        }
+    }
+
+    fn rand() -> f32 {
+        let mut rng = rand::thread_rng();
+        rng.gen()
+    }
+
+    fn two() -> Self {
+        2f32
+    }
+
+    fn half() -> Self {
+        0.5f32
+    }
+
+    fn to_f32_bits(self) -> u32 {
+        self.to_bits()
+    }
+}
@@ -0,0 +1,10 @@
+// this module has been ported from https://github.com/smartcorelib/smartcore/pull/108
+
+/// Base `Number` from `std` and `num-traits`
+pub mod basenum;
+
+/// implementation for `RealNumber`
+pub mod realnum;
+
+/// implementation for `FloatNumber`
+pub mod floatnum;
@@ -0,0 +1,151 @@
+//! # Real Number
+//! Most algorithms in SmartCore rely on basic linear algebra operations like dot product, matrix decomposition and other subroutines that are defined for a set of real numbers, ℝ.
+//! This module defines real number and some useful functions that are used in [Linear Algebra](../../linalg/index.html) module.
+
+use num_traits::Float;
+
+use crate::numbers::basenum::Number;
+
+/// Defines real number
+/// <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS_CHTML"></script>
+pub trait RealNumber: Number + Float {
+    /// Copy sign from `sign` - another real number
+    fn copysign(self, sign: Self) -> Self;
+
+    /// Calculates natural \\( \ln(1+e^x) \\) without overflow.
+    fn ln_1pe(self) -> Self;
+
+    /// Efficient implementation of Sigmoid function, \\( S(x) = \frac{1}{1 + e^{-x}} \\), see [Sigmoid function](https://en.wikipedia.org/wiki/Sigmoid_function)
+    fn sigmoid(self) -> Self;
+
+    /// Returns pseudorandom number between 0 and 1
+    fn rand() -> Self;
+
+    /// Returns 2
+    fn two() -> Self;
+
+    /// Returns .5
+    fn half() -> Self;
+
+    /// Returns \\( x^2 \\)
+    fn square(self) -> Self {
+        self * self
+    }
+
+    /// Raw transmutation to u32
+    fn to_f32_bits(self) -> u32;
+
+    /// Raw transmutation to u64
+    fn to_f64_bits(self) -> u64;
+}
+
+impl RealNumber for f64 {
+    fn copysign(self, sign: Self) -> Self {
+        self.copysign(sign)
+    }
+
+    fn ln_1pe(self) -> f64 {
+        if self > 15. {
+            self
+        } else {
+            self.exp().ln_1p()
+        }
+    }
+
+    fn sigmoid(self) -> f64 {
+        if self < -40. {
+            0.
+        } else if self > 40. {
+            1.
+        } else {
+            1. / (1. + f64::exp(-self))
+        }
+    }
+
+    fn rand() -> f64 {
+        1.0
+    }
+
+    fn two() -> Self {
+        2f64
+    }
+
+    fn half() -> Self {
+        0.5f64
+    }
+
+    fn to_f32_bits(self) -> u32 {
+        self.to_bits() as u32
+    }
+
+    fn to_f64_bits(self) -> u64 {
+        self.to_bits()
+    }
+}
+
+impl RealNumber for f32 {
+    fn copysign(self, sign: Self) -> Self {
+        self.copysign(sign)
+    }
+
+    fn ln_1pe(self) -> f32 {
+        if self > 15. {
+            self
+        } else {
+            self.exp().ln_1p()
+        }
+    }
+
+    fn sigmoid(self) -> f32 {
+        if self < -40. {
+            0.
+        } else if self > 40. {
+            1.
+        } else {
+            1. / (1. + f32::exp(-self))
+        }
+    }
+
+    fn rand() -> f32 {
+        1.0
+    }
+
+    fn two() -> Self {
+        2f32
+    }
+
+    fn half() -> Self {
+        0.5f32
+    }
+
+    fn to_f32_bits(self) -> u32 {
+        self.to_bits()
+    }
+
+    fn to_f64_bits(self) -> u64 {
+        self.to_bits() as u64
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::str::FromStr;
+
+    #[test]
+    fn sigmoid() {
+        assert_eq!(1.0.sigmoid(), 0.7310585786300049);
+        assert_eq!(41.0.sigmoid(), 1.);
+        assert_eq!((-41.0).sigmoid(), 0.);
+    }
+
+    #[test]
+    fn f32_from_string() {
+        assert_eq!(f32::from_str("1.111111").unwrap(), 1.111111)
+    }
+
+    #[test]
+    fn f64_from_string() {
+        assert_eq!(f64::from_str("1.111111111").unwrap(), 1.111111111)
+    }
+}