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

Release 0.3

Browse Source
This commit is contained in:
Lorenzo (Mec-iS)
2022-11-07 12:48:44 +00:00
committed by morenol
parent 0dc97a4e9b
commit 2df0795be9
27 changed files with 83 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/DEVELOPERS.md
+4 -1
View File
@@ -1,4 +1,7 @@
# Smartcore: Introduction to modules
# smartcore: Introduction to modules
Important source of information:
* [Rust API guidelines](https://rust-lang.github.io/api-guidelines/about.html)
## Walkthrough: traits system and basic structures
CHANGELOG.md
+4 -3
View File
@@ -4,13 +4,14 @@ 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).
## [Unreleased]
## [0.3] - 2022-11
## Added
- WARNING: Breaking changes!
- Seeds to multiple algorithims that depend on random number generation.
- Added feature `js` to use WASM in browser
- Drop `nalgebra-bindings` feature
- Complete refactoring with *extensive API changes* that includes:
- Complete refactoring with **extensive API changes** that includes:
* moving to a new traits system, less structs more traits
* adapting all the modules to the new traits system
* moving towards Rust 2021, in particular the use of `dyn` and `as_ref`
@@ -19,7 +20,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## BREAKING CHANGE
- Added a new parameter to `train_test_split` to define the seed.
## [0.2.1] - 2022-05-10
## [0.2.1] - 2021-05-10
## Added
- L2 regularization penalty to the Logistic Regression
Cargo.toml
+11 -5
View File
@@ -1,9 +1,9 @@
[package]
name = "smartcore"
description = "The most advanced machine learning library in rust."
description = "Machine Learning in Rust."
homepage = "https://smartcorelib.org"
version = "0.4.0"
authors = ["SmartCore Developers"]
version = "0.3.0"
authors = ["smartcore Developers"]
edition = "2021"
license = "Apache-2.0"
documentation = "https://docs.rs/smartcore"
@@ -11,6 +11,12 @@ repository = "https://github.com/smartcorelib/smartcore"
readme = "README.md"
keywords = ["machine-learning", "statistical", "ai", "optimization", "linear-algebra"]
categories = ["science"]
exclude = [
".github",
".gitignore",
"smartcore.iml",
"smartcore.svg",
]
[dependencies]
approx = "0.5.1"
@@ -23,10 +29,10 @@ rand_distr = { version = "0.4", optional = true }
serde = { version = "1", features = ["derive"], optional = true }
[features]
default = ["serde", "datasets"]
default = []
serde = ["dep:serde"]
ndarray-bindings = ["dep:ndarray"]
datasets = ["dep:rand_distr", "std"]
datasets = ["dep:rand_distr", "std", "serde"]
std = ["rand/std_rng", "rand/std"]
# wasm32 only
js = ["getrandom/js"]
LICENSE
+1 -1
View File
@@ -186,7 +186,7 @@
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2019-present at SmartCore developers (smartcorelib.org)
Copyright 2019-present at smartcore developers (smartcorelib.org)
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
README.md
+2 -2
View File
@@ -1,6 +1,6 @@
<p align="center">
<a href="https://smartcorelib.org">
<img src="smartcore.svg" width="450" alt="SmartCore">
<img src="smartcore.svg" width="450" alt="smartcore">
</a>
</p>
<p align = "center">
@@ -18,4 +18,4 @@
-----
[![CI](https://github.com/smartcorelib/smartcore/actions/workflows/ci.yml/badge.svg)](https://github.com/smartcorelib/smartcore/actions/workflows/ci.yml)
To start getting familiar with the new Smartcore v0.5 API, there is now available a [**Jupyter Notebook environment repository**](https://github.com/smartcorelib/smartcore-jupyter). Please see instructions there, contributions welcome see [CONTRIBUTING](.github/CONTRIBUTING.md).
To start getting familiar with the new smartcore v0.5 API, there is now available a [**Jupyter Notebook environment repository**](https://github.com/smartcorelib/smartcore-jupyter). Please see instructions there, contributions welcome see [CONTRIBUTING](.github/CONTRIBUTING.md).
smartcore.svg
+1 -1
View File
@@ -76,5 +76,5 @@
y="81.876823"
x="91.861809"
id="tspan842"
sodipodi:role="line">SmartCore</tspan></text>
sodipodi:role="line">smartcore</tspan></text>
</svg>
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 2.5 KiB

After

Width:  |  Height:  |  Size: 2.5 KiB

src/algorithm/neighbour/cover_tree.rs
+5 -5
View File
@@ -64,7 +64,7 @@ struct Node {
max_dist: f64,
parent_dist: f64,
children: Vec<Node>,
scale: i64,
_scale: i64,
}
#[derive(Debug)]
@@ -84,7 +84,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
max_dist: 0f64,
parent_dist: 0f64,
children: Vec::new(),
scale: 0,
_scale: 0,
};
let mut tree = CoverTree {
base,
@@ -245,7 +245,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
max_dist: 0f64,
parent_dist: 0f64,
children: Vec::new(),
scale: 100,
_scale: 100,
}
}
@@ -306,7 +306,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
max_dist: 0f64,
parent_dist: 0f64,
children,
scale: 100,
_scale: 100,
}
} else {
let mut far: Vec<DistanceSet> = Vec::new();
@@ -375,7 +375,7 @@ impl<T: Debug + PartialEq, D: Distance<T>> CoverTree<T, D> {
max_dist: self.max(consumed_set),
parent_dist: 0f64,
children,
scale: (top_scale - max_scale),
_scale: (top_scale - max_scale),
}
}
}
src/cluster/kmeans.rs
+3 -3
View File
@@ -11,7 +11,7 @@
//! these re-calculated centroids becoming the new centers of their respective clusters. Next all instances of the training set are re-assigned to their closest cluster again.
//! This iterative process continues until convergence is achieved and the clusters are considered settled.
//!
//! Initial choice of K data points is very important and has big effect on performance of the algorithm. SmartCore uses k-means++ algorithm to initialize cluster centers.
//! Initial choice of K data points is very important and has big effect on performance of the algorithm. smartcore uses k-means++ algorithm to initialize cluster centers.
//!
//! Example:
//!
@@ -74,7 +74,7 @@ pub struct KMeans<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>> {
k: usize,
_y: Vec<usize>,
size: Vec<usize>,
distortion: f64,
_distortion: f64,
centroids: Vec<Vec<f64>>,
_phantom_tx: PhantomData<TX>,
_phantom_ty: PhantomData<TY>,
@@ -313,7 +313,7 @@ impl<TX: Number, TY: Number, X: Array2<TX>, Y: Array1<TY>> KMeans<TX, TY, X, Y>
k: parameters.k,
_y: y,
size,
distortion,
_distortion: distortion,
centroids,
_phantom_tx: PhantomData,
_phantom_ty: PhantomData,
src/dataset/mod.rs
+1 -1
View File
@@ -1,6 +1,6 @@
//! Datasets
//!
//! In this module you will find small datasets that are used in SmartCore mostly for demonstration purposes.
//! In this module you will find small datasets that are used in smartcore mostly for demonstration purposes.
pub mod boston;
pub mod breast_cancer;
pub mod diabetes;
src/ensemble/mod.rs
+1 -1
View File
@@ -7,7 +7,7 @@
//! set and then aggregate their individual predictions to form a final prediction. In classification setting the overall prediction is the most commonly
//! occurring majority class among the individual predictions.
//!
//! In SmartCore you will find implementation of RandomForest - a popular averaging algorithms based on randomized [decision trees](../tree/index.html).
//! In smartcore you will find implementation of RandomForest - a popular averaging algorithms based on randomized [decision trees](../tree/index.html).
//! Random forests provide an improvement over bagged trees by way of a small tweak that decorrelates the trees. As in bagging, we build a number of
//! decision trees on bootstrapped training samples. But when building these decision trees, each time a split in a tree is considered,
//! a random sample of _m_ predictors is chosen as split candidates from the full set of _p_ predictors.
src/ensemble/random_forest_classifier.rs
-3
View File
@@ -104,7 +104,6 @@ pub struct RandomForestClassifier<
X: Array2<TX>,
Y: Array1<TY>,
> {
parameters: Option<RandomForestClassifierParameters>,
trees: Option<Vec<DecisionTreeClassifier<TX, TY, X, Y>>>,
classes: Option<Vec<TY>>,
samples: Option<Vec<Vec<bool>>>,
@@ -198,7 +197,6 @@ impl<TX: Number + FloatNumber + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y:
{
fn new() -> Self {
Self {
parameters: Option::None,
trees: Option::None,
classes: Option::None,
samples: Option::None,
@@ -501,7 +499,6 @@ impl<TX: FloatNumber + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY
}
Ok(RandomForestClassifier {
parameters: Some(parameters),
trees: Some(trees),
classes: Some(classes),
samples: maybe_all_samples,
src/ensemble/random_forest_regressor.rs
-3
View File
@@ -98,7 +98,6 @@ pub struct RandomForestRegressor<
X: Array2<TX>,
Y: Array1<TY>,
> {
parameters: Option<RandomForestRegressorParameters>,
trees: Option<Vec<DecisionTreeRegressor<TX, TY, X, Y>>>,
samples: Option<Vec<Vec<bool>>>,
}
@@ -177,7 +176,6 @@ impl<TX: Number + FloatNumber + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1
{
fn new() -> Self {
Self {
parameters: Option::None,
trees: Option::None,
samples: Option::None,
}
@@ -434,7 +432,6 @@ impl<TX: Number + FloatNumber + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1
}
Ok(RandomForestRegressor {
parameters: Some(parameters),
trees: Some(trees),
samples: maybe_all_samples,
})
src/lib.rs
+29 -10
View File
@@ -8,25 +8,38 @@
#![warn(missing_docs)]
#![warn(rustdoc::missing_doc_code_examples)]
//! # SmartCore
//! # smartcore
//!
//! Welcome to SmartCore, machine learning in Rust!
//! Welcome to smartcore, machine learning in Rust!
//!
//! SmartCore features various classification, regression and clustering algorithms including support vector machines, random forests, k-means and DBSCAN,
//! `smartcore` features various classification, regression and clustering algorithms including support vector machines, random forests, k-means and DBSCAN,
//! as well as tools for model selection and model evaluation.
//!
//! SmartCore provides its own traits system that extends Rust standard library, to deal with linear algebra and common
//! `smartcore` provides its own traits system that extends Rust standard library, to deal with linear algebra and common
//! computational models. Its API is designed using well recognizable patterns. Extra features (like support for [ndarray](https://docs.rs/ndarray)
//! structures) is available via optional features.
//!
//! ## Getting Started
//!
//! To start using SmartCore simply add the following to your Cargo.toml file:
//! To start using `smartcore` latest stable version simply add the following to your `Cargo.toml` file:
//! ```ignore
//! [dependencies]
//! smartcore = "*"
//! ```
//!
//! To start using smartcore development version with latest unstable additions:
//! ```ignore
//! [dependencies]
//! smartcore = { git = "https://github.com/smartcorelib/smartcore", branch = "development" }
//! ```
//!
//! There are different features that can be added to the base library, for example to add sample datasets:
//! ```ignore
//! [dependencies]
//! smartcore = { git = "https://github.com/smartcorelib/smartcore", features = ["datasets"] }
//! ```
//! Check `smartcore`'s `Cargo.toml` for available features.
//!
//! ## Using Jupyter
//! For quick introduction, Jupyter Notebooks are available [here](https://github.com/smartcorelib/smartcore-jupyter/tree/main/notebooks).
//! You can set up a local environment to run Rust notebooks using [EVCXR](https://github.com/google/evcxr)
@@ -37,7 +50,7 @@
//! For example, you can use this code to fit a [K Nearest Neighbors classifier](neighbors/knn_classifier/index.html) to a dataset that is defined as standard Rust vector:
//!
//! ```
//! // DenseMatrix defenition
//! // DenseMatrix definition
//! use smartcore::linalg::basic::matrix::DenseMatrix;
//! // KNNClassifier
//! use smartcore::neighbors::knn_classifier::*;
@@ -62,7 +75,9 @@
//! ```
//!
//! ## Overview
//! All machine learning algorithms in SmartCore are grouped into these broad categories:
//!
//! ### Supported algorithms
//! All machine learning algorithms are grouped into these broad categories:
//! * [Clustering](cluster/index.html), unsupervised clustering of unlabeled data.
//! * [Matrix Decomposition](decomposition/index.html), various methods for matrix decomposition.
//! * [Linear Models](linear/index.html), regression and classification methods where output is assumed to have linear relation to explanatory variables
@@ -71,11 +86,14 @@
//! * [Nearest Neighbors](neighbors/index.html), K Nearest Neighbors for classification and regression
//! * [Naive Bayes](naive_bayes/index.html), statistical classification technique based on Bayes Theorem
//! * [SVM](svm/index.html), support vector machines
//!
//! ### Linear Algebra traits system
//! For an introduction to `smartcore`'s traits system see [this notebook](https://github.com/smartcorelib/smartcore-jupyter/blob/5523993c53c6ec1fd72eea130ef4e7883121c1ea/notebooks/01-A-little-bit-about-numbers.ipynb)
/// Foundamental numbers traits
pub mod numbers;
/// Various algorithms and helper methods that are used elsewhere in SmartCore
/// Various algorithms and helper methods that are used elsewhere in smartcore
pub mod algorithm;
pub mod api;
@@ -89,7 +107,7 @@ pub mod decomposition;
/// Ensemble methods, including Random Forest classifier and regressor
pub mod ensemble;
pub mod error;
/// Diverse collection of linear algebra abstractions and methods that power SmartCore algorithms
/// Diverse collection of linear algebra abstractions and methods that power smartcore algorithms
pub mod linalg;
/// Supervised classification and regression models that assume linear relationship between dependent and explanatory variables.
pub mod linear;
@@ -105,7 +123,8 @@ pub mod neighbors;
pub mod optimization;
/// Preprocessing utilities
pub mod preprocessing;
/// Reading in data from serialized foramts
/// Reading in data from serialized formats
#[cfg(feature = "serde")]
pub mod readers;
/// Support Vector Machines
pub mod svm;
src/linear/linear_regression.rs
+1 -4
View File
@@ -12,7 +12,7 @@
//! \\[\hat{\beta} = (X^TX)^{-1}X^Ty \\]
//!
//! the \\((X^TX)^{-1}\\) term is both computationally expensive and numerically unstable. An alternative approach is to use a matrix decomposition to avoid this operation.
//! SmartCore uses [SVD](../../linalg/svd/index.html) and [QR](../../linalg/qr/index.html) matrix decomposition to find estimates of \\(\hat{\beta}\\).
//! smartcore uses [SVD](../../linalg/svd/index.html) and [QR](../../linalg/qr/index.html) matrix decomposition to find estimates of \\(\hat{\beta}\\).
//! The QR decomposition is more computationally efficient and more numerically stable than calculating the normal equation directly,
//! but does not work for all data matrices. Unlike the QR decomposition, all matrices have an SVD decomposition.
//!
@@ -113,7 +113,6 @@ pub struct LinearRegression<
> {
coefficients: Option<X>,
intercept: Option<TX>,
solver: LinearRegressionSolverName,
_phantom_ty: PhantomData<TY>,
_phantom_y: PhantomData<Y>,
}
@@ -210,7 +209,6 @@ impl<
Self {
coefficients: Option::None,
intercept: Option::None,
solver: LinearRegressionParameters::default().solver,
_phantom_ty: PhantomData,
_phantom_y: PhantomData,
}
@@ -276,7 +274,6 @@ impl<
Ok(LinearRegression {
intercept: Some(*w.get((num_attributes, 0))),
coefficients: Some(weights),
solver: parameters.solver,
_phantom_ty: PhantomData,
_phantom_y: PhantomData,
})
src/linear/logistic_regression.rs
+1 -1
View File
@@ -5,7 +5,7 @@
//!
//! \\[ Pr(y=1) \approx \frac{e^{\beta_0 + \sum_{i=1}^n \beta_iX_i}}{1 + e^{\beta_0 + \sum_{i=1}^n \beta_iX_i}} \\]
//!
//! SmartCore uses [limited memory BFGS](https://en.wikipedia.org/wiki/Limited-memory_BFGS) method to find estimates of regression coefficients, \\(\beta\\)
//! smartcore uses [limited memory BFGS](https://en.wikipedia.org/wiki/Limited-memory_BFGS) method to find estimates of regression coefficients, \\(\beta\\)
//!
//! Example:
//!
src/linear/ridge_regression.rs
+1 -4
View File
@@ -12,7 +12,7 @@
//! where \\(\alpha \geq 0\\) is a tuning parameter that controls strength of regularization. When \\(\alpha = 0\\) the penalty term has no effect, and ridge regression will produce the least squares estimates.
//! However, as \\(\alpha \rightarrow \infty\\), the impact of the shrinkage penalty grows, and the ridge regression coefficient estimates will approach zero.
//!
//! SmartCore uses [SVD](../../linalg/svd/index.html) and [Cholesky](../../linalg/cholesky/index.html) matrix decomposition to find estimates of \\(\hat{\beta}\\).
//! smartcore uses [SVD](../../linalg/svd/index.html) and [Cholesky](../../linalg/cholesky/index.html) matrix decomposition to find estimates of \\(\hat{\beta}\\).
//! The Cholesky decomposition is more computationally efficient and more numerically stable than calculating the normal equation directly,
//! but does not work for all data matrices. Unlike the Cholesky decomposition, all matrices have an SVD decomposition.
//!
@@ -197,7 +197,6 @@ pub struct RidgeRegression<
> {
coefficients: Option<X>,
intercept: Option<TX>,
solver: Option<RidgeRegressionSolverName>,
_phantom_ty: PhantomData<TY>,
_phantom_y: PhantomData<Y>,
}
@@ -259,7 +258,6 @@ impl<
Self {
coefficients: Option::None,
intercept: Option::None,
solver: Option::None,
_phantom_ty: PhantomData,
_phantom_y: PhantomData,
}
@@ -367,7 +365,6 @@ impl<
Ok(RidgeRegression {
intercept: Some(b),
coefficients: Some(w),
solver: Some(parameters.solver),
_phantom_ty: PhantomData,
_phantom_y: PhantomData,
})
src/metrics/auc.rs
+1 -1
View File
@@ -2,7 +2,7 @@
//! Computes the area under the receiver operating characteristic (ROC) curve that is equal to the probability that a classifier will rank a
//! randomly chosen positive instance higher than a randomly chosen negative one.
//!
//! SmartCore calculates ROC AUC from Wilcoxon or Mann-Whitney U test.
//! smartcore calculates ROC AUC from Wilcoxon or Mann-Whitney U test.
//!
//! Example:
//! ```
src/metrics/mod.rs
+1 -1
View File
@@ -4,7 +4,7 @@
//! In a feedback loop you build your model first, then you get feedback from metrics, improve it and repeat until your model achieve desirable performance.
//! Evaluation metrics helps to explain the performance of a model and compare models based on an objective criterion.
//!
//! Choosing the right metric is crucial while evaluating machine learning models. In SmartCore you will find metrics for these classes of ML models:
//! Choosing the right metric is crucial while evaluating machine learning models. In smartcore you will find metrics for these classes of ML models:
//!
//! * [Classification metrics](struct.ClassificationMetrics.html)
//! * [Regression metrics](struct.RegressionMetrics.html)
src/model_selection/mod.rs
+1 -1
View File
@@ -7,7 +7,7 @@
//! Splitting data into multiple subsets helps us to find the right combination of hyperparameters, estimate model performance and choose the right model for
//! the data.
//!
//! In SmartCore a random split into training and test sets can be quickly computed with the [train_test_split](./fn.train_test_split.html) helper function.
//! In smartcore a random split into training and test sets can be quickly computed with the [train_test_split](./fn.train_test_split.html) helper function.
//!
//! ```
//! use smartcore::linalg::basic::matrix::DenseMatrix;
src/neighbors/knn_classifier.rs
+1 -1
View File
@@ -1,6 +1,6 @@
//! # K Nearest Neighbors Classifier
//!
//! SmartCore relies on 2 backend algorithms to speedup KNN queries:
//! smartcore relies on 2 backend algorithms to speedup KNN queries:
//! * [`LinearSearch`](../../algorithm/neighbour/linear_search/index.html)
//! * [`CoverTree`](../../algorithm/neighbour/cover_tree/index.html)
//!
src/numbers/realnum.rs
+1 -1
View File
@@ -1,5 +1,5 @@
//! # 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.
//! 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;
src/svm/mod.rs
+1 -1
View File
@@ -9,7 +9,7 @@
//! SVM is memory efficient since it uses only a subset of training data to find a decision boundary. This subset is called support vectors.
//!
//! In SVM distance between a data point and the support vectors is defined by the kernel function.
//! SmartCore supports multiple kernel functions but you can always define a new kernel function by implementing the `Kernel` trait. Not all functions can be a kernel.
//! smartcore supports multiple kernel functions but you can always define a new kernel function by implementing the `Kernel` trait. Not all functions can be a kernel.
//! Building a new kernel requires a good mathematical understanding of the [Mercer theorem](https://en.wikipedia.org/wiki/Mercer%27s_theorem)
//! that gives necessary and sufficient condition for a function to be a kernel function.
//!
src/svm/svc.rs
+2 -3
View File
@@ -20,7 +20,7 @@
//!
//! Where \\( m \\) is a number of training samples, \\( y_i \\) is a label value (either 1 or -1) and \\(\langle\vec{w}, \vec{x}_i \rangle + b\\) is a decision boundary.
//!
//! To solve this optimization problem, SmartCore uses an [approximate SVM solver](https://leon.bottou.org/projects/lasvm).
//! To solve this optimization problem, smartcore uses an [approximate SVM solver](https://leon.bottou.org/projects/lasvm).
//! The optimizer reaches accuracies similar to that of a real SVM after performing two passes through the training examples. You can choose the number of passes
//! through the data that the algorithm takes by changing the `epoch` parameter of the classifier.
//!
@@ -934,8 +934,7 @@ mod tests {
use super::*;
use crate::linalg::basic::matrix::DenseMatrix;
use crate::metrics::accuracy;
#[cfg(feature = "serde")]
use crate::svm::*;
use crate::svm::Kernels;
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
src/svm/svr.rs
-2
View File
@@ -596,7 +596,6 @@ mod tests {
use super::*;
use crate::linalg::basic::matrix::DenseMatrix;
use crate::metrics::mean_squared_error;
#[cfg(feature = "serde")]
use crate::svm::Kernels;
// #[test]
@@ -617,7 +616,6 @@ mod tests {
// assert!(iter.next().is_none());
// }
//TODO: had to disable this test as it runs for too long
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test
src/tree/decision_tree_classifier.rs
+4 -8
View File
@@ -163,7 +163,6 @@ impl Default for SplitCriterion {
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, Clone)]
struct Node {
index: usize,
output: usize,
split_feature: usize,
split_value: Option<f64>,
@@ -406,9 +405,8 @@ impl Default for DecisionTreeClassifierSearchParameters {
}
impl Node {
fn new(index: usize, output: usize) -> Self {
fn new(output: usize) -> Self {
Node {
index,
output,
split_feature: 0,
split_value: Option::None,
@@ -582,7 +580,7 @@ impl<TX: Number + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>>
count[yi[i]] += samples[i];
}
let root = Node::new(0, which_max(&count));
let root = Node::new(which_max(&count));
change_nodes.push(root);
let mut order: Vec<Vec<usize>> = Vec::new();
@@ -831,11 +829,9 @@ impl<TX: Number + PartialOrd, TY: Number + Ord, X: Array2<TX>, Y: Array1<TY>>
let true_child_idx = self.nodes().len();
self.nodes
.push(Node::new(true_child_idx, visitor.true_child_output));
self.nodes.push(Node::new(visitor.true_child_output));
let false_child_idx = self.nodes().len();
self.nodes
.push(Node::new(false_child_idx, visitor.false_child_output));
self.nodes.push(Node::new(visitor.false_child_output));
self.nodes[visitor.node].true_child = Some(true_child_idx);
self.nodes[visitor.node].false_child = Some(false_child_idx);
src/tree/decision_tree_regressor.rs
+5 -9
View File
@@ -11,7 +11,7 @@
//!
//! where \\(\hat{y}_{Rk}\\) is the mean response for the training observations withing region _k_.
//!
//! SmartCore uses recursive binary splitting approach to build \\(R_1, R_2, ..., R_K\\) regions. The approach begins at the top of the tree and then successively splits the predictor space
//! smartcore uses recursive binary splitting approach to build \\(R_1, R_2, ..., R_K\\) regions. The approach begins at the top of the tree and then successively splits the predictor space
//! one predictor at a time. At each step of the tree-building process, the best split is made at that particular step, rather than looking ahead and picking a split that will lead to a better
//! tree in some future step.
//!
@@ -128,7 +128,6 @@ impl<TX: Number + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1<TY>>
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, Clone)]
struct Node {
index: usize,
output: f64,
split_feature: usize,
split_value: Option<f64>,
@@ -299,9 +298,8 @@ impl Default for DecisionTreeRegressorSearchParameters {
}
impl Node {
fn new(index: usize, output: f64) -> Self {
fn new(output: f64) -> Self {
Node {
index,
output,
split_feature: 0,
split_value: Option::None,
@@ -450,7 +448,7 @@ impl<TX: Number + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1<TY>>
sum += *sample_i as f64 * y_m.get(i).to_f64().unwrap();
}
let root = Node::new(0, sum / (n as f64));
let root = Node::new(sum / (n as f64));
nodes.push(root);
let mut order: Vec<Vec<usize>> = Vec::new();
@@ -662,11 +660,9 @@ impl<TX: Number + PartialOrd, TY: Number, X: Array2<TX>, Y: Array1<TY>>
let true_child_idx = self.nodes().len();
self.nodes
.push(Node::new(true_child_idx, visitor.true_child_output));
self.nodes.push(Node::new(visitor.true_child_output));
let false_child_idx = self.nodes().len();
self.nodes
.push(Node::new(false_child_idx, visitor.false_child_output));
self.nodes.push(Node::new(visitor.false_child_output));
self.nodes[visitor.node].true_child = Some(true_child_idx);
self.nodes[visitor.node].false_child = Some(false_child_idx);
src/tree/mod.rs
+1 -1
View File
@@ -9,7 +9,7 @@
//! Decision trees suffer from high variance and often does not deliver best prediction accuracy when compared to other supervised learning approaches, such as linear and logistic regression.
//! Hence some techniques such as [Random Forests](../ensemble/index.html) use more than one decision tree to improve performance of the algorithm.
//!
//! SmartCore uses [CART](https://en.wikipedia.org/wiki/Predictive_analytics#Classification_and_regression_trees_.28CART.29) learning technique to build both classification and regression trees.
//! smartcore uses [CART](https://en.wikipedia.org/wiki/Predictive_analytics#Classification_and_regression_trees_.28CART.29) learning technique to build both classification and regression trees.
//!
//! ## References:
//!