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/naive_bayes/categorical.rs
+160 -169
View File
@@ -6,50 +6,51 @@
//! Example:
//!
//! ```
//! use smartcore::linalg::naive::dense_matrix::*;
//! use smartcore::linalg::basic::matrix::DenseMatrix;
//! use smartcore::naive_bayes::categorical::CategoricalNB;
//!
//! let x = DenseMatrix::from_2d_array(&[
//! &[3., 4., 0., 1.],
//! &[3., 0., 0., 1.],
//! &[4., 4., 1., 2.],
//! &[4., 2., 4., 3.],
//! &[4., 2., 4., 2.],
//! &[4., 1., 1., 0.],
//! &[1., 1., 1., 1.],
//! &[0., 4., 1., 0.],
//! &[0., 3., 2., 1.],
//! &[0., 3., 1., 1.],
//! &[3., 4., 0., 1.],
//! &[3., 4., 2., 4.],
//! &[0., 3., 1., 2.],
//! &[0., 4., 1., 2.],
//! &[3, 4, 0, 1],
//! &[3, 0, 0, 1],
//! &[4, 4, 1, 2],
//! &[4, 2, 4, 3],
//! &[4, 2, 4, 2],
//! &[4, 1, 1, 0],
//! &[1, 1, 1, 1],
//! &[0, 4, 1, 0],
//! &[0, 3, 2, 1],
//! &[0, 3, 1, 1],
//! &[3, 4, 0, 1],
//! &[3, 4, 2, 4],
//! &[0, 3, 1, 2],
//! &[0, 4, 1, 2],
//! ]);
//! let y = vec![0., 0., 1., 1., 1., 0., 1., 0., 1., 1., 1., 1., 1., 0.];
//! let y: Vec<u32> = vec![0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0];
//!
//! let nb = CategoricalNB::fit(&x, &y, Default::default()).unwrap();
//! let y_hat = nb.predict(&x).unwrap();
//! ```
use num_traits::Unsigned;
use crate::api::{Predictor, SupervisedEstimator};
use crate::error::Failed;
use crate::linalg::BaseVector;
use crate::linalg::Matrix;
use crate::math::num::RealNumber;
use crate::linalg::basic::arrays::{Array1, Array2, ArrayView1};
use crate::naive_bayes::{BaseNaiveBayes, NBDistribution};
use crate::numbers::basenum::Number;
#[cfg(feature = "serde")]
use serde::{Deserialize, Serialize};
/// Naive Bayes classifier for categorical features
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug)]
struct CategoricalNBDistribution<T: RealNumber> {
#[derive(Debug, Clone)]
struct CategoricalNBDistribution<T: Number + Unsigned> {
/// number of training samples observed in each class
class_count: Vec<usize>,
/// class labels known to the classifier
class_labels: Vec<T>,
/// probability of each class
class_priors: Vec<T>,
coefficients: Vec<Vec<Vec<T>>>,
class_priors: Vec<f64>,
coefficients: Vec<Vec<Vec<f64>>>,
/// Number of features of each sample
n_features: usize,
/// Number of categories for each feature
@@ -60,7 +61,7 @@ struct CategoricalNBDistribution<T: RealNumber> {
category_count: Vec<Vec<Vec<usize>>>,
}
impl<T: RealNumber> PartialEq for CategoricalNBDistribution<T> {
impl<T: Number + Unsigned> PartialEq for CategoricalNBDistribution<T> {
fn eq(&self, other: &Self) -> bool {
if self.class_labels == other.class_labels
&& self.class_priors == other.class_priors
@@ -80,7 +81,7 @@ impl<T: RealNumber> PartialEq for CategoricalNBDistribution<T> {
return false;
}
for (a_i_j, b_i_j) in a_i.iter().zip(b_i.iter()) {
if (*a_i_j - *b_i_j).abs() > T::epsilon() {
if (*a_i_j - *b_i_j).abs() > std::f64::EPSILON {
return false;
}
}
@@ -93,29 +94,29 @@ impl<T: RealNumber> PartialEq for CategoricalNBDistribution<T> {
}
}
impl<T: RealNumber, M: Matrix<T>> NBDistribution<T, M> for CategoricalNBDistribution<T> {
fn prior(&self, class_index: usize) -> T {
impl<T: Number + Unsigned> NBDistribution<T, T> for CategoricalNBDistribution<T> {
fn prior(&self, class_index: usize) -> f64 {
if class_index >= self.class_labels.len() {
T::zero()
0f64
} else {
self.class_priors[class_index]
}
}
fn log_likelihood(&self, class_index: usize, j: &M::RowVector) -> T {
fn log_likelihood<'a>(&'a self, class_index: usize, j: &'a Box<dyn ArrayView1<T> + 'a>) -> f64 {
if class_index < self.class_labels.len() {
let mut likelihood = T::zero();
for feature in 0..j.len() {
let value = j.get(feature).floor().to_usize().unwrap();
let mut likelihood = 0f64;
for feature in 0..j.shape() {
let value = j.get(feature).to_usize().unwrap();
if self.coefficients[feature][class_index].len() > value {
likelihood += self.coefficients[feature][class_index][value];
} else {
return T::zero();
return 0f64;
}
}
likelihood
} else {
T::zero()
0f64
}
}
@@ -124,13 +125,13 @@ impl<T: RealNumber, M: Matrix<T>> NBDistribution<T, M> for CategoricalNBDistribu
}
}
impl<T: RealNumber> CategoricalNBDistribution<T> {
impl<T: Number + Unsigned> CategoricalNBDistribution<T> {
/// Fits the distribution to a NxM matrix where N is number of samples and M is number of features.
/// * `x` - training data.
/// * `y` - vector with target values (classes) of length N.
/// * `alpha` - Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing).
pub fn fit<M: Matrix<T>>(x: &M, y: &M::RowVector, alpha: T) -> Result<Self, Failed> {
if alpha < T::zero() {
pub fn fit<X: Array2<T>, Y: Array1<T>>(x: &X, y: &Y, alpha: f64) -> Result<Self, Failed> {
if alpha < 0f64 {
return Err(Failed::fit(&format!(
"alpha should be >= 0, alpha=[{}]",
alpha
@@ -138,7 +139,7 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
}
let (n_samples, n_features) = x.shape();
let y_samples = y.len();
let y_samples = y.shape();
if y_samples != n_samples {
return Err(Failed::fit(&format!(
"Size of x should equal size of y; |x|=[{}], |y|=[{}]",
@@ -152,11 +153,7 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
n_samples
)));
}
let y: Vec<usize> = y
.to_vec()
.iter()
.map(|y_i| y_i.floor().to_usize().unwrap())
.collect();
let y: Vec<usize> = y.iterator(0).map(|y_i| y_i.to_usize().unwrap()).collect();
let y_max = y
.iter()
@@ -164,7 +161,7 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
.ok_or_else(|| Failed::fit("Failed to get the labels of y."))?;
let class_labels: Vec<T> = (0..*y_max + 1)
.map(|label| T::from(label).unwrap())
.map(|label| T::from_usize(label).unwrap())
.collect();
let mut class_count = vec![0_usize; class_labels.len()];
for elem in y.iter() {
@@ -174,9 +171,9 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
let mut n_categories: Vec<usize> = Vec::with_capacity(n_features);
for feature in 0..n_features {
let feature_max = x
.get_col_as_vec(feature)
.iter()
.map(|f_i| f_i.floor().to_usize().unwrap())
.get_col(feature)
.iterator(0)
.map(|f_i| f_i.to_usize().unwrap())
.max()
.ok_or_else(|| {
Failed::fit(&format!(
@@ -187,34 +184,32 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
n_categories.push(feature_max + 1);
}
let mut coefficients: Vec<Vec<Vec<T>>> = Vec::with_capacity(class_labels.len());
let mut coefficients: Vec<Vec<Vec<f64>>> = Vec::with_capacity(class_labels.len());
let mut category_count: Vec<Vec<Vec<usize>>> = Vec::with_capacity(class_labels.len());
for (feature_index, &n_categories_i) in n_categories.iter().enumerate().take(n_features) {
let mut coef_i: Vec<Vec<T>> = Vec::with_capacity(n_features);
let mut coef_i: Vec<Vec<f64>> = Vec::with_capacity(n_features);
let mut category_count_i: Vec<Vec<usize>> = Vec::with_capacity(n_features);
for (label, &label_count) in class_labels.iter().zip(class_count.iter()) {
let col = x
.get_col_as_vec(feature_index)
.iter()
.get_col(feature_index)
.iterator(0)
.enumerate()
.filter(|(i, _j)| T::from(y[*i]).unwrap() == *label)
.filter(|(i, _j)| T::from_usize(y[*i]).unwrap() == *label)
.map(|(_, j)| *j)
.collect::<Vec<T>>();
let mut feat_count: Vec<usize> = vec![0_usize; n_categories_i];
for row in col.iter() {
let index = row.floor().to_usize().unwrap();
let index = row.to_usize().unwrap();
feat_count[index] += 1;
}
let coef_i_j = feat_count
.iter()
.map(|c| {
((T::from(*c).unwrap() + alpha)
/ (T::from(label_count).unwrap()
+ T::from(n_categories_i).unwrap() * alpha))
.map(|&c| {
((c as f64 + alpha) / (label_count as f64 + n_categories_i as f64 * alpha))
.ln()
})
.collect::<Vec<T>>();
.collect::<Vec<f64>>();
category_count_i.push(feat_count);
coef_i.push(coef_i_j);
}
@@ -224,8 +219,8 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
let class_priors = class_count
.iter()
.map(|&count| T::from(count).unwrap() / T::from(n_samples).unwrap())
.collect::<Vec<T>>();
.map(|&count| count as f64 / n_samples as f64)
.collect::<Vec<f64>>();
Ok(Self {
class_count,
@@ -242,44 +237,44 @@ impl<T: RealNumber> CategoricalNBDistribution<T> {
/// `CategoricalNB` parameters. Use `Default::default()` for default values.
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, Clone)]
pub struct CategoricalNBParameters<T: RealNumber> {
pub struct CategoricalNBParameters {
#[cfg_attr(feature = "serde", serde(default))]
/// Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing).
pub alpha: T,
pub alpha: f64,
}
impl<T: RealNumber> CategoricalNBParameters<T> {
impl CategoricalNBParameters {
/// Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing).
pub fn with_alpha(mut self, alpha: T) -> Self {
pub fn with_alpha(mut self, alpha: f64) -> Self {
self.alpha = alpha;
self
}
}
impl<T: RealNumber> Default for CategoricalNBParameters<T> {
impl Default for CategoricalNBParameters {
fn default() -> Self {
Self { alpha: T::one() }
Self { alpha: 1f64 }
}
}
/// CategoricalNB grid search parameters
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, Clone)]
pub struct CategoricalNBSearchParameters<T: RealNumber> {
pub struct CategoricalNBSearchParameters {
#[cfg_attr(feature = "serde", serde(default))]
/// Additive (Laplace/Lidstone) smoothing parameter (0 for no smoothing).
pub alpha: Vec<T>,
pub alpha: Vec<f64>,
}
/// CategoricalNB grid search iterator
pub struct CategoricalNBSearchParametersIterator<T: RealNumber> {
categorical_nb_search_parameters: CategoricalNBSearchParameters<T>,
pub struct CategoricalNBSearchParametersIterator {
categorical_nb_search_parameters: CategoricalNBSearchParameters,
current_alpha: usize,
}
impl<T: RealNumber> IntoIterator for CategoricalNBSearchParameters<T> {
type Item = CategoricalNBParameters<T>;
type IntoIter = CategoricalNBSearchParametersIterator<T>;
impl IntoIterator for CategoricalNBSearchParameters {
type Item = CategoricalNBParameters;
type IntoIter = CategoricalNBSearchParametersIterator;
fn into_iter(self) -> Self::IntoIter {
CategoricalNBSearchParametersIterator {
@@ -289,8 +284,8 @@ impl<T: RealNumber> IntoIterator for CategoricalNBSearchParameters<T> {
}
}
impl<T: RealNumber> Iterator for CategoricalNBSearchParametersIterator<T> {
type Item = CategoricalNBParameters<T>;
impl Iterator for CategoricalNBSearchParametersIterator {
type Item = CategoricalNBParameters;
fn next(&mut self) -> Option<Self::Item> {
if self.current_alpha == self.categorical_nb_search_parameters.alpha.len() {
@@ -307,7 +302,7 @@ impl<T: RealNumber> Iterator for CategoricalNBSearchParametersIterator<T> {
}
}
impl<T: RealNumber> Default for CategoricalNBSearchParameters<T> {
impl Default for CategoricalNBSearchParameters {
fn default() -> Self {
let default_params = CategoricalNBParameters::default();
@@ -320,92 +315,90 @@ impl<T: RealNumber> Default for CategoricalNBSearchParameters<T> {
/// CategoricalNB implements the categorical naive Bayes algorithm for categorically distributed data.
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, PartialEq)]
pub struct CategoricalNB<T: RealNumber, M: Matrix<T>> {
inner: BaseNaiveBayes<T, M, CategoricalNBDistribution<T>>,
pub struct CategoricalNB<T: Number + Unsigned, X: Array2<T>, Y: Array1<T>> {
inner: Option<BaseNaiveBayes<T, T, X, Y, CategoricalNBDistribution<T>>>,
}
impl<T: RealNumber, M: Matrix<T>> SupervisedEstimator<M, M::RowVector, CategoricalNBParameters<T>>
for CategoricalNB<T, M>
impl<T: Number + Unsigned, X: Array2<T>, Y: Array1<T>>
SupervisedEstimator<X, Y, CategoricalNBParameters> for CategoricalNB<T, X, Y>
{
fn fit(
x: &M,
y: &M::RowVector,
parameters: CategoricalNBParameters<T>,
) -> Result<Self, Failed> {
fn new() -> Self {
Self {
inner: Option::None,
}
}
fn fit(x: &X, y: &Y, parameters: CategoricalNBParameters) -> Result<Self, Failed> {
CategoricalNB::fit(x, y, parameters)
}
}
impl<T: RealNumber, M: Matrix<T>> Predictor<M, M::RowVector> for CategoricalNB<T, M> {
fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
impl<T: Number + Unsigned, X: Array2<T>, Y: Array1<T>> Predictor<X, Y> for CategoricalNB<T, X, Y> {
fn predict(&self, x: &X) -> Result<Y, Failed> {
self.predict(x)
}
}
impl<T: RealNumber, M: Matrix<T>> CategoricalNB<T, M> {
impl<T: Number + Unsigned, X: Array2<T>, Y: Array1<T>> CategoricalNB<T, X, Y> {
/// Fits CategoricalNB with given data
/// * `x` - training data of size NxM where N is the number of samples and M is the number of
/// features.
/// * `y` - vector with target values (classes) of length N.
/// * `parameters` - additional parameters like alpha for smoothing
pub fn fit(
x: &M,
y: &M::RowVector,
parameters: CategoricalNBParameters<T>,
) -> Result<Self, Failed> {
pub fn fit(x: &X, y: &Y, parameters: CategoricalNBParameters) -> Result<Self, Failed> {
let alpha = parameters.alpha;
let distribution = CategoricalNBDistribution::fit(x, y, alpha)?;
let inner = BaseNaiveBayes::fit(distribution)?;
Ok(Self { inner })
Ok(Self { inner: Some(inner) })
}
/// Estimates the class labels for the provided data.
/// * `x` - data of shape NxM where N is number of data points to estimate and M is number of features.
/// Returns a vector of size N with class estimates.
pub fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
self.inner.predict(x)
pub fn predict(&self, x: &X) -> Result<Y, Failed> {
self.inner.as_ref().unwrap().predict(x)
}
/// Class labels known to the classifier.
/// Returns a vector of size n_classes.
pub fn classes(&self) -> &Vec<T> {
&self.inner.distribution.class_labels
&self.inner.as_ref().unwrap().distribution.class_labels
}
/// Number of training samples observed in each class.
/// Returns a vector of size n_classes.
pub fn class_count(&self) -> &Vec<usize> {
&self.inner.distribution.class_count
&self.inner.as_ref().unwrap().distribution.class_count
}
/// Number of features of each sample
pub fn n_features(&self) -> usize {
self.inner.distribution.n_features
self.inner.as_ref().unwrap().distribution.n_features
}
/// Number of features of each sample
pub fn n_categories(&self) -> &Vec<usize> {
&self.inner.distribution.n_categories
&self.inner.as_ref().unwrap().distribution.n_categories
}
/// Holds arrays of shape (n_classes, n_categories of respective feature)
/// for each feature. Each array provides the number of samples
/// encountered for each class and category of the specific feature.
pub fn category_count(&self) -> &Vec<Vec<Vec<usize>>> {
&self.inner.distribution.category_count
&self.inner.as_ref().unwrap().distribution.category_count
}
/// Holds arrays of shape (n_classes, n_categories of respective feature)
/// for each feature. Each array provides the empirical log probability
/// of categories given the respective feature and class, ``P(x_i|y)``.
pub fn feature_log_prob(&self) -> &Vec<Vec<Vec<T>>> {
&self.inner.distribution.coefficients
pub fn feature_log_prob(&self) -> &Vec<Vec<Vec<f64>>> {
&self.inner.as_ref().unwrap().distribution.coefficients
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::linalg::naive::dense_matrix::DenseMatrix;
use crate::linalg::basic::matrix::DenseMatrix;
#[test]
fn search_parameters() {
@@ -424,28 +417,28 @@ mod tests {
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
fn run_categorical_naive_bayes() {
let x = DenseMatrix::from_2d_array(&[
&[0., 2., 1., 0.],
&[0., 2., 1., 1.],
&[1., 2., 1., 0.],
&[2., 1., 1., 0.],
&[2., 0., 0., 0.],
&[2., 0., 0., 1.],
&[1., 0., 0., 1.],
&[0., 1., 1., 0.],
&[0., 0., 0., 0.],
&[2., 1., 0., 0.],
&[0., 1., 0., 1.],
&[1., 1., 1., 1.],
&[1., 2., 0., 0.],
&[2., 1., 1., 1.],
let x = DenseMatrix::<u32>::from_2d_array(&[
&[0, 2, 1, 0],
&[0, 2, 1, 1],
&[1, 2, 1, 0],
&[2, 1, 1, 0],
&[2, 0, 0, 0],
&[2, 0, 0, 1],
&[1, 0, 0, 1],
&[0, 1, 1, 0],
&[0, 0, 0, 0],
&[2, 1, 0, 0],
&[0, 1, 0, 1],
&[1, 1, 1, 1],
&[1, 2, 0, 0],
&[2, 1, 1, 1],
]);
let y = vec![0., 0., 1., 1., 1., 0., 1., 0., 1., 1., 1., 1., 1., 0.];
let y: Vec<u32> = vec![0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0];
let cnb = CategoricalNB::fit(&x, &y, Default::default()).unwrap();
// checking parity with scikit
assert_eq!(cnb.classes(), &[0., 1.]);
assert_eq!(cnb.classes(), &[0, 1]);
assert_eq!(cnb.class_count(), &[5, 9]);
assert_eq!(cnb.n_features(), 4);
assert_eq!(cnb.n_categories(), &[3, 3, 2, 2]);
@@ -497,67 +490,65 @@ mod tests {
]
);
let x_test = DenseMatrix::from_2d_array(&[&[0., 2., 1., 0.], &[2., 2., 0., 0.]]);
let x_test = DenseMatrix::from_2d_array(&[&[0, 2, 1, 0], &[2, 2, 0, 0]]);
let y_hat = cnb.predict(&x_test).unwrap();
assert_eq!(y_hat, vec![0., 1.]);
assert_eq!(y_hat, vec![0, 1]);
}
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
fn run_categorical_naive_bayes2() {
let x = DenseMatrix::from_2d_array(&[
&[3., 4., 0., 1.],
&[3., 0., 0., 1.],
&[4., 4., 1., 2.],
&[4., 2., 4., 3.],
&[4., 2., 4., 2.],
&[4., 1., 1., 0.],
&[1., 1., 1., 1.],
&[0., 4., 1., 0.],
&[0., 3., 2., 1.],
&[0., 3., 1., 1.],
&[3., 4., 0., 1.],
&[3., 4., 2., 4.],
&[0., 3., 1., 2.],
&[0., 4., 1., 2.],
let x = DenseMatrix::<u32>::from_2d_array(&[
&[3, 4, 0, 1],
&[3, 0, 0, 1],
&[4, 4, 1, 2],
&[4, 2, 4, 3],
&[4, 2, 4, 2],
&[4, 1, 1, 0],
&[1, 1, 1, 1],
&[0, 4, 1, 0],
&[0, 3, 2, 1],
&[0, 3, 1, 1],
&[3, 4, 0, 1],
&[3, 4, 2, 4],
&[0, 3, 1, 2],
&[0, 4, 1, 2],
]);
let y = vec![0., 0., 1., 1., 1., 0., 1., 0., 1., 1., 1., 1., 1., 0.];
let y: Vec<u32> = vec![0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0];
let cnb = CategoricalNB::fit(&x, &y, Default::default()).unwrap();
let y_hat = cnb.predict(&x).unwrap();
assert_eq!(
y_hat,
vec![0., 0., 1., 1., 1., 0., 1., 0., 1., 1., 0., 1., 1., 1.]
);
assert_eq!(y_hat, vec![0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1]);
}
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
#[cfg(feature = "serde")]
fn serde() {
let x = DenseMatrix::<f64>::from_2d_array(&[
&[3., 4., 0., 1.],
&[3., 0., 0., 1.],
&[4., 4., 1., 2.],
&[4., 2., 4., 3.],
&[4., 2., 4., 2.],
&[4., 1., 1., 0.],
&[1., 1., 1., 1.],
&[0., 4., 1., 0.],
&[0., 3., 2., 1.],
&[0., 3., 1., 1.],
&[3., 4., 0., 1.],
&[3., 4., 2., 4.],
&[0., 3., 1., 2.],
&[0., 4., 1., 2.],
]);
// TODO: implement serialization
// #[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
// #[test]
// #[cfg(feature = "serde")]
// fn serde() {
// let x = DenseMatrix::from_2d_array(&[
// &[3, 4, 0, 1],
// &[3, 0, 0, 1],
// &[4, 4, 1, 2],
// &[4, 2, 4, 3],
// &[4, 2, 4, 2],
// &[4, 1, 1, 0],
// &[1, 1, 1, 1],
// &[0, 4, 1, 0],
// &[0, 3, 2, 1],
// &[0, 3, 1, 1],
// &[3, 4, 0, 1],
// &[3, 4, 2, 4],
// &[0, 3, 1, 2],
// &[0, 4, 1, 2],
// ]);
let y = vec![0., 0., 1., 1., 1., 0., 1., 0., 1., 1., 1., 1., 1., 0.];
let cnb = CategoricalNB::fit(&x, &y, Default::default()).unwrap();
// let y: Vec<u32> = vec![0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0];
// let cnb = CategoricalNB::fit(&x, &y, Default::default()).unwrap();
let deserialized_cnb: CategoricalNB<f64, DenseMatrix<f64>> =
serde_json::from_str(&serde_json::to_string(&cnb).unwrap()).unwrap();
// let deserialized_cnb: CategoricalNB<u32, DenseMatrix<u32>, Vec<u32>> =
// serde_json::from_str(&serde_json::to_string(&cnb).unwrap()).unwrap();
assert_eq!(cnb, deserialized_cnb);
}
// assert_eq!(cnb, deserialized_cnb);
// }
}