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

Port ensemble. Add Display to naive_bayes (#208)

Browse Source
This commit is contained in:
Lorenzo
2022-10-31 17:35:33 +00:00
committed by GitHub
parent 4f64f2e0ff
commit 083803c900
10 changed files with 330 additions and 242 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/naive_bayes/bernoulli.rs
+30 -17
View File
@@ -33,6 +33,8 @@
//! ## References:
//!
//! * ["Introduction to Information Retrieval", Manning C. D., Raghavan P., Schutze H., 2009, Chapter 13 ](https://nlp.stanford.edu/IR-book/information-retrieval-book.html)
use std::fmt;
use num_traits::Unsigned;
use crate::api::{Predictor, SupervisedEstimator};
@@ -62,6 +64,18 @@ struct BernoulliNBDistribution<T: Number + Ord + Unsigned> {
n_features: usize,
}
impl<T: Number + Ord + Unsigned> fmt::Display for BernoulliNBDistribution<T> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(
f,
"BernoulliNBDistribution: n_features: {:?}",
self.n_features
)?;
writeln!(f, "class_labels: {:?}", self.class_labels)?;
Ok(())
}
}
impl<T: Number + Ord + Unsigned> PartialEq for BernoulliNBDistribution<T> {
fn eq(&self, other: &Self) -> bool {
if self.class_labels == other.class_labels
@@ -598,23 +612,22 @@ mod tests {
assert_eq!(y_hat, vec!(2, 2, 0, 0, 0, 2, 1, 1, 0, 0, 0, 0, 0, 0, 0));
}
// 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(&[
// &[1, 1, 0, 0, 0, 0],
// &[0, 1, 0, 0, 1, 0],
// &[0, 1, 0, 1, 0, 0],
// &[0, 1, 1, 0, 0, 1],
// ]);
// let y: Vec<u32> = vec![0, 0, 0, 1];
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
#[cfg(feature = "serde")]
fn serde() {
let x = DenseMatrix::from_2d_array(&[
&[1, 1, 0, 0, 0, 0],
&[0, 1, 0, 0, 1, 0],
&[0, 1, 0, 1, 0, 0],
&[0, 1, 1, 0, 0, 1],
]);
let y: Vec<u32> = vec![0, 0, 0, 1];
// let bnb = BernoulliNB::fit(&x, &y, Default::default()).unwrap();
// let deserialized_bnb: BernoulliNB<i32, u32, DenseMatrix<i32>, Vec<u32>> =
// serde_json::from_str(&serde_json::to_string(&bnb).unwrap()).unwrap();
let bnb = BernoulliNB::fit(&x, &y, Default::default()).unwrap();
let deserialized_bnb: BernoulliNB<i32, u32, DenseMatrix<i32>, Vec<u32>> =
serde_json::from_str(&serde_json::to_string(&bnb).unwrap()).unwrap();
// assert_eq!(bnb, deserialized_bnb);
// }
assert_eq!(bnb, deserialized_bnb);
}
}
src/naive_bayes/categorical.rs
+40 -27
View File
@@ -30,6 +30,8 @@
//! let nb = CategoricalNB::fit(&x, &y, Default::default()).unwrap();
//! let y_hat = nb.predict(&x).unwrap();
//! ```
use std::fmt;
use num_traits::Unsigned;
use crate::api::{Predictor, SupervisedEstimator};
@@ -61,6 +63,18 @@ struct CategoricalNBDistribution<T: Number + Unsigned> {
category_count: Vec<Vec<Vec<usize>>>,
}
impl<T: Number + Ord + Unsigned> fmt::Display for CategoricalNBDistribution<T> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(
f,
"CategoricalNBDistribution: n_features: {:?}",
self.n_features
)?;
writeln!(f, "class_labels: {:?}", self.class_labels)?;
Ok(())
}
}
impl<T: Number + Unsigned> PartialEq for CategoricalNBDistribution<T> {
fn eq(&self, other: &Self) -> bool {
if self.class_labels == other.class_labels
@@ -521,34 +535,33 @@ mod tests {
assert_eq!(y_hat, vec![0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1]);
}
// 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],
// ]);
#[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<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: 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<u32, DenseMatrix<u32>, Vec<u32>> =
// 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);
}
}
src/naive_bayes/gaussian.rs
+32 -19
View File
@@ -22,6 +22,8 @@
//! let nb = GaussianNB::fit(&x, &y, Default::default()).unwrap();
//! let y_hat = nb.predict(&x).unwrap();
//! ```
use std::fmt;
use num_traits::Unsigned;
use crate::api::{Predictor, SupervisedEstimator};
@@ -49,6 +51,18 @@ struct GaussianNBDistribution<T: Number> {
theta: Vec<Vec<f64>>,
}
impl<T: Number + Ord + Unsigned> fmt::Display for GaussianNBDistribution<T> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(
f,
"GaussianNBDistribution: class_count: {:?}",
self.class_count
)?;
writeln!(f, "class_labels: {:?}", self.class_labels)?;
Ok(())
}
}
impl<X: Number + RealNumber, Y: Number + Ord + Unsigned> NBDistribution<X, Y>
for GaussianNBDistribution<Y>
{
@@ -415,25 +429,24 @@ mod tests {
assert_eq!(gnb.class_priors(), &priors);
}
// TODO: implement serialization
// #[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
// #[test]
// #[cfg(feature = "serde")]
// fn serde() {
// let x = DenseMatrix::<f64>::from_2d_array(&[
// &[-1., -1.],
// &[-2., -1.],
// &[-3., -2.],
// &[1., 1.],
// &[2., 1.],
// &[3., 2.],
// ]);
// let y: Vec<u32> = vec![1, 1, 1, 2, 2, 2];
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
#[cfg(feature = "serde")]
fn serde() {
let x = DenseMatrix::<f64>::from_2d_array(&[
&[-1., -1.],
&[-2., -1.],
&[-3., -2.],
&[1., 1.],
&[2., 1.],
&[3., 2.],
]);
let y: Vec<u32> = vec![1, 1, 1, 2, 2, 2];
// let gnb = GaussianNB::fit(&x, &y, Default::default()).unwrap();
// let deserialized_gnb: GaussianNB<f64, u32, DenseMatrix<f64>, Vec<u32>> =
// serde_json::from_str(&serde_json::to_string(&gnb).unwrap()).unwrap();
let gnb = GaussianNB::fit(&x, &y, Default::default()).unwrap();
let deserialized_gnb: GaussianNB<f64, u32, DenseMatrix<f64>, Vec<u32>> =
serde_json::from_str(&serde_json::to_string(&gnb).unwrap()).unwrap();
// assert_eq!(gnb, deserialized_gnb);
// }
assert_eq!(gnb, deserialized_gnb);
}
}
src/naive_bayes/multinomial.rs
+30 -17
View File
@@ -33,6 +33,8 @@
//! ## References:
//!
//! * ["Introduction to Information Retrieval", Manning C. D., Raghavan P., Schutze H., 2009, Chapter 13 ](https://nlp.stanford.edu/IR-book/information-retrieval-book.html)
use std::fmt;
use num_traits::Unsigned;
use crate::api::{Predictor, SupervisedEstimator};
@@ -62,6 +64,18 @@ struct MultinomialNBDistribution<T: Number> {
n_features: usize,
}
impl<T: Number + Ord + Unsigned> fmt::Display for MultinomialNBDistribution<T> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
writeln!(
f,
"MultinomialNBDistribution: n_features: {:?}",
self.n_features
)?;
writeln!(f, "class_labels: {:?}", self.class_labels)?;
Ok(())
}
}
impl<X: Number + Unsigned, Y: Number + Ord + Unsigned> NBDistribution<X, Y>
for MultinomialNBDistribution<Y>
{
@@ -510,23 +524,22 @@ mod tests {
assert_eq!(y_hat, vec!(2, 2, 0, 0, 0, 2, 2, 1, 0, 1, 0, 2, 0, 0, 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(&[
// &[1, 1, 0, 0, 0, 0],
// &[0, 1, 0, 0, 1, 0],
// &[0, 1, 0, 1, 0, 0],
// &[0, 1, 1, 0, 0, 1],
// ]);
// let y = vec![0, 0, 0, 1];
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
#[test]
#[cfg(feature = "serde")]
fn serde() {
let x = DenseMatrix::from_2d_array(&[
&[1, 1, 0, 0, 0, 0],
&[0, 1, 0, 0, 1, 0],
&[0, 1, 0, 1, 0, 0],
&[0, 1, 1, 0, 0, 1],
]);
let y = vec![0, 0, 0, 1];
// let mnb = MultinomialNB::fit(&x, &y, Default::default()).unwrap();
// let deserialized_mnb: MultinomialNB<u32, u32, DenseMatrix<u32>, Vec<u32>> =
// serde_json::from_str(&serde_json::to_string(&mnb).unwrap()).unwrap();
let mnb = MultinomialNB::fit(&x, &y, Default::default()).unwrap();
let deserialized_mnb: MultinomialNB<u32, u32, DenseMatrix<u32>, Vec<u32>> =
serde_json::from_str(&serde_json::to_string(&mnb).unwrap()).unwrap();
// assert_eq!(mnb, deserialized_mnb);
// }
assert_eq!(mnb, deserialized_mnb);
}
}