doc update

This commit is contained in:
gaxler
2021-02-02 18:20:27 -08:00
parent d31145b4fe
commit 237b1160b1
+15 -7
View File
@@ -8,6 +8,7 @@ use crate::math::num::RealNumber;
use std::collections::HashMap; use std::collections::HashMap;
use std::hash::Hash; use std::hash::Hash;
/// Bi-directional map category <-> label num.
#[derive(Debug, Clone)] #[derive(Debug, Clone)]
pub struct CategoryMapper<CategoryType> { pub struct CategoryMapper<CategoryType> {
category_map: HashMap<CategoryType, usize>, category_map: HashMap<CategoryType, usize>,
@@ -16,7 +17,9 @@ pub struct CategoryMapper<CategoryType> {
} }
impl<'a, CategoryType: 'a + Hash + Eq + Clone> CategoryMapper<CategoryType> { impl<'a, CategoryType: 'a + Hash + Eq + Clone> CategoryMapper<CategoryType> {
fn fit_to_iter(categories: impl Iterator<Item = CategoryType>) -> Self {
/// Fit an encoder to a lable iterator
pub fn fit_to_iter(categories: impl Iterator<Item = CategoryType>) -> Self {
let mut category_map: HashMap<CategoryType, usize> = HashMap::new(); let mut category_map: HashMap<CategoryType, usize> = HashMap::new();
let mut category_num = 0usize; let mut category_num = 0usize;
let mut unique_lables: Vec<CategoryType> = Vec::new(); let mut unique_lables: Vec<CategoryType> = Vec::new();
@@ -35,7 +38,8 @@ impl<'a, CategoryType: 'a + Hash + Eq + Clone> CategoryMapper<CategoryType> {
} }
} }
fn from_category_map(category_map: HashMap<CategoryType, usize>) -> Self { /// Build an encoder from a predefined (category -> class number) map
pub fn from_category_map(category_map: HashMap<CategoryType, usize>) -> Self {
let mut _unique_cat: Vec<(CategoryType, usize)> = let mut _unique_cat: Vec<(CategoryType, usize)> =
category_map.iter().map(|(k, v)| (k.clone(), *v)).collect(); category_map.iter().map(|(k, v)| (k.clone(), *v)).collect();
_unique_cat.sort_by(|a, b| a.1.cmp(&b.1)); _unique_cat.sort_by(|a, b| a.1.cmp(&b.1));
@@ -47,7 +51,8 @@ impl<'a, CategoryType: 'a + Hash + Eq + Clone> CategoryMapper<CategoryType> {
} }
} }
fn from_positional_category_vec(categories: Vec<CategoryType>) -> Self { /// Build an encoder from a predefined positional category-class num vector
pub fn from_positional_category_vec(categories: Vec<CategoryType>) -> Self {
let category_map: HashMap<CategoryType, usize> = categories let category_map: HashMap<CategoryType, usize> = categories
.iter() .iter()
.enumerate() .enumerate()
@@ -61,16 +66,17 @@ impl<'a, CategoryType: 'a + Hash + Eq + Clone> CategoryMapper<CategoryType> {
} }
/// Get label num of a category /// Get label num of a category
fn get_num(&self, category: &CategoryType) -> Option<&usize> { pub fn get_num(&self, category: &CategoryType) -> Option<&usize> {
self.category_map.get(category) self.category_map.get(category)
} }
/// Return category corresponding to label num /// Return category corresponding to label num
fn get_cat(&self, num: usize) -> &CategoryType { pub fn get_cat(&self, num: usize) -> &CategoryType {
&self.categories[num] &self.categories[num]
} }
fn get_categories(&self) -> &[CategoryType] { /// List all categories (position = category number)
pub fn get_categories(&self) -> &[CategoryType] {
&self.categories[..] &self.categories[..]
} }
} }
@@ -80,7 +86,7 @@ pub trait SeriesEncoder<CategoryType>:
where where
CategoryType:Hash + Eq + Clone CategoryType:Hash + Eq + Clone
{ {
/// Fit an encoder to a lable list /// Fit an encoder to a lable iterator
fn fit_to_iter(categories: impl Iterator<Item = CategoryType>) -> Self; fn fit_to_iter(categories: impl Iterator<Item = CategoryType>) -> Self;
/// Number of categories for categorical variable /// Number of categories for categorical variable
@@ -119,6 +125,7 @@ pub trait SeriesEncoder<CategoryType>:
self.transform_iter(v) self.transform_iter(v)
} }
} }
/// Make a one-hot encoded vector from a categorical variable /// Make a one-hot encoded vector from a categorical variable
/// ///
/// Example: /// Example:
@@ -233,6 +240,7 @@ impl<CategoryType: Hash + Eq + Clone> SeriesEncoder<CategoryType> for SeriesOneH
Some(&idx) => Some(make_one_hot(idx, self.num_categories())), Some(&idx) => Some(make_one_hot(idx, self.num_categories())),
} }
} }
} }
#[cfg(test)] #[cfg(test)]