Struct CategoryMapper

pub struct CategoryMapper<C> { /* private fields */ }

Bi-directional map category <-> label num.

Turn Hashable objects into a one-hot vectors or ordinal values. This struct encodes single class per exmample

You can fit_to_iter a category enumeration by passing an iterator of categories. category numbers will be assigned in the order they are encountered

Example:

use std::collections::HashMap;
use smartcore::preprocessing::series_encoder::CategoryMapper;

let fake_categories: Vec<usize> = vec![1, 2, 3, 4, 5, 3, 5, 3, 1, 2, 4];
let it = fake_categories.iter().map(|&a| a);
let enc = CategoryMapper::<usize>::fit_to_iter(it);
let oh_vec: Vec<f64> = enc.get_one_hot(&1).unwrap();
// notice that 1 is actually a zero-th positional category
assert_eq!(oh_vec, vec![1.0, 0.0, 0.0, 0.0, 0.0]);

You can also pass a predefined category enumeration such as a hashmap HashMap<C, usize> or a vector Vec<C>

use std::collections::HashMap;
use smartcore::preprocessing::series_encoder::CategoryMapper;

let category_map: HashMap<&str, usize> =
vec![("cat", 2), ("background",0), ("dog", 1)]
.into_iter()
.collect();
let category_vec = vec!["background", "dog", "cat"];

let enc_lv  = CategoryMapper::<&str>::from_positional_category_vec(category_vec);
let enc_lm  = CategoryMapper::<&str>::from_category_map(category_map);

// ["background", "dog", "cat"]
println!("{:?}", enc_lv.get_categories());
let lv: Vec<f64> = enc_lv.get_one_hot(&"dog").unwrap();
let lm: Vec<f64> = enc_lm.get_one_hot(&"dog").unwrap();
assert_eq!(lv, lm);

Implementations

impl<C> CategoryMapper<C>

where C: Hash + Eq + Clone,

pub fn num_categories(&self) -> usize

Get the number of categories in the mapper

pub fn fit_to_iter(categories: impl Iterator<Item = C>) -> Self

Fit an encoder to a lable iterator

pub fn from_category_map(category_map: HashMap<C, usize>) -> Self

Build an encoder from a predefined (category -> class number) map

pub fn from_positional_category_vec(categories: Vec<C>) -> Self

Build an encoder from a predefined positional category-class num vector

pub fn get_num(&self, category: &C) -> Option<&usize>

Get label num of a category

pub fn get_cat(&self, num: usize) -> &C

Return category corresponding to label num

pub fn get_categories(&self) -> &[C]

List all categories (position = category number)

pub fn get_one_hot<U, V>(&self, category: &C) -> Option<V>

where U: RealNumber, V: Array1<U>,

Get one-hot encoding of the category

pub fn invert_one_hot<U, V>(&self, one_hot: V) -> Result<C, Failed>

where U: RealNumber, V: Array1<U>,

Invert one-hot vector, back to the category

pub fn get_ordinal<U>(&self, category: &C) -> Option<U>

where U: RealNumber,

Get ordinal encoding of the catergory

Trait Implementations

impl<C: Clone> Clone for CategoryMapper<C>

fn clone(&self) -> CategoryMapper<C>

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<C: Debug> Debug for CategoryMapper<C>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.