Struct BoundsInfo

pub struct BoundsInfo<T> {
    pub type_classif: Classification,
    pub nb_class: u32,
    pub bounds: Vec<T>,
    pub min: T,
    pub max: T,
    pub mean: T,
}

A struct containing the bounds computed at its creation and some basic statistical informations : minimum, maximum and mean value.

The main field of BoundsInfo struct is the bounds field: a Vec<T> containing the bounds. The lower bound is the minimum of the input values and the upper bound is the maximum.

The get_class_index method allows to retrieve the index of the cluster in which belongs an input value.

Example :

extern crate classif;
extern crate num_traits;

let values = vec![1.0, 1.3, 2.4, 5.0, 2.1, 5.3, 4.0, 3.0, 1.3, 4.3, 6.0, 2.1];
let bounds_info = classif::BoundsInfo::new(4, &values, classif::Classification::EqualInterval).unwrap();
// The first bounds value is the minimum:
assert_eq!(*bounds_info.bounds.first().unwrap(), bounds_info.min);
// And the last bounds value is the maximum:
assert_eq!(*bounds_info.bounds.last().unwrap(), bounds_info.max);
// So for 4 class we need a vector of 5 values :
assert_eq!(bounds_info.bounds.len(), 5);
// In which class belong the value 4.4 ?
let ix = bounds_info.get_class_index(4.4).unwrap();

Fields

type_classif: Classification

nb_class: u32

bounds: Vec<T>

min: T

max: T

mean: T

Implementations

impl<T> BoundsInfo<T>

where T: Float + NumAssignOps,

pub fn new( nb_class: u32, values: &[T], type_classif: Classification, ) -> Result<Self, &'static str>

pub fn get_class_index(&self, value: T) -> Option<u32>

Returns the index of the class to which the value belongs, wrapped in an Option. Returns None if the value is outside the serie range.