smartcore 0.2.0

The most advanced machine learning library in rust.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130

#![allow(clippy::ptr_arg)]
use std::collections::HashMap;

use crate::math::num::RealNumber;
use crate::math::vector::RealNumberVector;

pub fn contingency_matrix<T: RealNumber>(
    labels_true: &Vec<T>,
    labels_pred: &Vec<T>,
) -> Vec<Vec<usize>> {
    let (classes, class_idx) = labels_true.unique_with_indices();
    let (clusters, cluster_idx) = labels_pred.unique_with_indices();

    let mut contingency_matrix = Vec::with_capacity(classes.len());

    for _ in 0..classes.len() {
        contingency_matrix.push(vec![0; clusters.len()]);
    }

    for i in 0..class_idx.len() {
        contingency_matrix[class_idx[i]][cluster_idx[i]] += 1;
    }

    contingency_matrix
}

pub fn entropy<T: RealNumber>(data: &[T]) -> Option<T> {
    let mut bincounts = HashMap::with_capacity(data.len());

    for e in data.iter() {
        let k = e.to_i64().unwrap();
        bincounts.insert(k, bincounts.get(&k).unwrap_or(&0) + 1);
    }

    let mut entropy = T::zero();
    let sum = T::from_usize(bincounts.values().sum()).unwrap();

    for &c in bincounts.values() {
        if c > 0 {
            let pi = T::from_usize(c).unwrap();
            entropy -= (pi / sum) * (pi.ln() - sum.ln());
        }
    }

    Some(entropy)
}

pub fn mutual_info_score<T: RealNumber>(contingency: &[Vec<usize>]) -> T {
    let mut contingency_sum = 0;
    let mut pi = vec![0; contingency.len()];
    let mut pj = vec![0; contingency[0].len()];
    let (mut nzx, mut nzy, mut nz_val) = (Vec::new(), Vec::new(), Vec::new());

    for r in 0..contingency.len() {
        for (c, pj_c) in pj.iter_mut().enumerate().take(contingency[0].len()) {
            contingency_sum += contingency[r][c];
            pi[r] += contingency[r][c];
            *pj_c += contingency[r][c];
            if contingency[r][c] > 0 {
                nzx.push(r);
                nzy.push(c);
                nz_val.push(contingency[r][c]);
            }
        }
    }

    let contingency_sum = T::from_usize(contingency_sum).unwrap();
    let contingency_sum_ln = contingency_sum.ln();
    let pi_sum_l = T::from_usize(pi.iter().sum()).unwrap().ln();
    let pj_sum_l = T::from_usize(pj.iter().sum()).unwrap().ln();

    let log_contingency_nm: Vec<T> = nz_val
        .iter()
        .map(|v| T::from_usize(*v).unwrap().ln())
        .collect();
    let contingency_nm: Vec<T> = nz_val
        .iter()
        .map(|v| T::from_usize(*v).unwrap() / contingency_sum)
        .collect();
    let outer: Vec<usize> = nzx
        .iter()
        .zip(nzy.iter())
        .map(|(&x, &y)| pi[x] * pj[y])
        .collect();
    let log_outer: Vec<T> = outer
        .iter()
        .map(|&o| -T::from_usize(o).unwrap().ln() + pi_sum_l + pj_sum_l)
        .collect();

    let mut result = T::zero();

    for i in 0..log_outer.len() {
        result += (contingency_nm[i] * (log_contingency_nm[i] - contingency_sum_ln))
            + contingency_nm[i] * log_outer[i]
    }

    result.max(T::zero())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn contingency_matrix_test() {
        let v1 = vec![0.0, 0.0, 1.0, 1.0, 2.0, 0.0, 4.0];
        let v2 = vec![1.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0];

        assert_eq!(
            vec!(vec!(1, 2), vec!(2, 0), vec!(1, 0), vec!(1, 0)),
            contingency_matrix(&v1, &v2)
        );
    }

    #[test]
    fn entropy_test() {
        let v1 = vec![0.0, 0.0, 1.0, 1.0, 2.0, 0.0, 4.0];

        assert!((1.2770f32 - entropy(&v1).unwrap()).abs() < 1e-4);
    }

    #[test]
    fn mutual_info_score_test() {
        let v1 = vec![0.0, 0.0, 1.0, 1.0, 2.0, 0.0, 4.0];
        let v2 = vec![1.0, 0.0, 0.0, 0.0, 0.0, 1.0, 0.0];
        let s: f32 = mutual_info_score(&contingency_matrix(&v1, &v2));

        assert!((0.3254 - s).abs() < 1e-4);
    }
}