scirs2-datasets 0.4.1

Datasets module for SciRS2 (scirs2-datasets)
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

//! Embedded Iris dataset (Fisher, 1936)
//!
//! 150 samples, 4 features, 3 classes

use super::DatasetResult;
use crate::error::Result;
use scirs2_core::ndarray::{Array1, Array2};

pub(super) fn load() -> Result<DatasetResult> {
    #[rustfmt::skip]
    let raw: Vec<f64> = vec![
        5.1,3.5,1.4,0.2, 4.9,3.0,1.4,0.2, 4.7,3.2,1.3,0.2, 4.6,3.1,1.5,0.2, 5.0,3.6,1.4,0.2,
        5.4,3.9,1.7,0.4, 4.6,3.4,1.4,0.3, 5.0,3.4,1.5,0.2, 4.4,2.9,1.4,0.2, 4.9,3.1,1.5,0.1,
        5.4,3.7,1.5,0.2, 4.8,3.4,1.6,0.2, 4.8,3.0,1.4,0.1, 4.3,3.0,1.1,0.1, 5.8,4.0,1.2,0.2,
        5.7,4.4,1.5,0.4, 5.4,3.9,1.3,0.4, 5.1,3.5,1.4,0.3, 5.7,3.8,1.7,0.3, 5.1,3.8,1.5,0.3,
        5.4,3.4,1.7,0.2, 5.1,3.7,1.5,0.4, 4.6,3.6,1.0,0.2, 5.1,3.3,1.7,0.5, 4.8,3.4,1.9,0.2,
        5.0,3.0,1.6,0.2, 5.0,3.4,1.6,0.4, 5.2,3.5,1.5,0.2, 5.2,3.4,1.4,0.2, 4.7,3.2,1.6,0.2,
        4.8,3.1,1.6,0.2, 5.4,3.4,1.5,0.4, 5.2,4.1,1.5,0.1, 5.5,4.2,1.4,0.2, 4.9,3.1,1.5,0.2,
        5.0,3.2,1.2,0.2, 5.5,3.5,1.3,0.2, 4.9,3.6,1.4,0.1, 4.4,3.0,1.3,0.2, 5.1,3.4,1.5,0.2,
        5.0,3.5,1.3,0.3, 4.5,2.3,1.3,0.3, 4.4,3.2,1.3,0.2, 5.0,3.5,1.6,0.6, 5.1,3.8,1.9,0.4,
        4.8,3.0,1.4,0.3, 5.1,3.8,1.6,0.2, 4.6,3.2,1.4,0.2, 5.3,3.7,1.5,0.2, 5.0,3.3,1.4,0.2,
        7.0,3.2,4.7,1.4, 6.4,3.2,4.5,1.5, 6.9,3.1,4.9,1.5, 5.5,2.3,4.0,1.3, 6.5,2.8,4.6,1.5,
        5.7,2.8,4.5,1.3, 6.3,3.3,4.7,1.6, 4.9,2.4,3.3,1.0, 6.6,2.9,4.6,1.3, 5.2,2.7,3.9,1.4,
        5.0,2.0,3.5,1.0, 5.9,3.0,4.2,1.5, 6.0,2.2,4.0,1.0, 6.1,2.9,4.7,1.4, 5.6,2.9,3.6,1.3,
        6.7,3.1,4.4,1.4, 5.6,3.0,4.5,1.5, 5.8,2.7,4.1,1.0, 6.2,2.2,4.5,1.5, 5.6,2.5,3.9,1.1,
        5.9,3.2,4.8,1.8, 6.1,2.8,4.0,1.3, 6.3,2.5,4.9,1.5, 6.1,2.8,4.7,1.2, 6.4,2.9,4.3,1.3,
        6.6,3.0,4.4,1.4, 6.8,2.8,4.8,1.4, 6.7,3.0,5.0,1.7, 6.0,2.9,4.5,1.5, 5.7,2.6,3.5,1.0,
        5.5,2.4,3.8,1.1, 5.5,2.4,3.7,1.0, 5.8,2.7,3.9,1.2, 6.0,2.7,5.1,1.6, 5.4,3.0,4.5,1.5,
        6.0,3.4,4.5,1.6, 6.7,3.1,4.7,1.5, 6.3,2.3,4.4,1.3, 5.6,3.0,4.1,1.3, 5.5,2.5,4.0,1.3,
        5.5,2.6,4.4,1.2, 6.1,3.0,4.6,1.4, 5.8,2.6,4.0,1.2, 5.0,2.3,3.3,1.0, 5.6,2.7,4.2,1.3,
        5.7,3.0,4.2,1.2, 5.7,2.9,4.2,1.3, 6.2,2.9,4.3,1.3, 5.1,2.5,3.0,1.1, 5.7,2.8,4.1,1.3,
        6.3,3.3,6.0,2.5, 5.8,2.7,5.1,1.9, 7.1,3.0,5.9,2.1, 6.3,2.9,5.6,1.8, 6.5,3.0,5.8,2.2,
        7.6,3.0,6.6,2.1, 4.9,2.5,4.5,1.7, 7.3,2.9,6.3,1.8, 6.7,2.5,5.8,1.8, 7.2,3.6,6.1,2.5,
        6.5,3.2,5.1,2.0, 6.4,2.7,5.3,1.9, 6.8,3.0,5.5,2.1, 5.7,2.5,5.0,2.0, 5.8,2.8,5.1,2.4,
        6.4,3.2,5.3,2.3, 6.5,3.0,5.5,1.8, 7.7,3.8,6.7,2.2, 7.7,2.6,6.9,2.3, 6.0,2.2,5.0,1.5,
        6.9,3.2,5.7,2.3, 5.6,2.8,4.9,2.0, 7.7,2.8,6.7,2.0, 6.3,2.7,4.9,1.8, 6.7,3.3,5.7,2.1,
        7.2,3.2,6.0,1.8, 6.2,2.8,4.8,1.8, 6.1,3.0,4.9,1.8, 6.4,2.8,5.6,2.1, 7.2,3.0,5.8,1.6,
        7.4,2.8,6.1,1.9, 7.9,3.8,6.4,2.0, 6.4,2.8,5.6,2.2, 6.3,2.8,5.1,1.5, 6.1,2.6,5.6,1.4,
        7.7,3.0,6.1,2.3, 6.3,3.4,5.6,2.4, 6.4,3.1,5.5,1.8, 6.0,3.0,4.8,1.8, 6.9,3.1,5.4,2.1,
        6.7,3.1,5.6,2.4, 6.9,3.1,5.1,2.3, 5.8,2.7,5.1,1.9, 6.8,3.2,5.9,2.3, 6.7,3.3,5.7,2.5,
        6.7,3.0,5.2,2.3, 6.3,2.5,5.0,1.9, 6.5,3.0,5.2,2.0, 6.2,3.4,5.4,2.3, 5.9,3.0,5.1,1.8,
    ];

    let data = Array2::from_shape_vec((150, 4), raw).map_err(|e| {
        crate::error::DatasetsError::ComputationError(format!("Iris data error: {e}"))
    })?;

    let mut target_vec = Vec::with_capacity(150);
    target_vec.extend(std::iter::repeat_n(0.0_f64, 50));
    target_vec.extend(std::iter::repeat_n(1.0_f64, 50));
    target_vec.extend(std::iter::repeat_n(2.0_f64, 50));
    let target = Array1::from_vec(target_vec);

    Ok(DatasetResult {
        data,
        target,
        feature_names: vec![
            "sepal_length".into(),
            "sepal_width".into(),
            "petal_length".into(),
            "petal_width".into(),
        ],
        target_names: vec!["setosa".into(), "versicolor".into(), "virginica".into()],
        description: "Iris Plants Dataset (Fisher, 1936)\n\n\
            150 samples of iris flowers from 3 species.\n\
            Features: sepal length/width, petal length/width (cm).\n\
            Classes: Setosa (0), Versicolor (1), Virginica (2).\n\
            One class is linearly separable; the other two are not."
            .into(),
    })
}