datarust 0.6.1

Scikit-learn-style preprocessing and classical ML 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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240

//! Iris flower classification dataset.
//!
//! 150 samples, 4 features (sepal/petal length/width in cm), 3 classes
//! (setosa, versicolor, virginica). The classic "hello world" of machine
//! learning, originally from Fisher (1936).
//!
//! ```rust
//! use datarust::datasets::iris;
//!
//! let data = iris::load();
//! assert_eq!(data.n_samples(), 150);
//! assert_eq!(data.n_features(), 4);
//! assert_eq!(data.n_classes(), 3);
//!
//! let x = data.features(); // Matrix 150×4
//! let y = data.targets();  // &[f64], values in {0, 1, 2}
//! ```

use super::Dataset;

const FEATURE_NAMES: [&str; 4] = ["sepal_length", "sepal_width", "petal_length", "petal_width"];

const TARGET_NAMES: [&str; 3] = ["setosa", "versicolor", "virginica"];

const IRIS_DATA: [[f64; 4]; 150] = [
    [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, 0.1],
    [5.0, 3.2, 1.2, 0.2],
    [5.5, 3.5, 1.3, 0.2],
    [4.9, 3.1, 1.5, 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],
];

const IRIS_TARGET: [f64; 150] = [
    0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
    0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
    0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
    1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
    1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0,
    1.0, 1.0, 1.0, 1.0, 1.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0,
    2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0,
    2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0,
];

/// Loads the Iris dataset.
///
/// Returns a [`Dataset`] with 150 samples, 4 features, and 3 balanced classes.
/// Targets are `0.0` (setosa), `1.0` (versicolor), `2.0` (virginica).
pub fn load() -> Dataset {
    let data: Vec<Vec<f64>> = IRIS_DATA.iter().map(|r| r.to_vec()).collect();
    let target = IRIS_TARGET.to_vec();
    Dataset::from_const(data, target, &FEATURE_NAMES, &TARGET_NAMES)
}

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

    #[test]
    fn iris_dimensions() {
        let d = load();
        assert_eq!(d.n_samples(), 150);
        assert_eq!(d.n_features(), 4);
        assert_eq!(d.n_classes(), 3);
    }

    #[test]
    fn iris_class_balance() {
        let d = load();
        let y = d.targets();
        let n0 = y.iter().filter(|&&v| v == 0.0).count();
        let n1 = y.iter().filter(|&&v| v == 1.0).count();
        let n2 = y.iter().filter(|&&v| v == 2.0).count();
        assert_eq!([n0, n1, n2], [50, 50, 50]);
    }

    #[test]
    fn iris_features_matrix() {
        let d = load();
        let x = d.features();
        assert_eq!(x.nrows(), 150);
        assert_eq!(x.ncols(), 4);
        // First sample: sepal_length=5.1
        assert!((x.get(0, 0) - 5.1).abs() < 1e-12);
    }

    #[test]
    fn iris_feature_names() {
        let d = load();
        assert_eq!(
            d.feature_names(),
            ["sepal_length", "sepal_width", "petal_length", "petal_width"]
        );
        assert_eq!(d.target_names(), ["setosa", "versicolor", "virginica"]);
    }
}