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
use csv::ReaderBuilder;
use flate2::read::GzDecoder;
use linfa::Dataset;
use ndarray::prelude::*;
use ndarray_csv::Array2Reader;
#[cfg(any(feature = "iris", feature = "diabetes", feature = "winequality"))]
fn array_from_buf(buf: &[u8]) -> Array2<f64> {
let file = GzDecoder::new(buf);
let mut reader = ReaderBuilder::new()
.has_headers(true)
.delimiter(b',')
.from_reader(file);
reader.deserialize_array2_dynamic().unwrap()
}
#[cfg(feature = "iris")]
pub fn iris() -> Dataset<f64, usize> {
let data = include_bytes!("../data/iris.csv.gz");
let array = array_from_buf(&data[..]);
let (data, targets) = (
array.slice(s![.., 0..4]).to_owned(),
array.column(4).to_owned(),
);
Dataset::new(data, targets).map_targets(|x| *x as usize)
}
#[cfg(feature = "diabetes")]
pub fn diabetes() -> Dataset<f64, f64> {
let data = include_bytes!("../data/diabetes_data.csv.gz");
let data = array_from_buf(&data[..]);
let targets = include_bytes!("../data/diabetes_target.csv.gz");
let targets = array_from_buf(&targets[..]).column(0).to_owned();
Dataset::new(data, targets)
}
#[cfg(feature = "winequality")]
pub fn winequality() -> Dataset<f64, usize> {
let data = include_bytes!("../data/winequality-red.csv.gz");
let array = array_from_buf(&data[..]);
let (data, targets) = (
array.slice(s![.., 0..11]).to_owned(),
array.column(11).to_owned(),
);
Dataset::new(data, targets).map_targets(|x| *x as usize)
}