feat: adds dataset module, fixs problem in CoverTree implementation
This commit is contained in:
Volodymyr Orlov
@@ -0,0 +1,90 @@
|
||||
//! # The Iris Dataset flower
|
||||
//!
|
||||
//! [Fisher's Iris dataset](https://archive.ics.uci.edu/ml/datasets/iris) is a multivariate dataset that was published in 1936 by Ronald Fisher.
|
||||
//! This multivariate dataset is frequently used to demonstrate various machine learning algorithms.
|
||||
use crate::dataset::Dataset;
|
||||
|
||||
/// Get dataset
|
||||
pub fn load_dataset() -> Dataset<f32, f32> {
|
||||
let x = 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, 0.1, 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,
|
||||
];
|
||||
|
||||
let setosa = std::iter::repeat(0f32).take(50);
|
||||
let versicolor = std::iter::repeat(1f32).take(50);
|
||||
let virginica = std::iter::repeat(2f32).take(50);
|
||||
let y = setosa
|
||||
.chain(versicolor)
|
||||
.chain(virginica)
|
||||
.collect::<Vec<f32>>();
|
||||
let shape = (150, 4);
|
||||
|
||||
Dataset {
|
||||
data: x,
|
||||
target: y,
|
||||
num_samples: shape.0,
|
||||
num_features: shape.1,
|
||||
feature_names: vec![
|
||||
"sepal length (cm)",
|
||||
"sepal width (cm)",
|
||||
"petal length (cm)",
|
||||
"petal width (cm)",
|
||||
]
|
||||
.iter()
|
||||
.map(|s| s.to_string())
|
||||
.collect(),
|
||||
target_names: vec!["setosa", "versicolor", "virginica"]
|
||||
.iter()
|
||||
.map(|s| s.to_string())
|
||||
.collect(),
|
||||
description: "Iris dataset: https://archive.ics.uci.edu/ml/datasets/iris".to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn iris_dataset() {
|
||||
let dataset = load_dataset();
|
||||
assert_eq!(dataset.data.len(), 50 * 3 * 4);
|
||||
assert_eq!(dataset.target.len(), 50 * 3);
|
||||
assert_eq!(dataset.num_features, 4);
|
||||
assert_eq!(dataset.num_samples, 50 * 3);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,65 @@
|
||||
//! Datasets
|
||||
//!
|
||||
//! In this module you will find small datasets that are used in SmartCore for demonstration purpose mostly.
|
||||
|
||||
/// Iris flower data set
|
||||
pub mod iris;
|
||||
|
||||
/// Dataset
|
||||
pub struct Dataset<X, Y> {
|
||||
/// data in one-dimensional array.
|
||||
pub data: Vec<X>,
|
||||
/// target values or class labels.
|
||||
pub target: Vec<Y>,
|
||||
/// number of samples (number of rows in matrix form).
|
||||
pub num_samples: usize,
|
||||
/// number of features (number of columns in matrix form).
|
||||
pub num_features: usize,
|
||||
/// names of dependent variables.
|
||||
pub feature_names: Vec<String>,
|
||||
/// names of target variables.
|
||||
pub target_names: Vec<String>,
|
||||
/// dataset description
|
||||
pub description: String,
|
||||
}
|
||||
|
||||
impl<X, Y> Dataset<X, Y> {
|
||||
/// Reshape data into a two-dimensional matrix
|
||||
pub fn as_2d_vector(&self) -> Vec<Vec<&X>> {
|
||||
let mut result: Vec<Vec<&X>> = Vec::with_capacity(self.num_samples);
|
||||
|
||||
for r in 0..self.num_samples {
|
||||
let mut row = Vec::with_capacity(self.num_features);
|
||||
for c in 0..self.num_features {
|
||||
row.push(&self.data[r * self.num_features + c]);
|
||||
}
|
||||
result.push(row);
|
||||
}
|
||||
|
||||
result
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn as_2d_vector() {
|
||||
let dataset = Dataset {
|
||||
data: vec![1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
|
||||
target: vec![1, 2, 3],
|
||||
num_samples: 2,
|
||||
num_features: 5,
|
||||
feature_names: vec![],
|
||||
target_names: vec![],
|
||||
description: "".to_string(),
|
||||
};
|
||||
|
||||
let m = dataset.as_2d_vector();
|
||||
|
||||
assert_eq!(m.len(), 2);
|
||||
assert_eq!(m[0].len(), 5);
|
||||
assert_eq!(*m[1][3], 9);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user