#statistics #regression #ols

linregress

ordinary least squared linear regression with some basic statistics

18 releases

0.5.1 Feb 4, 2023
0.5.0 Jul 12, 2022
0.5.0-alpha.1 Feb 24, 2022
0.4.4 Aug 25, 2021
0.1.3 Mar 24, 2019

#47 in Algorithms

Download history 15424/week @ 2022-12-02 14082/week @ 2022-12-09 13219/week @ 2022-12-16 8813/week @ 2022-12-23 9779/week @ 2022-12-30 13382/week @ 2023-01-06 14680/week @ 2023-01-13 15093/week @ 2023-01-20 13347/week @ 2023-01-27 15261/week @ 2023-02-03 14133/week @ 2023-02-10 14709/week @ 2023-02-17 16515/week @ 2023-02-24 16576/week @ 2023-03-03 16664/week @ 2023-03-10 16341/week @ 2023-03-17

68,526 downloads per month
Used in 135 crates (4 directly)

MIT license

75KB
1.5K SLoC

linregress

A Rust library providing an easy to use implementation of ordinary least squared linear regression with some basic statistics.

Contact

Linregress has been developed by the Computational Systems Medicine group at the Chair of Experimental Bioinformatics. Contact:

Documentation

Full API documentation

License

This project is licensed under the MIT License. See LICENSE-MIT for details.

Third party software

The stats module contains code adapted from the statrs library, that is licensed under the MIT License. See LICENSE-THIRD-PARTY for details.


lib.rs:

linregress provides an easy to use implementation of ordinary least squared linear regression with some basic statistics. See RegressionModel for details.

The builder FormulaRegressionBuilder is used to construct a model from a table of data and an R-style formula or a list of columns to use. Currently only very simple formulae are supported, see FormulaRegressionBuilder.formula for details.

Example

use linregress::{FormulaRegressionBuilder, RegressionDataBuilder};

# use linregress::Error;
# fn main() -> Result<(), Error> {
let y = vec![1., 2. ,3. , 4., 5.];
let x1 = vec![5., 4., 3., 2., 1.];
let x2 = vec![729.53, 439.0367, 42.054, 1., 0.];
let x3 = vec![258.589, 616.297, 215.061, 498.361, 0.];
let data = vec![("Y", y), ("X1", x1), ("X2", x2), ("X3", x3)];
let data = RegressionDataBuilder::new().build_from(data)?;
let formula = "Y ~ X1 + X2 + X3";
let model = FormulaRegressionBuilder::new()
.data(&data)
.formula(formula)
.fit()?;
let parameters: Vec<_> = model.iter_parameter_pairs().collect();
let pvalues: Vec<_> = model.iter_p_value_pairs().collect();
let standard_errors: Vec<_> = model.iter_se_pairs().collect();
assert_eq!(
parameters,
vec![
("X1", -0.9999999999999745),
("X2", 1.5872719805187785e-15),
("X3", -1.4246416546459528e-15),
]
);
assert_eq!(
standard_errors,
vec![
("X1", 9.799066977595267e-13),
("X2", 4.443774660560714e-15),
("X3", 2.713389610740135e-15),
]
);
assert_eq!(
pvalues,
vec![
("X1", 6.238279788691533e-13),
("X2", 0.7815975465725482),
("X3", 0.6922074604135647),
]
);
# Ok(())
# }

Dependencies

~3MB
~56K SLoC