Blyx

CUSUM

Change-detection library · 0.1.0

Detect persistent shifts in a sequence of standardized observations with a two-sided cumulative sum.

Install with Conda

Create an environment containing CUSUM 0.1.0, its Blyx source and a runnable example. Run the second command with Blyx 0.2.1, Rust and a host linker installed.

conda create -y --prefix ./blyx-env --override-channels -c https://rahulchaube1.github.io/blyx-packages blyx-cusum=0.1.0=0
blyxc native-run ./blyx-env/share/blyx/cusum/main.blyx

To use this package in your application, copy share/blyx/cusum/vendor/cusum from the environment into your project's vendor directory.

Install the full collection with Homebrew or Scoop

Import into a Blyx project

Install Blyx 0.2.1, Rust 1.85 or newer and a host linker. From the directory containing your entry file, clone this tagged release.

git clone --depth 1 --branch v0.1.0 https://github.com/Rahulchaube1/blyx-cusum.git vendor/cusum

Save this as main.blyx beside vendor and run blyxc native-run main.blyx.

use vendor::cusum::cusum;
fn main() {
    let mut state = cs_empty();
    let observations = [2, 2, -3.5];
    let mut i = 0;
    while i < len(observations) {
        state = cs_step(state, at(observations, i), 0.5, 3.0);
        println!(at(state, 2));
        i += 1;
    }
}

Expected output

0
1
-1

API and input requirements

Supply standardized observations in order. The allowance controls how much deviation is ignored. The limit is inclusive. An observation following an alarm starts a fresh episode. Tune both values for the time series you monitor.

APIUse
cs_empty()Start with zero evidence of an upward or downward shift.
cs_step(state, z, allowance, limit)Return [upward magnitude, downward magnitude, direction]. Save this state for the next point.

Develop and contribute

Open the tagged source to read the implementation and examples. Include the smallest reproducible Blyx program, compiler version and expected result when reporting an issue.