glm

glm.js

Responsive generalized linear models in pure Javascript. This tool is useful for responsive feedback when doing data cleansing or adjusting parameters that actually change the data.

This is essentially a port of a python GLM implementation that uses the iteratively reweighted least squares algorithm in the excellent statsmodels library.

Applications

• Visualization
• Data processing
• Teaching / education linear models

Example usage in browser

Run "python -m SimpleHTTPServer" in the root of this repo and navigate your browser to "http://localhost:8000/examples/"

Example usage in Node

var glm = require('glm');
var glm_model = GLM(GLM.families.Gaussian());
glm_model.fit([1, 2], [[1], [2]]);
console.log(glm_model.predict([3, 4])); // should predict 3 and 4

Compiling

To compile, first install the dependencies with npm and then run make. To test, run "make test".