vega-regression

What is vega-regression?

The vega-regression npm package provides tools for performing regression analysis on datasets. It supports various types of regression models, including linear, exponential, logarithmic, and polynomial regressions. This package is particularly useful for data visualization and analysis within the Vega ecosystem.

What are vega-regression's main functionalities?

Linear Regression

This feature allows you to perform linear regression on a dataset. The code sample demonstrates how to use the vega-regression package to fit a linear model to a set of data points and predict values.

const vega = require('vega-regression');
const data = [ [0, 1], [1, 3], [2, 5], [3, 7] ];
const model = vega.regression('linear').data(data).predict();
console.log(model);

Exponential Regression

This feature allows you to perform exponential regression on a dataset. The code sample demonstrates how to use the vega-regression package to fit an exponential model to a set of data points and predict values.

const vega = require('vega-regression');
const data = [ [0, 1], [1, 2.7], [2, 7.4], [3, 20.1] ];
const model = vega.regression('exponential').data(data).predict();
console.log(model);

Logarithmic Regression

This feature allows you to perform logarithmic regression on a dataset. The code sample demonstrates how to use the vega-regression package to fit a logarithmic model to a set of data points and predict values.

const vega = require('vega-regression');
const data = [ [1, 0], [2, 1.1], [3, 1.8], [4, 2.3] ];
const model = vega.regression('log').data(data).predict();
console.log(model);

Polynomial Regression

This feature allows you to perform polynomial regression on a dataset. The code sample demonstrates how to use the vega-regression package to fit a polynomial model of degree 2 to a set of data points and predict values.

const vega = require('vega-regression');
const data = [ [0, 1], [1, 6], [2, 17], [3, 34] ];
const model = vega.regression('poly', 2).data(data).predict();
console.log(model);

Other packages similar to vega-regression

regression

The regression package provides a simple interface for performing various types of regression analysis, including linear, exponential, logarithmic, and polynomial regressions. It is similar to vega-regression in terms of functionality but is more general-purpose and not specifically tied to the Vega ecosystem.

simple-statistics

The simple-statistics package offers a wide range of statistical tools, including regression analysis. It supports linear, exponential, and polynomial regressions, among others. Compared to vega-regression, simple-statistics provides a broader set of statistical functions beyond just regression.

ml-regression

The ml-regression package is part of the machine learning library for JavaScript and provides various regression models, including linear and polynomial regressions. It is more focused on machine learning applications and offers additional features like regularization, which are not available in vega-regression.

README

vega-regression

Regression model fitting for Vega dataflows.

This package provides the following Vega data transforms:

• Loess <>
• Regression <>