PredictionBuilder

PredictionBuilder is a library for machine learning that builds predictions using a linear regression.

Installation

CocoaPods

To install PredictionBuilder using CocoaPods, add this line to your Podfile:

pod 'PredictionBuilder', '~> 1.2.0'

Carthage

To install PredictionBuilder using Carthage, add this line to your Cartfile:

github "denissimon/prediction-builder-swift"

Swift Package Manager

To install PredictionBuilder using Swift Package Manager, add the following to your Package.swift:

dependencies: [
    .Package(url: "https://github.com/denissimon/prediction-builder-swift.git", majorVersion: 1)
]

Manually

Copy PredictionBuilder.swift into your project.

Example

import PredictionBuilder

let data: [[Double]] = [[1,20],[2,70],[2,45],[3,81],[5,73],[6,80],[7,110]]
let x: Double = 4.5

let prediction = PredictionBuilder()

prediction.set(x: x, data: data)

// What is the expected y value for a given x value?
do {
    let result = try prediction.build() // y = 76.65
} catch let msg {
    print(msg)
}

The returned instance has the following properties:

result.lnModel linear model that fits the data: “29.56362+10.46364x”

result.cor correlation coefficient: 0.8348

result.x given x value: 4.5

result.y predicted y value: 76.65

License

Licensed under the MIT License