HRLClassifier

Use Machine Learning to predict if a person is working out based of his/her heart rate.

Example

To run the example project, clone the repo, and run pod install from the Example directory first.

Installation

HRLClassifier is available through CocoaPods. To install it, simply add the following line to your Podfile:

pod"HRLClassifier"

Usage

import HRLClassifier
letfilename="/path/to/archive"letbaseDate=Date(timeIntervalSinceReferenceDate:0)letdayInterval=24*60*60letmaxBPM=200
// Fill data frame
varauxDataFrame=NSKeyedUnarchiver.unarchiveObject(withFile: filename)as?DataFrameif auxDataFrame ==nil{
auxDataFrame =DataFrame()foriin0..<7{for_in0..<80{lettimeInterval= i * dayInterval + Int(arc4random_uniform(UInt32(dayInterval)))letdate= baseDate.addingTimeInterval(TimeInterval(timeInterval))letbpm=Float(arc4random_uniform(UInt32(maxBPM)))letrecord=Record(date: date, bpm: bpm)letisWorkingOut=arc4random_uniform(2)==1?true:false
auxDataFrame!.append(record: record, isWorkingOut: isWorkingOut)}}}letdataFrame= auxDataFrame!
// Make classifier
guardlet classifier =try?ClassifierFactory().makeClassifier(dataFrame: dataFrame)else{print("Given that all records are created in a random fashion, this is expected")return}
// Archive data frame
NSKeyedArchiver.archiveRootObject(dataFrame, toFile: filename)
// Predict
letdate= baseDate.addingTimeInterval(TimeInterval(7* dayInterval))letbpm=Float(arc4random_uniform(UInt32(maxBPM)))letrecord=Record(date: date, bpm: bpm)letprediction= classifier.predictedWorkingOut(for: record)print("At \(date) with \(bpm) bpm, is user working out? \(prediction)")

License

HRLClassifier is available under the MIT license. See the LICENSE file for more info.