Language Safety Score using Logistic Regression

Script.fsx

(*
This is a reaction to this blog post by Steve Shogren: 
http://deliberate-software.com/safety-rank-part-2/
*)

#I @"../packages"
#r @"Accord.3.0.1-alpha\lib\net45\Accord.dll"
#r @"Accord.MachineLearning.3.0.1-alpha\lib\net45\Accord.MachineLearning.dll"
#r @"Accord.Math.3.0.1-alpha\lib\net45\Accord.Math.dll"
#r @"Accord.Statistics.3.0.1-alpha\lib\net45\Accord.Statistics.dll"

let language, bugrate, criteria = 
    [|  "F#",           0.023486288,    [|1.;1.;1.;0.;1.;1.;1.;0.;0.;0.;1.;1.;1.;0.|]
        "Haskell",      0.015551204,    [|1.;1.;1.;0.;1.;1.;1.;1.;1.;0.;1.;1.;0.;1.|]
        "Javascript",   0.039445132,    [|0.;0.;0.;0.;0.;0.;0.;0.;0.;0.;1.;0.;1.;0.|] 
        "CoffeeScript", 0.047242288,    [|0.;0.;0.;0.;0.;0.;0.;0.;0.;0.;1.;0.;1.;0.|] 
        "Clojure",      0.011503478,    [|0.;1.;0.;0.;0.;0.;1.;0.;1.;1.;1.;0.;0.;0.|] 
        "C#",           0.03261284,     [|0.;0.;1.;0.;0.;1.;1.;0.;0.;0.;1.;0.;1.;0.|] 
        "Python",       0.02531419,     [|0.;0.;0.;0.;0.;0.;0.;0.;0.;0.;1.;0.;1.;0.|] 
        "Java",         0.032567736,    [|0.;0.;0.;0.;0.;0.;0.;0.;0.;0.;1.;0.;1.;0.|] 
        "Ruby",         0.020303702,    [|0.;0.;0.;0.;0.;0.;0.;0.;0.;0.;1.;0.;1.;0.|] 
        "Scala",        0.01904762,     [|1.;1.;1.;0.;1.;1.;1.;0.;0.;0.;1.;0.;0.;0.|] 
        "Go",           0.024698375,    [|0.;0.;1.;0.;0.;1.;1.;0.;0.;0.;1.;0.;1.;0.|] 
        "PHP",          0.031669293,    [|0.;0.;0.;0.;0.;0.;0.;0.;0.;0.;1.;0.;1.;0.|] |]
    |> Array.unzip3

open Accord.Statistics.Models.Regression
open Accord.Statistics.Models.Regression.Fitting 

let features = 14
let model = LogisticRegression(features)
let learner = LogisticGradientDescent(model)

let rec learn () = 
    let delta = learner.Run(criteria, bugrate)
    if delta > 0.0001
    then learn ()
    else ignore ()

learn () |> ignore

for i in 0 .. (language.Length - 1) do    
    let lang = language.[i]
    let predicted = model.Compute(criteria.[i])
    let real = bugrate.[i]
    printfn "%16s Real: %.3f Pred: %.3f" lang real predicted

#load "FSharp.Charting.0.90.12\FSharp.Charting.fsx"
open FSharp.Charting

let last = language.Length - 1

Chart.Combine [
    Chart.Line ([ for i in 0 .. last -> bugrate.[i]], "Real", Labels=language)
    Chart.Line ([ for i in 0 .. last -> model.Compute(criteria.[i])], "Pred") ] 
|> Chart.WithLegend()

let criteriaNames = [|
    "Null Variable Usage"
    "Null List Iteration"
    "Prevent Variable Reuse"
    "Ensure List Element Exists"
    "Safe Type Casting"
    "Passing Wrong Type"
    "Misspelled Method"
    "Missing Enum Value"
    "Variable Mutation"
    "Prevent Deadlocks"
    "Memory Deallocation"
    "Tail Call Optimization"
    "Guaranteed Code Evaluation"
    "Functional Purity" |]    
        
for i in 0 .. (features - 1) do 
    let name = criteriaNames.[i]
    let wald = model.GetWaldTest(i)
    let odds = model.GetOddsRatio(i)
    (printfn "%28s odds: %4.2f significant: %b" name odds wald.Significant)

[ for i in 0 .. (features - 1) -> 
    let name = criteriaNames.[i]
    let odds = model.GetOddsRatio(i)
    name,odds ]
|> List.sortBy snd
|> List.iter (printfn "%A")

With Accord.3.4.0 you can do things more functional style and don't have to write the learn-loop manually:

let alg = LogisticRegression(NumberOfInputs = features)
let learner = LogisticGradientDescent(alg, Iterations=10000)
let model = learner.Learn(criteria, bugrate)

With Accord.3.4.0 you can do things more functional style and don't have to write the learn-loop manually:

let alg = LogisticRegression(NumberOfInputs = features)
let learner = LogisticGradientDescent(alg, Iterations=10000)
let model = learner.Learn(criteria, bugrate)