F# Community Twitter Clients (2014)

twitter_clients_2014.fsx

#I @"packages/"
#r @"FSharp.Data/lib/net40/FSharp.Data.dll"
#load @"FSPlot\FsPlotBootstrap.fsx"
#r @"Deedle\lib\net40\Deedle.dll"
do fsi.AddPrinter(fun (printer:Deedle.Internal.IFsiFormattable) -> "\n" + (printer.Format()))

open FSharp.Data
 
type Tweets = CsvProvider<"fsharp_2013-2014.csv">
let tweets = Tweets.GetSample()

let extractNameFromAnchorTag (anchorTag: string) =
    let indexOfDisplayText = anchorTag.IndexOf("\">") + 2
    let displayTextIncCloseTag = anchorTag.Substring(indexOfDisplayText, anchorTag.Length - indexOfDisplayText)
    displayTextIncCloseTag.Remove(displayTextIncCloseTag.Length - 4, 4) // remove trailing "</a>"

let topTwitterClients =
    tweets.Rows
    |> Seq.filter (fun x -> x.CreatedDate.Year = 2014)
    |> Seq.groupBy (fun x ->
        match x.Source with
        | "web" -> "web"
        | _ when x.Source.StartsWith("<a href=") -> extractNameFromAnchorTag x.Source
        | _ -> failwithf "unexpected source on %A" x
    )
    |> Seq.map (fun (group, items) ->
        (group, Seq.length items))
    |> Seq.sortBy (fun (_, cnt) -> -cnt)
    |> Seq.filter (fun (_, cnt) -> cnt > 15) // at least 15 usages

open FsPlot.Highcharts.Charting

topTwitterClients |> Chart.Pie |> Chart.WithTitle "F# Community Twitter Clients"