How To Call WekaSharp Commands From C#

问题

Thank you all for you help on my F# and C# question and am really beginning to enjoy the fruits of the learning. I have asked a question like this before and I know these are on the line of the purposes of this forum, but I think this is useful and would provide some help to all us F# data miners out there :-). I am utilizing Yin Zhu's WekaSharp for my experiments and am interested in the rates of computation between F# and C#. I have written a snippet based on his example in the F# and would like to make its like in C# but am not sure how to approach it. Yin Zhu has create the same code to access these functions from the C# called WekaCSharp but the example he provides does not really touch on this operation. I hate to keep bugging him with my menial questions so if anyone has the time and is willing here is the F# script:

(* K-Means cluster Algorithm *)

// load the data set
let sonar = 
    System.IO.Path.Combine(__SOURCE_DIRECTORY__,  @"..\..\data\KDDCup99.arff")
    |> Dataset.readArff
    |> Dataset.setClassIndexWithLastAttribute

// set different parameters 
let Cs = [0.01; 0.1; 1.; 10.; 50.; 100.; 500.; 1000.; 2000.; 5000. ]

// make the tasks with the parameter set
let tasks = 
    Cs
    |> List.map (fun c -> Parameter.KNN.DefaultPara)
    |> List.map (fun p -> CrossValidation(3, sonar, ClassifierType.KNN, p))

Profile.tic()
// the accuracy result
let results = 
    tasks
    |> Eval.evalBulkClassify
    |> List.map Eval.getAccuracy

Profile.toc("sequential time: ")


Profile.tic()
let resultsParallel = 
    tasks
    |> Eval.evalBulkClassifyParallel
    |> List.map Eval.getAccuracy

Profile.toc("parallel (PSeq) time: ")

Again, I apologize if I am streaching the intent of this forum but this would be greatly useful for all us learning to use Weka in .NET . Here is what I have so far:

class Program
    {

        static void Classify()
        {
            Instances dataSetForTrain = new Instances(new BufferedReader(
                new FileReader(@"C:\Users\Deines\Documents\School\Software\WekaSharp2012\data\iris.arff")));
            dataSetForTrain.setClassIndex(dataSetForTrain.numAttributes() - 1);

            string options = @"-P 100 -S 1 -I 10 -W weka.classifiers.bayes.NaiveBayes -- -M 2 -V 0.0010 -N 3 -S 1 -L -1";
            Bagging model = new Bagging();
            model.setOptions(options.Split(' '));
            model.buildClassifier(dataSetForTrain);


            // test the instances from iris.arff
            Instances dataSetForTest = new Instances(new BufferedReader(
                new FileReader(@"C:\Users\Deines\Documents\School\Software\WekaSharp2012\data\iris.arff")));

            dataSetForTest.setClassIndex(dataSetForTest.numAttributes() - 1);

            for (int i = 0; i < dataSetForTest.numInstances(); i++)
            {
                var inst = dataSetForTest.instance(i);
                int label = (int)model.classifyInstance(inst);
                System.Console.WriteLine(label);
            }

        }


        public static void Main(string[] args)
        {
            Classify();
        }
    }

Thank you very much.

来源：https://stackoverflow.com/questions/20204678/how-to-call-wekasharp-commands-from-c-sharp

标签

data-mining

weka