SkillDatingKMeans.cs

using System;
using System.IO;
using Microsoft.ML;
using Microsoft.ML.Data;

var dataPath = Path.Combine(Environment.CurrentDirectory, "skills.csv");
var mlContext = new MLContext();

var dataView = mlContext.Data.LoadFromTextFile<SkillData>(dataPath, ',', true);
const string featuresColumnName = "Features";
var pipeline = mlContext.Transforms
    .Concatenate(featuresColumnName, "Windows", "Linux", "MobileDevelopment", "WebAPIs", "Cloud", "IoT", "Android")
    .Append(mlContext.Clustering.Trainers.KMeans(featuresColumnName, numberOfClusters: 2));

var model = pipeline.Fit(dataView);
var predictor = mlContext.Model.CreatePredictionEngine<SkillData, ClusterPrediction>(model);

var prediction = predictor.Predict(new SkillData
{
    Android = 1, Cloud = 5, IoT = 1, Linux = 4,
    MobileDevelopment = 4,
    WebAPIs = 5, Windows = 5
});

Console.WriteLine("Cluster: {0}", prediction.PredictedClusterId);
Console.WriteLine("Distances: {0}", string.Join(" ", prediction.Distances));
Console.ReadLine();

public class SkillData
{
    [LoadColumn(0)] public string Name;
    [LoadColumn(1)] public float Windows;
    [LoadColumn(2)] public float Linux;
    [LoadColumn(3)] public float MobileDevelopment;
    [LoadColumn(4)] public float WebAPIs;
    [LoadColumn(5)] public float Cloud;
    [LoadColumn(6)] public float IoT;
    [LoadColumn(7)] public float Android;
}

public class ClusterPrediction
{
    [ColumnName("PredictedLabel")] public uint PredictedClusterId;

    [ColumnName("Score")] public float[] Distances;
}

skills.csv