Skill ML.NET Classification

Predict yes/no outcomes from multiple input tags using ML.NET FastTree Binary Classification. The AI generates the full C# Script Class with multi-feature training pipeline, connects it to live tags, creates output tags for predicted label and probability, and configures model persistence.

When to Use This Skill

User chose Binary Classification — FastTree in the ML.NET router skill (Step 0)
Predicting a yes/no outcome from 2–5 input features
User goals: fault prediction, quality control pass/fail, predictive maintenance with multiple sensors

Prerequisites

Solution open with input feature tags and a boolean label tag already created and receiving data
Solution target platform set to Multiplatform (ML.NET requires .NET 8+)
The user has confirmed: (1) which tags are features, (2) which tag is the boolean label, (3) what the yes/no outcome represents

MCP Tools and Tables

Category	Items
Tools	`get_table_schema`, `write_objects`, `get_objects`
Tables	`UnsTags`, `ScriptsClasses`, `ScriptsTasks`

Step 1: Create Output Tags

get_table_schema('UnsTags')

{
  "table_type": "UnsTags",
  "data": [
    { "Name": "<AssetPath>/ML/PredictedLabel", "DataType": "Boolean", "Description": "Predicted outcome (true/false)" },
    { "Name": "<AssetPath>/ML/Probability", "DataType": "Double", "Description": "Prediction probability (0-1)" },
    { "Name": "<AssetPath>/ML/LastPrediction", "DataType": "DateTime", "Description": "Timestamp of last prediction" }
  ]
}

Replace <AssetPath> with the actual asset folder path.

Step 2: Create the Script Class

ML.NET Namespace Declaration

Critical: The field AddMLNetNamespaces does not exist and is silently ignored. Always use NamespaceDeclarations.

"NamespaceDeclarations": "Microsoft.ML;Microsoft.ML.Data;Microsoft.ML.Transforms;Microsoft.ML.Transforms.TimeSeries;Microsoft.ML.Transforms.Text;Microsoft.ML.Trainers;Microsoft.ML.TimeSeries"

Tag References Inside Script Classes

Always use @Tag. prefix. ML.NET expects float but FrameworX tags use double — always cast with (float) when feeding ML.NET and (double) when writing to tags.

FastTree Binary Classification Pipeline

var pipeline = mlContext.Transforms.Concatenate("Features", "Feature1", "Feature2", "Feature3")
    .Append(mlContext.BinaryClassification.Trainers.FastTree(
        labelColumnName: "Label",
        featureColumnName: "Features"));

Output: bool PredictedLabel, float Score, float Probability

Full Class Example — Binary Classification

public class ProcessData
{
    public float Feature1 { get; set; }  // e.g., Vibration
    public float Feature2 { get; set; }  // e.g., Temperature
    public float Feature3 { get; set; }  // e.g., Current
    public bool Label { get; set; }      // e.g., DidFault (true/false)
}

public class ClassificationPrediction
{
    public bool PredictedLabel { get; set; }
    public float Score { get; set; }
    public float Probability { get; set; }
}

private static MLContext mlContext = new MLContext(seed: 0);
private static ITransformer model;
private static IDataView lastTrainingDataView;
private static PredictionEngine<ProcessData, ClassificationPrediction> predictionEngine;
private static bool modelTrained = false;
private static List<ProcessData> trainingBuffer = new List<ProcessData>();
private const int MinTrainingSize = 200;
private static readonly string ModelPath = Path.Combine(@Info.GetExecutionPath(), "<ClassName>.mlnet");

public void Predict(double input1, double input2, double input3, bool label)
{
    trainingBuffer.Add(new ProcessData
    {
        Feature1 = (float)input1,
        Feature2 = (float)input2,
        Feature3 = (float)input3,
        Label = label
    });

    if (!modelTrained && trainingBuffer.Count >= MinTrainingSize)
        TrainModel();

    if (modelTrained)
        RunPrediction(input1, input2, input3);
}

public void LoadModel()
{
    if (File.Exists(ModelPath))
    {
        model = mlContext.Model.Load(ModelPath, out _);
        predictionEngine = mlContext.Model.CreatePredictionEngine<ProcessData, ClassificationPrediction>(model);
        modelTrained = true;
    }
}

private void TrainModel()
{
    lastTrainingDataView = mlContext.Data.LoadFromEnumerable(trainingBuffer);
    var pipeline = mlContext.Transforms.Concatenate("Features",
            nameof(ProcessData.Feature1),
            nameof(ProcessData.Feature2),
            nameof(ProcessData.Feature3))
        .Append(mlContext.BinaryClassification.Trainers.FastTree(
            labelColumnName: "Label",
            featureColumnName: "Features"));

    model = pipeline.Fit(lastTrainingDataView);
    predictionEngine = mlContext.Model.CreatePredictionEngine<ProcessData, ClassificationPrediction>(model);
    modelTrained = true;
    SaveModel();
}

private void SaveModel()
{
    mlContext.Model.Save(model, lastTrainingDataView.Schema, ModelPath);
}

private void RunPrediction(double input1, double input2, double input3)
{
    var input = new ProcessData
    {
        Feature1 = (float)input1,
        Feature2 = (float)input2,
        Feature3 = (float)input3
    };
    var result = predictionEngine.Predict(input);

    @Tag.<AssetPath>/ML/PredictedLabel.Value = result.PredictedLabel;
    @Tag.<AssetPath>/ML/Probability.Value = (double)result.Probability;
    @Tag.<AssetPath>/ML/LastPrediction.Value = DateTime.Now;
}

Note on training data: The label parameter is needed during training — it's the known fault/pass flag. After training, only the feature inputs are needed. The AI should adapt the signature based on whether a label tag exists.

Step 3: Write the Class via MCP

get_table_schema('ScriptsClasses')

{
  "table_type": "ScriptsClasses",
  "data": [
    {
      "Name": "<ClassName>",
      "Code": "CSharp",
      "Domain": "Server",
      "ClassContent": "Methods",
      "NamespaceDeclarations": "Microsoft.ML;Microsoft.ML.Data;Microsoft.ML.Transforms;Microsoft.ML.Transforms.TimeSeries;Microsoft.ML.Transforms.Text;Microsoft.ML.Trainers;Microsoft.ML.TimeSeries",
      "Contents": "<AI-generated C# code from full class example above>"
    }
  ]
}

Field names matter: Code = language (not Language), Contents = code body (not Code). Wrong names = silent data loss.

Step 4: Create the Trigger

Task (Periodic) — best for multi-input classification

get_table_schema('ScriptsTasks')

{
  "table_type": "ScriptsTasks",
  "data": [
    {
      "Name": "ML_Classify_Periodic",
      "Language": "CSharp",
      "Execution": "Periodic",
      "Period": 5000,
      "Code": "@Script.Class.<ClassName>.Predict(\n    @Tag.Plant/Motor1/VibrationX.Value,\n    @Tag.Plant/Motor1/Temperature.Value,\n    @Tag.Plant/Motor1/Current.Value,\n    @Tag.Plant/Motor1/DidFault.Value);"
    }
  ]
}

The @ prefix is mandatory when referencing runtime objects inside ScriptsTasks. Without it: CS0234.

ServerStartup — always wire LoadModel

Read the existing ServerStartup task first (document object — read-modify-write), then append:

Script.Class.<ClassName>.LoadModel();

Step 5: Verify

Confirm Multiplatform — ML.NET requires .NET 8+. Instruct the user: “Solution → Settings → Target Platform = Multiplatform, then Product → Modify.”
Do NOT start the runtime automatically.
Wait for training — needs MinTrainingSize data points (default 200)
Check output tags — verify LastPrediction updates, PredictedLabel and Probability have reasonable values

Common Pitfalls

Mistake	Why It Happens	How to Avoid
Missing ML.NET namespaces	Used `AddMLNetNamespaces: true`	Always set `NamespaceDeclarations`
`CS0234` in ScriptsTasks	Missing `@` prefix	Always `@Script.Class.Name.Predict()`
`CS0029` bool-to-int on Digital tag	Digital tags are `int`, not `bool`	Use ternary: `@Tag.Path.Value = (condition) ? 1 : 0;`
`CS0246` Class not found	Build order issue	Set `BuildOrder: "1"` on ML Script Class
`System.Math` load error	.NET 4.8 target	Switch to Multiplatform
Wrong data types	ML.NET=float, tags=double	Cast `(float)`/`(double)`
Model lost on restart	SaveModel/LoadModel missing	Include both + ServerStartup
PredictionEngine null	Forgot to create after loading	Call `CreatePredictionEngine` in LoadModel
Imbalanced training data	Very few fault=true examples	Ensure training buffer has enough positive examples before training

Page tree