aswi2021tri-musketyri-gitlab/Server/ServerApp/Predictor/AbstractClassificationPredictor.cs @ 63a595be

//
// Author: Roman Kalivoda
//

using System;
using System.Collections.Generic;
using log4net;
using Microsoft.ML;

namespace ServerApp.Predictor
{
    abstract class AbstractClassificationPredictor : IPredictor
    {
        private static readonly ILog _log = LogManager.GetLogger(typeof(AbstractClassificationPredictor));

        /// <summary>
        /// Context of the ML.NET framework.
        /// </summary>
        protected MLContext _mlContext;

        /// <summary>
        /// Model instance
        /// </summary>
        protected ITransformer _trainedModel;

        protected PredictionEngine<ModelInput, ModelOutput> _predictionEngine;

        protected IDataView _trainingDataView;

        public void Evaluate(IEnumerable<ModelInput> modelInputs)
        {
            var testDataView = this._mlContext.Data.LoadFromEnumerable(modelInputs);
            var data = _trainedModel.Transform(testDataView);
            var testMetrics = _mlContext.MulticlassClassification.Evaluate(data);

            Console.WriteLine($"*************************************************************************************************************");
            Console.WriteLine($"*       Metrics for Multi-class Classification model - Test Data     ");
            Console.WriteLine($"*------------------------------------------------------------------------------------------------------------");
            Console.WriteLine($"*       MicroAccuracy:    {testMetrics.MicroAccuracy:0.###}");
            Console.WriteLine($"*       MacroAccuracy:    {testMetrics.MacroAccuracy:0.###}");
            Console.WriteLine($"*       LogLoss:          {testMetrics.LogLoss:#.###}");
            Console.WriteLine($"*       LogLossReduction: {testMetrics.LogLossReduction:#.###}");
            Console.WriteLine($"*       Confusion Matrix: {testMetrics.ConfusionMatrix.GetFormattedConfusionTable()}");
            Console.WriteLine($"*************************************************************************************************************");
        }

        public abstract void Fit(IEnumerable<ModelInput> trainInput);

        public void Load(string filename)
        {
            DataViewSchema modelSchema;
            this._trainedModel = _mlContext.Model.Load(filename, out modelSchema);
            // TODO check if the loaded model has valid input and output schema
            this._predictionEngine = _mlContext.Model.CreatePredictionEngine<ModelInput, ModelOutput>(this._trainedModel);
        }

        public string Predict(ModelInput input)
        {
            _log.Debug($"Predicting for input: {input}");
            return this._predictionEngine.Predict(input).PredictedLabel;
        }

        public void Save(string filename)
        {
            if (this._trainingDataView is null)
            {
                throw new NullReferenceException("DataView is not set.");
            }
            if (this._trainedModel is null)
            {
                throw new NullReferenceException("Trained model instance does not exist. This predictor has not been trained yet.");
            }
            if (filename is null)
            {
                throw new ArgumentNullException(nameof(filename));
            }
            this._mlContext.Model.Save(this._trainedModel, this._trainingDataView.Schema, filename);
        }
    }
}