using Microsoft.ML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Reflection;
using System.Text;
using System.Threading.Tasks;
using System.Xml.Linq;

namespace testML
{
	internal class Program
	{
		static string[] tags = new string[] { "Rojo", "Amarillo", "Verde claro", "Verde oscuro", "Violeta", "Naranja", "Azul", "Blanco" };
		static Random rnd = new Random();

		static void Main(string[] args)
		{

			#region Preparamos los datos de entrenamiento

			var tmpData = new List<Data>();
		
			for (var c = 0; c < 100000; c++)
			{
				var d = CreateRandomData();
				tmpData.Add(d);
			}

			#endregion


			MLContext mlContext = new MLContext();
			var data = mlContext.Data.LoadFromEnumerable(tmpData);

			#region Cortamos los datos de entrenamiento en (Datos para entenar y Datos para hacer el test de precisión)

			DataOperationsCatalog.TrainTestData dataSplit = mlContext.Data.TrainTestSplit(data, testFraction: 0.1);
			IDataView trainData = dataSplit.TrainSet;
			IDataView testData = dataSplit.TestSet;

			#endregion

			#region Preparamos los datos de entrada y salida

			var trainer = mlContext.Regression.Trainers.Sdca(maximumNumberOfIterations:1000);
			//var trainer = mlContext.Regression.Trainers.OnlineGradientDescent(numberOfIterations: 100, learningRate: 0.01f );

			var pipeline = mlContext.Transforms.CopyColumns(outputColumnName: "Label", inputColumnName: "IntegerNumber")
				//.Append(mlContext.Transforms.Text.NormalizeText("StringTest"))
				//.Append(mlContext.Transforms.Text.FeaturizeText("StringTest"))
				.Append(mlContext.Transforms.Concatenate("Features", "Enum1", "Enum2", "Enum3", "Enum4"))
				.Append(mlContext.Transforms.NormalizeMinMax("Features"))
				.Append(trainer);

			#endregion

			//Entrenamos el modelo
			ITransformer model = pipeline.Fit(trainData);

			#region Hacemos un test para medir el % de error

			// Use trained model to make inferences on test data
			IDataView testDataPredictions = model.Transform(testData);

			// Extract model metrics and get RSquared
			RegressionMetrics trainedModelMetrics = mlContext.Regression.Evaluate(testDataPredictions);
			double rSquared = trainedModelMetrics.RSquared;

			Console.WriteLine("ModelMetrics: {0}", rSquared);

			#endregion


			#region Ponemos a prueba haciendo algunas predicciones

			var predictionFunction = mlContext.Model.CreatePredictionEngine<Data, DataPrediction>(model);

			for (var c = 0; c < 1000; c++)
			{
				var test = CreateRandomData();
				var expected = test.IntegerNumber;
				test.IntegerNumber = 0;

				var p = predictionFunction.Predict(test);

				//p.IntegerNumber = (float)Math.Round(p.IntegerNumber);


				Console.WriteLine("{4} {3}, Found: {0:#,##0.00}\tExpected: {1:#,##0.00}\t\tDiff: {2:#,##0.00}", p.IntegerNumber, expected , expected- p.IntegerNumber, test.Enum4, test.Enum2);
			}

			#endregion


			Console.WriteLine();
			Console.WriteLine("Press enter to Exit");
			Console.ReadLine();

		}

		private static Data CreateRandomData()
		{
			var d = new Data()
			{
				Accession = rnd.Next(0, 99999999).ToString("00000000"),
				Enum1 = rnd.Next(1, 4),
				Enum2 = rnd.Next(1, 11),
				Enum3 = rnd.Next(1, 6),
				Enum4 = rnd.Next(1, 4),
				StringTest = tags[rnd.Next(0, tags.Length)]
			};

			switch (d.Enum4)
			{
				case 1: d.IntegerNumber = 1; break;
				case 2: d.IntegerNumber = rnd.NextDouble() > 0.5 ? 1 : 0; break;
				case 3: d.IntegerNumber = 0; break;
			}


			return d;

		}
	}


}