Adaptado para que agrupe los datos

testML/DictionaryToObjectConverter.cs

@@ -10,14 +10,18 @@ using System.Linq;
 using System.Reflection;
 using System.Runtime.CompilerServices;
 using System.Text;
+using System.Text.RegularExpressions;
 using System.Threading.Tasks;
 
 namespace testML
 {
 	public static class DictionaryToObjectConverter
 	{
-		public static IEnumerable<object> Convert(List<Dictionary<string, object>> data, string toPredict, out Type classType, out Type classPredictionType, out DataViewSchema schema)
+		public static IEnumerable<object> Convert(List<Dictionary<string, object>> data, string toPredict, string objectFilename, out Type classType, out Type classPredictionType, out DataViewSchema schema)
 		{
+			var regexCR = new Regex(@"_CR\d+");
+			var currentCR = regexCR.Match(toPredict).Groups[0].Value;
+
 			var schemaBuilder = new DataViewSchema.Builder();
 
 			var definition = new Dictionary<string, Type>();
@@ -27,6 +31,11 @@ namespace testML
 			{
 				foreach (var key in sample.Keys)
 				{
+					if (!key.Contains(currentCR))
+					{
+						continue;
+					}
+
 					//Buscamos el tipo
 					var sampleValue = (from x in data where x.ContainsKey(key) && x[key] != null select x[key]).FirstOrDefault();
 					if (sampleValue != null)
@@ -58,22 +67,34 @@ namespace testML
 				}
 			}
 
+			var className = "OBJ"+ Path.GetFileNameWithoutExtension(objectFilename).Replace(".", "_");
+
+			Assembly dllAssembly = null;
+			if (File.Exists(Path.Combine(Environment.CurrentDirectory, objectFilename)))
+			{
+				dllAssembly = Assembly.LoadFrom(Path.Combine(Environment.CurrentDirectory, objectFilename));
+			}
+			else
+			{
 				var converter = new DictionaryToObjectConverterClass()
 				{
-				ClassName = "OBJ" + Guid.NewGuid().ToString("N").ToUpper(),
+					ClassName = className,
 					ToPredict = toPredict,
 					Definition = definition
 				};
 
 				var classCode = converter.TransformText();
 
+				File.WriteAllText(Path.Combine(Environment.CurrentDirectory, objectFilename + ".cs"), classCode, Encoding.UTF8);
+
 				string exDir = System.Runtime.InteropServices.RuntimeEnvironment.GetRuntimeDirectory().Trim(Path.DirectorySeparatorChar);
 				CompilerParameters compilerParameters = new CompilerParameters
 				{
 					GenerateExecutable = false,
-				GenerateInMemory = true,
+					GenerateInMemory = false,
 					IncludeDebugInformation = true,
 					TreatWarningsAsErrors = false,
+					OutputAssembly = Path.Combine(Environment.CurrentDirectory, objectFilename),
 					CompilerOptions = string.Format("/target:library /lib:{0}", exDir)
 				};
 
@@ -92,10 +113,11 @@ namespace testML
 						new string[] { classCode }
 					);
 
-			var dllAssembly = compilerResults.CompiledAssembly;
+				dllAssembly = compilerResults.CompiledAssembly;
+			}
 
-			classType = dllAssembly.GetType("DictionaryToObjectConverterNamespace." + converter.ClassName);
+			classType = dllAssembly.GetType("DictionaryToObjectConverterNamespace." + className);
-			classPredictionType = dllAssembly.GetType("DictionaryToObjectConverterNamespace." + converter.ClassName + "Prediction");
+			classPredictionType = dllAssembly.GetType("DictionaryToObjectConverterNamespace." + className + "Prediction");
 
 			Type listType = typeof(List<>);
 			Type genericType = listType.MakeGenericType(classType);

testML/Program.cs

@@ -16,6 +16,7 @@ using System.Reflection;
 using System.Security.AccessControl;
 using System.Security.Cryptography;
 using System.Text;
+using System.Text.RegularExpressions;
 using System.Threading.Tasks;
 using System.Xml.Linq;
 using static TorchSharp.torch.utils;
@@ -30,21 +31,23 @@ namespace testML
 		{
 			XSSFWorkbook wb;
 			//using (FileStream file = new FileStream(@"C:\Users\miguel.maldonado\Downloads\entrenar_IAMenos.xlsx", FileMode.Open, FileAccess.Read))
-			using (FileStream file = new FileStream(@"C:\Users\miguel.maldonado\Downloads\entrenar_IA.xlsx", FileMode.Open, FileAccess.Read))
+			using (FileStream file = new FileStream(@"entrenar_IA (1).xlsx", FileMode.Open, FileAccess.Read))
 			{
 				wb = new XSSFWorkbook(file);
 			}
 
 			var sheet = wb.GetSheetAt(0);
 
-			var headerRow = sheet.GetRow(0);
+			var CRRow = sheet.GetRow(0);
+			var headerRow = sheet.GetRow(1);
+
 
 
 			#region Preparamos los datos de entrenamiento
 
 			var tmpData = new List<Dictionary<string, object>>();
 
-			for (var r = 1; r < sheet.LastRowNum - 1; r++)
+			for (var r = headerRow.RowNum + 1; r < sheet.LastRowNum - 1; r++)
 			{
 				//if (r == 50) break;
 				Console.WriteLine(string.Format("{0} / {1}", r, sheet.LastRowNum - 1));
@@ -58,6 +61,7 @@ namespace testML
 				{
 					var usePrefix = true;
 					var columnName = headerRow.GetCell(c)?.StringCellValue;
+					var crCell = CRRow.GetCell(c)?.NumericCellValue;
 
 					columnName = FixColumnName(columnName);
 
@@ -93,6 +97,12 @@ namespace testML
 					}
 
 					var finalColumnName = (usePrefix ? prefix : string.Empty) + columnName;
+
+					if (crCell != null)
+					{
+						finalColumnName = finalColumnName + "_CR" + crCell.Value.ToString();
+					}
+
 					if (value is string)
 					{
 						rowData.Add(finalColumnName, valuePrefix + value);
@@ -164,11 +174,21 @@ namespace testML
 
 		private static void MakePrediction(List<Dictionary<string, object>> tmpData, string columnToPredict)
 		{
+			var regexCR = new Regex(@"_CR\d+");
+
+			var currentCR = regexCR.Match(columnToPredict).Groups[0].Value;
+
+
 			var firstRow = tmpData[0] as IDictionary<string, object>;
 
 			var hashKey = new StringBuilder();
 			foreach (var key in firstRow.Keys.Where(x => !x.StartsWith("DESCENDIENTE_") && (x.Contains("_S4i") || x.Contains("_SNP"))).OrderBy(x => x))
 			{
+				if(!key.Contains(currentCR))
+				{
+					continue;
+				}
+
 				if (hashKey.Length > 0) { hashKey.Append("+"); }
 				hashKey.Append(key);
 			}
@@ -177,6 +197,7 @@ namespace testML
 			var hash = string.Join("", md5.ComputeHash(new MemoryStream(new UTF8Encoding(false).GetBytes(hashKey.ToString()))).Select(x => x.ToString("X2").ToUpper()).ToArray());
 
 			var modelFilename = columnToPredict + "." + hash + ".zip";
+			var objectFilename = columnToPredict + "." + hash + ".dll";
 
 
 			#endregion
@@ -185,7 +206,6 @@ namespace testML
 			MLContext mlContext = new MLContext();
 
 
-
 			mlContext.Log += (_, e) =>
 			{
 				if (e.Kind == Microsoft.ML.Runtime.ChannelMessageKind.Trace && e.Source.EndsWith(" Cursor")) { return; }
@@ -203,7 +223,7 @@ namespace testML
 			};
 
 
-			var dataConverted = DictionaryToObjectConverter.Convert(tmpData, columnToPredict, out Type classType, out Type classPredictionType, out DataViewSchema schema);
+			var dataConverted = DictionaryToObjectConverter.Convert(tmpData, columnToPredict, objectFilename, out Type classType, out Type classPredictionType, out DataViewSchema schema);
 
 			ITransformer _trainedModel;
 			if (!File.Exists(modelFilename))
@@ -236,6 +256,7 @@ namespace testML
 				var trainingPipeline = BuildAndTrainModel(mlContext, trainData, pipeline, classType, classPredictionType);
 				
 				Console.WriteLine("Training...");
+				
 				_trainedModel = trainingPipeline.Fit(trainData);
 
 				mlContext.Model.Save(_trainedModel, data.Schema, modelFilename);