Miki/TestMicrosoftML
1
0
Fork 0
Code Releases Activity

Ya hace predicciones y crea el ZIP

Browse Source
This commit is contained in:
Miguel Á M.S.
2023-01-18 14:20:53 +01:00
parent fe96cd41a4
commit 7f68e262f4
4 changed files with 281 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
testML/DictionaryToObjectConverter.cs
View File

@@ -16,7 +16,7 @@ namespace testML
{
public static class DictionaryToObjectConverter
{
public static IEnumerable<object> Convert(List<Dictionary<string, object>> data, string toPredict, out Type classType, out DataViewSchema schema)
public static IEnumerable<object> Convert(List<Dictionary<string, object>> data, string toPredict, out Type classType, out Type classPredictionType, out DataViewSchema schema)
{
var schemaBuilder = new DataViewSchema.Builder();
@@ -32,12 +32,6 @@ namespace testML
if (sampleValue != null)
{
var keyType = sampleValue.GetType();
if (key == toPredict)
{
keyType = typeof(float);
}
definition.Add(key, keyType);
if (keyType == typeof(string))
@@ -101,25 +95,12 @@ namespace testML
var dllAssembly = compilerResults.CompiledAssembly;
classType = dllAssembly.GetType("DictionaryToObjectConverterNamespace." + converter.ClassName);
classPredictionType = dllAssembly.GetType("DictionaryToObjectConverterNamespace." + converter.ClassName + "Prediction");
Type listType = typeof(List<>);
Type genericType = listType.MakeGenericType(classType);
var result =(IList) Activator.CreateInstance(genericType) ;
Dictionary<string, float> translate = new Dictionary<string, float>();
translate.Add(string.Empty, 0);
foreach (var inputData in data)
{
if (inputData.ContainsKey(toPredict) && inputData[toPredict] != null)
{
if (!translate.ContainsKey(inputData[toPredict] as string))
{
var max = translate.Values.Max()+1;
translate.Add(inputData[toPredict] as string, max);
}
}
}
var result = (IList)Activator.CreateInstance(genericType);
foreach (var inputData in data)
@@ -128,17 +109,10 @@ namespace testML
result.Add(outputData);
foreach (var key in inputData.Keys)
{
if (key == toPredict)
{
outputData[key] = translate[inputData[key] as string ?? string.Empty];
}
else
{
outputData[key] = inputData[key];
}
}
}
schema = schemaBuilder.ToSchema();

82
testML/DictionaryToObjectConverterClass.cs
View File

@@ -28,8 +28,14 @@ namespace testML
/// </summary>
public virtual string TransformText()
{
this.Write("\r\nusing System;\r\nusing System.Text;\r\nusing Microsoft.ML.Data;\r\n\r\nnamespace Dictio" +
"naryToObjectConverterNamespace\r\n{\r\n\tpublic class ");
#line 6 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
var toPredictType = Definition[ToPredict];
#line default
#line hidden
this.Write("using System;\r\nusing System.Text;\r\nusing Microsoft.ML.Data;\r\n\r\nnamespace Dictiona" +
"ryToObjectConverterNamespace\r\n{\r\n\tpublic class ");
#line 13 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ClassName));
@@ -141,7 +147,77 @@ namespace testML
#line default
#line hidden
this.Write("\r\n\t\t\t}\r\n\t\t\treturn null;\r\n\t\t}\r\n\t}\r\n}");
this.Write("\r\n\t\t\t}\r\n\t\t\treturn null;\r\n\t\t}\r\n\t}\r\n\r\n\tpublic class ");
#line 54 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ClassName));
#line default
#line hidden
this.Write("Prediction: testML.IDictionaryToObjectConverter\r\n\t{\r\n\t\t[ColumnName(\"PredictedLabe" +
"l\")]\t\r\n\t\tpublic ");
#line 57 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(toPredictType.FullName));
#line default
#line hidden
this.Write(" ");
#line 57 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ToPredict));
#line default
#line hidden
this.Write(@" { get; set; }
public object this[string propertyName]
{
get { return GetValue(propertyName); }
set { SetValue(propertyName, value); }
}
public void SetValue(string propertyName, object value)
{
switch(propertyName)
{
case """);
#line 69 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ToPredict));
#line default
#line hidden
this.Write("\":\t");
#line 69 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ToPredict));
#line default
#line hidden
this.Write(" = (");
#line 69 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(toPredictType.FullName));
#line default
#line hidden
this.Write(")value;\tbreak;\r\n\t\t\t}\r\n\t\t}\r\n\r\n\t\tpublic object GetValue(string propertyName)\r\n\t\t{\r\n" +
"\t\t\tswitch(propertyName)\r\n\t\t\t{\r\n\t\t\t\tcase \"");
#line 77 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ToPredict));
#line default
#line hidden
this.Write("\":\treturn ");
#line 77 "C:\Users\miguel.maldonado\Documents\Subversion\TestML\testML\DictionaryToObjectConverterClass.tt"
this.Write(this.ToStringHelper.ToStringWithCulture(ToPredict));
#line default
#line hidden
this.Write(";\r\n\t\t\t}\r\n\t\t\treturn null;\r\n\t\t}\r\n\t}\r\n}");
return this.GenerationEnvironment.ToString();
}
}

31
testML/DictionaryToObjectConverterClass.tt
View File

@@ -3,7 +3,7 @@
<#@ import namespace="System.Linq" #>
<#@ import namespace="System.Text" #>
<#@ import namespace="System.Collections.Generic" #>
<# var toPredictType = Definition[ToPredict]; #>
using System;
using System.Text;
using Microsoft.ML.Data;
@@ -50,4 +50,33 @@ namespace DictionaryToObjectConverterNamespace
return null;
}
}
public class <#= ClassName #>Prediction: testML.IDictionaryToObjectConverter
{
[ColumnName("PredictedLabel")]
public <#= toPredictType.FullName #> <#= ToPredict #> { get; set; }
public object this[string propertyName]
{
get { return GetValue(propertyName); }
set { SetValue(propertyName, value); }
}
public void SetValue(string propertyName, object value)
{
switch(propertyName)
{
case "<#= ToPredict #>": <#= ToPredict #> = (<#= toPredictType.FullName #>)value; break;
}
}
public object GetValue(string propertyName)
{
switch(propertyName)
{
case "<#= ToPredict #>": return <#= ToPredict #>;
}
return null;
}
}
}

181
testML/Program.cs
View File

@@ -2,6 +2,8 @@
using Microsoft.ML.AutoML;
using Microsoft.ML.Data;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms.Text;
using Microsoft.SqlServer.Server;
using NPOI.XSSF.UserModel;
using System;
using System.Collections.Generic;
@@ -24,7 +26,8 @@ namespace testML
static void Main(string[] args)
{
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_IAMenos.xlsx", FileMode.Open, FileAccess.Read))
using (FileStream file = new FileStream(@"C:\Users\miguel.maldonado\Downloads\entrenar_IA.xlsx", FileMode.Open, FileAccess.Read))
{
wb = new XSSFWorkbook(file);
}
@@ -40,7 +43,7 @@ namespace testML
for (var r = 1; r < sheet.LastRowNum - 1; r++)
{
if (r == 300) break;
//if (r == 50) break;
Console.WriteLine(string.Format("{0} / {1}", r, sheet.LastRowNum - 1));
var row = sheet.GetRow(r);
@@ -102,86 +105,133 @@ namespace testML
tmpData.Add(rowData);
}
var columnToPredict = "DESCENDIENTE_S4i001";
var firstRow = tmpData[0] as IDictionary<string, object>;
foreach (var key in firstRow.Keys.ToArray())
{
var firstValue = (from x in tmpData where x.ContainsKey(key) && x[key] != null && !string.IsNullOrEmpty(x[key] as string) select x[key]).FirstOrDefault();
if (firstValue == null)
{
foreach (var item in tmpData)
{
if (item.ContainsKey(key))
{
item.Remove(key);
}
}
}
}
#endregion
MLContext mlContext = new MLContext();
var dataConverted = DictionaryToObjectConverter.Convert(tmpData, "DESCENDIENTE_S4i001", out Type classType, out DataViewSchema schema);
mlContext.Log += (_, e) =>
{
if (e.Kind == Microsoft.ML.Runtime.ChannelMessageKind.Trace && e.Source.EndsWith(" Cursor")) { return; }
if (e.Kind == Microsoft.ML.Runtime.ChannelMessageKind.Trace && e.Source.EndsWith(" CursorSplitter")) { return; }
if (e.Kind == Microsoft.ML.Runtime.ChannelMessageKind.Trace && e.Source.EndsWith(" Consolidate")) { return; }
if (e.Kind == Microsoft.ML.Runtime.ChannelMessageKind.Trace && e.Source.EndsWith(" Training")) { return; }
if (e.Kind == Microsoft.ML.Runtime.ChannelMessageKind.Trace && e.Source.Equals("RangeFilter; Checking parameters")) { return; }
//if (e.Source.Equals("AutoMLExperiment"))
//{
Console.WriteLine(e.RawMessage);
//}
};
var dataConverted = DictionaryToObjectConverter.Convert(tmpData, columnToPredict, out Type classType, out Type classPredictionType, out DataViewSchema schema);
tmpData = null; //Liberamos la memoria
var loadMethod = mlContext.Data.GetType().GetMethods().Where(x => x.Name == "LoadFromEnumerable" && x.IsGenericMethodDefinition).FirstOrDefault();
var loadMethodObj = loadMethod.MakeGenericMethod(classType);
var data = (IDataView)loadMethodObj.Invoke(mlContext.Data, new object[] { dataConverted, null });
//var data = mlContext.Data.LoadFromEnumerable(dataConverted, schema);
//var data = new DictionaryView<Expando>(tmpData, schema.ToSchema(), converter);
#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);
DataOperationsCatalog.TrainTestData dataSplit = mlContext.Data.TrainTestSplit(data, testFraction: 0.5);
IDataView trainData = dataSplit.TrainSet;
IDataView testData = dataSplit.TestSet;
#endregion
#region Preparamos los datos de entrada y salida
//var trainer = mlContext.Regression.Trainers.Sdca(maximumNumberOfIterations: 100);
var trainer = mlContext.Regression.Trainers.OnlineGradientDescent(numberOfIterations: 100, learningRate: 0.01f);
//var pipeline = mlContext.Transforms.CopyColumns(outputColumnName: "Label", inputColumnName: "DESCENDIENTE_S4i001");
//IEstimator<ITransformer> pipe = (IEstimator<ITransformer>)pipeline;
//pipe = pipe.Append(mlContext.Transforms.Text.NormalizeText("Label"));
//pipe = pipe.Append(mlContext.Transforms.Text.FeaturizeText("Label"));
var firstRow = tmpData[0] as IDictionary<string, object>;
var columnInference = new ColumnInformation()
var columnNameAndTypes = new Dictionary<string, Type>();
foreach (var item in (from x in firstRow.Keys
select new { Key = x, Type = (from y in dataConverted.Cast<IDictionaryToObjectConverter>() where y.GetValue(x) != null select y.GetValue(x).GetType()).FirstOrDefault() })
)
{
LabelColumnName = "DESCENDIENTE_S4i001"
};
foreach (var key in firstRow.Keys)
{
if (key == columnInference.LabelColumnName)
{
continue;
columnNameAndTypes.Add(item.Key, item.Type);
}
if (key.Contains("_S4i") || key.Contains("_SNP"))
var pipeline = ProcessData(mlContext, columnToPredict, columnNameAndTypes);
var trainingPipeline = BuildAndTrainModel(mlContext, trainData, pipeline, classType, classPredictionType);
Console.WriteLine("Training...");
var _trainedModel = trainingPipeline.Fit(trainData);
mlContext.Model.Save(_trainedModel, data.Schema, columnToPredict + ".zip");
var createPredictionEngineMethod = mlContext.Model.GetType().GetMethods().Where(x => x.Name == "CreatePredictionEngine" && x.IsGenericMethodDefinition).FirstOrDefault();
var createPredictionEngineMethodObj = createPredictionEngineMethod.MakeGenericMethod(classType, classPredictionType);
var _predEngine = createPredictionEngineMethodObj.Invoke(mlContext.Model, new object[] { _trainedModel, null, null, null });
//Test
var predictMethod = _predEngine.GetType().GetMethods().Where(x => x.Name == "Predict" && x.GetParameters().Length == 1 && x.GetParameters()[0].ParameterType == classType).FirstOrDefault();
var ok = 0;
var fail = 0;
foreach (var item in dataConverted.Cast<IDictionaryToObjectConverter>())
{
columnInference.CategoricalColumnNames.Add(key);
}
}
var expected = item.GetValue(columnToPredict);
if (expected == null || string.IsNullOrEmpty(expected as string)) { continue; }
mlContext.Log += (_, e) => {
if (e.Source.Equals("AutoMLExperiment"))
item.SetValue(columnToPredict, null);
var prediction = predictMethod.Invoke(_predEngine, new object[] { item }) as IDictionaryToObjectConverter;
var predicted = prediction.GetValue(columnToPredict);
if (expected is string a && predicted is string b)
{
Console.WriteLine(e.RawMessage);
Console.Write(item.GetValue("DESCENDIENTE") ?? string.Empty);
Console.Write(": ");
Console.Write(string.Format("Expected: {0}\t\tPredicted: {1}", a, b));
if (string.Equals(a, b))
{
ok++;
Console.WriteLine("\tOk");
}
else
{
fail++;
Console.WriteLine("\tERROR!!!");
}
};
}
SweepablePipeline pipeline = mlContext.Auto().Featurizer(data, columnInference)
.Append(mlContext.Auto().Regression(labelColumnName: columnInference.LabelColumnName));
}
AutoMLExperiment experiment = mlContext.Auto().CreateExperiment();
Console.WriteLine(string.Format("Ok: {0}, Fail: {1}, Percent: {2}%", ok, fail, (((double)ok / (double)(ok + fail)) * 100.0).ToString("##0.0000")));
experiment
.SetPipeline(pipeline)
.SetRegressionMetric(RegressionMetric.RSquared, labelColumn: columnInference.LabelColumnName)
.SetTrainingTimeInSeconds(10)
.SetDataset(trainData);
var result = experiment.Run();
#endregion
/*
//Entrenamos el modelo
//ITransformer model = pipe.Fit(trainData);
@@ -215,13 +265,48 @@ namespace testML
}
#endregion
*/
Console.WriteLine();
Console.WriteLine("Press enter to Exit");
Console.ReadLine();
}
private static IEstimator<ITransformer> ProcessData(MLContext mlContext, string predictColumnName, Dictionary<string, Type> columnNames)
{
IEstimator<ITransformer> pipeline = mlContext.Transforms.Conversion.MapValueToKey(inputColumnName: predictColumnName, outputColumnName: "Label");
var featured = new List<string>();
foreach (var key in columnNames.Keys)
{
if (key == predictColumnName) { continue; }
if (key.StartsWith("DESCENDIENTE_")) { continue; }
var type = columnNames[key];
if (type == typeof(string))
{
pipeline = pipeline.Append(mlContext.Transforms.Text.FeaturizeText(inputColumnName: key, outputColumnName: key));
featured.Add(key);
}
}
pipeline = pipeline.Append(mlContext.Transforms.Concatenate("Features", featured.ToArray()));
return pipeline;
}
public static IEstimator<ITransformer> BuildAndTrainModel(MLContext mlContext, IDataView trainingDataView, IEstimator<ITransformer> pipeline, Type modelType, Type prodelPredictionType)
{
var trainingPipeline = pipeline.Append(mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features", maximumNumberOfIterations: 1000))
.Append(mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
return trainingPipeline;
}
private static string FixColumnName(string columnName)
{
var result = new StringBuilder(columnName.Length);