static void Main(string[] args)
{
cntkModelToGraphviz();
return;
//Iris flower recognition
//Famous multi class classification datset: https://archive.ics.uci.edu/ml/datasets/iris
string root = "C:\\sc\\github\\anndotnet\\src\\tool\\";
var mlConfigFile2 = $"{root}\\anndotnet.tool\\model_mlconfigs\\iris.mlconfig";
Console.WriteLine(Environment.NewLine);
Console.WriteLine($"****Iris flower recognition****");
Console.WriteLine(Environment.NewLine);
var token2 = new CancellationToken();
var result = MachineLearning.Run(mlConfigFile2, DeviceDescriptor.UseDefaultDevice(), token2, trainingProgress, null);
////evaluate model and export the result of testing
MachineLearning.EvaluateModel(mlConfigFile2, result.BestModelFile, DeviceDescriptor.UseDefaultDevice());
//******run all configurations in the solution******
//for (int i = 0; i < 10; i++)
// runAllml_configurations(strLocation1)
//*****end of program*****
Console.WriteLine("Press any key to continue!");
Console.ReadKey();
}
private static void runConvNetExample()
{
//cat&dag dataset location C:\sc\Datasets\cat-dog\train
//train mlconfig
var mlConfigFile1 = $"model_mlconfigs\\convNet.mlconfig";
var result = MachineLearning.Train(mlConfigFile1, trainingProgress, new CancellationToken(), null);
}
static void TrainExamples()
{
for (int i = 0; i < 10; i++)
{
//Iris flower recognition
//Famous multi class classification datset: https://archive.ics.uci.edu/ml/datasets/iris
var mlConfigFile2 = "./model_mlconfigs/iris.mlconfig";
Console.WriteLine(Environment.NewLine);
Console.Title = $"****Iris flower recognition****";
Console.WriteLine($"****Iris flower recognition****");
Console.WriteLine(Environment.NewLine);
var token2 = new CancellationToken();
var result = MachineLearning.Train(mlConfigFile2, trainingProgress, token2, null);
//Bezier Curve Machine Learning Demonstration
//dataset taken form Code Project Article:
//https://www.codeproject.com/Articles/1256883/Bezier-Curve-Machine-Learning-Demonstration
var mlConfigFile = "./model_mlconfigs/BCML.mlconfig";
Console.WriteLine(Environment.NewLine);
Console.WriteLine($"****Bezier Curve Machine Learning Demonstration****");
Console.WriteLine(Environment.NewLine);
var token = new CancellationToken();
MachineLearning.Train(mlConfigFile, trainingProgress, token, null);
//1. daily sales
//modified dataset from preidct future sales
var ds_mlConfigFile = "./model_mlconfigs/daily_sales.mlconfig";
Console.WriteLine(Environment.NewLine);
Console.WriteLine($"****Predict Daily Sales for 10 items****");
Console.WriteLine(Environment.NewLine);
MachineLearning.Train(ds_mlConfigFile, trainingProgress, new CancellationToken(), null);
//1. solar production
//CNTK Tutorial 106B_ https://cntk.ai/pythondocs/CNTK_106B_LSTM_Timeseries_with_IOT_Data.html
var mlConfigFile11 = "C:\\Users\\bhrnjica\\OneDrive - BHRNJICA\\AI Projects\\ann-custom-models" +
"\\solar_production.mlconfig";
Console.WriteLine(Environment.NewLine);
Console.WriteLine($"****Predict Solar production****");
Console.WriteLine(Environment.NewLine);
var token11 = new CancellationToken();
MachineLearning.Train(mlConfigFile11, trainingProgress, token11, null);
//2. Predict future sales,- Multiple Input variables
//Kaggle competition dataset
var mlConfigFile1 = "C:\\Users\\bhrnjica\\OneDrive - BHRNJICA\\AI Projects\\ann-custom-models" +
"\\predict_future_sales.mlconfig";
Console.WriteLine(Environment.NewLine);
Console.WriteLine($"****Predict Future Sales****");
Console.WriteLine(Environment.NewLine);
var token1 = new CancellationToken();
//MachineLearning.Train(mlConfigFile1, trainingProgress, token1, CustomNNModels.CustomModelCallEntryPoint);
}
}
private static void runExample(string title, string mlConfigPath, CreateCustomModel model = null)
{
var mlConfigFile2 = mlConfigPath;
Console.WriteLine(Environment.NewLine);
Console.WriteLine($"****{title}****");
Console.WriteLine(Environment.NewLine);
var token2 = new CancellationToken();
MachineLearning.Train(mlConfigFile2, trainingProgress, token2, model);
}
static void Main(string[] args)
{
//graphConvNetExample();
//runConvNetExample();
//cntkModelToGraphviz();
//Console.ReadKey();
//return;
var rnd = new Random(1);
Color randomColor = Color.FromArgb(rnd.Next(256), rnd.Next(256), rnd.Next(256));
//var root = "C:\\sc\\github\\anndotnet\\src\\tool";
//Iris flower recognition
//Famous multi class classification datset: https://archive.ics.uci.edu/ml/datasets/iris
var mlConfigFile3 = $"model_mlconfigs\\iris.mlconfig";
//run example
// var token2 = new CancellationToken();
//train mlconfig
var result = MachineLearning.Train(mlConfigFile3, trainingProgress, new CancellationToken(), null);
//once the mode is trained you can write performance analysis of the model
MachineLearning.PrintPerformance(mlConfigFile3);
//SHow training history
showTrainingHistory(mlConfigFile3);
//evaluate model and export the result of testing
//MLExport.ExportToCSV(mlConfigFile2, DeviceDescriptor.UseDefaultDevice(),"./model_mlconfigs/iris_result.csv" ).Wait();
//******run all configurations in the solution******
//for (int i = 0; i < 10; i++)
// runAllml_configurations(strLocation1);
//*****end of program*****
Console.WriteLine("Press any key to continue!");
Console.ReadKey();
}
static void Main(string[] args)
{
string root = "C:\\sc\\github\\anndotnet\\src\\tool\\";
//transformDailyLevelVeanaLake();
//return;
//regression
var mlConfigFile1 = $"{root}anndotnet.wnd\\Resources\\Concrete\\ConcreteSlumpProject\\FFNModel.mlconfig";
//binary classification
var mlConfigFile2 = $"{root}anndotnet.wnd\\Resources\\Titanic\\TitanicProject\\DNNModel.mlconfig";
//Multi-class classification
//Famous multi class classification datset: https://archive.ics.uci.edu/ml/datasets/iris
var mlConfigFile3 = "./model_mlconfigs/iris.mlconfig";
//run example
var token2 = new CancellationToken();
//train mlconfig
var result = MachineLearning.Train(mlConfigFile3, trainingProgress, token2, null);
//once the mode is trained you can write performance analysis of the model
MachineLearning.PrintPerformance(mlConfigFile1);
//evaluate model and export the result of testing
MLExport.ExportToCSV(mlConfigFile2, DeviceDescriptor.UseDefaultDevice(), "./model_mlconfigs/iris_result.csv").Wait();
//******run all configurations in the solution******
//string strLocation1 = "C:\\sc\\github\\anndotnet\\src\\tool\\";
//for (int i = 0; i < 10; i++)
// runAllml_configurations(strLocation1);
//*****end of program*****
Console.WriteLine("Press any key to continue!");
Console.ReadKey();
}
private static void showTrainingHistory(string mlConfigFile3)
{
var history = MachineLearning.ShowTrainingHistory(mlConfigFile3);
var data = history.First().Value;
var header = history.First().Key;
var x = header.Split(new char[] { ';' }, StringSplitOptions.RemoveEmptyEntries);
var model = DataProcessing.Core.ChartComponent.LinePlot("Model Evaluation", "Training Data",
data.Select(d => (double)d.Item1).ToArray(),
data.Select(d => (double)d.Item4).ToArray(),
Color.Blue, MarkerType.Circle,
"Iterations", x.Last());
var ss = DataProcessing.Core.ChartComponent.LineSeries("Validation Data",
data.Select(d => (double)d.Item1).ToArray(),
data.Select(d => (double)d.Item5).ToArray(),
Color.Orange, MarkerType.Circle);
model.Series.Add(ss);
model.LegendPosition = LegendPosition.LeftTop;
showPlot(model).Wait();
}