#MLNET – Hello World in ML.Net, Machine Learning for .Net !

Machine Learning 1 Minute

Hi!

I can not wait to start writing a little more about ML.Net. For now just a couple of code snippets to show how simple and fast it can be

Starting with a set of data with ages to classify babies and kids, in a CSV file. All based on my personal criteria


0 3 baby
1 3 baby
3 3 baby
4 6 kid
6 8 kid
5 9 kid
6 10 kid
9 10 kid

view raw
MLNetAgeRanges.csv
hosted with ❤ by GitHub

And now a little magic with ML. A .Net Core Console application where we create a LearningPipeline and train it with the previous CSV information

using System;
using Microsoft.ML;
using Microsoft.ML.Runtime.Api;
using Microsoft.ML.Trainers;
using Microsoft.ML.Transforms;
namespace MlNetConsole01
{
class Program
{
static void Main(string[] args)
{
var agesRangesCsv = "AgeRangeData.csv";
var pipeline = new LearningPipeline
{
new TextLoader<AgeRangeData>(agesRangesCsv, separator: ","),
new Dictionarizer("Label"),
new ColumnConcatenator("Features", "AgeStart", "AgeEnd"),
new StochasticDualCoordinateAscentClassifier(),
new PredictedLabelColumnOriginalValueConverter {PredictedLabelColumn = "PredictedLabel"}
};
var model = pipeline.Train<AgeRangeData, AgeRangePrediction>();
var prediction = model.Predict(new AgeRangeData()
{
AgeStart = 1,
AgeEnd = 2
});
Console.WriteLine($"Predicted age range is: {prediction.PredictedLabels}");
prediction = model.Predict(new AgeRangeData()
{
AgeStart = 7,
AgeEnd = 7
});
Console.WriteLine($"Predicted age range is: {prediction.PredictedLabels}");
Console.ReadLine();
}
}
public class AgeRangeData
{
[Column(ordinal: "0")]
public float AgeStart;
[Column(ordinal: "1")]
public float AgeEnd;
[Column(ordinal: "2", name: "Label")]
public string Label;
}
public class AgeRangePrediction
{
[ColumnName("PredictedLabel")]
public string PredictedLabels;
}
}

view raw
MLNetAgeRanges.cs
hosted with ❤ by GitHub

Below we check a couple of predictions with Age Ranges that are not part of the original CSV

I1

Happy coding!

Greetings @ Burlington

El Bruno

References

 

Published

21 thoughts on “#MLNET – Hello World in ML.Net, Machine Learning for .Net !”

  1. Pingback: #MLNET – Entendiendo el paso a paso del Hola Mundo – El Bruno
  2. Pingback: #MLNET – Understanding the step by step of Hello World – El Bruno
  3. Pingback: #MLNET – Guardando y reutilizando modelos con Machine Learning .Net – El Bruno
  4. Pingback: #MLNET – Write and Load models using Machine Learning .Net – El Bruno
  5. Pingback: #MLNET – Que es un modelo en #MachineLearning? Un video de 7 minutos que es la mejor explicación posible – El Bruno
  6. Pingback: #MLNET – What’s a #MachineLearning model? A 7 minute video as the best possible explanation – El Bruno
  7. Pingback: #MLNET – Novedades en la version 0.2.0 – El Bruno
  8. Pingback: #MLNET – What’s new in version 0.2.0 – El Bruno
  9. Pingback: #MLNET – Cargando datos en nuestra LearningPipeline con List (colecciones for ever!) – El Bruno
  10. Pingback: #MLNET – Loading Data In our LearningPipeline With List (Lists for ever!) – El Bruno
  11. Pingback: #MLNET – Exportando modelos de Machine Learning.Net a formato #ONNX – El Bruno
  12. Pingback: #MLNET – Export Machine Learning.Net models to #ONNX format – El Bruno
  13. Pingback: #MLNET – Cambios en la API con la nueva version 0.6.0 – El Bruno
  14. Pingback: #MLNET – API improvements in the new 0.6.0 version – El Bruno
  15. Pingback: #MLNET – Analizando datos de la Pipeline con la nueva version API 0.6.0 (gracias LINQ!) – El Bruno
  16. Pingback: #MLNET – Analyzing pipeline data in Machine Learning.Net using the new API 0.6.0 (thanks LINQ!) – El Bruno
  17. Pingback: #MLNET – Novedades en la version 0.7 de Machine Learning.Net (la excusa perfecta para actualizar proximos eventos!) – El Bruno
  18. Pingback: #MLNET – New version 0.7 for Machine Learning.Net (the perfect excuse to update my content for next events!) – El Bruno
  19. Pingback: #MLNET – Hello World in ML.Net, Machine Learning for .Net ! – El Bruno - IntelliNova
  20. Pingback: #MLNet – Visualizando datos del Pipeline en la versión 0.7.0 – El Bruno
  21. Pingback: #MLNet – Looking at data in the Pipeline in version 0.7.0 – El Bruno

Leave a Reply

Fill in your details below or click an icon to log in:

Gravatar
WordPress.com Logo

You are commenting using your WordPress.com account. ( Log Out /  Change )

Google photo

You are commenting using your Google account. ( Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. ( Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. ( Log Out /  Change )

Cancel

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.