Trying Out Machine Learning with .NET Core, Getting the ML-Net Framework Running

Introduction to ML.NET

Official website: https://dotnet.microsoft.com/apps/machinelearning-ai/ml-dotnet

Official introduction: The ML.NET command line interface (CLI), provides tools for building machine learning models with ML.NET.

ML.NET is an open-source, cross-platform machine learning framework for .NET developers. ML.NET also includes Model Builder (a simple UI tool) and the CLI, making it very easy to build custom machine learning (ML) models using automated machine learning (AutoML).

First, install .NET Core; this is a must~

Installing ML.NET

dotnet tool install -g mlnet

Downloading the Training Set

The following is user comment data from Wikipedia; please download it yourself

https://raw.githubusercontent.com/dotnet/machinelearning/master/test/data/wikipedia-detox-250-line-data.tsv

After downloading, name it wikipedia-data.tsv~

Training the Model

mlnet auto-train --task binary-classification --dataset "wikipedia-data.tsv" --label-column-index 0 --has-header true --max-exploration-time 10

If training succeeds, the results will be displayed as follows:

And it will generate code in the directory

Model Code

Let's take a look at the model code automatically generated by ML.NET:

ModelInput.cs

using Microsoft.ML.Data;

namespace SampleBinaryClassification.Model.DataModels
{
    public class ModelInput
    {
        [ColumnName("Sentiment"), LoadColumn(0)]
        public bool Sentiment { get; set; }

        [ColumnName("SentimentText"), LoadColumn(1)]
        public string SentimentText { get; set; }
    }
}

ModelOutput.cs

using System;
using Microsoft.ML.Data;

namespace SampleBinaryClassification.Model.DataModels
{
    public class ModelOutput
    {
        // ColumnName attribute is used to change the column name from
        // its default value, which is the name of the field.
        [ColumnName("PredictedLabel")]
        public bool Prediction { get; set; }

        public float Score { get; set; }
    }
}

Leaving a Cliffhanger

I'll leave a cliffhanger for now and continue researching tomorrow.

References

• .NET Machine Learning: ML.NET 1.4 Preview and Model Builder Updates