LinearSupportVectorMachines trainer not working

[daholste]

System information

• OS version/distro: Windows 10
• .NET Version (eg., dotnet --info): .NET Core 2.1

Issue

Setup code

const string trainDataPath = @"C:\data\sample_train2.csv";
const string validationDataPath = @"C:\data\sample_valid2.csv";
const string testDataPath = @"C:\data\sample_test2.csv";

var mlContext = new MLContext();

// auto-infer text loader args
var textLoaderArgs = RecipeInference.MyAutoMlInferTextLoaderArguments(mlContext, trainDataPath, "Label");

// load data
var textLoader = new TextLoader(mlContext,
	new TextLoader.Arguments()
	{
		Separator = ",",
		HasHeader = true,
		Column = new[]
		{
			new TextLoader.Column("Age", DataKind.R4, 0),
			new TextLoader.Column("Workclass", DataKind.TX, 1),
			new TextLoader.Column("Fnlwgt", DataKind.R4, 2),
			new TextLoader.Column("Education", DataKind.TX, 3),
			new TextLoader.Column("EducationNum", DataKind.R4, 4),
			new TextLoader.Column("MaritalStatus", DataKind.TX, 5),
			new TextLoader.Column("Occupation", DataKind.TX, 6),
			new TextLoader.Column("Relationship", DataKind.TX, 7),
			new TextLoader.Column("Race", DataKind.TX, 8),
			new TextLoader.Column("Sex", DataKind.TX, 9),
			new TextLoader.Column("CapitalGain", DataKind.R4, 10),
			new TextLoader.Column("CapitalLoss", DataKind.R4, 11),
			new TextLoader.Column("HoursPerWeek", DataKind.R4, 12),
			new TextLoader.Column("NativeCountry", DataKind.TX, 13),
			new TextLoader.Column("Label", DataKind.Bool, 14),
		}
	});

var trainData = textLoader.Read(trainDataPath);
var validationData = textLoader.Read(validationDataPath);
var testData = textLoader.Read(testDataPath);

// preprocess
var preprocessorEstimator = mlContext.Transforms.Categorical.OneHotEncoding("Workclass", "Workclass")
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("Education", "Education"))
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("MaritalStatus", "MaritalStatus"))
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("Occupation", "Occupation"))
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("Relationship", "Relationship"))
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("Race", "Race"))
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("Sex", "Sex"))
	.Append(mlContext.Transforms.Categorical.OneHotEncoding("NativeCountry", "NativeCountry"))
	.Append(mlContext.Transforms.Concatenate(DefaultColumnNames.Features,
		"Age", "Workclass", "Fnlwgt", "Education", "EducationNum", "MaritalStatus", "Occupation", "Relationship",
		"Race", "Sex", "CapitalGain", "CapitalLoss", "HoursPerWeek", "NativeCountry"));

Code that worked

// train model
var trainer = mlContext.BinaryClassification.Trainers.StochasticDualCoordinateAscent();
var estimatorChain = preprocessorEstimator.Append(trainer);
var model = estimatorChain.Fit(trainData);

Code that didn't work

// train model
var trainer = mlContext.BinaryClassification.Trainers.LinearSupportVectorMachines();
var estimatorChain = preprocessorEstimator.Append(trainer);
var model = estimatorChain.Fit(trainData);

Exception
System.InvalidOperationException: 'Weight column 'Weight' is not found'

[Ivanidzo4ka]

Just run it on my machine with latest master, and it works fine.
What version of ml.net are you using?

[TomFinley]

Thanks for reporting @daholste ! @Ivanidzo4ka, this appears to have been incidentally fixed as far as I see #1847 in a one-line fix (not sure how @artidoro came across it, and I don't really see it mentioned, but I haven't looked through everything in that PR).