public void AutoFitRegressionTest(string culture)
{
var originalCulture = Thread.CurrentThread.CurrentCulture;
try
{
Thread.CurrentThread.CurrentCulture = new CultureInfo(culture);
// If users run AutoML with a different locale, sometimes
// the sweeper encounters problems when parsing some strings.
// So testing in another culture is necessary.
// Furthermore, these issues might only occur after ~70
// iterations, so more experiment time is needed for this to
// occur.
uint experimentTime = (uint)(culture == "en-US" ? 0 : 180);
var experimentSettings = new RegressionExperimentSettings {
MaxExperimentTimeInSeconds = experimentTime
};
if (!Environment.Is64BitProcess)
{
// LightGBM isn't available on x86 machines
experimentSettings.Trainers.Remove(RegressionTrainer.LightGbm);
}
var context = new MLContext(1);
var dataPath = DatasetUtil.GetMlNetGeneratedRegressionDataset();
var columnInference = context.Auto().InferColumns(dataPath, DatasetUtil.MlNetGeneratedRegressionLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(dataPath);
var validationData = context.Data.TakeRows(trainData, 20);
trainData = context.Data.SkipRows(trainData, 20);
var result = context.Auto()
.CreateRegressionExperiment(experimentSettings)
.Execute(trainData, validationData,
new ColumnInformation()
{
LabelColumnName = DatasetUtil.MlNetGeneratedRegressionLabel
});
Assert.True(result.RunDetails.Max(i => i.ValidationMetrics.RSquared > 0.9));
// Ensure experimentTime allows enough iterations to fully test the internationalization code
// If the below assertion fails, increase the experiment time so the number of iterations is met
Assert.True(culture == "en-US" || result.RunDetails.Count() >= 75, $"RunDetails.Count() = {result.RunDetails.Count()}, below 75");
}
finally
{
Thread.CurrentThread.CurrentCulture = originalCulture;
}
}
public void AutoFitRegressionTest(string culture)
{
var originalCulture = Thread.CurrentThread.CurrentCulture;
try
{
Thread.CurrentThread.CurrentCulture = new CultureInfo(culture);
// If users run AutoML with a different locale, sometimes
// the sweeper encounters problems when parsing some strings.
// So testing in another culture is necessary.
// Furthermore, these issues might only occur after ~70
// iterations, so setting the internal maxModels parameter.
int maxModels = culture == "en-US" ? 1 : 75;
var experimentSettings = new RegressionExperimentSettings {
MaxModels = maxModels
};
if (!Environment.Is64BitProcess)
{
// LightGBM isn't available on x86 machines
experimentSettings.Trainers.Remove(RegressionTrainer.LightGbm);
}
var context = new MLContext(1);
var dataPath = DatasetUtil.GetMlNetGeneratedRegressionDataset();
var columnInference = context.Auto().InferColumns(dataPath, DatasetUtil.MlNetGeneratedRegressionLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(dataPath);
var validationData = context.Data.TakeRows(trainData, 20);
trainData = context.Data.SkipRows(trainData, 20);
var result = context.Auto()
.CreateRegressionExperiment(experimentSettings)
.Execute(trainData, validationData,
new ColumnInformation()
{
LabelColumnName = DatasetUtil.MlNetGeneratedRegressionLabel
});
Assert.True(result.RunDetails.Max(i => i?.ValidationMetrics?.RSquared) > 0.99);
// Test the internal maxModels parameter
Assert.True(culture == "en-US" || result.RunDetails.Count() == 75, $"RunDetails.Count() = {result.RunDetails.Count()}, is not 75");
}
finally
{
Thread.CurrentThread.CurrentCulture = originalCulture;
}
}
public void InferColumnsColumnInfoParam()
{
var columnInfo = new ColumnInformation()
{
LabelColumnName = DatasetUtil.MlNetGeneratedRegressionLabel
};
var result = new MLContext(1).Auto().InferColumns(DatasetUtil.GetMlNetGeneratedRegressionDataset(),
columnInfo);
var labelCol = result.TextLoaderOptions.Columns.First(c => c.Name == DatasetUtil.MlNetGeneratedRegressionLabel);
Assert.Equal(DataKind.Single, labelCol.DataKind);
Assert.Equal(DatasetUtil.MlNetGeneratedRegressionLabel, result.ColumnInformation.LabelColumnName);
Assert.Single(result.ColumnInformation.NumericColumnNames);
Assert.Equal(DefaultColumnNames.Features, result.ColumnInformation.NumericColumnNames.First());
Assert.Null(result.ColumnInformation.ExampleWeightColumnName);
}
public void AutoFitRegressionTest()
{
var context = new MLContext(1);
var dataPath = DatasetUtil.GetMlNetGeneratedRegressionDataset();
var columnInference = context.Auto().InferColumns(dataPath, DatasetUtil.MlNetGeneratedRegressionLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(dataPath);
var validationData = context.Data.TakeRows(trainData, 20);
trainData = context.Data.SkipRows(trainData, 20);
var result = context.Auto()
.CreateRegressionExperiment(0)
.Execute(trainData, validationData,
new ColumnInformation()
{
LabelColumnName = DatasetUtil.MlNetGeneratedRegressionLabel
});
Assert.True(result.RunDetails.Max(i => i.ValidationMetrics.RSquared > 0.9));
}
public void AutoFitRegressionTest(string culture)
{
var originalCulture = Thread.CurrentThread.CurrentCulture;
try
{
Thread.CurrentThread.CurrentCulture = new CultureInfo(culture);
// If users run AutoML with a different locale, sometimes
// the sweeper encounters problems when parsing some strings.
// So testing in another culture is necessary.
// Furthermore, these issues might only occur after ~70
// iterations, so more experiment time is needed for this to
// occur.
uint experimentTime = (uint)(culture == "en-US" ? 0 : 180);
var experimentSettings = new RegressionExperimentSettings {
MaxExperimentTimeInSeconds = experimentTime
};
if (!Environment.Is64BitProcess)
{
// LightGBM isn't available on x86 machines
experimentSettings.Trainers.Remove(RegressionTrainer.LightGbm);
}
var context = new MLContext(1);
var dataPath = DatasetUtil.GetMlNetGeneratedRegressionDataset();
var columnInference = context.Auto().InferColumns(dataPath, DatasetUtil.MlNetGeneratedRegressionLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(dataPath);
var validationData = context.Data.TakeRows(trainData, 20);
trainData = context.Data.SkipRows(trainData, 20);
var result = context.Auto()
.CreateRegressionExperiment(experimentSettings)
.Execute(trainData, validationData,
new ColumnInformation()
{
LabelColumnName = DatasetUtil.MlNetGeneratedRegressionLabel
});
Assert.True(result.RunDetails.Max(i => i?.ValidationMetrics?.RSquared) > 0.9);
// Ensure experimentTime allows enough iterations to fully test the internationalization code
// If the below assertion fails, increase the experiment time so the number of iterations is met
Assert.True(culture == "en-US" || result.RunDetails.Count() >= 75, $"RunDetails.Count() = {result.RunDetails.Count()}, below 75");
}
catch (AggregateException ae)
{
// During CI unit testing, the host machines can run slower than normal, which
// can increase the run time of unit tests and throw OperationCanceledExceptions
// from multiple threads in the form of a single AggregateException.
foreach (var ex in ae.Flatten().InnerExceptions)
{
var ignoredExceptions = new List <Exception>();
if (ex is OperationCanceledException)
{
continue;
}
else
{
ignoredExceptions.Add(ex);
}
if (ignoredExceptions.Count > 0)
{
throw new AggregateException(ignoredExceptions);
}
}
}
finally
{
Thread.CurrentThread.CurrentCulture = originalCulture;
}
}