public void PurposeInferenceHiddenColumnsTest()
{
var context = new MLContext();
// build basic data view
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn(DefaultColumnNames.Label, BooleanDataViewType.Instance);
schemaBuilder.AddColumn(DefaultColumnNames.Features, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
IDataView data = DataViewTestFixture.BuildDummyDataView(schema);
// normalize 'Features' column. this has the effect of creating 2 columns named
// 'Features' in the data view, the first of which gets marked as 'Hidden'
var normalizer = context.Transforms.NormalizeMinMax(DefaultColumnNames.Features);
data = normalizer.Fit(data).Transform(data);
// infer purposes
var purposes = PurposeInference.InferPurposes(context, data, new ColumnInformation());
Assert.Equal(3, purposes.Count());
Assert.Equal(ColumnPurpose.Label, purposes[0].Purpose);
// assert first 'Features' purpose (hidden column) is Ignore
Assert.Equal(ColumnPurpose.Ignore, purposes[1].Purpose);
// assert second 'Features' purpose is NumericFeature
Assert.Equal(ColumnPurpose.NumericFeature, purposes[2].Purpose);
}
public void ValidateEmptyTrainingDataThrows()
{
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn("Number", NumberDataViewType.Single);
schemaBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
var dataView = DataViewTestFixture.BuildDummyDataView(schema, createDummyRow: false);
var ex = Assert.Throws <ArgumentException>(() => UserInputValidationUtil.ValidateExperimentExecuteArgs(dataView, new ColumnInformation(),
null, TaskKind.Regression));
Assert.StartsWith("Training data has 0 rows", ex.Message);
}
public void ValidateFeaturesColInvalidType()
{
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn(DefaultColumnNames.Features, NumberDataViewType.Double);
schemaBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
var dataView = DataViewTestFixture.BuildDummyDataView(schema);
var ex = Assert.Throws <ArgumentException>(() => UserInputValidationUtil.ValidateExperimentExecuteArgs(dataView, new ColumnInformation(), null, TaskKind.Regression));
Assert.StartsWith("Features column must be of data type Single", ex.Message);
}
public void ValidateColumnNotContainedInData()
{
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn(DefaultColumnNames.Features, NumberDataViewType.Single);
schemaBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
var dataView = DataViewTestFixture.BuildDummyDataView(schema);
var columnInfo = new ColumnInformation();
columnInfo.CategoricalColumnNames.Add("Categorical");
Assert.Throws <ArgumentException>(() => ColumnInferenceValidationUtil.ValidateSpecifiedColumnsExist(columnInfo, dataView));
}
public void ValidateProhibitedFeatureColumnType()
{
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn("UInt64", NumberDataViewType.UInt64);
schemaBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
var dataView = DataViewTestFixture.BuildDummyDataView(schema);
var ex = Assert.Throws <ArgumentException>(() => UserInputValidationUtil.ValidateExperimentExecuteArgs(dataView, new ColumnInformation(),
null, TaskKind.Regression));
Assert.StartsWith("Only supported feature column types are Boolean, Single, and String. Please change the feature column UInt64 of type UInt64 to one of the supported types.", ex.Message);
}
private static void TestApplyTransformsToRealDataView(IEnumerable <SuggestedTransform> transforms,
IEnumerable <DatasetColumnInfo> columns)
{
// create a dummy data view from input columns
var data = DataViewTestFixture.BuildDummyDataView(columns);
// iterate thru suggested transforms and apply it to a real data view
foreach (var transform in transforms.Select(t => t.Estimator))
{
data = transform.Fit(data).Transform(data);
}
// assert Features column of type 'R4' exists
var featuresCol = data.Schema.GetColumnOrNull(DefaultColumnNames.Features);
Assert.NotNull(featuresCol);
Assert.True(featuresCol.Value.Type.IsVector());
Assert.Equal(NumberDataViewType.Single, featuresCol.Value.Type.GetItemType());
}
public void ValidateTextColumnNotText()
{
const string TextPurposeColName = "TextColumn";
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn(DefaultColumnNames.Features, NumberDataViewType.Single);
schemaBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single);
schemaBuilder.AddColumn(TextPurposeColName, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
var dataView = DataViewTestFixture.BuildDummyDataView(schema);
var columnInfo = new ColumnInformation();
columnInfo.TextColumnNames.Add(TextPurposeColName);
var ex = Assert.Throws <ArgumentException>(() => UserInputValidationUtil.ValidateExperimentExecuteArgs(dataView, columnInfo, null, TaskKind.Regression));
Assert.Equal("Provided text column 'TextColumn' was of type Single, but only type String is allowed.", ex.Message);
}
public void ValidateEmptyValidationDataThrows()
{
// Training data
var dataViewBuilder = new ArrayDataViewBuilder(new MLContext());
dataViewBuilder.AddColumn("Number", NumberDataViewType.Single, 0f);
dataViewBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single, 0f);
var trainingData = dataViewBuilder.GetDataView();
// Validation data
var schemaBuilder = new DataViewSchema.Builder();
schemaBuilder.AddColumn("Number", NumberDataViewType.Single);
schemaBuilder.AddColumn(DefaultColumnNames.Label, NumberDataViewType.Single);
var schema = schemaBuilder.ToSchema();
var validationData = DataViewTestFixture.BuildDummyDataView(schema, createDummyRow: false);
var ex = Assert.Throws <ArgumentException>(() => UserInputValidationUtil.ValidateExperimentExecuteArgs(trainingData, new ColumnInformation(),
validationData, TaskKind.Regression));
Assert.StartsWith("Validation data has 0 rows", ex.Message);
}
