public static CommonOutputs.TransformOutput TextTransform(IHostEnvironment env, TextFeaturizingEstimator.Arguments input)
{
var h = EntryPointUtils.CheckArgsAndCreateHost(env, "FeaturizeTextEstimator", input);
var xf = TextFeaturizingEstimator.Create(h, input, input.Data);
return(new CommonOutputs.TransformOutput()
{
Model = new TransformModelImpl(h, xf, input.Data),
OutputData = xf
});
}
public TransformApplierParams(TextFeaturizingEstimator parent)
{
var host = parent._host;
host.Check(Enum.IsDefined(typeof(Language), parent.OptionalSettings.Language));
host.Check(Enum.IsDefined(typeof(CaseMode), parent.OptionalSettings.CaseMode));
WordExtractorFactory = parent._wordFeatureExtractor?.CreateComponent(host, parent._dictionary);
CharExtractorFactory = parent._charFeatureExtractor?.CreateComponent(host, parent._dictionary);
Norm = parent.OptionalSettings.Norm;
Language = parent.OptionalSettings.Language;
UsePredefinedStopWordRemover = parent.OptionalSettings.UsePredefinedStopWordRemover;
TextCase = parent.OptionalSettings.CaseMode;
KeepDiacritics = parent.OptionalSettings.KeepDiacritics;
KeepPunctuations = parent.OptionalSettings.KeepPunctuations;
KeepNumbers = parent.OptionalSettings.KeepNumbers;
OutputTextTokens = parent.OptionalSettings.OutputTokens;
Dictionary = parent._dictionary;
}
public TransformApplierParams(TextFeaturizingEstimator parent)
{
var host = parent._host;
host.Check(Enum.IsDefined(typeof(Language), parent.AdvancedSettings.TextLanguage));
host.Check(Enum.IsDefined(typeof(CaseNormalizationMode), parent.AdvancedSettings.TextCase));
WordExtractorFactory = parent._wordFeatureExtractor?.CreateComponent(host, parent._dictionary);
CharExtractorFactory = parent._charFeatureExtractor?.CreateComponent(host, parent._dictionary);
VectorNormalizer = parent.AdvancedSettings.VectorNormalizer;
Language = parent.AdvancedSettings.TextLanguage;
StopWordsRemover = parent._stopWordsRemover;
TextCase = parent.AdvancedSettings.TextCase;
KeepDiacritics = parent.AdvancedSettings.KeepDiacritics;
KeepPunctuations = parent.AdvancedSettings.KeepPunctuations;
KeepNumbers = parent.AdvancedSettings.KeepNumbers;
OutputTextTokens = parent.AdvancedSettings.OutputTokens;
Dictionary = parent._dictionary;
}