/// <summary>
/// Apply this transform model to the given input data.
/// </summary>
public IDataView Apply(IHostEnvironment env, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(input, nameof(input));
return(ApplyTransformUtils.ApplyAllTransformsToData(env, _chain, input));
}
void CrossValidation()
{
var dataset = TestDatasets.Sentiment;
int numFolds = 5;
using (var env = new LocalEnvironment(seed: 1, conc: 1))
{
// Pipeline.
var loader = TextLoader.ReadFile(env, MakeSentimentTextLoaderArgs(), new MultiFileSource(GetDataPath(dataset.trainFilename)));
var text = TextFeaturizingEstimator.Create(env, MakeSentimentTextTransformArgs(false), loader);
IDataView trans = new GenerateNumberTransform(env, text, "StratificationColumn");
// Train.
var trainer = new LinearClassificationTrainer(env, new LinearClassificationTrainer.Arguments
{
NumThreads = 1,
ConvergenceTolerance = 1f
});
var metrics = new List <BinaryClassificationMetrics>();
for (int fold = 0; fold < numFolds; fold++)
{
IDataView trainPipe = new RangeFilter(env, new RangeFilter.Arguments()
{
Column = "StratificationColumn",
Min = (Double)fold / numFolds,
Max = (Double)(fold + 1) / numFolds,
Complement = true
}, trans);
trainPipe = new OpaqueDataView(trainPipe);
var trainData = new RoleMappedData(trainPipe, label: "Label", feature: "Features");
// Auto-normalization.
NormalizeTransform.CreateIfNeeded(env, ref trainData, trainer);
var preCachedData = trainData;
// Auto-caching.
if (trainer.Info.WantCaching)
{
var prefetch = trainData.Schema.GetColumnRoles().Select(kc => kc.Value.Index).ToArray();
var cacheView = new CacheDataView(env, trainData.Data, prefetch);
// Because the prefetching worked, we know that these are valid columns.
trainData = new RoleMappedData(cacheView, trainData.Schema.GetColumnRoleNames());
}
var predictor = trainer.Train(new Runtime.TrainContext(trainData));
IDataView testPipe = new RangeFilter(env, new RangeFilter.Arguments()
{
Column = "StratificationColumn",
Min = (Double)fold / numFolds,
Max = (Double)(fold + 1) / numFolds,
Complement = false
}, trans);
testPipe = new OpaqueDataView(testPipe);
var pipe = ApplyTransformUtils.ApplyAllTransformsToData(env, preCachedData.Data, testPipe, trainPipe);
var testRoles = new RoleMappedData(pipe, trainData.Schema.GetColumnRoleNames());
IDataScorerTransform scorer = ScoreUtils.GetScorer(predictor, testRoles, env, testRoles.Schema);
BinaryClassifierMamlEvaluator eval = new BinaryClassifierMamlEvaluator(env, new BinaryClassifierMamlEvaluator.Arguments()
{
});
var dataEval = new RoleMappedData(scorer, testRoles.Schema.GetColumnRoleNames(), opt: true);
var dict = eval.Evaluate(dataEval);
var foldMetrics = BinaryClassificationMetrics.FromMetrics(env, dict["OverallMetrics"], dict["ConfusionMatrix"]);
metrics.Add(foldMetrics.Single());
}
}
}
public static IDataTransform Create(IHostEnvironment env, Arguments args, IDataView input)
{
Contracts.CheckValue(env, nameof(env));
var host = env.Register("Tree Featurizer Transform");
host.CheckValue(args, nameof(args));
host.CheckValue(input, nameof(input));
host.CheckUserArg(!string.IsNullOrWhiteSpace(args.TrainedModelFile) || args.Trainer != null, nameof(args.TrainedModelFile),
"Please specify either a trainer or an input model file.");
host.CheckUserArg(!string.IsNullOrEmpty(args.FeatureColumn), nameof(args.FeatureColumn), "Transform needs an input features column");
IDataTransform xf;
using (var ch = host.Start("Create Tree Ensemble Scorer"))
{
var scorerArgs = new TreeEnsembleFeaturizerBindableMapper.Arguments()
{
Suffix = args.Suffix
};
if (!string.IsNullOrWhiteSpace(args.TrainedModelFile))
{
if (args.Trainer != null)
{
ch.Warning("Both an input model and a trainer were specified. Using the model file.");
}
ch.Trace("Loading model");
IPredictor predictor;
using (Stream strm = new FileStream(args.TrainedModelFile, FileMode.Open, FileAccess.Read))
using (var rep = RepositoryReader.Open(strm, ch))
ModelLoadContext.LoadModel <IPredictor, SignatureLoadModel>(host, out predictor, rep, ModelFileUtils.DirPredictor);
ch.Trace("Creating scorer");
var data = TrainAndScoreTransformer.CreateDataFromArgs(ch, input, args);
// Make sure that the given predictor has the correct number of input features.
if (predictor is CalibratedPredictorBase)
{
predictor = ((CalibratedPredictorBase)predictor).SubPredictor;
}
// Predictor should be a TreeEnsembleModelParameters, which implements IValueMapper, so this should
// be non-null.
var vm = predictor as IValueMapper;
ch.CheckUserArg(vm != null, nameof(args.TrainedModelFile), "Predictor in model file does not have compatible type");
if (vm.InputType.VectorSize != data.Schema.Feature.Type.VectorSize)
{
throw ch.ExceptUserArg(nameof(args.TrainedModelFile),
"Predictor in model file expects {0} features, but data has {1} features",
vm.InputType.VectorSize, data.Schema.Feature.Type.VectorSize);
}
var bindable = new TreeEnsembleFeaturizerBindableMapper(env, scorerArgs, predictor);
var bound = bindable.Bind(env, data.Schema);
xf = new GenericScorer(env, scorerArgs, input, bound, data.Schema);
}
else
{
ch.AssertValue(args.Trainer);
ch.Trace("Creating TrainAndScoreTransform");
var trainScoreArgs = new TrainAndScoreTransformer.Arguments();
args.CopyTo(trainScoreArgs);
trainScoreArgs.Trainer = args.Trainer;
trainScoreArgs.Scorer = ComponentFactoryUtils.CreateFromFunction <IDataView, ISchemaBoundMapper, RoleMappedSchema, IDataScorerTransform>(
(e, data, mapper, trainSchema) => Create(e, scorerArgs, data, mapper, trainSchema));
var mapperFactory = ComponentFactoryUtils.CreateFromFunction <IPredictor, ISchemaBindableMapper>(
(e, predictor) => new TreeEnsembleFeaturizerBindableMapper(e, scorerArgs, predictor));
var labelInput = AppendLabelTransform(host, ch, input, trainScoreArgs.LabelColumn, args.LabelPermutationSeed);
var scoreXf = TrainAndScoreTransformer.Create(host, trainScoreArgs, labelInput, mapperFactory);
if (input == labelInput)
{
return(scoreXf);
}
return((IDataTransform)ApplyTransformUtils.ApplyAllTransformsToData(host, scoreXf, input, labelInput));
}
}
return(xf);
}
public IDataView Transform(IDataView input) => ApplyTransformUtils.ApplyAllTransformsToData(_env, _xf, input);