// Factory method for SignatureDataTransform.
private 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);
Contracts.Assert(data.Schema.Feature.HasValue);
// 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.Value.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.Value.Type.VectorSize);
}
ISchemaBindableMapper 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 ParameterMixingCalibratedPredictor TrainKMeansAndLR()
{
using (var env = new ConsoleEnvironment(seed: 1, verbose: false, sensitivity: MessageSensitivity.None, outWriter: EmptyWriter.Instance))
{
// Pipeline
var loader = TextLoader.ReadFile(env,
new TextLoader.Arguments()
{
HasHeader = true,
Separator = ",",
Column = new[] {
new TextLoader.Column("Label", DataKind.R4, 14),
new TextLoader.Column("CatFeatures", DataKind.TX,
new [] {
new TextLoader.Range()
{
Min = 1, Max = 1
},
new TextLoader.Range()
{
Min = 3, Max = 3
},
new TextLoader.Range()
{
Min = 5, Max = 9
},
new TextLoader.Range()
{
Min = 13, Max = 13
}
}),
new TextLoader.Column("NumFeatures", DataKind.R4,
new [] {
new TextLoader.Range()
{
Min = 0, Max = 0
},
new TextLoader.Range()
{
Min = 2, Max = 2
},
new TextLoader.Range()
{
Min = 4, Max = 4
},
new TextLoader.Range()
{
Min = 10, Max = 12
}
})
}
}, new MultiFileSource(_dataPath));
IDataView trans = new OneHotEncodingEstimator(env, "CatFeatures").Fit(loader).Transform(loader);
trans = NormalizeTransform.CreateMinMaxNormalizer(env, trans, "NumFeatures");
trans = new ColumnConcatenatingTransformer(env, "Features", "NumFeatures", "CatFeatures").Transform(trans);
trans = TrainAndScoreTransformer.Create(env, new TrainAndScoreTransformer.Arguments
{
Trainer = ComponentFactoryUtils.CreateFromFunction(host =>
new KMeansPlusPlusTrainer(host, "Features", advancedSettings: s =>
{
s.K = 100;
})),
FeatureColumn = "Features"
}, trans);
trans = new ColumnConcatenatingTransformer(env, "Features", "Features", "Score").Transform(trans);
// Train
var trainer = new LogisticRegression(env, "Label", "Features", advancedSettings: args => { args.EnforceNonNegativity = true; args.OptTol = 1e-3f; });
var trainRoles = new RoleMappedData(trans, label: "Label", feature: "Features");
return(trainer.Train(trainRoles));
}
}
