/// <summary>
/// Potentially apply a min-max normalizer to the data's feature column, keeping all existing role
/// mappings except for the feature role mapping.
/// </summary>
/// <param name="env">The host environment to use to potentially instantiate the transform</param>
/// <param name="data">The role-mapped data that is potentially going to be modified by this method.</param>
/// <param name="trainer">The trainer to query with <see cref="NormalizeUtils.NeedNormalization(ITrainer)"/>.
/// This method will not modify <paramref name="data"/> if the return from that is <c>null</c> or
/// <c>false</c>.</param>
/// <returns>True if the normalizer was applied and <paramref name="data"/> was modified</returns>
public static bool CreateIfNeeded(IHostEnvironment env, ref RoleMappedData data, ITrainer trainer)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(data, nameof(data));
env.CheckValue(trainer, nameof(trainer));
// If this is false or null, we do not want to normalize.
if (trainer.NeedNormalization() != true)
{
return(false);
}
// If this is true or null, we do not want to normalize.
if (data.Schema.FeaturesAreNormalized() != false)
{
return(false);
}
var featInfo = data.Schema.Feature;
env.AssertValue(featInfo); // Should be defined, if FEaturesAreNormalized returned a definite value.
var view = CreateMinMaxNormalizer(env, data.Data, name: featInfo.Name);
data = RoleMappedData.Create(view, data.Schema.GetColumnRoleNames());
return(true);
}
// Returns true if a normalizer was added.
public static bool AddNormalizerIfNeeded(IHostEnvironment env, IChannel ch, ITrainer trainer, ref IDataView view, string featureColumn, NormalizeOption autoNorm)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(ch, nameof(ch));
ch.CheckValue(trainer, nameof(trainer));
ch.CheckValue(view, nameof(view));
ch.CheckValueOrNull(featureColumn);
ch.CheckUserArg(Enum.IsDefined(typeof(NormalizeOption), autoNorm), nameof(TrainCommand.Arguments.NormalizeFeatures),
"Normalize option is invalid. Specify one of 'norm=No', 'norm=Warn', 'norm=Auto', or 'norm=Yes'.");
if (autoNorm == NormalizeOption.No)
{
ch.Info("Not adding a normalizer.");
return(false);
}
if (string.IsNullOrEmpty(featureColumn))
{
return(false);
}
int featCol;
var schema = view.Schema;
if (schema.TryGetColumnIndex(featureColumn, out featCol))
{
if (autoNorm != NormalizeOption.Yes)
{
DvBool isNormalized = DvBool.False;
if (trainer.NeedNormalization() != true || schema.IsNormalized(featCol))
{
ch.Info("Not adding a normalizer.");
return(false);
}
if (autoNorm == NormalizeOption.Warn)
{
ch.Warning("A normalizer is needed for this trainer. Either add a normalizing transform or use the 'norm=Auto', 'norm=Yes' or 'norm=No' options.");
return(false);
}
}
ch.Info("Automatically adding a MinMax normalization transform, use 'norm=Warn' or 'norm=No' to turn this behavior off.");
IDataView ApplyNormalizer(IHostEnvironment innerEnv, IDataView input)
=> NormalizeTransform.CreateMinMaxNormalizer(innerEnv, input, featureColumn);
if (view is IDataLoader loader)
{
view = CompositeDataLoader.ApplyTransform(env, loader, tag: null, creationArgs: null, ApplyNormalizer);
}
else
{
view = ApplyNormalizer(env, view);
}
return(true);
}
return(false);
}