/// <summary>
/// Initializes a new instance of <see cref="FastForestRegression"/> by using the legacy <see cref="Arguments"/> class.
/// </summary>
public FastForestRegression(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeR4ScalarLabel(args.LabelColumn), true)
{
}
internal LightGbmRankingTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeR4ScalarColumn(options.LabelColumnName))
{
Contracts.CheckUserArg(options.Sigmoid > 0, nameof(Options.Sigmoid), "must be > 0.");
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestClassification"/> by using the legacy <see cref="Arguments"/> class.
/// </summary>
public FastForestClassification(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
}
internal LightGbmRegressorTrainer(IHostEnvironment env, LightGbmArguments args)
: base(env, LoadNameValue, args, TrainerUtils.MakeR4ScalarColumn(args.LabelColumn))
{
}
private protected GamTrainerBase(IHostEnvironment env,
string name,
SchemaShape.Column label,
string featureColumnName,
string weightCrowGroupColumnName,
int numberOfIterations,
double learningRate,
int maximumBinCountPerFeature)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(featureColumnName), label, TrainerUtils.MakeR4ScalarWeightColumn(weightCrowGroupColumnName))
{
GamTrainerOptions = new TOptions();
GamTrainerOptions.NumberOfIterations = numberOfIterations;
GamTrainerOptions.LearningRate = learningRate;
GamTrainerOptions.MaximumBinCountPerFeature = maximumBinCountPerFeature;
GamTrainerOptions.LabelColumnName = label.Name;
GamTrainerOptions.FeatureColumnName = featureColumnName;
if (weightCrowGroupColumnName != null)
{
GamTrainerOptions.ExampleWeightColumnName = weightCrowGroupColumnName;
}
Info = new TrainerInfo(normalization: false, calibration: NeedCalibration, caching: false, supportValid: true);
_gainConfidenceInSquaredStandardDeviations = Math.Pow(ProbabilityFunctions.Probit(1 - (1 - GamTrainerOptions.GainConfidenceLevel) * 0.5), 2);
_entropyCoefficient = GamTrainerOptions.EntropyCoefficient * 1e-6;
InitializeThreads();
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestClassification"/> by using the <see cref="Options"/> class.
/// </summary>
/// <param name="env">The instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="options">Algorithm advanced settings.</param>
internal FastForestClassification(IHostEnvironment env, Options options)
: base(env, options, TrainerUtils.MakeBoolScalarLabel(options.LabelColumn))
{
}
private protected LightGbmTrainerBase(IHostEnvironment env, string name, Options options, SchemaShape.Column label)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(options.FeatureColumnName), label,
TrainerUtils.MakeR4ScalarWeightColumn(options.ExampleWeightColumnName), TrainerUtils.MakeU4ScalarColumn(options.RowGroupColumnName))
{
Host.CheckValue(options, nameof(options));
LightGbmTrainerOptions = options;
InitParallelTraining();
}
internal LightGbmBinaryTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeBoolScalarLabel(options.LabelColumn))
{
}
internal LightGbmRankingTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeR4ScalarColumn(options.LabelColumn))
{
}
internal OnlineGradientDescentTrainer(IHostEnvironment env, Arguments args)
: base(args, env, UserNameValue, TrainerUtils.MakeR4ScalarLabel(args.LabelColumn))
{
LossFunction = args.LossFunction.CreateComponent(env);
}
internal LightGbmBinaryTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeBoolScalarLabel(options.LabelColumnName))
{
Contracts.CheckUserArg(options.Sigmoid > 0, nameof(Options.Sigmoid), "must be > 0.");
Contracts.CheckUserArg(options.WeightOfPositiveExamples > 0, nameof(Options.WeightOfPositiveExamples), "must be > 0.");
}
/// <summary>
/// Initializes a new instance of <see cref="LogisticRegression"/>
/// </summary>
internal LogisticRegression(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
_posWeight = 0;
ShowTrainingStats = Args.ShowTrainingStats;
}
/// <summary>
/// Initializes a new instance of <see cref="BinaryClassificationGamTrainer"/>
/// </summary>
internal BinaryClassificationGamTrainer(IHostEnvironment env, Options options)
: base(env, options, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(options.LabelColumnName))
{
_sigmoidParameter = 1;
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestBinaryTrainer"/> by using the <see cref="Options"/> class.
/// </summary>
/// <param name="env">The instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="options">Algorithm advanced settings.</param>
internal FastForestBinaryTrainer(IHostEnvironment env, Options options)
: base(env, options, TrainerUtils.MakeBoolScalarLabel(options.LabelColumnName))
{
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeTweedieTrainer"/> by using the <see cref="Options"/> class.
/// </summary>
/// <param name="env">The instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="options">Algorithm advanced settings.</param>
internal FastTreeTweedieTrainer(IHostEnvironment env, Options options)
: base(env, options, TrainerUtils.MakeR4ScalarColumn(options.LabelColumn))
{
Initialize();
}
private protected LightGbmTrainerBase(IHostEnvironment env, string name, LightGbmArguments args, SchemaShape.Column label)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(args.FeatureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(args.WeightColumn, args.WeightColumn.IsExplicit))
{
Host.CheckValue(args, nameof(args));
Args = args;
InitParallelTraining();
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeBinaryClassificationTrainer"/> by using the legacy <see cref="Arguments"/> class.
/// </summary>
internal FastTreeBinaryClassificationTrainer(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
// Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
_sigmoidParameter = 2.0 * Args.LearningRates;
}
private protected LightGbmTrainerBase(IHostEnvironment env,
string name,
SchemaShape.Column label,
string featureColumn,
string weightColumn,
string groupIdColumn,
int?numLeaves,
int?minDataPerLeaf,
double?learningRate,
int numBoostRound,
Action <LightGbmArguments> advancedSettings)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(featureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(weightColumn), TrainerUtils.MakeU4ScalarColumn(groupIdColumn))
{
Args = new LightGbmArguments();
Args.NumLeaves = numLeaves;
Args.MinDataPerLeaf = minDataPerLeaf;
Args.LearningRate = learningRate;
Args.NumBoostRound = numBoostRound;
//apply the advanced args, if the user supplied any
advancedSettings?.Invoke(Args);
Args.LabelColumn = label.Name;
Args.FeatureColumn = featureColumn;
if (weightColumn != null)
{
Args.WeightColumn = Optional <string> .Explicit(weightColumn);
}
if (groupIdColumn != null)
{
Args.GroupIdColumn = Optional <string> .Explicit(groupIdColumn);
}
InitParallelTraining();
}
private protected LightGbmTrainerBase(IHostEnvironment env,
string name,
SchemaShape.Column labelColumn,
string featureColumnName,
string exampleWeightColumnName,
string rowGroupColumnName,
int?numberOfLeaves,
int?minimumExampleCountPerLeaf,
double?learningRate,
int numberOfIterations)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(featureColumnName),
labelColumn, TrainerUtils.MakeR4ScalarWeightColumn(exampleWeightColumnName), TrainerUtils.MakeU4ScalarColumn(rowGroupColumnName))
{
LightGbmTrainerOptions = new Options();
LightGbmTrainerOptions.NumberOfLeaves = numberOfLeaves;
LightGbmTrainerOptions.MinimumExampleCountPerLeaf = minimumExampleCountPerLeaf;
LightGbmTrainerOptions.LearningRate = learningRate;
LightGbmTrainerOptions.NumberOfIterations = numberOfIterations;
LightGbmTrainerOptions.LabelColumnName = labelColumn.Name;
LightGbmTrainerOptions.FeatureColumnName = featureColumnName;
LightGbmTrainerOptions.ExampleWeightColumnName = exampleWeightColumnName;
LightGbmTrainerOptions.RowGroupColumnName = rowGroupColumnName;
InitParallelTraining();
}
/// <summary>
/// Initializes a new instance of <see cref="PoissonRegression"/>
/// </summary>
internal PoissonRegression(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeR4ScalarLabel(args.LabelColumn))
{
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeTweedieTrainer"/> by using the legacy <see cref="Arguments"/> class.
/// </summary>
internal FastTreeTweedieTrainer(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeR4ScalarLabel(args.LabelColumn))
{
Initialize();
}
internal RegressionGamTrainer(IHostEnvironment env, Options options)
: base(env, options, LoadNameValue, TrainerUtils.MakeR4ScalarColumn(options.LabelColumn))
{
}
internal LightGbmMulticlassTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeU4ScalarColumn(options.LabelColumnName))
{
_numClass = -1;
}
internal RegressionGamTrainer(IHostEnvironment env, Arguments args)
: base(env, args, LoadNameValue, TrainerUtils.MakeR4ScalarLabel(args.LabelColumn))
{
}
private RandomizedPcaTrainer(IHostEnvironment env, Arguments args, string featureColumn, string weightColumn,
int rank = 20, int oversampling = 20, bool center = true, int?seed = null)
: base(Contracts.CheckRef(env, nameof(env)).Register(LoadNameValue), TrainerUtils.MakeR4VecFeature(featureColumn), null, TrainerUtils.MakeR4ScalarWeightColumn(weightColumn))
{
// if the args are not null, we got here from maml, and the internal ctor.
if (args != null)
{
_rank = args.Rank;
_center = args.Center;
_oversampling = args.Oversampling;
_seed = args.Seed ?? Host.Rand.Next();
}
else
{
_rank = rank;
_center = center;
_oversampling = oversampling;
_seed = seed ?? Host.Rand.Next();
}
_featureColumn = featureColumn;
Host.CheckUserArg(_rank > 0, nameof(_rank), "Rank must be positive");
Host.CheckUserArg(_oversampling >= 0, nameof(_oversampling), "Oversampling must be non-negative");
}
/// <summary>
/// Initializes a new instance of <see cref="MulticlassLogisticRegression"/>
/// </summary>
internal MulticlassLogisticRegression(IHostEnvironment env, Arguments args)
: base(env, args, TrainerUtils.MakeU4ScalarColumn(args.LabelColumn))
{
ShowTrainingStats = Args.ShowTrainingStats;
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeRegressionTrainer"/> by using the <see cref="Options"/> class.
/// </summary>
/// <param name="env">The instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="options">Algorithm advanced settings.</param>
internal FastTreeRegressionTrainer(IHostEnvironment env, Options options)
: base(env, options, TrainerUtils.MakeR4ScalarColumn(options.LabelColumn))
{
}
/// <summary>
/// Initializes a new instance of <see cref="BinaryClassificationGamTrainer"/>
/// </summary>
internal BinaryClassificationGamTrainer(IHostEnvironment env, Arguments args)
: base(env, args, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
_sigmoidParameter = 1;
}
internal AveragedPerceptronTrainer(IHostEnvironment env, Arguments args)
: base(args, env, UserNameValue, TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
_args = args;
LossFunction = _args.LossFunction.CreateComponent(env);
}
private protected LightGbmTrainerBase(IHostEnvironment env,
string name,
SchemaShape.Column label,
string featureColumn,
string weightColumn,
string groupIdColumn,
int?numLeaves,
int?minDataPerLeaf,
double?learningRate,
int numBoostRound)
: base(Contracts.CheckRef(env, nameof(env)).Register(name), TrainerUtils.MakeR4VecFeature(featureColumn), label, TrainerUtils.MakeR4ScalarWeightColumn(weightColumn), TrainerUtils.MakeU4ScalarColumn(groupIdColumn))
{
LightGbmTrainerOptions = new Options();
LightGbmTrainerOptions.NumLeaves = numLeaves;
LightGbmTrainerOptions.MinDataPerLeaf = minDataPerLeaf;
LightGbmTrainerOptions.LearningRate = learningRate;
LightGbmTrainerOptions.NumBoostRound = numBoostRound;
LightGbmTrainerOptions.LabelColumn = label.Name;
LightGbmTrainerOptions.FeatureColumn = featureColumn;
LightGbmTrainerOptions.WeightColumn = weightColumn;
LightGbmTrainerOptions.GroupIdColumn = groupIdColumn;
InitParallelTraining();
}
