/// <summary>
/// Initializes a new instance of <see cref="LightGbmMulticlassTrainer"/>
/// </summary>
/// <param name="env">The private instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="labelColumn">The name of The label column.</param>
/// <param name="featureColumn">The name of the feature column.</param>
/// <param name="weights">The name for the column containing the initial weight.</param>
/// <param name="numLeaves">The number of leaves to use.</param>
/// <param name="numBoostRound">Number of iterations.</param>
/// <param name="minDataPerLeaf">The minimal number of documents allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
internal LightGbmMulticlassTrainer(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weights = null,
int?numLeaves = null,
int?minDataPerLeaf = null,
double?learningRate = null,
int numBoostRound = LightGBM.Options.Defaults.NumBoostRound)
: base(env, LoadNameValue, TrainerUtils.MakeU4ScalarColumn(labelColumn), featureColumn, weights, null, numLeaves, minDataPerLeaf, learningRate, numBoostRound)
{
_numClass = -1;
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmMulticlassClassificationTrainer"/>
/// </summary>
/// <param name="env">The private instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="labelColumnName">The name of The label column.</param>
/// <param name="featureColumnName">The name of the feature column.</param>
/// <param name="exampleWeightColumnName">The name of the example weight column (optional).</param>
/// <param name="numberOfLeaves">The number of leaves to use.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of data points allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="numberOfIterations">The number of iterations to use.</param>
internal LightGbmMulticlassClassificationTrainer(IHostEnvironment env,
string labelColumnName = DefaultColumnNames.Label,
string featureColumnName = DefaultColumnNames.Features,
string exampleWeightColumnName = null,
int?numberOfLeaves = null,
int?minimumExampleCountPerLeaf = null,
double?learningRate = null,
int numberOfIterations = Trainers.LightGbm.Options.Defaults.NumberOfIterations)
: base(env, LoadNameValue, TrainerUtils.MakeU4ScalarColumn(labelColumnName), featureColumnName, exampleWeightColumnName, null, numberOfLeaves, minimumExampleCountPerLeaf, learningRate, numberOfIterations)
{
_numClass = -1;
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmMulticlassTrainer"/>
/// </summary>
/// <param name="env">The private instance of <see cref="IHostEnvironment"/>.</param>
/// <param name="labelColumn">The name of the label column.</param>
/// <param name="featureColumn">The name of the feature column.</param>
/// <param name="weightColumn">The name for the column containing the initial weight.</param>
/// <param name="numLeaves">The number of leaves to use.</param>
/// <param name="numBoostRound">Number of iterations.</param>
/// <param name="minDataPerLeaf">The minimal number of documents allowed in a leaf of the tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="advancedSettings">A delegate to set more settings.
/// The settings here will override the ones provided in the direct signature,
/// if both are present and have different values.
/// The columns names, however need to be provided directly, not through the <paramref name="advancedSettings"/>.</param>
public LightGbmMulticlassTrainer(IHostEnvironment env,
string labelColumn,
string featureColumn,
string weightColumn = null,
int?numLeaves = null,
int?minDataPerLeaf = null,
double?learningRate = null,
int numBoostRound = LightGbmArguments.Defaults.NumBoostRound,
Action <LightGbmArguments> advancedSettings = null)
: base(env, LoadNameValue, TrainerUtils.MakeU4ScalarColumn(labelColumn), featureColumn, weightColumn, null, numLeaves, minDataPerLeaf, learningRate, numBoostRound, advancedSettings)
{
_numClass = -1;
}
/// <summary>
/// Initializes a new instance of <see cref="MulticlassLogisticRegression"/>
/// </summary>
/// <param name="env">The environment to use.</param>
/// <param name="labelColumn">The name of the label column.</param>
/// <param name="featureColumn">The name of the feature column.</param>
/// <param name="weights">The name for the example weight column.</param>
/// <param name="enforceNoNegativity">Enforce non-negative weights.</param>
/// <param name="l1Weight">Weight of L1 regularizer term.</param>
/// <param name="l2Weight">Weight of L2 regularizer term.</param>
/// <param name="memorySize">Memory size for <see cref="LogisticRegression"/>. Low=faster, less accurate.</param>
/// <param name="optimizationTolerance">Threshold for optimizer convergence.</param>
internal MulticlassLogisticRegression(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weights = null,
float l1Weight = Options.Defaults.L1Weight,
float l2Weight = Options.Defaults.L2Weight,
float optimizationTolerance = Options.Defaults.OptTol,
int memorySize = Options.Defaults.MemorySize,
bool enforceNoNegativity = Options.Defaults.EnforceNonNegativity)
: base(env, featureColumn, TrainerUtils.MakeU4ScalarColumn(labelColumn), weights, l1Weight, l2Weight, optimizationTolerance, memorySize, enforceNoNegativity)
{
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
ShowTrainingStats = Args.ShowTrainingStats;
}
/// <summary>
/// Initializes a new instance of <see cref="MulticlassLogisticRegression"/>
/// </summary>
/// <param name="env">The environment to use.</param>
/// <param name="labelColumn">The name of the label column.</param>
/// <param name="featureColumn">The name of the feature column.</param>
/// <param name="weightColumn">The name for the example weight column.</param>
/// <param name="enforceNoNegativity">Enforce non-negative weights.</param>
/// <param name="l1Weight">Weight of L1 regularizer term.</param>
/// <param name="l2Weight">Weight of L2 regularizer term.</param>
/// <param name="memorySize">Memory size for <see cref="LogisticRegression"/>. Lower=faster, less accurate.</param>
/// <param name="optimizationTolerance">Threshold for optimizer convergence.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public MulticlassLogisticRegression(IHostEnvironment env, string featureColumn, string labelColumn,
string weightColumn = null,
float l1Weight = Arguments.Defaults.L1Weight,
float l2Weight = Arguments.Defaults.L2Weight,
float optimizationTolerance = Arguments.Defaults.OptTol,
int memorySize = Arguments.Defaults.MemorySize,
bool enforceNoNegativity = Arguments.Defaults.EnforceNonNegativity,
Action <Arguments> advancedSettings = null)
: base(env, featureColumn, TrainerUtils.MakeU4ScalarColumn(labelColumn), weightColumn, advancedSettings,
l1Weight, l2Weight, optimizationTolerance, memorySize, enforceNoNegativity)
{
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
ShowTrainingStats = Args.ShowTrainingStats;
}
/// <summary>
/// Initializes a new instance of <see cref="MulticlassLogisticRegression"/>
/// </summary>
internal MulticlassLogisticRegression(IHostEnvironment env, Options options)
: base(env, options, TrainerUtils.MakeU4ScalarColumn(options.LabelColumn))
{
ShowTrainingStats = Args.ShowTrainingStats;
}
internal LightGbmMulticlassTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeU4ScalarColumn(options.LabelColumnName))
{
Contracts.CheckUserArg(options.Sigmoid > 0, nameof(Options.Sigmoid), "must be > 0.");
_numClass = -1;
}
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();
}
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();
}
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))
{
Args = new Options();
Args.NumLeaves = numLeaves;
Args.MinDataPerLeaf = minDataPerLeaf;
Args.LearningRate = learningRate;
Args.NumBoostRound = numBoostRound;
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();
}
internal LightGbmMulticlassClassificationTrainer(IHostEnvironment env, Options options)
: base(env, LoadNameValue, options, TrainerUtils.MakeU4ScalarColumn(options.LabelColumnName))
{
_numClass = -1;
}
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.LabelColumnName = label.Name;
LightGbmTrainerOptions.FeatureColumnName = featureColumn;
LightGbmTrainerOptions.ExampleWeightColumnName = weightColumn;
LightGbmTrainerOptions.RowGroupColumnName = groupIdColumn;
InitParallelTraining();
}