/// <summary>
/// Initializes a new instance of <see cref="FastTreeBinaryClassificationTrainer"/>
/// </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="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
/// <param name="numLeaves">The max number of leaves in each regression tree.</param>
/// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
public FastTreeBinaryClassificationTrainer(IHostEnvironment env,
string labelColumn,
string featureColumn,
string weightColumn = null,
int numLeaves = Defaults.NumLeaves,
int numTrees = Defaults.NumTrees,
int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
double learningRate = Defaults.LearningRates,
Action <Arguments> advancedSettings = null)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
// Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
_sigmoidParameter = 2.0 * Args.LearningRates;
if (advancedSettings != null)
{
CheckArgsAndAdvancedSettingMismatch(numLeaves, numTrees, minDocumentsInLeafs, learningRate, new Arguments(), Args);
}
//override with the directly provided values.
Args.NumLeaves = numLeaves;
Args.NumTrees = numTrees;
Args.MinDocumentsInLeafs = minDocumentsInLeafs;
Args.LearningRates = learningRate;
}
protected CalibratorEstimatorBase(IHostEnvironment env,
TCalibratorTrainer calibratorTrainer,
IPredictor predictor = null,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weightColumn = null)
{
Host = env;
Predictor = predictor;
CalibratorTrainer = calibratorTrainer;
ScoreColumn = TrainerUtils.MakeR4ScalarColumn(DefaultColumnNames.Score); // Do we fantom this being named anything else (renaming column)? Complete metadata?
LabelColumn = TrainerUtils.MakeBoolScalarLabel(labelColumn);
FeatureColumn = TrainerUtils.MakeR4VecFeature(featureColumn);
PredictedLabel = new SchemaShape.Column(DefaultColumnNames.PredictedLabel,
SchemaShape.Column.VectorKind.Scalar,
BoolType.Instance,
false,
new SchemaShape(MetadataUtils.GetTrainerOutputMetadata()));
if (weightColumn != null)
{
WeightColumn = TrainerUtils.MakeR4ScalarWeightColumn(weightColumn);
}
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestClassification"/>
/// </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="groupIdColumn">The name for the column containing the group ID.</param>
/// <param name="weightColumn">The name for the column containing the initial weight.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public FastForestClassification(IHostEnvironment env, string labelColumn, string featureColumn,
string groupIdColumn = null, string weightColumn = null, Action <Arguments> advancedSettings = null)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, groupIdColumn, advancedSettings: advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmBinaryTrainer"/>
/// </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="groupIdColumn">The name for the column containing the group ID. </param>
/// <param name="weightColumn">The name for the column containing the initial weight.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public LightGbmBinaryTrainer(IHostEnvironment env, string labelColumn, string featureColumn,
string groupIdColumn = null, string weightColumn = null, Action <LightGbmArguments> advancedSettings = null)
: base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, groupIdColumn, advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
}
/// <summary>
/// Initializes a new instance of <see cref="SymSgdClassificationTrainer"/>
/// </summary>
internal SymSgdClassificationTrainer(IHostEnvironment env, Arguments args)
: base(Contracts.CheckRef(env, nameof(env)).Register(LoadNameValue), TrainerUtils.MakeR4VecFeature(args.FeatureColumn),
TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
args.Check(Host);
_args = args;
Info = new TrainerInfo();
}
/// <summary>
/// Initializes a new instance of <see cref="BinaryClassificationGamTrainer"/>
/// </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="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public BinaryClassificationGamTrainer(IHostEnvironment env, string labelColumn, string featureColumn, string weightColumn = null, Action <Arguments> advancedSettings = null)
: base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
_sigmoidParameter = 1;
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmBinaryTrainer"/>
/// </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 LightGbmBinaryTrainer(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.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, minDataPerLeaf, learningRate, numBoostRound, advancedSettings)
{
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeBinaryClassificationTrainer"/>
/// </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="groupIdColumn">The name for the column containing the group ID. </param>
/// <param name="weightColumn">The name for the column containing the initial weight.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public FastTreeBinaryClassificationTrainer(IHostEnvironment env, string labelColumn, string featureColumn,
string groupIdColumn = null, string weightColumn = null, Action <Arguments> advancedSettings = null)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, groupIdColumn, advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
// Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
_sigmoidParameter = 2.0 * Args.LearningRates;
}
/// <summary>
/// Initializes a new instance of <see cref="SymSgdClassificationTrainer"/>
/// </summary>
internal SymSgdClassificationTrainer(IHostEnvironment env, Options options)
: base(Contracts.CheckRef(env, nameof(env)).Register(LoadNameValue), TrainerUtils.MakeR4VecFeature(options.FeatureColumn),
TrainerUtils.MakeBoolScalarLabel(options.LabelColumn))
{
Host.CheckValue(options, nameof(options));
options.Check(Host);
_options = options;
Info = new TrainerInfo(supportIncrementalTrain: true);
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmBinaryClassificationTrainer"/>
/// </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">Number of iterations.</param>
internal LightGbmBinaryClassificationTrainer(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.MakeBoolScalarLabel(labelColumnName), featureColumnName, exampleWeightColumnName, null, numberOfLeaves, minimumExampleCountPerLeaf, learningRate, numberOfIterations)
{
}
/// <summary>
/// Initializes a new instance of <see cref="BinaryClassificationGamTrainer"/>
/// </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="learningRate">The learning rate.</param>
/// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public BinaryClassificationGamTrainer(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weightColumn = null,
int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
double learningRate = Defaults.LearningRates,
Action <Arguments> advancedSettings = null)
: base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, minDatapointsInLeaves, learningRate, advancedSettings)
{
_sigmoidParameter = 1;
}
/// <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;
if (ShowTrainingStats && Args.StdComputer == null)
{
Args.StdComputer = new ComputeLRTrainingStdImpl();
}
}
/// <summary>
/// Initializes a new instance of <see cref="BinaryClassificationGamTrainer"/>
/// </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="numIterations">The number of iterations to use in learning the features.</param>
/// <param name="learningRate">The learning rate. GAMs work best with a small learning rate.</param>
/// <param name="maxBins">The maximum number of bins to use to approximate features</param>
internal BinaryClassificationGamTrainer(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weightColumn = null,
int numIterations = GamDefaults.NumIterations,
double learningRate = GamDefaults.LearningRates,
int maxBins = GamDefaults.MaxBins)
: base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, numIterations, learningRate, maxBins)
{
_sigmoidParameter = 1;
}
/// <summary>
/// Initializes a new instance of <see cref="GamBinaryTrainer"/>
/// </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="rowGroupColumnName">The name for the column containing the example weight.</param>
/// <param name="numberOfIterations">The number of iterations to use in learning the features.</param>
/// <param name="learningRate">The learning rate. GAMs work best with a small learning rate.</param>
/// <param name="maximumBinCountPerFeature">The maximum number of bins to use to approximate features</param>
internal GamBinaryTrainer(IHostEnvironment env,
string labelColumnName = DefaultColumnNames.Label,
string featureColumnName = DefaultColumnNames.Features,
string rowGroupColumnName = null,
int numberOfIterations = GamDefaults.NumberOfIterations,
double learningRate = GamDefaults.LearningRate,
int maximumBinCountPerFeature = GamDefaults.MaximumBinCountPerFeature)
: base(env, LoadNameValue, TrainerUtils.MakeBoolScalarLabel(labelColumnName), featureColumnName, rowGroupColumnName, numberOfIterations, learningRate, maximumBinCountPerFeature)
{
_sigmoidParameter = 1;
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmBinaryTrainer"/>
/// </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 LightGbmBinaryTrainer(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.MakeBoolScalarLabel(labelColumn), featureColumn, weights, null, numLeaves, minDataPerLeaf, learningRate, numBoostRound)
{
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestClassification"/>
/// </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 max number of leaves in each regression tree.</param>
/// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
/// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
internal FastForestClassification(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weightColumn = null,
int numLeaves = Defaults.NumLeaves,
int numTrees = Defaults.NumTrees,
int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestBinaryTrainer"/>
/// </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 for the column containing the example weight.</param>
/// <param name="numberOfLeaves">The max number of leaves in each regression tree.</param>
/// <param name="numberOfTrees">Total number of decision trees to create in the ensemble.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
internal FastForestBinaryTrainer(IHostEnvironment env,
string labelColumnName = DefaultColumnNames.Label,
string featureColumnName = DefaultColumnNames.Features,
string exampleWeightColumnName = null,
int numberOfLeaves = Defaults.NumberOfLeaves,
int numberOfTrees = Defaults.NumberOfTrees,
int minimumExampleCountPerLeaf = Defaults.MinimumExampleCountPerLeaf)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumnName), featureColumnName, exampleWeightColumnName, null, numberOfLeaves, numberOfTrees, minimumExampleCountPerLeaf)
{
Host.CheckNonEmpty(labelColumnName, nameof(labelColumnName));
Host.CheckNonEmpty(featureColumnName, nameof(featureColumnName));
}
public AveragedPerceptronTrainer(IHostEnvironment env, Arguments args)
: base(args, env, UserNameValue, TrainerUtils.MakeBoolScalarLabel(args.LabelColumn))
{
_args = args;
LossFunction = _args.LossFunction.CreateComponent(env);
_outputColumns = new[]
{
new SchemaShape.Column(DefaultColumnNames.Score, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false, new SchemaShape(MetadataUtils.GetTrainerOutputMetadata())),
new SchemaShape.Column(DefaultColumnNames.Probability, SchemaShape.Column.VectorKind.Scalar, NumberType.R4, false, new SchemaShape(MetadataUtils.GetTrainerOutputMetadata(true))),
new SchemaShape.Column(DefaultColumnNames.PredictedLabel, SchemaShape.Column.VectorKind.Scalar, BoolType.Instance, false, new SchemaShape(MetadataUtils.GetTrainerOutputMetadata()))
};
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeBinaryTrainer"/>
/// </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 for the column containing the example weight.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="minimumExampleCountPerLeaf">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
/// <param name="numberOfLeaves">The max number of leaves in each regression tree.</param>
/// <param name="numberOfTrees">Total number of decision trees to create in the ensemble.</param>
internal FastTreeBinaryTrainer(IHostEnvironment env,
string labelColumnName = DefaultColumnNames.Label,
string featureColumnName = DefaultColumnNames.Features,
string exampleWeightColumnName = null,
int numberOfLeaves = Defaults.NumberOfLeaves,
int numberOfTrees = Defaults.NumberOfTrees,
int minimumExampleCountPerLeaf = Defaults.MinimumExampleCountPerLeaf,
double learningRate = Defaults.LearningRate)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumnName), featureColumnName, exampleWeightColumnName, null, numberOfLeaves, numberOfTrees, minimumExampleCountPerLeaf, learningRate)
{
// Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
_sigmoidParameter = 2.0 * FastTreeTrainerOptions.LearningRate;
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeBinaryClassificationTrainer"/>
/// </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="learningRate">The learning rate.</param>
/// <param name="minDatapointsInLeaves">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
/// <param name="numLeaves">The max number of leaves in each regression tree.</param>
/// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
internal FastTreeBinaryClassificationTrainer(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weightColumn = null,
int numLeaves = Defaults.NumLeaves,
int numTrees = Defaults.NumTrees,
int minDatapointsInLeaves = Defaults.MinDocumentsInLeaves,
double learningRate = Defaults.LearningRates)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDatapointsInLeaves, learningRate)
{
// Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
_sigmoidParameter = 2.0 * FastTreeTrainerOptions.LearningRates;
}
/// <summary>
/// Initializes a new instance of <see cref="FastTreeBinaryClassificationTrainer"/>
/// </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="learningRate">The learning rate.</param>
/// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
/// <param name="numLeaves">The max number of leaves in each regression tree.</param>
/// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public FastTreeBinaryClassificationTrainer(IHostEnvironment env,
string labelColumn,
string featureColumn,
string weightColumn = null,
int numLeaves = Defaults.NumLeaves,
int numTrees = Defaults.NumTrees,
int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
double learningRate = Defaults.LearningRates,
Action <Arguments> advancedSettings = null)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDocumentsInLeafs, learningRate, advancedSettings)
{
// Set the sigmoid parameter to the 2 * learning rate, for traditional FastTreeClassification loss
_sigmoidParameter = 2.0 * Args.LearningRates;
}
/// <summary>
/// Initializes a new instance of <see cref="FastForestClassification"/>
/// </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 max number of leaves in each regression tree.</param>
/// <param name="numTrees">Total number of decision trees to create in the ensemble.</param>
/// <param name="minDocumentsInLeafs">The minimal number of documents allowed in a leaf of a regression tree, out of the subsampled data.</param>
/// <param name="learningRate">The learning rate.</param>
/// <param name="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public FastForestClassification(IHostEnvironment env,
string labelColumn,
string featureColumn,
string weightColumn = null,
int numLeaves = Defaults.NumLeaves,
int numTrees = Defaults.NumTrees,
int minDocumentsInLeafs = Defaults.MinDocumentsInLeafs,
double learningRate = Defaults.LearningRates,
Action <Arguments> advancedSettings = null)
: base(env, TrainerUtils.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, numLeaves, numTrees, minDocumentsInLeafs, learningRate, advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
}
/// <summary>
/// Initializes a new instance of <see cref="SymSgdClassificationTrainer"/>
/// </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="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</param>
public SymSgdClassificationTrainer(IHostEnvironment env, string featureColumn, string labelColumn, Action <Arguments> advancedSettings = null)
: base(Contracts.CheckRef(env, nameof(env)).Register(LoadNameValue), TrainerUtils.MakeR4VecFeature(featureColumn),
TrainerUtils.MakeBoolScalarLabel(labelColumn))
{
_args = new Arguments();
// Apply the advanced args, if the user supplied any.
_args.Check(Host);
advancedSettings?.Invoke(_args);
_args.FeatureColumn = featureColumn;
_args.LabelColumn = labelColumn;
Info = new TrainerInfo();
}
/// <summary>
/// Initializes a new instance of <see cref="LogisticRegression"/>
/// </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 LogisticRegression(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.MakeBoolScalarLabel(labelColumn), weights,
l1Weight, l2Weight, optimizationTolerance, memorySize, enforceNoNegativity)
{
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
_posWeight = 0;
ShowTrainingStats = Args.ShowTrainingStats;
}
private protected CalibratorEstimatorBase(IHostEnvironment env,
ICalibratorTrainer calibratorTrainer, string labelColumn, string scoreColumn, string weightColumn)
{
Host = env;
_calibratorTrainer = calibratorTrainer;
if (!string.IsNullOrWhiteSpace(labelColumn))
{
LabelColumn = TrainerUtils.MakeBoolScalarLabel(labelColumn);
}
else
{
env.CheckParam(!calibratorTrainer.NeedsTraining, nameof(labelColumn), "For trained calibrators, " + nameof(labelColumn) + " must be specified.");
}
ScoreColumn = TrainerUtils.MakeR4ScalarColumn(scoreColumn); // Do we fanthom this being named anything else (renaming column)? Complete metadata?
if (weightColumn != null)
{
WeightColumn = TrainerUtils.MakeR4ScalarWeightColumn(weightColumn);
}
}
/// <summary>
/// Initializes a new instance of <see cref="LightGbmBinaryTrainer"/>
/// </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="advancedSettings">A delegate to apply all the advanced arguments to the algorithm.</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>
public LightGbmBinaryTrainer(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.MakeBoolScalarLabel(labelColumn), featureColumn, weightColumn, null, advancedSettings)
{
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
if (advancedSettings != null)
{
CheckArgsAndAdvancedSettingMismatch(numLeaves, minDataPerLeaf, learningRate, numBoostRound, new LightGbmArguments(), Args);
}
// override with the directly provided values
Args.NumBoostRound = numBoostRound;
Args.NumLeaves = numLeaves ?? Args.NumLeaves;
Args.LearningRate = learningRate ?? Args.LearningRate;
Args.MinDataPerLeaf = minDataPerLeaf ?? Args.MinDataPerLeaf;
}
/// <summary>
/// Initializes a new instance of <see cref="LogisticRegression"/>
/// </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"/>. 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 LogisticRegression(IHostEnvironment env,
string labelColumn = DefaultColumnNames.Label,
string featureColumn = DefaultColumnNames.Features,
string weights = 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.MakeBoolScalarLabel(labelColumn), weights, advancedSettings,
l1Weight, l2Weight, optimizationTolerance, memorySize, enforceNoNegativity)
{
Host.CheckNonEmpty(featureColumn, nameof(featureColumn));
Host.CheckNonEmpty(labelColumn, nameof(labelColumn));
_posWeight = 0;
ShowTrainingStats = Args.ShowTrainingStats;
if (ShowTrainingStats && Args.StdComputer == null)
{
Args.StdComputer = new ComputeLRTrainingStdImpl();
}
}
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="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="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))
{
}