Rondom Forest implementation. More...

#include <rf.hpp>

Inheritance diagram for LightGBM::RF:

Public Member Functions
void	Init (const Config config, const Dataset train_data, const ObjectiveFunction objective_function, const std::vector< const Metric > &training_metrics) override
	Initialization logic.

void	ResetConfig (const Config *config) override
	Reset Boosting Config.

void	ResetTrainingData (const Dataset train_data, const ObjectiveFunction objective_function, const std::vector< const Metric * > &training_metrics) override
	Reset the training data.

void	Boosting () override
	calculate the object function

bool	TrainOneIter (const score_t gradients, const score_t hessians) override
	Training logic.

void	RollbackOneIter () override
	Rollback one iteration.

void	MultiplyScore (const int cur_tree_id, double val)

void	AddValidDataset (const Dataset valid_data, const std::vector< const Metric > &valid_metrics) override
	Adding a validation dataset.

bool	NeedAccuratePrediction () const override
	Can use early stopping for prediction or not.

Public Member Functions inherited from LightGBM::GBDT
	GBDT ()
	Constructor.

	~GBDT ()
	Destructor.

void	MergeFrom (const Boosting *other) override
	Merge model from other boosting object. Will insert to the front of current boosting object.

void	ShuffleModels (int start_iter, int end_iter) override
	Shuffle Existing Models.

void	Train (int snapshot_freq, const std::string &model_output_path) override
	Perform a full training procedure.

void	RefitTree (const std::vector< std::vector< int > > &tree_leaf_prediction) override
	Update the tree output by new training data.

int	GetCurrentIteration () const override
	Get current iteration.

std::vector< double >	GetEvalAt (int data_idx) const override
	Get evaluation result at data_idx data.

virtual const double *	GetTrainingScore (int64_t *out_len) override
	Get current training score.

virtual int64_t	GetNumPredictAt (int data_idx) const override
	Get size of prediction at data_idx data.

void	GetPredictAt (int data_idx, double out_result, int64_t out_len) override
	Get prediction result at data_idx data.

int	NumPredictOneRow (int num_iteration, bool is_pred_leaf, bool is_pred_contrib) const override
	Get number of prediction for one data.

void	PredictRaw (const double features, double output, const PredictionEarlyStopInstance *earlyStop) const override
	Prediction for one record, not sigmoid transform.

void	PredictRawByMap (const std::unordered_map< int, double > &features, double output, const PredictionEarlyStopInstance early_stop) const override

void	Predict (const double features, double output, const PredictionEarlyStopInstance *earlyStop) const override
	Prediction for one record, sigmoid transformation will be used if needed.

void	PredictByMap (const std::unordered_map< int, double > &features, double output, const PredictionEarlyStopInstance early_stop) const override

void	PredictLeafIndex (const double features, double output) const override
	Prediction for one record with leaf index.

void	PredictLeafIndexByMap (const std::unordered_map< int, double > &features, double *output) const override

void	PredictContrib (const double features, double output, const PredictionEarlyStopInstance *earlyStop) const override
	Feature contributions for the model's prediction of one record.

std::string	DumpModel (int start_iteration, int num_iteration) const override
	Dump model to json format string.

std::string	ModelToIfElse (int num_iteration) const override
	Translate model to if-else statement.

bool	SaveModelToIfElse (int num_iteration, const char *filename) const override
	Translate model to if-else statement.

virtual bool	SaveModelToFile (int start_iteration, int num_iterations, const char *filename) const override
	Save model to file.

std::string	SaveModelToString (int num_iterations)
	Save model to string.

virtual std::string	SaveModelToString (int start_iteration, int num_iterations) const override

bool	LoadModelFromString (std::string str)
	Restore from a serialized buffer.

bool	LoadModelFromString (const char *buffer, size_t len) override

std::vector< double >	FeatureImportance (int num_iteration, int importance_type) const override
	Calculate feature importances.

int	MaxFeatureIdx () const override
	Get max feature index of this model.

std::vector< std::string >	FeatureNames () const override
	Get feature names of this model.

int	LabelIdx () const override
	Get index of label column.

int	NumberOfTotalModel () const override
	Get number of weak sub-models.

int	NumModelPerIteration () const override
	Get number of tree per iteration.

int	NumberOfClasses () const override
	Get number of classes.

void	InitPredict (int num_iteration, bool is_pred_contrib) override
	Initial work for the prediction.

double	GetLeafValue (int tree_idx, int leaf_idx) const override

void	SetLeafValue (int tree_idx, int leaf_idx, double val) override

virtual const char *	SubModelName () const override
	Get Type name of this boosting object.

Public Member Functions inherited from LightGBM::Boosting
virtual	~Boosting ()
	virtual destructor

std::string	SaveModelToString (int num_iterations)
	Save model to string.

bool	LoadModelFromString (std::string str)
	Restore from a serialized string.

Boosting &	operator= (const Boosting &)=delete
	Disable copy.

	Boosting (const Boosting &)=delete
	Disable copy.

Additional Inherited Members
Static Public Member Functions inherited from LightGBM::Boosting
static bool	LoadFileToBoosting (Boosting boosting, const char filename)

static Boosting *	CreateBoosting (const std::string &type, const char *filename)
	Create boosting object.

Protected Member Functions inherited from LightGBM::GBDT
virtual bool	EvalAndCheckEarlyStopping ()
	Print eval result and check early stopping.

void	ResetBaggingConfig (const Config *config, bool is_change_dataset)
	reset config for bagging

virtual void	Bagging (int iter)
	Implement bagging logic.

data_size_t	BaggingHelper (Random &cur_rand, data_size_t start, data_size_t cnt, data_size_t *buffer)
	Helper function for bagging, used for multi-threading optimization.

virtual void	UpdateScore (const Tree *tree, const int cur_tree_id)
	updating score after tree was trained

virtual std::vector< double >	EvalOneMetric (const Metric metric, const double score) const
	eval results for one metric

std::string	OutputMetric (int iter)
	Print metric result of current iteration.

double	BoostFromAverage (int class_id, bool update_scorer)

Protected Attributes inherited from LightGBM::GBDT
int	iter_
	current iteration

const Dataset *	train_data_
	Pointer to training data.

std::unique_ptr< Config >	config_
	Config of gbdt.

std::unique_ptr< TreeLearner >	tree_learner_
	Tree learner, will use this class to learn trees.

const ObjectiveFunction *	objective_function_
	Objective function.

std::unique_ptr< ScoreUpdater >	train_score_updater_
	Store and update training data's score.

std::vector< const Metric * >	training_metrics_
	Metrics for training data.

std::vector< std::unique_ptr< ScoreUpdater > >	valid_score_updater_
	Store and update validation data's scores.

std::vector< std::vector< const Metric * > >	valid_metrics_
	Metric for validation data.

int	early_stopping_round_
	Number of rounds for early stopping.

std::vector< std::vector< int > >	best_iter_
	Best iteration(s) for early stopping.

std::vector< std::vector< double > >	best_score_
	Best score(s) for early stopping.

std::vector< std::vector< std::string > >	best_msg_
	output message of best iteration

std::vector< std::unique_ptr< Tree > >	models_
	Trained models(trees)

int	max_feature_idx_
	Max feature index of training data.

std::vector< score_t >	gradients_
	First order derivative of training data.

std::vector< score_t >	hessians_
	Secend order derivative of training data.

std::vector< data_size_t >	bag_data_indices_
	Store the indices of in-bag data.

data_size_t	bag_data_cnt_
	Number of in-bag data.

std::vector< data_size_t >	tmp_indices_
	Store the indices of in-bag data.

data_size_t	num_data_
	Number of training data.

int	num_tree_per_iteration_
	Number of trees per iterations.

int	num_class_
	Number of class.

data_size_t	label_idx_
	Index of label column.

int	num_iteration_for_pred_
	number of used model

double	shrinkage_rate_
	Shrinkage rate for one iteration.

int	num_init_iteration_
	Number of loaded initial models.

std::vector< std::string >	feature_names_
	Feature names.

std::vector< std::string >	feature_infos_

int	num_threads_
	number of threads

std::vector< data_size_t >	offsets_buf_
	Buffer for multi-threading bagging.

std::vector< data_size_t >	left_cnts_buf_
	Buffer for multi-threading bagging.

std::vector< data_size_t >	right_cnts_buf_
	Buffer for multi-threading bagging.

std::vector< data_size_t >	left_write_pos_buf_
	Buffer for multi-threading bagging.

std::vector< data_size_t >	right_write_pos_buf_
	Buffer for multi-threading bagging.

std::unique_ptr< Dataset >	tmp_subset_

bool	is_use_subset_

std::vector< bool >	class_need_train_

bool	is_constant_hessian_

std::unique_ptr< ObjectiveFunction >	loaded_objective_

bool	average_output_

bool	need_re_bagging_

std::string	loaded_parameter_

Json	forced_splits_json_

Detailed Description

Rondom Forest implementation.

Member Function Documentation

◆ AddValidDataset()

void LightGBM::RF::AddValidDataset	(	const Dataset *	valid_data,
		const std::vector< const Metric * > &	valid_metrics
	)

inlineoverridevirtual

Adding a validation dataset.

Parameters

valid_data	Validation dataset
valid_metrics	Metrics for validation dataset

Reimplemented from LightGBM::GBDT.

◆ Boosting()

void LightGBM::RF::Boosting ( )

inlineoverridevirtual

calculate the object function

Reimplemented from LightGBM::GBDT.

◆ Init()

void LightGBM::RF::Init	(	const Config *	gbdt_config,
		const Dataset *	train_data,
		const ObjectiveFunction *	objective_function,
		const std::vector< const Metric * > &	training_metrics
	)

inlineoverridevirtual

Initialization logic.

Parameters

gbdt_config	Config for boosting
train_data	Training data
objective_function	Training objective function
training_metrics	Training metrics

Reimplemented from LightGBM::GBDT.

◆ NeedAccuratePrediction()

bool LightGBM::RF::NeedAccuratePrediction ( ) const

inlineoverridevirtual

Can use early stopping for prediction or not.

Returns: True if cannot use early stopping for prediction

Reimplemented from LightGBM::GBDT.

◆ ResetConfig()

void LightGBM::RF::ResetConfig ( const Config * gbdt_config )

inlineoverridevirtual

Reset Boosting Config.

Parameters

gbdt_config Config for boosting

Reimplemented from LightGBM::GBDT.

◆ ResetTrainingData()

void LightGBM::RF::ResetTrainingData	(	const Dataset *	train_data,
		const ObjectiveFunction *	objective_function,
		const std::vector< const Metric * > &	training_metrics
	)

inlineoverridevirtual

Reset the training data.

Parameters

train_data	New Training data
objective_function	Training objective function
training_metrics	Training metrics

Reimplemented from LightGBM::GBDT.

◆ RollbackOneIter()

void LightGBM::RF::RollbackOneIter ( )

inlineoverridevirtual

Rollback one iteration.

Reimplemented from LightGBM::GBDT.

◆ TrainOneIter()

bool LightGBM::RF::TrainOneIter	(	const score_t *	gradients,
		const score_t *	hessians
	)

inlineoverridevirtual

Training logic.

Parameters

gradients	nullptr for using default objective, otherwise use self-defined boosting
hessians	nullptr for using default objective, otherwise use self-defined boosting

Returns: True if cannot train any more

Reimplemented from LightGBM::GBDT.

The documentation for this class was generated from the following file:

External/LightGBM_2.2.3/LightGBM-2.2.3/src/boosting/rf.hpp

Public Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ AddValidDataset()

◆ Boosting()

◆ Init()

◆ NeedAccuratePrediction()

◆ ResetConfig()

◆ ResetTrainingData()

◆ RollbackOneIter()

◆ TrainOneIter()