Vowpal Wabbit library who have been developed in Yahoo Research, It has various machine learning models specially for text. More...

#include <MedVW.h>

Inheritance diagram for MedVW:

Public Member Functions
void	init_defaults ()

int	init_from_string (string text)
	The initialization parameters - please look at vowpal wabbit documentation.

int	Learn (float x, float y, const float *w, int nsamples, int nftrs)
	Learn should be implemented for each model.

int	Predict (float x, float &preds, int nsamples, int nftrs) const
	Predict should be implemented for each model.

size_t	get_size ()
	Gets bytes sizes for serializations.

size_t	serialize (unsigned char *blob)
	Serialiazing object to blob memory. return number ob bytes wrote to memory.

size_t	deserialize (unsigned char *blob)
	Deserialiazing blob to object. returns number of bytes read.

int	write_to_file (const string &path)
	The Serialization function.

int	read_from_file (const string &path)
	The Serialization function.

Public Member Functions inherited from MedPredictor
virtual int	init (void *classifier_params)

int	init_from_string (string initialization_text)

virtual int	init (map< string, string > &mapper)
	Virtual to init object from parsed fields.

virtual int	set_params (map< string, string > &mapper)

virtual void	print (FILE *fp, const string &prefix, int level=0) const

virtual int	n_preds_per_sample () const
	Number of predictions per sample. typically 1 - but some models return several per sample (for example a probability vector)

virtual int	denormalize_model (float f_avg, float f_std, float label_avg, float label_std)

int	learn (float x, float y, int nsamples, int nftrs)
	simple no weights call

virtual int	learn (MedMat< float > &x, MedMat< float > &y, const vector< float > &wgts)
	MedMat x,y : will transpose/normalize x,y if needed by algorithm The convention is that untransposed mats are always samples x features, and transposed are features x samples.

int	learn (MedMat< float > &x, MedMat< float > &y)
	MedMat x,y : will transpose/normalize x,y if needed by algorithm The convention is that untransposed mats are always samples x features, and transposed are features x samples.

int	learn (MedMat< float > &x, vector< float > &y, const vector< float > &wgts)
	MedMat x, vector y: will transpose normalize x if needed (y assumed to be normalized)

int	learn (MedMat< float > &x, vector< float > &y)
	MedMat x, vector y: will transpose normalize x if needed (y assumed to be normalized)

int	learn (vector< float > &x, vector< float > &y, const vector< float > &wgts, int n_samples, int n_ftrs)
	vector x,y: transpose/normalizations not done.

int	learn (vector< float > &x, vector< float > &y, int n_samples, int n_ftrs)
	vector x,y: transpose/normalizations not done.

virtual int	predict (MedMat< float > &x, vector< float > &preds) const

int	predict (vector< float > &x, vector< float > &preds, int n_samples, int n_ftrs) const

int	threaded_predict (MedMat< float > &x, vector< float > &preds, int nthreads) const

int	learn (const MedFeatures &features)

int	learn (const MedFeatures &features, vector< string > &names)

virtual int	predict (MedFeatures &features) const

virtual void	calc_feature_importance (vector< float > &features_importance_scores, const string &general_params)
	Feature Importance - assume called after learn.

virtual void	calc_feature_importance (vector< float > &features_importance_scores, const string &general_params, const MedFeatures *features)

virtual void	calc_feature_contribs (MedMat< float > &x, MedMat< float > &contribs)
	Feature contributions explains the prediction on each sample (aka BUT_WHY)

virtual void	calc_feature_contribs_conditional (MedMat< float > &mat_x_in, unordered_map< string, float > &contiditional_variables, MedMat< float > &mat_x_out, MedMat< float > &mat_contribs)

virtual void	export_predictor (const string &output_fname)

int	learn_prob_calibration (MedMat< float > &x, vector< float > &y, vector< float > &min_range, vector< float > &max_range, vector< float > &map_prob, int min_bucket_size=10000, float min_score_jump=0.001, float min_prob_jump=0.005, bool fix_prob_order=false)
	calibration for probability using training data

int	convert_scores_to_prob (const vector< float > &preds, const vector< float > &min_range, const vector< float > &max_range, const vector< float > &map_prob, vector< float > &probs) const
	If you have ran learn_prob_calibration before, you have min_range,max_range,map_prob from This function - that is used to convert preds to probs.

int	learn_prob_calibration (MedMat< float > &x, vector< float > &y, int poly_rank, vector< double > &params, int min_bucket_size=10000, float min_score_jump=0.001)
	Will create probability bins using Platt scale method.

template<class T , class L >
int	convert_scores_to_prob (const vector< T > &preds, const vector< double > &params, vector< L > &converted) const
	Converts probability from Platt scale model.

virtual bool	predict_single_not_implemented ()
	Prepartion function for fast prediction on single item each time.

virtual void	prepare_predict_single ()

virtual void	predict_single (const vector< float > &x, vector< float > &preds) const

virtual void	predict_single (const vector< double > &x, vector< double > &preds) const

virtual void	calc_feature_importance_shap (vector< float > &features_importance_scores, string &importance_type, const MedFeatures *features)

void *	new_polymorphic (string derived_class_name)
	for polymorphic classes that want to be able to serialize/deserialize a pointer * to the derived class given its type one needs to implement this function to return a new to the derived class given its type (as in my_type)

size_t	get_predictor_size ()

size_t	predictor_serialize (unsigned char *blob)

Public Member Functions inherited from SerializableObject
virtual int	version () const
	Relevant for serializations.

virtual string	my_class_name () const
	For better handling of serializations it is highly recommended that each SerializableObject inheriting class will implement the next method.

virtual void	serialized_fields_name (vector< string > &field_names) const
	The names of the serialized fields.

virtual void	pre_serialization ()

virtual void	post_deserialization ()

size_t	serialize_vec (vector< unsigned char > &blob)

size_t	deserialize_vec (vector< unsigned char > &blob)

virtual size_t	serialize (vector< unsigned char > &blob)

virtual size_t	deserialize (vector< unsigned char > &blob)

virtual int	read_from_file_unsafe (const string &fname)
	read and deserialize model without checking version number - unsafe read

int	init_from_string (string init_string)
	Init from string.

int	init_params_from_file (string init_file)

int	init_param_from_file (string file_str, string &param)

int	update_from_string (const string &init_string)

virtual int	update (map< string, string > &map)
	Virtual to update object from parsed fields.

virtual string	object_json () const

Additional Inherited Members
Static Public Member Functions inherited from MedPredictor
static MedPredictor *	make_predictor (string model_type)

static MedPredictor *	make_predictor (MedPredictorTypes model_type)

static MedPredictor *	make_predictor (string model_type, string params)

static MedPredictor *	make_predictor (MedPredictorTypes model_type, string params)

Data Fields inherited from MedPredictor
MedPredictorTypes	classifier_type
	The Predicotr enum type.

bool	transpose_for_learn
	True if need to transpose before learn.

bool	normalize_for_learn
	True if need to normalize before learn.

bool	normalize_y_for_learn
	True if need to normalize labels before learn.

bool	transpose_for_predict
	True if need to transpose before predict.

bool	normalize_for_predict
	True if need to normalize before predict.

vector< string >	model_features
	The model features used in Learn, to validate when caling predict.

int	features_count = 0
	The model features count used in Learn, to validate when caling predict.

Protected Member Functions inherited from MedPredictor
void	prepare_x_mat (MedMat< float > &x, const vector< float > &wgts, int &nsamples, int &nftrs, bool transpose_needed) const

void	predict_thread (void *p) const

Detailed Description

Vowpal Wabbit library who have been developed in Yahoo Research, It has various machine learning models specially for text.

It may be initialize by string

Member Function Documentation

◆ deserialize()

size_t MedVW::deserialize ( unsigned char * blob )

virtual

Deserialiazing blob to object. returns number of bytes read.

Reimplemented from SerializableObject.

◆ get_size()

size_t MedVW::get_size ( )

virtual

Gets bytes sizes for serializations.

Reimplemented from SerializableObject.

◆ init_defaults()

void MedVW::init_defaults ( )

virtual

Reimplemented from MedPredictor.

◆ Learn()

int MedVW::Learn	(	float *	x,
		float *	y,
		const float *	w,
		int	n_samples,
		int	n_ftrs
	)

virtual

Learn should be implemented for each model.

This API always assumes the data is already normalized/transposed as needed, and never changes data in x,y,w. method should support calling with w=NULL.

Reimplemented from MedPredictor.

◆ Predict()

int MedVW::Predict	(	float *	x,
		float *&	preds,
		int	n_samples,
		int	n_ftrs
	)		const

virtual

Predict should be implemented for each model.

This API assumes x is normalized/transposed if needed. preds should either be pre-allocated or NULL - in which case the predictor should allocate it to the right size.

Reimplemented from MedPredictor.

◆ read_from_file()

int MedVW::read_from_file ( const string & path )

virtual

The Serialization function.

Reimplemented from SerializableObject.

◆ serialize()

size_t MedVW::serialize ( unsigned char * blob )

virtual

Serialiazing object to blob memory. return number ob bytes wrote to memory.

Reimplemented from SerializableObject.

◆ write_to_file()

int MedVW::write_to_file ( const string & path )

virtual

The Serialization function.

Reimplemented from SerializableObject.

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

Internal/MedAlgo/MedAlgo/MedVW.h
Internal/MedAlgo/MedAlgo/MedVW.cpp

Public Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ deserialize()

◆ get_size()

◆ init_defaults()

◆ Learn()

◆ Predict()

◆ read_from_file()

◆ serialize()

◆ write_to_file()