puts values in each feature selected randomly from it's distribution More...

#include <SamplesGenerator.h>

Inheritance diagram for UnivariateSamplesGenerator< T >:

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

void	learn (const map< string, vector< T > > &data, const vector< string > &learn_features, bool skip_missing)
	learn of sample generator

void	get_samples (map< string, vector< T > > &data, void *params, const vector< bool > &mask, const vector< T > &mask_values)
	apply of sample generator - deafult arguments with mask, and mask values to generate values in mask, where mask[i]==false.

void	get_samples (MedMat< T > &data, int sample_per_row, void *params, const vector< vector< bool > > &mask, const MedMat< T > &mask_values)
	vector api from generating samples

void	get_samples (map< string, vector< T > > &data, void *params, const vector< bool > &mask, const vector< T > &mask_values, mt19937 &rnd_gen) const
	apply of sample generator - deafult arguments with mask, and mask values to generate values in mask, where mask[i]==false.

void	get_samples (MedMat< T > &data, int sample_per_row, void *params, const vector< vector< bool > > &mask, const MedMat< T > &mask_values, mt19937 &rnd_gen) const
	vector api from generating samples

void	pre_serialization ()

void	post_deserialization ()

T	find_pos (const vector< T > &v, const vector< double > &cumsum, double p) const

Public Member Functions inherited from SamplesGenerator< T >
virtual void	prepare (void *params)
	prepare to generate

void	learn (const map< string, vector< T > > &data)
	learn of sample generator

void *	new_polymorphic (string derived_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)

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 size_t	get_size ()
	Gets bytes sizes for serializations.

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

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

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 (const string &fname)
	read and deserialize model

virtual int	write_to_file (const string &fname)
	serialize model and write to file

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

Data Fields
T	missing_value = MED_MAT_MISSING_VALUE

int	min_samples
	minimal count of samples in strata size to use strata

featureSetStrata	strata_settings
	strata settings

ADD_SERIALIZATION_FUNCS(feature_values, feature_val_probs, strata_feature_val_agg_prob, names, missing_value, strata_settings, strata_sizes, min_samples, strata_feature_val_agg_val) private vector< vector< double > >	feature_val_probs
	< first index is feature name, second is order index

vector< vector< vector< T > > >	strata_feature_val_agg_val
	indexed by strata, feature_name, index of sorted value

vector< vector< vector< double > > >	strata_feature_val_agg_prob
	indexed by strata, feature_name, index of sorted value

vector< int >	strata_sizes
	the strata size

vector< string >	names
	names for all features

Data Fields inherited from SamplesGenerator< T >
bool	use_vector_api = true
	In gibbs it's faster to use map<string, float> api.

Additional Inherited Members
Protected Member Functions inherited from SamplesGenerator< T >
	SamplesGenerator (bool _use_vector_api)

Detailed Description

template<typename T>
class UnivariateSamplesGenerator< T >

puts values in each feature selected randomly from it's distribution

Member Function Documentation

◆ get_samples() [1/4]

template<typename T >

void UnivariateSamplesGenerator< T >::get_samples	(	map< string, vector< T > > &	data,
		void *	params,
		const vector< bool > &	mask,
		const vector< T > &	mask_values
	)

virtual

apply of sample generator - deafult arguments with mask, and mask values to generate values in mask, where mask[i]==false.

when mask[i]==true fix values from mask_values

Reimplemented from SamplesGenerator< T >.

◆ get_samples() [2/4]

template<typename T >

void UnivariateSamplesGenerator< T >::get_samples	(	map< string, vector< T > > &	data,
		void *	params,
		const vector< bool > &	mask,
		const vector< T > &	mask_values,
		mt19937 &	rnd_gen
	)		const

virtual

apply of sample generator - deafult arguments with mask, and mask values to generate values in mask, where mask[i]==false.

when mask[i]==true fix values from mask_values

Reimplemented from SamplesGenerator< T >.

◆ get_samples() [3/4]

template<typename T >

void UnivariateSamplesGenerator< T >::get_samples	(	MedMat< T > &	data,
		int	sample_per_row,
		void *	params,
		const vector< vector< bool > > &	mask,
		const MedMat< T > &	mask_values
	)

virtual

vector api from generating samples

Reimplemented from SamplesGenerator< T >.

◆ get_samples() [4/4]

template<typename T >

void UnivariateSamplesGenerator< T >::get_samples	(	MedMat< T > &	data,
		int	sample_per_row,
		void *	params,
		const vector< vector< bool > > &	mask,
		const MedMat< T > &	mask_values,
		mt19937 &	rnd_gen
	)		const

virtual

vector api from generating samples

Reimplemented from SamplesGenerator< T >.

◆ init()

template<typename T >

int UnivariateSamplesGenerator< T >::init ( map< string, string > & map )

virtual

Virtual to init object from parsed fields.

Reimplemented from SerializableObject.

◆ learn()

template<typename T >

void UnivariateSamplesGenerator< T >::learn	(	const map< string, vector< T > > &	data,
		const vector< string > &	learn_features,
		bool	skip_missing
	)

virtual

learn of sample generator

Reimplemented from SamplesGenerator< T >.

◆ post_deserialization()

template<typename T >

void UnivariateSamplesGenerator< T >::post_deserialization ( )

virtual

Reimplemented from SamplesGenerator< T >.

◆ pre_serialization()

template<typename T >

void UnivariateSamplesGenerator< T >::pre_serialization ( )

virtual

Reimplemented from SamplesGenerator< T >.

Field Documentation

◆ feature_val_probs

template<typename T >

ADD_SERIALIZATION_FUNCS (feature_values, feature_val_probs, strata_feature_val_agg_prob, names, missing_value, strata_settings, strata_sizes, min_samples, strata_feature_val_agg_val) private vector<vector<double> > UnivariateSamplesGenerator< T >::feature_val_probs

< first index is feature name, second is order index

feature name to map of value and prob - first index is feature name, second is order index

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

Internal/MedAlgo/MedAlgo/SamplesGenerator.h
Internal/MedAlgo/MedAlgo/SamplesGenerator.cpp

Public Member Functions

Data Fields

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ get_samples() [1/4]

◆ get_samples() [2/4]

◆ get_samples() [3/4]

◆ get_samples() [4/4]

◆ init()

◆ learn()

◆ post_deserialization()

◆ pre_serialization()

Field Documentation

◆ feature_val_probs