FeatureProcessor Class Reference

Inheritance diagram for FeatureProcessor:

Public Member Functions
virtual string	select_learn_matrix (const vector< string > &matrix_tags) const
	Will be called before learn to create new version for the matrix if needed - in parallel of existing matrix.
virtual void	clear ()
void	init_defaults ()
virtual void	copy (FeatureProcessor *processor)
virtual void	set_feature_name (const string &feature_name)
virtual string	get_feature_name ()
virtual void	get_feature_names (vector< string > &feature_names)
virtual int	Learn (MedFeatures &features, unordered_set< int > &ids)
int	learn (MedFeatures &features)
	PostProcess of MedFeatures - on all ids.
int	learn (MedFeatures &features, unordered_set< int > &ids)
virtual int	_apply (MedFeatures &features, unordered_set< int > &ids, bool learning)
virtual int	_apply (MedFeatures &features, unordered_set< int > &ids)
virtual int	_conditional_apply (MedFeatures &features, unordered_set< int > &ids, unordered_set< string > &req_features, bool learning)
int	apply (MedFeatures &features, bool learning)
	PostProcess of MedFeatures - on all or a subset of the ids calls virtaul function "_apply/_conditional_apply" for the specific implementation.
int	apply (MedFeatures &features, unordered_set< string > &req_features, bool learning)
int	apply (MedFeatures &features, unordered_set< int > &ids, bool learning)
int	apply (MedFeatures &features, unordered_set< int > &ids, unordered_set< string > &req_features, bool learning)
int	apply (MedFeatures &features)
int	apply (MedFeatures &features, unordered_set< string > &req_features)
int	apply (MedFeatures &features, unordered_set< int > &ids)
int	apply (MedFeatures &features, unordered_set< int > &ids, unordered_set< string > &req_features)
virtual int	init (void *processor_params)
virtual int	init (map< string, string > &mapper)
	Virtual to init object from parsed fields.
virtual int	filter (unordered_set< string > &features)
	Filter according to a subset of features.
string	resolve_feature_name (MedFeatures &features, string substr)
	Utility : get corresponding name in MedFeatures.
virtual bool	are_features_affected (unordered_set< string > &out_req_features)
	check if a set of features is affected by the current processor
virtual void	update_req_features_vec (unordered_set< string > &out_req_features, unordered_set< string > &in_req_features)
	update sets of required as input according to set required as output to processor Empty sets = require everything.
virtual bool	is_selector ()
	allows testing if this feature processor is a selector
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_processor_size ()
size_t	processor_serialize (unsigned char *blob)
virtual void	dprint (const string &pref, int rp_flag)
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 ()
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

Static Public Member Functions
static FeatureProcessor *	make_processor (string processor_name)
static FeatureProcessor *	make_processor (FeatureProcessorTypes type)
static FeatureProcessor *	make_processor (string processor_name, string params)
static FeatureProcessor *	make_processor (FeatureProcessorTypes type, string params)

Data Fields
string	feature_name = "unset_feature_name"
	Feature name ( + name as appears in MedFeatures) ;.
string	resolved_feature_name
FeatureProcessorTypes	processor_type = FTR_PROCESS_LAST
int	learn_nthreads
int	clean_nthreads

Member Function Documentation

_apply() [1/2]

int FeatureProcessor::_apply ( MedFeatures &  features, unordered_set< int > &  ids  )

virtual

Reimplemented in FeatureSelector.

_apply() [2/2]

virtual int FeatureProcessor::_apply ( MedFeatures &  features, unordered_set< int > &  ids, bool  learning  )

inlinevirtual

Reimplemented in FeatureIterativeImputer.

apply()

int FeatureProcessor::apply	(	MedFeatures &	features,
		bool	learning
	)

PostProcess of MedFeatures - on all or a subset of the ids calls virtaul function "_apply/_conditional_apply" for the specific implementation.

Returns

0 if succesfull, otherwise errorcode -1

are_features_affected()

virtual bool FeatureProcessor::are_features_affected ( unordered_set< string > &  out_req_features )

inlinevirtual

check if a set of features is affected by the current processor

Reimplemented in DoCalcFeatProcessor, MultiFeatureProcessor, FeatureSelector, FeatureEncoder, OneHotFeatProcessor, and FeatureIterativeImputer.

filter()

virtual int FeatureProcessor::filter ( unordered_set< string > &  features )

inlinevirtual

Filter according to a subset of features.

Reimplemented in MultiFeatureProcessor.

init()

virtual int FeatureProcessor::init ( map< string, string > &  map )

inlinevirtual

Virtual to init object from parsed fields.

Reimplemented from SerializableObject.

Reimplemented in DoCalcFeatProcessor, DuplicateProcessor, MultiFeatureProcessor, FeatureBasicOutlierCleaner, FeatureNormalizer, FeatureImputer, LassoSelector, DgnrtFeatureRemvoer, UnivariateFeatureSelector, MRMRFeatureSelector, TagFeatureSelector, ImportanceFeatureSelector, IterativeFeatureSelector, FeaturePCA, OneHotFeatProcessor, GetProbFeatProcessor, MultiplierProcessor, MissingIndicatorProcessor, BinningFeatProcessor, FeatureIterativeImputer, PredictorImputer, and ResampleMissingProcessor.

is_selector()

virtual bool FeatureProcessor::is_selector ( )

inlinevirtual

allows testing if this feature processor is a selector

Reimplemented in FeatureSelector.

learn()

int FeatureProcessor::learn

(

MedFeatures &

features

)

PostProcess of MedFeatures - on all ids.

stores information to post process new features. calls virtual function "Learn" for the specific implementation

Returns

0 if succesfull, otherwise errorcode -1

Learn()

virtual int FeatureProcessor::Learn ( MedFeatures &  features, unordered_set< int > &  ids  )

inlinevirtual

Reimplemented in FeatureSelector, and FeatureIterativeImputer.

new_polymorphic()

void * FeatureProcessor::new_polymorphic ( string  derived_name )

virtual

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)

Reimplemented from SerializableObject.

select_learn_matrix()

virtual string FeatureProcessor::select_learn_matrix ( const vector< string > &  matrix_tags ) const

inlinevirtual

Will be called before learn to create new version for the matrix if needed - in parallel of existing matrix.

Reimplemented in MultiFeatureProcessor, FeatureNormalizer, and ResampleMissingProcessor.

update_req_features_vec()

virtual void FeatureProcessor::update_req_features_vec ( unordered_set< string > &  out_req_features, unordered_set< string > &  in_req_features  )

inlinevirtual

update sets of required as input according to set required as output to processor Empty sets = require everything.

Default behaviour of simple processor - leave set as is

Reimplemented in DoCalcFeatProcessor, MultiFeatureProcessor, FeatureImputer, FeatureSelector, FeatureEncoder, OneHotFeatProcessor, MissingIndicatorProcessor, and FeatureIterativeImputer.

---

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

• Internal/MedProcessTools/MedProcessTools/FeatureProcess.h
• Internal/MedProcessTools/MedProcessTools/FeatureProcess.cpp