FeatureBasicOutlierCleaner Class Reference

A simple cleaner considering each value of a certain feature separatley. More...

#include <FeatureProcess.h>

Inheritance diagram for FeatureBasicOutlierCleaner:

Public Member Functions
	FeatureBasicOutlierCleaner (string &feature_name)
	FeatureBasicOutlierCleaner (string &feature_name, string init_string)
	FeatureBasicOutlierCleaner (string &feature_name, ValueCleanerParams *_params)
void	init_defaults ()
int	init (void *processor_params)
int	init (map< string, string > &mapper)
	The parsed fields from init command.
virtual void	copy (FeatureProcessor *processor)
int	Learn (MedFeatures &features, unordered_set< int > &ids)
int	iterativeLearn (MedFeatures &features, unordered_set< int > &ids)
int	quantileLearn (MedFeatures &features, unordered_set< int > &ids)
int	_apply (MedFeatures &features, unordered_set< int > &ids)
Public Member Functions inherited from FeatureProcessor
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	set_feature_name (const string &feature_name)
virtual string	get_feature_name ()
virtual void	get_feature_names (vector< string > &feature_names)
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	_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	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
Public Member Functions inherited from MedValueCleaner
int	get_quantile_min_max (vector< float > &values)
	Learning.
int	get_iterative_min_max (vector< float > &values)
int	init (void *params)
int	init (map< string, string > &mapper)
	The parsed fields from init command.
ValueCleanerType	get_cleaner_type (string name)
	Get Type.
	MedValueCleaner ()
	default ctor:

Additional Inherited Members
Static Public Member Functions inherited from FeatureProcessor
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 inherited from FeatureProcessor
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
Data Fields inherited from MedValueCleaner
ValueCleanerParams	params
	Learning parameters.
float	trimMax
	Thresholds for trimming.
float	trimMin
float	removeMax
	Thresholds for removing.
float	removeMin
float	nbrsMax
	Thresholds for neighbors.
float	nbrsMin
int	num_samples_after_cleaning

Detailed Description

A simple cleaner considering each value of a certain feature separatley.

To Use this selector specify "basic_outlier_cleaner" or basic_cleaner in the fp_type

Member Function Documentation

_apply()

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

virtual

Reimplemented from FeatureProcessor.

copy()

virtual void FeatureBasicOutlierCleaner::copy ( FeatureProcessor *  processor )

inlinevirtual

Reimplemented from FeatureProcessor.

init() [1/2]

int FeatureBasicOutlierCleaner::init ( map< string, string > &  mapper )

virtual

The parsed fields from init command.

        if (field == "type") params.type = get_cleaner_type(entry.second);
        else if (field == "take_log") params.take_log = med_stoi(entry.second);
        else if (field == "missing_value") params.missing_value = med_stof(entry.second);
        else if (field == "trimming_sd_num") params.trimming_sd_num = med_stof(entry.second);
        else if (field == "removing_sd_num") params.removing_sd_num = med_stof(entry.second);
        else if (field == "nbrs_sd_num") params.nbrs_sd_num = med_stof(entry.second);
        else if (field == "quantile") params.quantile = med_stof(entry.second);
        else if (field == "trimming_quantile_factor") params.trimming_quantile_factor = med_stof(entry.second);
        else if (field == "removing_quantile_factor") params.removing_quantile_factor = med_stof(entry.second);
        else if (field == "nbrs_quantile_factor") params.nbrs_quantile_factor = med_stof(entry.second);
        else if (field == "doTrim") params.doTrim = (med_stoi(entry.second) != 0);
        else if (field == "doRemove") params.doRemove = (med_stoi(entry.second) != 0);
        else if (field == "range_min") params.range_min = med_stof(entry.second);
        else if (field == "range_max") params.range_max = med_stof(entry.second);
        else if (field == "trim_range_min") params.trim_range_min = med_stof(entry.second);
        else if (field == "trim_range_max") params.trim_range_max = med_stof(entry.second);
        else if (field == "max_samples") params.max_samples = med_stoi(entry.second);
        else if (remove_me.find(field) == remove_me.end()) MWARN("MedValueCleaner:: Warn Unknown param \"%s\"\n", field.c_str());

[FeatureBasicOutlierCleaner::init]

[FeatureBasicOutlierCleaner::init]

Reimplemented from FeatureProcessor.

init() [2/2]

int FeatureBasicOutlierCleaner::init ( void *  processor_params )

inlinevirtual

Reimplemented from FeatureProcessor.

init_defaults()

void FeatureBasicOutlierCleaner::init_defaults ( )

inlinevirtual

Reimplemented from MedValueCleaner.

Learn()

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

virtual

Reimplemented from FeatureProcessor.

---

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

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