RangeFeatGenerator Class Reference

RangeFeatGenerator : Generate features for a time range with value signal (for example drug) More...

#include <FeatureGenerator.h>

Inheritance diagram for RangeFeatGenerator:

Public Member Functions
void	set (string &_signalName, RangeFeatureTypes _type)
void	set (string &_signalName, RangeFeatureTypes _type, int _time_win_from, int _time_win_to)
void	set_names ()
void	get_required_signal_categories (unordered_map< string, vector< string > > &signal_categories_in_use) const
	returns for each used signal it's used categories
int	init (map< string, string > &mapper)
	The parsed fields from init command.
void	init_defaults ()
RangeFeatureTypes	name_to_type (const string &name)
	please reffer to RangeFeatureTypes to understand the options
void	init_tables (MedDictionarySections &dict)
virtual void	copy (FeatureGenerator *generator)
int	_learn (MedPidRepository &rep, const MedSamples &samples, vector< RepProcessor * > processors)
int	_generate (PidDynamicRec &rec, MedFeatures &features, int index, int num, vector< float * > &_p_data)
float	get_value (PidDynamicRec &rec, int index, int date)
void	set_signal_ids (MedSignals &sigs)
Public Member Functions inherited from FeatureGenerator
virtual void	prepare (MedFeatures &features, MedPidRepository &rep, MedSamples &samples)
virtual void	get_p_data (MedFeatures &features, vector< float * > &_p_data)
void	get_p_data (MedFeatures &features)
virtual void	clear ()
void	get_required_signal_names (unordered_set< string > &signalNames)
virtual void	set_required_signal_ids (MedDictionarySections &dict)
void	get_required_signal_ids (unordered_set< int > &signalIds)
virtual void	get_generated_features (unordered_set< string > &names_list)
virtual void	fit_for_repository (MedPidRepository &rep)
	Prepartion and adjustment for model based on repository.
int	learn (MedPidRepository &rep, const MedSamples &samples, vector< RepProcessor * > processors)
int	learn (MedPidRepository &rep, const MedSamples &samples)
int	_generate (PidDynamicRec &in_rep, MedFeatures &features, int index, int num)
int	generate (PidDynamicRec &in_rep, MedFeatures &features, int index, int num)
int	generate (PidDynamicRec &in_rep, MedFeatures &features)
int	generate (MedPidRepository &rep, int id, MedFeatures &features)
int	generate (MedPidRepository &rep, int id, MedFeatures &features, int index, int num)
virtual int	_generate (MedFeatures &features)
int	generate (MedFeatures &features)
virtual int	init (void *generator_params)
virtual int	nfeatures ()
virtual int	filter_features (unordered_set< string > &validFeatures)
	summary> prints summary of generator job.
virtual void	make_summary ()
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_generator_size ()
size_t	generator_serialize (unsigned char *blob)
virtual void	print ()
virtual void	dprint (const string &pref, int fg_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

Data Fields
string	signalName
	Signal to consider.
int	signalId
vector< string >	sets
	FTR_RANGE_EVER checks if the signal ever was in one of these sets/defs from the respective dict.
RangeFeatureTypes	type
	Type of comorbidity index to generate.
int	win_from = 0
	time window for feature: from is the minimal time before prediciton time
int	win_to = 360000
	time window for feature: to is the maximal time before prediciton time
int	time_unit_win = MedTime::Undefined
	the time unit in which the windows are given. Default: Undefined
int	time_unit_sig = MedTime::Undefined
	the time init in which the signal is given. (set correctly from Repository in learn and Generate)
int	val_channel = 0
	n >= 0 : use val channel n , default : 0.
int	check_first = 1
	if 1 choose first occurance of check_val otherwise choose last
float	div_factor = 1.0f
vector< char >	lut
	dividing by this number in time_covered option
int	recurrence_delta = 30 * 24 * 60
	maximum time for a subsequent range signal to be considered a recurrence in in window time units
int	min_range_time = -1
	if different from -1, the minimum length for a range to be considered valid in window time units (else not checked)
int	N_th = 0
	the index of the N-th range in order to consider in the last_nth_time_len option
int	zero_missing = 0
	in some cases we may want to get 0 instead of missing values
int	strict_times = 0
	if on , will ignore cases in which the second time channel is after the prediction time
int	conditional_channel = -1
	in some cases (currently last_nth_len, and time_covered) we allow doing the calculation only on ranges passing the condition of being included in sets in this channel
bool	regex_on_sets = false
	if on , regex is applied on .*sets[i].* and aggregated.
int	first_evidence_time_channel = 1
	sometimes we have a different time channel stating WHEN the range started. We are strict and use the default of last time in range, but sometimes it is not like that and this can allow calculating if we are now IN the range, and how LONG since the start.
string	timeRangeSignalName = ""
int	timeRangeSignalId
TimeRangeTypes	timeRangeType = TIME_RANGE_CURRENT
int	time_unit_range_sig = MedTime::Undefined
	the time unit in which the range signal is given. (set correctly from Repository in learn and _generate)
Data Fields inherited from FeatureGenerator
FeatureGeneratorTypes	generator_type = FTR_GEN_LAST
	Type.
vector< string >	names
	Feature name.
int	learn_nthreads = 16
int	pred_nthreads = 16
float	missing_val = (float)MED_MAT_MISSING_VALUE
	Missing value.
vector< string >	tags
	Tags - for defining labels or groups. may be used later for filtering for example.
int	iGenerateWeights = 0
	Feature/Weights generator.
vector< float * >	p_data
vector< string >	req_signals
vector< int >	req_signal_ids
int	serial_id

Additional Inherited Members
Static Public Member Functions inherited from FeatureGenerator
static FeatureGenerator *	make_generator (string name)
static FeatureGenerator *	make_generator (string name, string params)
static FeatureGenerator *	make_generator (FeatureGeneratorTypes type)
static FeatureGenerator *	make_generator (FeatureGeneratorTypes type, string params)
static FeatureGenerator *	create_generator (string &params)

Detailed Description

RangeFeatGenerator : Generate features for a time range with value signal (for example drug)

Member Function Documentation

_generate()

int RangeFeatGenerator::_generate ( PidDynamicRec &  rec, MedFeatures &  features, int  index, int  num, vector< float * > &  _p_data  )

virtual

Reimplemented from FeatureGenerator.

_learn()

int RangeFeatGenerator::_learn ( MedPidRepository &  rep, const MedSamples &  samples, vector< RepProcessor * >  processors  )

inlinevirtual

Reimplemented from FeatureGenerator.

copy()

virtual void RangeFeatGenerator::copy ( FeatureGenerator *  generator )

inlinevirtual

Reimplemented from FeatureGenerator.

get_required_signal_categories()

void RangeFeatGenerator::get_required_signal_categories ( unordered_map< string, vector< string > > &  signal_categories_in_use ) const

virtual

returns for each used signal it's used categories

Reimplemented from FeatureGenerator.

init()

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

virtual

The parsed fields from init command.

        if (field == "type") { type = name_to_type(entry.second); }
        else if (field == "win_from") win_from = med_stoi(entry.second);
        else if (field == "win_to") win_to = med_stoi(entry.second);
        else if (field == "signalName" || field == "signal") signalName = entry.second;
        else if (field == "time_unit" || field == "win_time_unit") time_unit_win = med_time_converter.string_to_type(entry.second);
        else if (field == "val_channel") val_channel = med_stoi(entry.second);
        else if (field == "sets") boost::split(sets, entry.second, boost::is_any_of(","));
        else if (field == "tags") boost::split(tags, entry.second, boost::is_any_of(","));
        else if (field == "weights_generator") iGenerateWeights = med_stoi(entry.second);
        else if (field == "check_first") check_first = med_stoi(entry.second);
        else if (field == "time_range_signal") timeRangeSignalName = entry.second;
        else if (field == "time_range_signal_type") timeRangeType = time_range_name_to_type(entry.second);
        else if (field == "recurrence_delta") recurrence_delta = med_stoi(entry.second);
        else if (field == "min_range_time") min_range_time = med_stoi(entry.second);
        else if (field == "div_factor") div_factor = med_stof(entry.second);
        else if (field == "Nth" || field == "nth") N_th = med_stoi(entry.second);
        else if (field == "zero_missing") zero_missing = med_stoi(entry.second);
        else if (field == "strict_times") strict_times = med_stoi(entry.second);
        else if (field == "conditional_channel") conditional_channel = med_stoi(entry.second);
        else if (field == "first_evidence_time_channel") first_evidence_time_channel = med_stoi(entry.second);
        else if (field == "regex_on_sets") regex_on_sets = (bool)med_stoi(entry.second);
        else if (field != "fg_type")
            MLOG("Unknown parameter \'%s\' for RangeFeatGenerator\n", field.c_str());

[RangeFeatGenerator::init]

[RangeFeatGenerator::init]

Reimplemented from FeatureGenerator.

init_defaults()

void RangeFeatGenerator::init_defaults ( )

virtual

Reimplemented from FeatureGenerator.

init_tables()

void RangeFeatGenerator::init_tables ( MedDictionarySections &  dict )

virtual

Reimplemented from FeatureGenerator.

set_names()

void RangeFeatGenerator::set_names ( )

virtual

Reimplemented from FeatureGenerator.

set_signal_ids()

void RangeFeatGenerator::set_signal_ids ( MedSignals &  sigs )

inlinevirtual

Reimplemented from FeatureGenerator.

Field Documentation

lut

vector<char> RangeFeatGenerator::lut

dividing by this number in time_covered option

to be used when generating FTR_RANGE_EVER

---

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

• Internal/MedProcessTools/MedProcessTools/FeatureGenerator.h
• Internal/MedProcessTools/MedProcessTools/FeatureGenerator.cpp