IterativeImputer Class Reference

IterativeImputer

A general strong imputer that does the following:
(1) Runs a simple stratified imputer
(2) Runs iterations completing values (from the least missing to the max missing) where:
(a) continuous values are calculated using a regressor
(b) categorial values (less than some bound) are calculated using a multi category classifier
(3) Repeats the process several times until it converges or until max_iters is reached. More...

#include <IterativeImputer.h>

Inheritance diagram for IterativeImputer:

Public Member Functions
int	init (map< string, string > &mapper)
	The parsed fields from init command.
int	init_internals (MedFeatures &mfd)
int	init_feature_info (MedFeatures &mfd, string feat_name)
int	init_feature_info_update (MedFeatures &mfd, feature_info &fi)
int	round_to_resolution (MedFeatures &mfd)
int	round_arr (float *arr, int len, float resolution, float _min, float _max)
int	learn_first_round (MedFeatures &mfd)
int	learn_iteration (MedFeatures &mfd, int iter)
int	apply_first_round (MedFeatures &mfd, bool learning)
int	apply_iteration (MedFeatures &mfd, int iter)
int	find_feats_to_learn_from (int f_idx)
int	feats_for_pred_inds_to_names (feature_info &fi)
int	Learn (MedFeatures &mfd)
int	Apply (MedFeatures &mfd, bool learning)
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 *	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)
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
IterativeImputerParams	params
vector< int >	train_idx
vector< int >	test_idx
vector< char >	is_train
MedFeatures	learn_features_map
unordered_set< int >	train_ids
unordered_set< int >	test_ids
vector< feature_info >	feats
vector< FeatureImputer >	first_round_imputers
vector< int >	predictors_order
vector< vector< MedPredictor * > >	predictors

Detailed Description

IterativeImputer

A general strong imputer that does the following:
(1) Runs a simple stratified imputer
(2) Runs iterations completing values (from the least missing to the max missing) where:
(a) continuous values are calculated using a regressor
(b) categorial values (less than some bound) are calculated using a multi category classifier
(3) Repeats the process several times until it converges or until max_iters is reached.

Member Function Documentation

init()

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

inlinevirtual

The parsed fields from init command.

        if (field == "regressor") regressor = entry.second;
        else if (field == "regressor_params") regressor_params = entry.second;
        else if (field == "multi_categ_classifier") multi_categ_classifier = entry.second;
        else if (field == "multi_categ_classifier_params") multi_categ_classifier_params = entry.second;
        else if (field == "add_ncateg_var_name") add_ncateg_var_name = entry.second;
        else if (field == "round1_strata") round1_strata = entry.second;
        else if (field == "do_round1") do_round1 = stoi(entry.second);
        else if (field == "round1_moment") round1_moment = stoi(entry.second);
        else if (field == "categorial_bound") categorial_bound = stoi(entry.second);
        else if (field == "max_iterations") max_iterations = stoi(entry.second);
        else if (field == "p_validation") p_validation = stof(entry.second);
        else if (field == "min_vals_for_training") min_vals_for_training = stoi(entry.second);
        else if (field == "missing_value") missing_value = stof(entry.second);
        else if (field == "missing_bound") missing_bound = stof(entry.second);
        else if (field == "round_to_resolution") round_to_resolution = stoi(entry.second);
        else if (field == "verbose") verbose = stoi(entry.second);
        else if (field == "features" || field == "names") {
            vector<string> f;
            boost::split(f, entry.second, boost::is_any_of(",:"));
            features_to_impute.insert(features_to_impute.end(), f.begin(), f.end());
        }

Reimplemented from SerializableObject.

init_feature_info()

int IterativeImputer::init_feature_info	(	MedFeatures &	mfd,
		string	feat_name
	)

if (fi.n_missing > 0 && fi.n_with_values > 0)

---

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

• Internal/MedProcessTools/MedProcessTools/IterativeImputer.h
• Internal/MedProcessTools/MedProcessTools/IterativeImputer.cpp