meta::classify::linear_model< FeatureId, FeatureValue, ClassId > Class Template Reference

A storage class for multiclass linear classifier models. More...

#include <linear_model.h>

Public Types
using	feature_id = FeatureId
	The identifier for features.
using	feature_value = FeatureValue
	The value type for features. More...
using	class_id = ClassId
	The ids for the classes.
using	weight_vector = util::sparse_vector< class_id, feature_value >
	A single weight vector for a specific feature id. More...
using	weight_vectors = std::unordered_map< feature_id, weight_vector >
	A collection of weight_vector by feature id.
using	scored_class = std::pair< class_id, feature_value >
	A class_id with an associated score.
using	scored_classes = std::vector< scored_class >
	A vector of class ids and associated scores.
using	exception = linear_model_exception
	The exception thrown during interactions with linear_models.

Public Member Functions
void	load (std::istream &is)
	Loads a linear model from a stream. More...
void	save (std::ostream &os) const
	Writes a linear model to a stream. More...
template<class FeatureVector , class Filter >
class_id	best_class (FeatureVector &&features, Filter &&filter) const
	Determines the highest scoring class that satisfies a filter predicate for a given feature vector. More...
template<class FeatureVector >
class_id	best_class (FeatureVector &&features) const
	Determines the highest scoring class for a given feature vector. More...
template<class FeatureVector , class Filter >
scored_classes	best_classes (FeatureVector &&features, size_t num, Filter &&filter) const
	Determines the top \(k\) classes for a given feature vector that satisfy the filter predicate. More...
template<class FeatureVector >
scored_classes	best_classes (FeatureVector &&features, size_t num) const
	Determines the top \(k\) classes for a given feature vector. More...
void	update (const weight_vectors &updates, feature_value scale=1)
	Updates all of the weights of this model by adding in the contribution from another set of weight vectors, multiplied by a scalar value (default 1). More...
void	update (const class_id &cid, const feature_id &fid, feature_value delta)
	Updates a single weight in the model. More...
void	condense (bool log=false)
	Removes all weights that have value 0. More...
const weight_vectors &	weights () const
template<class FeatureVector , class Filter >
auto	best_class (FeatureVector &&features, Filter &&filter) const -> class_id
template<class FeatureVector >
auto	best_class (FeatureVector &&features) const -> class_id
template<class FeatureVector , class Filter >
auto	best_classes (FeatureVector &&features, size_t num, Filter &&filter) const -> scored_classes
template<class FeatureVector >
auto	best_classes (FeatureVector &&features, size_t num) const -> scored_classes

Private Attributes
weight_vectors	weights_
	The weights for the model.

Detailed Description

template<class FeatureId, class FeatureValue, class ClassId>
class meta::classify::linear_model< FeatureId, FeatureValue, ClassId >

A storage class for multiclass linear classifier models.

This class should be used to store classifiers that fit in memory.

Member Typedef Documentation

template<class FeatureId, class FeatureValue, class ClassId>

using meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::feature_value = FeatureValue

The value type for features.

Typically this is a double or a float, but it could in principle be any numeric type.

template<class FeatureId, class FeatureValue, class ClassId>

using meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::weight_vector = util::sparse_vector<class_id, feature_value>

A single weight vector for a specific feature id.

This stores the weights that a given feature has for each class.

Member Function Documentation

template<class FeatureId , class FeatureValue , class ClassId >

void meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::load

(

std::istream &

is

)

Loads a linear model from a stream.

If the stream is from a file, we are assuming that it has been opened in binary mode.

Parameters

is	The stream to read from

template<class FeatureId , class FeatureValue , class ClassId >

void meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::save

(

std::ostream &

os

)

const

Writes a linear model to a stream.

If the stream is from a file,w e are assuming it has been opened in binary mode.

Parameters

os	The stream to write to

template<class FeatureId, class FeatureValue, class ClassId>

template<class FeatureVector , class Filter >

class_id meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::best_class	(	FeatureVector &&	features,
		Filter &&	filter
	)		const

Determines the highest scoring class that satisfies a filter predicate for a given feature vector.

Any class id that does not return true when passed to the filter will not be considered. If no classes satisfy the filter predicate, the default class id will be returned.

Parameters

features	The feature vector to score
filter	The filter predicate to use

Returns

the highest scoring class that passes the filter predicate

template<class FeatureId, class FeatureValue, class ClassId>

template<class FeatureVector >

class_id meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::best_class

(

FeatureVector &&

features

)

const

Determines the highest scoring class for a given feature vector.

Parameters

features

The feature vector to score

Returns

the highest scoring class

template<class FeatureId, class FeatureValue, class ClassId>

template<class FeatureVector , class Filter >

scored_classes meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::best_classes	(	FeatureVector &&	features,
		size_t	num,
		Filter &&	filter
	)		const

Determines the top \(k\) classes for a given feature vector that satisfy the filter predicate.

Any class id that does not return true when passed to the filter will not be considered. If no classes satisfy the filter predicate, the returned vector will be empty.

Parameters

features	The feature vector to score
num	The number of classes to return ( \(k\))
filter	The filter predicate

Returns

a vector of (up to) \(k\) scored classes sorted by score

template<class FeatureId, class FeatureValue, class ClassId>

template<class FeatureVector >

scored_classes meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::best_classes	(	FeatureVector &&	features,
		size_t	num
	)		const

Determines the top \(k\) classes for a given feature vector.

Parameters

features	The feature vector to score
num	The number of classes to return ( \(k\))

Returns

a vector of (up to) \(k\) scored classes sorted by score

template<class FeatureId , class FeatureValue , class ClassId >

void meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::update	(	const weight_vectors &	updates,
		feature_value	scale = 1
	)

Updates all of the weights of this model by adding in the contribution from another set of weight vectors, multiplied by a scalar value (default 1).

Parameters

updates	The weight vector containing the updates
scale	The scalar to multiply everything in the update by before adding it to the model

template<class FeatureId , class FeatureValue , class ClassId >

void meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::update	(	const class_id &	cid,
		const feature_id &	fid,
		feature_value	delta
	)

Updates a single weight in the model.

Parameters

cid	The class
fid	The feature
delta	The amount to be added to that weight

template<class FeatureId , class FeatureValue , class ClassId >

void meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::condense

(

bool

log = false

)

Removes all weights that have value 0.

Parameters

log	Whether or not to log statistics about the condensed weight vector (info level)

template<class FeatureId , class FeatureValue , class ClassId >

auto meta::classify::linear_model< FeatureId, FeatureValue, ClassId >::weights

(

)

const

Returns

the weights

---

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

• /home/chase/projects/meta/include/classify/models/linear_model.h
• /home/chase/projects/meta/include/classify/models/linear_model.tcc