meta/doxygen/classifier_8h_source.html

 #ifndef META_CLASSIFIER_H_

 #define META_CLASSIFIER_H_


 #include <vector>

 #include "classify/confusion_matrix.h"


 namespace meta

 {

 namespace classify

 {


 class classifier

 {

   public:

     classifier(std::shared_ptr<index::forward_index> idx);


     virtual class_label classify(doc_id d_id) = 0;


     virtual void train(const std::vector<doc_id>& docs) = 0;


     virtual confusion_matrix test(const std::vector<doc_id>& docs);


     virtual confusion_matrix

         cross_validate(const std::vector<doc_id>& input_docs, size_t k,

                        bool even_split = false, int seed = 1);


     virtual void reset() = 0;


   protected:

     std::shared_ptr<index::forward_index> idx_;


   private:

     void create_even_split(std::vector<doc_id>& docs, int seed = 2) const;

 };

 }

 }

 #endif

meta::classify::classifier::train
virtual void train(const std::vector< doc_id > &docs)=0
Creates a classification model based on training documents.

meta::classify::classifier::reset
virtual void reset()=0
Clears any learning data associated with this classifier.

meta::classify::classifier::create_even_split
void create_even_split(std::vector< doc_id > &docs, int seed=2) const
Modifies input_docs to be a vector of size <= the original vector size with an even distribution of c...
Definition: classifier.cpp:59

meta::classify::confusion_matrix
Allows interpretation of classification errors.
Definition: confusion_matrix.h:25

meta::classify::classifier::classify
virtual class_label classify(doc_id d_id)=0
Classifies a document into a specific group, as determined by training data.

meta::classify::classifier::idx_
std::shared_ptr< index::forward_index > idx_
the index that the classifer is run on
Definition: classifier.h:77

meta
The ModErn Text Analysis toolkit is a suite of natural language processing, classification, information retreival, data mining, and other applications of text processing.
Definition: analyzer.h:24

meta::classify::classifier
A classifier uses a document's feature space to identify which group it belongs to.
Definition: classifier.h:24

meta::classify::classifier::test
virtual confusion_matrix test(const std::vector< doc_id > &docs)
Classifies a collection document into specific groups, as determined by training data; this function ...
Definition: classifier.cpp:22

confusion_matrix.h

meta::classify::classifier::classifier
classifier(std::shared_ptr< index::forward_index > idx)
Definition: classifier.cpp:16

meta::classify::classifier::cross_validate
virtual confusion_matrix cross_validate(const std::vector< doc_id > &input_docs, size_t k, bool even_split=false, int seed=1)
Performs k-fold cross-validation on a set of documents.
Definition: classifier.cpp:32