SHOGUN  v1.1.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines
Public Member Functions
CMeanSquaredError Class Reference

Detailed Description

Class MeanSquaredError used to compute an error of regression model.

Formally, for real labels $ L,R, |L|=|R|$ mean squared error (MSE) is estimated as

\[ \frac{1}{|L|} \sum_{i=1}^{|L|} (L_i - R_i)^2 \]

Definition at line 33 of file MeanSquaredError.h.

Inheritance diagram for CMeanSquaredError:
Inheritance graph
[legend]

List of all members.

Public Member Functions

 CMeanSquaredError ()
virtual ~CMeanSquaredError ()
virtual float64_t evaluate (CLabels *predicted, CLabels *ground_truth)
EEvaluationDirection get_evaluation_direction ()
virtual const char * get_name () const

Constructor & Destructor Documentation

constructor

Definition at line 37 of file MeanSquaredError.h.

virtual ~CMeanSquaredError ( ) [virtual]

destructor

Definition at line 40 of file MeanSquaredError.h.


Member Function Documentation

float64_t evaluate ( CLabels predicted,
CLabels ground_truth 
) [virtual]

evaluate mean squared error

Parameters:
predictedlabels for evaluating
ground_truthlabels assumed to be correct
Returns:
mean squared error

Implements CEvaluation.

Definition at line 17 of file MeanSquaredError.cpp.

Returns:
whether criterium has to be maximized or minimized

Implements CEvaluation.

Definition at line 49 of file MeanSquaredError.h.

virtual const char* get_name ( ) const [virtual]

get name

Implements CSGObject.

Definition at line 55 of file MeanSquaredError.h.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines

SHOGUN Machine Learning Toolbox - Documentation