#### Versions

You are viewing the RapidMiner Studio documentation for version 8.2 - Check here for latest version

# Combine Performances (RapidMiner Studio Core)

## Synopsis

This operator takes a performance vector as input and returns a performance vector containing the weighted fitness value of the specified criteria.

## Description

This Combine Performances operator takes a performance vector as input and returns a performance vector containing the weighted fitness value of the specified criteria. The user can specify the weights of different criteria. This operator takes the weighted average of the values of the specified criteria. It should be noted that some criteria values are considered positive by this operator e.g. accuracy. On the other hand some criteria values (usually error related) are considered negative by this operator e.g. relative error. Please study the attached Example Process for better understanding of this operator.

## Input

• performance (Performance Vector)

This port expects a performance vector. A performance vector is a list of performance criteria values.

## Output

• performance (Performance Vector)

The performance vector containing the weighted fitness value of the specified criteria is returned through this port.

## Parameters

• default_weightThis parameter specifies the default weight for all criteria that are not assigned a weight through the criteria weights parameter. Range: real
• criteria_weightsDifferent performance criteria can be assigned different weights through this parameter. The criteria that are not assigned a weight through this parameter will have the default weight (i.e. specified by the default weight parameter). Range: list

## Tutorial Processes

### Introduction to the Combine Performances operator

This Example Process starts with the Subprocess operator. The subprocess is used for generating a sample performance vector. Therefore it is not necessary to understand the operators in the subprocess. A breakpoint is inserted after the Subprocess operator so that you can have a look at the performance vector. The performance vector has the following criteria values:

Accuracy: 0.250 Absolute error: 0.750 Root mean squared error: 0.866 It is important to note that the accuracy is considered positive and the remaining two criteria are considered negative in the calculations by the Combine Performances operator.

The Combine Performances operator is applied on this performance vector. Have a look at the criteria weights parameter of the Combine Performances operator. The following weights are assigned to criteria: Accuracy: 2.0 Absolute error: 1.0 Root mean squared error: 0.0 The weighted fitness value is calculated by multiplying the weight with the corresponding value and finally averaging the results. In this case the following calculation is performed: (2(0.250) + 1(-0.750) + 0(0.866)) / 3 = (0.500 - 0.750 + 0.000) / 3 = -0.083 