You are viewing the RapidMiner Studio documentation for version 9.5 - Check here for latest version

# Scale by Weights (RapidMiner Studio Core)

## Synopsis

This operator scales the input ExampleSet according to the given weights. This operator deselects attributes with weight 0 and calculates new values for numeric attributes according to the given weights.## Description

The Scale by Weights operator selects attributes with non zero weight. The values of the remaining numeric attributes are recalculated based on the weights delivered at the weights input port. The new values of numeric attributes are calculated by multiplying the original values by the weight of that attribute. This operator can hardly be used for selecting a subset of attributes according to weights determined by a former weighting scheme. For this purpose the Select by Weights operator should be used which selects only those attributes that fulfill a specified weight relation.

## Input

- example set (IOObject)
This input port expects an ExampleSet. It is the output of the Weight by Chi Squared Statistic operator in the attached Example Process. The output of other operators can also be used as input. It is essential that meta data should be attached with the data for the input because attributes are specified in their meta data.

- weights
This port expects the attribute weights. There are numerous operators that provide the attribute weights. The Weight by Chi Squared Statistic operator is used in the Example Process.

## Output

- example set (IOObject)
The attributes with weight 0 are removed from the input ExampleSet. The values of the remaining numeric attributes are recalculated based on the weights provided at the weights input port. The resultant ExampleSet is delivered through this port.

## Tutorial Processes

### Applying the Scale by Weights operator on the Golf data set

The 'Golf' data set is loaded using the Retrieve operator. The Weight by Chi Squared Statistic operator is applied on it to generate attribute weights. A breakpoint is inserted here. You can see the attributes with their weights here. You can see that the Wind, Humidity, Outlook and Temperature attributes have weights 0, 0.438, 0.450 and 1 respectively. The Scale by Weights operator is applied next. The 'Golf' data set is provided at the example set input port and weights calculated by the Weight by Chi Squared Statistic operator are provided at the weights input port. The Scale by Weights operator removes the attributes with weight 0 i.e. the Wind attribute is removed. The values of the remaining numeric attributes (i.e. the Temperature and Humidity attribute) are recalculated based on their weights. The weight of the Temperature attribute is 1 thus its values remain unchanged. The weight of the Humidity attribute is 0.438 thus its new values are calculated by multiplying the original values by 0.438. This can be verified by viewing the results in the Results Workspace.