RapidMiner 9.7 is Now Available

Lots of amazing new improvements including true version control! Learn more about what's new here.

CLICK HERE TO DOWNLOAD

"How to perform ARIMA"

ratheesanratheesan Member Posts: 68  Maven
edited May 2019 in Help
Hi all,
How to perform ARIMA modelling of time series data in RM?
Which operators are used for the same.
Thanks
Ratheesan
Tagged:

Answers

  • landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,529   Unicorn
    Hi,
    we don't have an explicit ARIMA operator in rapid miner, but I think you could get the same if you apply a MovingAverage operator at first, then window the data and apply a linear regression on the windowed data.

    You have to look in the preprocessing/series group. Take a deeper look on all operator descriptions there.

    Greetings,
      Sebastian
  • ratheesanratheesan Member Posts: 68  Maven
    Hi,
    I followed the method you mentioned above.I used WindowExamples2ModelingData operator.But i am not getting the idea about label-name-stem.
    Thanks
    Ratheesan
  • landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,529   Unicorn
    Hi,
    the label name stem is actually only the name of the label attribute before windowing. After windowing you should have something like label-0, label-1, label-2 and so on, denoting the value of the label in the indexed time points. The stem then would be "label".

    Greetings,
      Sebastian
  • ratheesanratheesan Member Posts: 68  Maven
    Hi,

    Whenever I am working with  WindowExamples2ModelingData operator I am getting "NumberFormatException caught for Input String" message. Any suggestion regarding this?

    Thanks,
    Ratheesan
  • landland RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 2,529   Unicorn
    Hi,
    here's a small example process. I hope this will guide you around the pitfalls in this area. If you add a few breakpoints, you will see, what each operator does.
    <operator name="Root" class="Process" expanded="yes">
        <operator name="ExampleSetGenerator" class="ExampleSetGenerator">
            <parameter key="target_function" value="sum"/>
            <parameter key="number_of_attributes" value="50"/>
        </operator>
        <operator name="ChangeAttributeRole" class="ChangeAttributeRole">
            <parameter key="name" value="label"/>
        </operator>
        <operator name="MultivariateSeries2WindowExamples" class="MultivariateSeries2WindowExamples">
            <parameter key="window_size" value="10"/>
        </operator>
        <operator name="WindowExamples2ModelingData" class="WindowExamples2ModelingData">
            <parameter key="label_name_stem" value="label"/>
        </operator>
        <operator name="LinearRegression" class="LinearRegression">
            <parameter key="keep_example_set" value="true"/>
        </operator>
        <operator name="ModelApplier" class="ModelApplier">
            <list key="application_parameters">
            </list>
        </operator>
        <operator name="WindowExamples2OriginalData" class="WindowExamples2OriginalData">
        </operator>
    </operator>
    Greetings,
      Sebastian
Sign In or Register to comment.