No "prediction" attribute?

srt19170

I'm probably missing something obvious, but I hope you'll help out anyway!

I have a RM process that reads a model (neural net), applies it to some test data, and then writes the results to an Excel file. When I examine the Excel file all has worked fine, and the last column is labeled "prediction(mov)" and contains the predicted result.

However, the prediction isn't quite in the form I need it, so I'd like to add some operators in the process chain after the "Apply Model" to modify the prediction. Unfortunately, the prediction attribute doesn't appear in the "labeled data" output by Apply Model. Or rather, it does show up in the summary as a special attribute, but it isn't in the attribute list, so I can't use it in say, "Generate Attribute".

I'll append the XML below if that's of any value.

Any suggestions on how to fix this? Do I need to create the prediction attribute myself (e.g., w "Generate Attribute") before applying the model? I appreciate any help, thanks!

-- Scott

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" expanded="true" name="Process">
<parameter key="logverbosity" value="3"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="1"/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="parallelize_main_process" value="false"/>
<process expanded="true" height="701" width="974">
<operator activated="true" class="read_model" expanded="true" height="60" name="Read Model" width="90" x="112" y="75">
<parameter key="model_file" value="C:\Lisp\NCAA2\Models\nn-full-margin.mod"/>
</operator>
<operator activated="true" class="read_excel" expanded="true" height="60" name="Read Excel" width="90" x="45" y="570">
<parameter key="excel_file" value="C:\Lisp\NCAA2\Test Data\season-2010-2-25.xls"/>
<parameter key="sheet_number" value="1"/>
<parameter key="row_offset" value="0"/>
<parameter key="column_offset" value="0"/>
<parameter key="first_row_as_names" value="true"/>
<list key="annotations"/>
</operator>
<operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="179" y="570">
<parameter key="name" value="ID"/>
<parameter key="target_role" value="id"/>
</operator>
<operator activated="true" class="numerical_to_real" expanded="true" height="76" name="Numerical to Real" width="90" x="313" y="570">
<parameter key="attribute_filter_type" value="0"/>
<parameter key="attribute" value=""/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="0"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="2"/>
<parameter key="block_type" value="0"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="2"/>
<parameter key="invert_selection" value="false"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" class="select_attributes" expanded="true" height="76" name="Select Attributes" width="90" x="447" y="570">
<parameter key="attribute_filter_type" value="subset"/>
<parameter key="attribute" value=""/>
<parameter key="attributes" value="Ascore|Away|Date|Home|Hscore"/>
<parameter key="use_except_expression" value="false"/>
<parameter key="value_type" value="0"/>
<parameter key="use_value_type_exception" value="false"/>
<parameter key="except_value_type" value="11"/>
<parameter key="block_type" value="0"/>
<parameter key="use_block_type_exception" value="false"/>
<parameter key="except_block_type" value="8"/>
<parameter key="invert_selection" value="true"/>
<parameter key="include_special_attributes" value="false"/>
</operator>
<operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="246" y="75">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="join" expanded="true" height="76" name="Join" width="90" x="380" y="75">
<parameter key="remove_double_attributes" value="true"/>
<parameter key="join_type" value="0"/>
</operator>
<operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="514" y="75">
<list key="function_descriptions">
<parameter key="actual" value="if(Hscore>Ascore,1,-1)"/>
</list>
<parameter key="use_standard_constants" value="true"/>
<parameter key="keep_all" value="true"/>
</operator>
<operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes (2)" width="90" x="648" y="75">
<list key="function_descriptions">
<parameter key="correct" value="sgn(prediction)"/>
</list>
<parameter key="use_standard_constants" value="true"/>
<parameter key="keep_all" value="true"/>
</operator>
<operator activated="true" class="write_excel" expanded="true" height="60" name="Write Excel" width="90" x="849" y="75">
<parameter key="excel_file" value="C:\Lisp\NCAA2\Test Data\2010-out-02-25-margin.xls"/>
</operator>
<connect from_op="Read Model" from_port="output" to_op="Apply Model" to_port="model"/>
<connect from_op="Read Excel" from_port="output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Numerical to Real" to_port="example set input"/>
<connect from_op="Numerical to Real" from_port="example set output" to_op="Select Attributes" to_port="example set input"/>
<connect from_op="Select Attributes" from_port="example set output" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Select Attributes" from_port="original" to_op="Join" to_port="right"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Join" to_port="left"/>
<connect from_op="Join" from_port="join" to_op="Generate Attributes" to_port="example set input"/>
<connect from_op="Generate Attributes" from_port="example set output" to_op="Generate Attributes (2)" to_port="example set input"/>
<connect from_op="Generate Attributes (2)" from_port="example set output" to_op="Write Excel" to_port="input"/>
<connect from_op="Write Excel" from_port="through" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>

Find more posts tagged with

AI Studio

Accepted answers

All comments

haddock

Hi Scott,

You can rename and change the role of the attribute from prediction to regular, then it becomes usable, like this...


<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="566" width="969">
      <operator activated="true" class="generate_data" expanded="true" height="60" name="Generate Data" width="90" x="112" y="75"/>
      <operator activated="true" class="support_vector_machine" expanded="true" height="112" name="SVM" width="90" x="112" y="210"/>
      <operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="313" y="210">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="447" y="210">
        <parameter key="old_name" value="prediction(label)"/>
        <parameter key="new_name" value="nu"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="581" y="210">
        <parameter key="name" value="nu"/>
      </operator>
      <operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="715" y="210">
        <list key="function_descriptions">
          <parameter key="test" value="nu*att1"/>
        </list>
      </operator>
      <connect from_op="Generate Data" from_port="output" to_op="SVM" to_port="training set"/>
      <connect from_op="SVM" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="SVM" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Rename" to_port="example set input"/>
      <connect from_op="Rename" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
      <connect from_op="Generate Attributes" from_port="example set output" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

srt19170

haddock wrote:

You can rename and change the role of the attribute from prediction to regular, then it becomes usable, like this...

Thanks for the reply! Unfortunately, this doesn't help, because the prediction attribute doesn't appear in the labeled data output from "Apply Model". So when I try to "Rename" it, I get an error "The attribute 'prediction(mov)' is missing in the input example set."

-- Scott

haddock

Hi there,

Intriguing, what model appliers do for a living is to stick in prediction columns, so if yours aren't showing I'd check that the join is working ( mouse over the input ports ), or take it out altogether to check the rest. Without the data it is hard to say more.

srt19170

Take a look at the process below. It's the example you posted, but it reads a saved model. In this case, the "labeled data" output of Apply Model does not contain a prediction attribute.

So apparently the problem has to do with reading the model from a file?

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
<context>
<input>
<location/>
</input>
<output>
<location/>
<location/>
</output>
<macros/>
</context>
<operator activated="true" class="process" expanded="true" name="Process">
<process expanded="true" height="566" width="969">
<operator activated="true" class="generate_data" expanded="true" height="60" name="Generate Data" width="90" x="112" y="75"/>
<operator activated="true" class="support_vector_machine" expanded="true" height="112" name="SVM" width="90" x="112" y="210"/>
<operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="313" y="210">
<list key="application_parameters"/>
</operator>
<operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="447" y="210">
<parameter key="old_name" value="prediction(label)"/>
<parameter key="new_name" value="nu"/>
</operator>
<operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="581" y="210">
<parameter key="name" value="nu"/>
</operator>
<operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="715" y="210">
<list key="function_descriptions">
<parameter key="test" value="nu*att1"/>
</list>
</operator>
<connect from_op="Generate Data" from_port="output" to_op="SVM" to_port="training set"/>
<connect from_op="SVM" from_port="model" to_op="Apply Model" to_port="model"/>
<connect from_op="SVM" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Rename" to_port="example set input"/>
<connect from_op="Rename" from_port="example set output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
<connect from_op="Generate Attributes" from_port="example set output" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>

haddock

It's the example you posted, but it reads a saved model.

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="566" width="969">
      <operator activated="true" class="generate_data" expanded="true" height="60" name="Generate Data" width="90" x="112" y="75"/>
      <operator activated="true" class="support_vector_machine" expanded="true" height="112" name="SVM" width="90" x="112" y="210"/>
      <operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="313" y="210">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="447" y="210">
        <parameter key="old_name" value="prediction(label)"/>
        <parameter key="new_name" value="nu"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="581" y="210">
        <parameter key="name" value="nu"/>
      </operator>
      <operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="715" y="210">
        <list key="function_descriptions">
          <parameter key="test" value="nu*att1"/>
        </list>
      </operator>
      <connect from_op="Generate Data" from_port="output" to_op="SVM" to_port="training set"/>
      <connect from_op="SVM" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="SVM" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Rename" to_port="example set input"/>
      <connect from_op="Rename" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
      <connect from_op="Generate Attributes" from_port="example set output" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
    </process>
  </operator>
</process>

Where does it do that model reading stuff ?

srt19170

I must have pasted in the wrong file. I'll post the correct one tomorrow, sorry.

srt19170

Here's the process using "Read Model":

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
<context>
<input/>
<output/>
<macros/>
</context>
<operator activated="true" class="process" expanded="true" name="Process">
<parameter key="logverbosity" value="3"/>
<parameter key="random_seed" value="2001"/>
<parameter key="send_mail" value="1"/>
<parameter key="process_duration_for_mail" value="30"/>
<parameter key="encoding" value="SYSTEM"/>
<parameter key="parallelize_main_process" value="false"/>
<process expanded="true" height="566" width="969">
<operator activated="true" class="generate_data" expanded="true" height="60" name="Generate Data (2)" width="90" x="179" y="345">
<parameter key="target_function" value="random"/>
<parameter key="number_examples" value="100"/>
<parameter key="number_of_attributes" value="5"/>
<parameter key="attributes_lower_bound" value="-10.0"/>
<parameter key="attributes_upper_bound" value="10.0"/>
<parameter key="use_local_random_seed" value="false"/>
<parameter key="local_random_seed" value="1992"/>
<parameter key="datamanagement" value="0"/>
</operator>
<operator activated="true" class="read_model" expanded="true" height="60" name="Read Model" width="90" x="112" y="210">
<parameter key="model_file" value="C:\Lisp\NCAA2\Models\nn-full.mod"/>
</operator>
<operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="313" y="210">
<list key="application_parameters"/>
<parameter key="create_view" value="false"/>
</operator>
<operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="447" y="210">
<parameter key="old_name" value="prediction(label)"/>
<parameter key="new_name" value="nu"/>
</operator>
<operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="581" y="210">
<parameter key="name" value="nu"/>
<parameter key="target_role" value="regular"/>
</operator>
<operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="715" y="210">
<list key="function_descriptions">
<parameter key="test" value="nu*att1"/>
</list>
<parameter key="use_standard_constants" value="true"/>
<parameter key="keep_all" value="true"/>
</operator>
<connect from_op="Generate Data (2)" from_port="output" to_op="Apply Model" to_port="unlabelled data"/>
<connect from_op="Read Model" from_port="output" to_op="Apply Model" to_port="model"/>
<connect from_op="Apply Model" from_port="labelled data" to_op="Rename" to_port="example set input"/>
<connect from_op="Rename" from_port="example set output" to_op="Set Role" to_port="example set input"/>
<connect from_op="Set Role" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
<connect from_op="Generate Attributes" from_port="example set output" to_port="result 1"/>
<portSpacing port="source_input 1" spacing="0"/>
<portSpacing port="sink_result 1" spacing="0"/>
<portSpacing port="sink_result 2" spacing="0"/>
</process>
</operator>
</process>

haddock

It must be your model then, as the following works fine...


<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="415" width="884">
      <operator activated="true" class="generate_data" expanded="true" height="60" name="Generate Data (2)" width="90" x="112" y="30"/>
      <operator activated="true" class="support_vector_machine" expanded="true" height="112" name="SVM" width="90" x="211" y="83"/>
      <operator activated="true" class="write_model" expanded="true" height="60" name="Write Model" width="90" x="367" y="76">
        <parameter key="model_file" value="test"/>
      </operator>
      <operator activated="true" class="read_model" expanded="true" height="60" name="Read Model" width="90" x="112" y="210">
        <parameter key="model_file" value="test"/>
      </operator>
      <operator activated="true" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="313" y="210">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="447" y="210">
        <parameter key="old_name" value="prediction(label)"/>
        <parameter key="new_name" value="nu"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="581" y="210">
        <parameter key="name" value="nu"/>
      </operator>
      <operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="715" y="210">
        <list key="function_descriptions">
          <parameter key="test" value="nu*att1"/>
        </list>
      </operator>
      <connect from_op="Generate Data (2)" from_port="output" to_op="SVM" to_port="training set"/>
      <connect from_op="SVM" from_port="model" to_op="Write Model" to_port="input"/>
      <connect from_op="SVM" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Write Model" from_port="through" to_port="result 2"/>
      <connect from_op="Read Model" from_port="output" to_op="Apply Model" to_port="model"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Rename" to_port="example set input"/>
      <connect from_op="Rename" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
      <connect from_op="Generate Attributes" from_port="example set output" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
      <portSpacing port="sink_result 3" spacing="0"/>
    </process>
  </operator>
</process>

srt19170

haddock wrote:

It must be your model then, as the following works fine...

When I open that in RapidMiner, it shows three errors in the Problems tab. What version of RapidMiner are you using? (I'm using 5.0.005)

haddock

Okidokey, it has always been the case ( even in 4.6 ) that RM spews out erroneous warnings, and this is a case in point. The Rename operator looks at the example set, and does not realise that the model applier will stick in the prediction column.

However, and this is the point, if you press the play button the process does work, and the prediction attribute does appear in the labeled data output from "Apply Model", as in the following.

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<process version="5.0">
  <context>
    <input>
      <location/>
    </input>
    <output>
      <location/>
      <location/>
      <location/>
    </output>
    <macros/>
  </context>
  <operator activated="true" class="process" expanded="true" name="Process">
    <process expanded="true" height="650" width="890">
      <operator activated="true" class="generate_data" expanded="true" height="60" name="Generate Data (2)" width="90" x="45" y="30"/>
      <operator activated="true" class="support_vector_machine" expanded="true" height="112" name="SVM" width="90" x="179" y="75"/>
      <operator activated="true" class="write_model" expanded="true" height="60" name="Write Model" width="90" x="447" y="75">
        <parameter key="model_file" value="test"/>
      </operator>
      <operator activated="true" class="read_model" expanded="true" height="60" name="Read Model" width="90" x="45" y="210">
        <parameter key="model_file" value="test"/>
      </operator>
      <operator activated="true" breakpoints="after" class="apply_model" expanded="true" height="76" name="Apply Model" width="90" x="313" y="210">
        <list key="application_parameters"/>
      </operator>
      <operator activated="true" class="rename" expanded="true" height="76" name="Rename" width="90" x="447" y="210">
        <parameter key="old_name" value="prediction(label)"/>
        <parameter key="new_name" value="nu"/>
      </operator>
      <operator activated="true" class="set_role" expanded="true" height="76" name="Set Role" width="90" x="581" y="210">
        <parameter key="name" value="nu"/>
      </operator>
      <operator activated="true" class="generate_attributes" expanded="true" height="76" name="Generate Attributes" width="90" x="715" y="210">
        <list key="function_descriptions">
          <parameter key="test" value="nu*att1"/>
        </list>
      </operator>
      <connect from_op="Generate Data (2)" from_port="output" to_op="SVM" to_port="training set"/>
      <connect from_op="SVM" from_port="model" to_op="Write Model" to_port="input"/>
      <connect from_op="SVM" from_port="exampleSet" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Write Model" from_port="through" to_port="result 2"/>
      <connect from_op="Read Model" from_port="output" to_op="Apply Model" to_port="model"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Rename" to_port="example set input"/>
      <connect from_op="Rename" from_port="example set output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Generate Attributes" to_port="example set input"/>
      <connect from_op="Generate Attributes" from_port="example set output" to_port="result 1"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
      <portSpacing port="sink_result 3" spacing="0"/>
    </process>
  </operator>
</process>

srt19170

D'oh! It never occurred to me that I could go ahead and execute anyway. That's my software development background for you -- fix all the compiler errors first :-)

Thanks for your help (and patience!)

-- Scott

haddock

Greets Scott,

I spend most of my time writing Prolog, yes really, Prolog, and know exactly what you mean. The truth about RM is that it is very idiot proof, as I can vouch for, and produces much less silicon smoke than a really serious Prolog stack explosion; on the other hand when you need a built-in theorem prover .... So horses for courses.

Happy datagrinding!