Problem with loop modelling output saving

sebastian_gonza

Hi

 

I have a Data set with Client ID | Order ID | Quantity | Price, what I want to do is a regression per client ID  like Quantity = Beta + alpha*Price and save the output in a collection, I got to the collection but it keeps printing the same value over and over again, also I would like to append the Client ID to their respective model but I dont know how, could someone help me please?

 

Thanks

 

Attached: Sample data and process

 

<?xml version="1.0" encoding="UTF-8"?><process version="9.0.002">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.0.002" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="retrieve" compatibility="9.0.002" expanded="true" height="68" name="Retrieve pedidos_con_cliente_importe" width="90" x="45" y="340">
        <parameter key="repository_entry" value="pedidos_con_cliente_importe"/>
      </operator>
      <operator activated="true" class="select_attributes" compatibility="9.0.002" expanded="true" height="82" name="Select Attributes (5)" width="90" x="179" y="340">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="Cantidad|IdCliente|IdPedido|Importe|Precio calculado"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.0.002" expanded="true" height="82" name="Set Role" width="90" x="313" y="340">
        <parameter key="attribute_name" value="Cantidad"/>
        <parameter key="target_role" value="label"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="remove_duplicates" compatibility="9.0.002" expanded="true" height="103" name="Remove Duplicates" width="90" x="447" y="340">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="IdCliente|IdPedido|Importe|Cantidad"/>
      </operator>
      <operator activated="true" class="concurrency:loop_values" compatibility="9.0.002" expanded="true" height="82" name="Loop Values" width="90" x="581" y="340">
        <parameter key="attribute" value="IdCliente"/>
        <process expanded="true">
          <operator activated="true" class="select_attributes" compatibility="9.0.002" expanded="true" height="82" name="Select Attributes (6)" width="90" x="112" y="34">
            <parameter key="attribute_filter_type" value="subset"/>
            <parameter key="attributes" value="Cantidad|Precio calculado"/>
          </operator>
          <operator activated="true" class="linear_regression" compatibility="9.0.002" expanded="true" height="103" name="Linear Regression" width="90" x="246" y="34">
            <parameter key="eliminate_colinear_features" value="false"/>
            <parameter key="use_bias" value="false"/>
          </operator>
          <connect from_port="input 1" to_op="Select Attributes (6)" to_port="example set input"/>
          <connect from_op="Select Attributes (6)" from_port="example set output" to_op="Linear Regression" to_port="training set"/>
          <connect from_op="Linear Regression" from_port="model" to_port="output 1"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="source_input 2" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="collect" compatibility="9.0.002" expanded="true" height="82" name="Collect" width="90" x="715" y="340"/>
      <connect from_op="Retrieve pedidos_con_cliente_importe" from_port="output" to_op="Select Attributes (5)" to_port="example set input"/>
      <connect from_op="Select Attributes (5)" 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="Remove Duplicates" to_port="example set input"/>
      <connect from_op="Remove Duplicates" from_port="example set output" to_op="Loop Values" to_port="input 1"/>
      <connect from_op="Loop Values" from_port="output 1" to_op="Collect" to_port="input 1"/>
      <connect from_op="Collect" from_port="collection" 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>

 

 

MartinLiebig

Hi,

attached is a solution. You need Operator Toolbox extension to run this.

 

Best,

Martin

 

<?xml version="1.0" encoding="UTF-8"?><process version="9.0.002">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.0.002" expanded="true" name="Process">
    <process expanded="true">
      <operator activated="true" class="retrieve" compatibility="9.0.002" expanded="true" height="68" name="Retrieve pedidos_con_cliente_importe" width="90" x="45" y="340">
        <parameter key="repository_entry" value="pedidos_con_cliente_importe"/>
      </operator>
      <operator activated="true" class="select_attributes" compatibility="9.0.002" expanded="true" height="82" name="Select Attributes (5)" width="90" x="179" y="340">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="Cantidad|IdCliente|IdPedido|Importe|Precio calculado"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.0.002" expanded="true" height="82" name="Set Role" width="90" x="313" y="340">
        <parameter key="attribute_name" value="Cantidad"/>
        <parameter key="target_role" value="label"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="remove_duplicates" compatibility="9.0.002" expanded="true" height="103" name="Remove Duplicates" width="90" x="447" y="340">
        <parameter key="attribute_filter_type" value="subset"/>
        <parameter key="attributes" value="IdCliente|IdPedido|Importe|Cantidad"/>
      </operator>
      <operator activated="false" class="concurrency:loop_values" compatibility="9.0.002" expanded="true" height="68" name="Loop Values" width="90" x="782" y="238">
        <parameter key="attribute" value="IdCliente"/>
        <process expanded="true">
          <operator activated="true" class="select_attributes" compatibility="9.0.002" expanded="true" height="82" name="Select Attributes (6)" width="90" x="581" y="136">
            <parameter key="attribute_filter_type" value="subset"/>
            <parameter key="attributes" value="Cantidad|Precio calculado"/>
          </operator>
          <operator activated="true" class="linear_regression" compatibility="9.0.002" expanded="true" height="103" name="Linear Regression" width="90" x="715" y="136">
            <parameter key="eliminate_colinear_features" value="false"/>
            <parameter key="use_bias" value="false"/>
          </operator>
          <connect from_op="Select Attributes (6)" from_port="example set output" to_op="Linear Regression" to_port="training set"/>
          <portSpacing port="source_input 1" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
        </process>
      </operator>
      <operator activated="true" class="collect" compatibility="9.0.002" expanded="true" height="82" name="Collect" width="90" x="983" y="340"/>
      <operator activated="true" class="operator_toolbox:group_into_collection" compatibility="1.5.000-SNAPSHOT" expanded="true" height="82" name="Group Into Collection" width="90" x="581" y="340">
        <parameter key="group_by_attribute" value="IdCliente"/>
      </operator>
      <operator activated="true" class="loop_collection" compatibility="9.0.002" expanded="true" height="82" name="Loop Collection" width="90" x="782" y="340">
        <process expanded="true">
          <operator activated="true" class="select_attributes" compatibility="9.0.002" expanded="true" height="82" name="Select Attributes (2)" width="90" x="179" y="85">
            <parameter key="attribute_filter_type" value="subset"/>
            <parameter key="attributes" value="Cantidad|Precio calculado"/>
          </operator>
          <operator activated="true" class="linear_regression" compatibility="9.0.002" expanded="true" height="103" name="Linear Regression (2)" width="90" x="313" y="85">
            <parameter key="eliminate_colinear_features" value="false"/>
            <parameter key="use_bias" value="false"/>
          </operator>
          <connect from_port="single" to_op="Select Attributes (2)" to_port="example set input"/>
          <connect from_op="Select Attributes (2)" from_port="example set output" to_op="Linear Regression (2)" to_port="training set"/>
          <connect from_op="Linear Regression (2)" from_port="model" to_port="output 1"/>
          <portSpacing port="source_single" spacing="0"/>
          <portSpacing port="sink_output 1" spacing="0"/>
          <portSpacing port="sink_output 2" spacing="0"/>
        </process>
      </operator>
      <connect from_op="Retrieve pedidos_con_cliente_importe" from_port="output" to_op="Select Attributes (5)" to_port="example set input"/>
      <connect from_op="Select Attributes (5)" 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="Remove Duplicates" to_port="example set input"/>
      <connect from_op="Remove Duplicates" from_port="example set output" to_op="Collect" to_port="input 1"/>
      <connect from_op="Collect" from_port="collection" 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>