How to set the filename of the loaded data as an attribute

Answers

• Options

  MartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,507 RM Data Scientist

  January 2018

  Hi Oliver,

   

  if you read Files with Read Excel or Read CSV or even with a Read Database they have an annotation called source which includes the path. That means you do not forget the original location.

  You can add this annotation as a attribute to your table if you want to. Attached is a process demonstrating it.

   

  Best,

  Martin

   

  <?xml version="1.0" encoding="UTF-8"?><process version="8.0.001">
    <context>
      <input/>
      <output/>
      <macros/>
    </context>
    <operator activated="true" class="process" compatibility="8.0.001" expanded="true" name="Process">
      <process expanded="true">
        <operator activated="true" class="read_csv" compatibility="8.0.001" expanded="true" height="68" name="Read CSV" width="90" x="112" y="136">
          <parameter key="csv_file" value="C:\Users\Martin\Desktop\0_Hotel_Review_Data.csv"/>
          <parameter key="column_separators" value=","/>
          <parameter key="first_row_as_names" value="false"/>
          <list key="annotations">
            <parameter key="0" value="Name"/>
          </list>
          <parameter key="encoding" value="windows-1252"/>
          <list key="data_set_meta_data_information">
            <parameter key="0" value="Text.true.polynominal.attribute"/>
            <parameter key="1" value="Rating.true.real.attribute"/>
            <parameter key="2" value="ReviewId.true.real.attribute"/>
          </list>
        </operator>
        <operator activated="true" class="annotations_to_data" compatibility="8.0.001" expanded="true" height="82" name="Annotations to Data" width="90" x="246" y="136"/>
        <operator activated="true" class="filter_examples" compatibility="8.0.001" expanded="true" height="103" name="Filter Examples" width="90" x="380" y="34">
          <list key="filters_list">
            <parameter key="filters_entry_key" value="annotation.equals.Source"/>
          </list>
        </operator>
        <operator activated="true" class="extract_macro" compatibility="8.0.001" expanded="true" height="68" name="Extract Macro" width="90" x="581" y="34">
          <parameter key="macro" value="Source"/>
          <parameter key="macro_type" value="data_value"/>
          <parameter key="attribute_name" value="value"/>
          <parameter key="example_index" value="1"/>
          <list key="additional_macros"/>
        </operator>
        <operator activated="true" class="delay" compatibility="8.0.001" expanded="true" height="103" name="Delay" width="90" x="715" y="85">
          <parameter key="delay_amount" value="0"/>
          <description align="center" color="transparent" colored="false" width="126">Only to ensure execution order</description>
        </operator>
        <operator activated="true" class="generate_attributes" compatibility="8.0.001" expanded="true" height="82" name="Generate Attributes" width="90" x="849" y="136">
          <list key="function_descriptions">
            <parameter key="Source" value="%{source}"/>
          </list>
        </operator>
        <connect from_op="Read CSV" from_port="output" to_op="Annotations to Data" to_port="object"/>
        <connect from_op="Annotations to Data" from_port="annotations" to_op="Filter Examples" to_port="example set input"/>
        <connect from_op="Annotations to Data" from_port="object through" to_op="Delay" to_port="through 2"/>
        <connect from_op="Filter Examples" from_port="example set output" to_op="Extract Macro" to_port="example set"/>
        <connect from_op="Extract Macro" from_port="example set" to_op="Delay" to_port="through 1"/>
        <connect from_op="Delay" from_port="through 1" to_port="result 1"/>
        <connect from_op="Delay" from_port="through 2" to_op="Generate Attributes" to_port="example set input"/>
        <connect from_op="Generate Attributes" from_port="example set output" to_port="result 2"/>
        <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>
  

  - Sr. Director Data Solutions, Altair RapidMiner -
  Dortmund, Germany

  2
• Options

  oliver23 Member Posts: 4 Contributor I

  January 2018

  Thanks!

  0