Setting Options for the Reclassify Node

There are three steps to using the Reclassify node:

  1. First, select whether you want to reclassify multiple fields or a single field.
  2. Next, choose whether to recode into the existing field or create a new field.
  3. Then, use the dynamic options in the Reclassify node dialog box to map sets as desired.

    Mode. Select Single to reclassify the categories for one field. Select Multiple to activate options enabling the transformation of more than one field at a time.

    Reclassify into. Select New field to keep the original nominal field and derive an additional field containing the reclassified values. Select Existing field to overwrite the values in the original field with the new classifications. This is essentially a "fill" operation.

    Once you have specified mode and replacement options, you must select the transformation field and specify the new classification values using the dynamic options on the bottom half of the dialog box. These options vary depending on the mode you have selected above.

    Reclassify field(s). Use the Field Chooser button on the right to select one (Single mode) or more (Multiple mode) categorical fields.

    New field name. Specify a name for the new nominal field containing recoded values. This option is available only in Single mode when New field is selected above. When Existing field is selected, the original field name is retained. When working in Multiple mode, this option is replaced with controls for specifying an extension added to each new field. See the topic Reclassifying Multiple Fields for more information.

    Reclassify values. This table enables a clear mapping from old set values to those you specify here.

    • Original value. This column lists existing values for the select field(s).
    • New value. Use this column to type new category values or select one from the drop-down list. When you automatically generate a Reclassify node using values from a Distribution chart, these values are included in the drop-down list. This allows you to quickly map existing values to a known set of values. For example, healthcare organizations sometimes group diagnoses differently based upon network or locale. After a merger or acquisition, all parties will be required to reclassify new or even existing data in a consistent fashion. Rather than manually typing each target value from a lengthy list, you can read the master list of values in to IBM® SPSS® Modeler, run a Distribution chart for the Diagnosis field, and generate a Reclassify (values) node for this field directly from the chart. This process will make all of the target Diagnosis values available from the New Values drop-down list.
  4. Click Get to read original values for one or more fields selected above.
  5. Click Copy to paste original values over to the New value column for fields that have not been mapped yet. The unmapped original values are added to the drop-down list.
  6. Click Clear new to erase all specifications in the New value column. Note: This option does not erase the values from the drop-down list.
  7. Click Auto to automatically generate consecutive integers for each of the original values. Only integer values (no real values, such as 1.5, 2.5, and so on) can be generated.

For example, you can automatically generate consecutive product ID numbers for product names or course numbers for university class offerings. This functionality corresponds to the Automatic Recode transformation for sets in IBM SPSS Statistics.

For unspecified values use. This option is used for filling unspecified values in the new field. You can either choose to keep the original value by selecting Original value or specify a default value.