Fields (automated data preparation)

The Fields main view displays the processed fields and whether ADP recommends using them in downstream models. You can override the recommendation for any field; for example, to exclude constructed features or include features that ADP recommends excluding. If a field has been transformed, you can decide whether to accept the suggested transformation or use the original version.

The Fields view consists of two tables, one for the target and one for predictors that were either processed or created.

Target table

The Target table is only shown if a target is defined in the data.

The table contains two columns:

• Name. This is the name or label of the target field; the original name is always used, even if the field has been transformed.
• Measurement Level. This displays the icon representing the measurement level; hover the mouse over the icon to display a label (continuous, ordinal, nominal, and so on) that describes the data.

  If the target has been transformed the Measurement Level column reflects the final transformed version. Note: you cannot turn off transformations for the target.

Predictors table

The Predictors table is always shown. Each row of the table represents a field. By default the rows are sorted in descending order of predictive power.

For ordinary features, the original name is always used as the row name. Both original and derived versions of date/time fields appear in the table (in separate rows); the table also includes constructed predictors.

Note that transformed versions of fields shown in the table always represent the final versions.

By default only recommended fields are shown in the Predictors table. To display the remaining fields, select the Include nonrecommended fields in table box above the table; these fields are then displayed at the bottom of the table.

The table contains the following columns:

• Version to Use. This displays a drop-down list that controls whether a field will be used downstream and whether to use the suggested transformations. By default, the drop-down list reflects the recommendations.

  For ordinary predictors that have been transformed the drop-down list has three choices: Transformed, Original, and Do not use.

  For untransformed ordinary predictors the choices are: Original and Do not use.

  For derived date/time fields and constructed predictors the choices are: Transformed and Do not use.

  For original date fields the drop-down list is disabled and set to Do not use.

  Note: For predictors with both original and transformed versions, changing between Original and Transformed versions automatically updates the Measurement Level and Predictive Power settings for those features.

• Name. Each field's name is a link. Click a name to display more information about the field in the linked view. See the topic Field Details (automated data preparation) for more information.
• Measurement Level. This displays the icon representing the data type; hover the mouse over the icon to display a label (continuous, ordinal, nominal, and so on) that describes the data.
• Predictive Power. Predictive power is displayed only for fields that ADP recommends. This column is not displayed if there is no target defined. Predictive power ranges from 0 to 1, with larger values indicating "better" predictors. In general, predictive power is useful for comparing predictors within an ADP analysis, but predictive power values should not be compared across analyses.