Missing Values

Missing Values is a transformation type that replaces missing values with an appropriate value.

To specify a Missing Values transformation:

1. In the Transform Type field, select the option Missing Values.

2. In the Missing Values field, select an option:

   • Statistic: Replaces the missing value with a statistical measure. Statistic is the default treatment for missing values. The applicable Statistic type depends on the data type of the column:

     • For numeric columns, you can replace missing values with Mean (default), Median, Minimum, Maximum.

     • For categorical columns, you can replace missing values with Mode (default).

   • Value: Replaces Missing Values with the specified value. Oracle Data Miner provides a default value that you can change.

     • If statistics are not available, then the default value is 0.

     • If statistics are available, then the default value is:
       Mean for numerical columns
       Mode for categorical columns

     Both these treatments can be applied to attributes that have a date or time data type DATE, TIMESTAMP, TIMESTAMP_WITH_LOCAL_ TIMEZONE, and TIMESTAMP_WITH_TIMEZONE.

3. After you are done, click OK.