User's Manual

102
Chapter 6
Screening or Removing Fields
To screen out fields with too many mis sing value s, you have seve r al options:
 You can use a Data Audit node to filter field s based on quality.
 You can use a Featu r e Selection node to screen out fields with more than a specified percentage
of missing valu es and to rank fields based on importance relative to a specified target.
 Instead of rem oving the fields, you ca n use a Type node to se t the fie ld role to None. This will
keep the fields in the data set but exclude them from the modelin g processes.
Imputing or Filling Missing Values
In cases where there are only a few missing values, it may be useful to in sert values to replace
the blanks. You can do this fr om the Data Audit report, which allows you t o specify options for
specific fields as appropriate and then generate a SuperNode that imputes values using a number
of methods. This is the most flexible method, and it al so allows you to specify handling for large
numbers of fields in a single node.
The following methods are available f or impu ting missing values:
Fixed. Substitutes a fixed value (either the field mean, midpoint of the range, or a constant that
you specify).
Random. Substitutes a random value based on a normal or uniform distribution.
Expression. Allows you to specify a custom expressio n. For example, you coul d replace values
with a global variable created by the Set Globals node.
Algorithm. Substitutes a value pre dicted by a model based on the C&RT algorithm. For each field
imputed using this method, there will be a separate C&RT model, along with a Filler node that
replaces blanks and nulls with the value predicted by the model. A Filter node is then used to
remove the prediction fields generated by the m odel.
Alternatively, to coerce values for specific fields, you can us e a Type n ode to ensure that th e
field types cover o nly legal values and then set the Check c olumn to Coerce for the fields w hose
blank values need replacing.
CLEM Functions for Missing Values
There are several fun ctions used to hand le missing value s. The following functions are often used
in Select and Filler nodes to discard or fill missing values :
 count_nulls(LIST)
 @BLANK(FIELD)
 @NULL(FIELD)
 undef