This selection displays the result of applying an Oracle Data Mining model to a table or view.
The viewer has the following menus:
The following tabs are displayed:
The apply output is displayed with the columns that you specified for apply output when you created the apply operation.
The default is to fetch (and display) 100 rows; to fetch the next 100 rows, click Refresh. To change the number of rows that are fetched, type a different number in the Fetch Size box and click Refresh. You can sort columns by clicking the column headings.
The data returned depends on the model being applied. For example, when you apply a decision tree model, the node of the tree is returned. For all models, a prediction and a probability are returned.
If you apply a classification model and specify more than one target, data is returned for each target. For example, if you select two target values for a tree model, the node and the probability are returned for each value. The node for a value is displayed in the column NODE_lab, where lab is the Base Column Name for the value. In many cases, the Base Column Name is identical to the value; otherwise, it is a truncated version of the value.
For anomaly detection models, the following columns are displayed: the case id column that was specified, PREDICTION, PROBABILITY, and any other columns that you specified. PREDICTION is either 0 indicating an anomalous value or 1 indicating a typical value. Values in the PROBABILITY column should be interpreted as relative values, not as absolute probabilities. The case with the highest probability value is the most likely to be an anomalous value.
You specify settings when you create the apply activity. This tab displays the following:
This tab describes the task used to apply the model. It shows when the task ran, what input was used, and what output was created.
Copyright © 2006, 2008, Oracle. All rights reserved.