Classifier Model Configuration
The steps to configure a classifier model begin with the data that you want to classify. The content of the reference data that you add to the model must reflect the data that you connect to the Classifier transformation. The transformation compares the data values and patterns in the input data to the data values and patterns in the classifier model.
To create a classifier model that you can use in a Classifier transformation, perform the following tasks:
- 1. Identify the reference data values and the label values to add to the model.
You can use a fragment of the data that you want to classify. Create a data object in the Model repository that reads the data fragment.
- 2. Create a content set, and add a classifier model to the content set.
- 3. Add the reference data values to the model.
- 4. Add the label values to the model.
You can import the data from the data object in the Model repository. You can also enter a single row of reference data or a single label.
- 5. Assign a label to each row of reference data.
You can assign a label to multiple rows in a single operation.
- 6. Compile the model.
After you compile the classifier model, you can use the model in a Classifier transformation.
Appending Data from a Data Source to a Classifier Model
You can import multiple rows of reference data values or label values to a classifier model in a single operation.
1. Open the content set that contains the classifier model.
2. Select the model name, and click Edit.
3. Click Append Data.
The Classifier Model wizard opens.
4. Browse the Model repository and select the data object that contains the data to import.
Do not select a social media data object.
Click Next.
5. Review the columns on the data object, and select one or more columns to add to the model. You can add reference data columns and a label column in the same operation.
- - To import a column of data as reference data, select the column name and click Data.
You can select multiple data columns. The Developer tool merges the contents of the columns that you select to a single column.
- - To import a column of data as label values, select the column name and click Label.
When you import reference data and label values, the Developer tool assigns the label on each row to the reference data string on the same row. You can preview the data before you select the columns. You can change the label assignments after you create the model.
Click Next.
6. Select the number of rows to import from the data source.
By default, the Developer tool imports all rows from the data source. If you enter a number, the model counts the rows from the start of the data set.
7. Click Finish, and save the model.
Adding a Reference Data Row to a Classifier Model
You can add a single row of reference data to a classifier model.
1. Open the content set that contains the classifier model.
2. Select the model name, and click Edit.
3. Click Add Row.
The Developer tool adds a row below the current row in the reference data.
4. Enter the reference data values to the row.
You can use Windows shortcuts to paste data to the row.
Adding a Label to a Classifier Model
You can add a single label to a classifier model.
1. Open the content set that contains the classifier model.
2. Select the model name, and click Edit.
3. Open the Manage Labels dialog box.
The dialog box lists the labels in the model.
4. Click New.
The Developer tool adds a row at the bottom of the list of labels.
5. Double-click the default value in the Name column, and enter a label name.
6. Click OK.
After you create the label, you can assign the label to one or more rows of reference data. The Usage column in the Manage Labels dialog box indicates the number of rows that use the label.
Assigning a Label to Reference Data Rows
You can assign a label to one or more reference data rows in a single operation.
1. Open the content set that contains the model.
2. Select the model name, and click Edit.
3. Select one or more reference data rows. Use the check box options to select the rows.
Note: You can use the filter option to show all of the rows that contain a data value that you specify. Use the Select All check box option to select all of the rows that contain the value.
4. Click Assign Label.
The Developer tool displays the list of labels in the classifier model.
5. Select a label value, and click Assign.
The Developer tool updates the reference data rows that you selected with the label value.
Optionally, compile the model to add the label names to the classifier model logic.
Identifying Unused Label Values
Use the Manage Labels dialog box to find any label value that remains unused in the classifier model. The Manage Labels dialog box displays usage data for the label values in the classifier model. Use the usage data to verify the number of reference data rows that use a label value and to find unused label values.
1. Open the content set that contains the classifier model.
2. Select the model name, and click Edit.
3. Open the Manage Labels dialog box. The dialog box lists the labels in the classifier model.
4. Review the Usage column data for each label.
The Usage column lists the number of reference data rows that use the label. If a label value is unused, the Usage column has a value of zero.
Deleting Rows from a Classifier Model
You can delete one or more reference data rows from a classifier model in a single action.
1. Open the content set that contains the model.
2. Select the model name, and click Edit.
3. Select one or more reference data rows. Use the check box options to select the rows.
4. Click Delete.
The Developer tool removes the rows that you selected from the classifier model.
To undo the operation, press the Ctrl + Z keys on the keyboard.
Deleting a Label from a Classifier Model
Use the Manage Labels dialog box to delete a label from a classifier model.
1. Open the content set that contains the model.
2. Select the model name, and click Edit.
3. Open the Manage Labelsdialog box.
4. Click Delete.
5. Click Yes to confirm the operation.
The Developer tool deletes the label from the model. The Developer tool does not delete any reference data row that uses the label.
6. Click OK to close the dialog box.
To undo the operation, press the Ctrl + Z keys on the keyboard.
Compiling a Classifier Model
Each time you edit a label value or reference data value in a classifier model, you must compile the model. When you compile the model, you update the compilation data in the model.
- •To update the compilation data, open the model in the Developer tool and click Compile.