Apply an OCI Language Model to a Dataset

Apply an OCI Language model to a dataset in Oracle Analytics to analyze your data and store the results in another dataset. For example, with customer data, sentiment analysis can help you analyze customer reviews that they've typed into a feedback portal.

Prerequisites:
  1. On the Oracle Analytics Home page, click Create, and then click Data Flow.
  2. Select the dataset containing the text you want to analyze, then click Add.
  3. In the Data Flow editor, click Add a step (+).
  4. From the Data Flow Steps pane, double-click Apply AI Model, and then select the model to use.
  5. In the Apply AI Model dialog, go to the Inputs section, and configure the parameters.

    At a minimum, configure Input Column and Reference Column 1.

    You can optionally assign values to Reference Columns 2 and 3 to further enhance the output dataset. For example, you might select two additional columns from your source dataset that will included in the AI model output dataset.

  6. In the data flow editor, click Add a step (+) and select Save Data.
  7. Enter the name of the dataset in which to store the output results.
  8. In the Save data to field, specify the location for saving the output data.
  9. Click Save, enter a name and description for the data flow, and click OK to save the data flow.
  10. Click Run Data Flow to analyze the images and output the results in a new dataset.
When the data flow completes the analysis, open the dataset that you specified in Step 7.

To locate the generated dataset, from the Oracle Analytics home page, navigate to Data, then Datasets
Description of ocilanguage3.png follows
Description of the illustration ocilanguage3.png

.

You can now visualize the data in a workbook.
Description of ocilanguage4.png follows
Description of the illustration ocilanguage4.png