Uploaded image for project: 'Moodle QA'
  1. Moodle QA
  2. MDLQA-14131 Moodle 3.9 QA
  3. MDLQA-14657

CLONE - Managers can manage analytics prediction models

XMLWordPrintable

      There is a QA testing site available: Analytics QA Test Site

      This site uses selected data from a data set donated to the Moodle Learning Analytics team from a university. The data has been thoroughly anonymised and dates have been shifted forward to make the site more current for reporting purposes.

      Test 1:

      1. Log in as admin
      2. Create a new topics course with start date the 1st of last month and end date in 5 or 10 minutes (basically the time you need to follow this step below)
      3. Assign a user as a student to the course, log in as the student and generate 10 logs or more (e.g. access the course page, access the forum, check participants...)
      4. Log back as an admin
      5. Go to "Site admin > Analytics > Analytics settings" and disable "Analytics processes execution via command line only" setting
      6. Log in as a manager and go to 'Analytics models' in the Site administration.
      7. Wait until you reach the course end date time you specified above
      8. For 'Students at risk of dropping out' select 'Evaluate' in the Actions column.
      9. Verify that accuracy and information about the model performance using each of the time-splitting methods enabled on your site is displayed (by default Last quarter, All previous quarters and From start to end).
      10. Click 'Continue'.
      11. For 'Students at risk of dropping out' select 'Evaluation log' in the Actions column.
      12. Verify that a list of previous evaluations is displayed, with version (last time the model indicators were modified), indicators included in the evaluation, analysis interval and reported accuracy.
      13. Click View in the Info column.
      14. Verify that extra information reported by the machine learning algorithm is displayed in a modal window.

      Test 2:

      1. Log in as a manager and create a new course with tomorrow as the start date (the course should not have any teachers nor students)
      2. Go to 'Analytics models' in the Site administration.
      3. For 'Courses at risk of not starting' select 'Execute scheduled analysis' in the Actions column.
      4. Scroll down the page listing info and click the continue button.
      5. Verify that for 'Courses at risk of not starting' the Insights column contains a drop-down menu with a single item 'All predictions'.
      6. Select 'All predictions' and verify that the model insights are displayed.
      7. Return to 'Analytics models' in the Site administration.
      8. For 'Courses at risk of not starting' select 'Clear predictions' in the Actions column.
      9. Verify that the Insights column displays the message 'No predictions available yet'.
      10. For 'Courses at risk of not starting' select Disable in the Actions column.
      11. Verify that the Insights column displays the message 'Disabled model' and that the option 'Execute scheduled analysis' is not available in the Actions menu.
      12. For 'Courses at risk of not starting' select 'Enable' in the Actions column, then select 'Execute scheduled analysis'.
      13. Scroll down the page listing info and click the continue button.
      14. Verify that for 'Courses at risk of not starting' the Insights column again contains a drop-down menu with a single item 'All predictions'.

            sanderbangma Sander Bangma
            Votes:
            0 Vote for this issue
            Watchers:
            1 Start watching this issue

              Created:
              Updated:
              Resolved:

                Error rendering 'clockify-timesheets-time-tracking-reports:timer-sidebar'. Please contact your Jira administrators.