Merge pull request #104 from saraburns1/saraburns1_datatest_maint

test: Fix data tests

.github/workflows/coverage.yml

@@ -42,6 +42,10 @@ jobs:
           tutor local start -d
           tutor local do init -l aspects
           tutor local do load-xapi-test-data
+      - name: Check dbt tests
+        run: |
+          dbt run
+          dbt test
       - name: Check docs coverage
         run: |
           dbt run

models/enrollment/schema.yml

@@ -27,7 +27,7 @@ models:
         description: "The mode of enrollment"
       - name: enrollment_status
         description: "Whether a learner is actively enrolled in a course"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["registered", "unregistered"]
         data_type: String
@@ -84,7 +84,7 @@ models:
       - name: enrollment_status
         data_type: string
         description: "Whether a learner is actively enrolled in a course"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["registered", "unregistered"]
       - name: enrollment_mode

models/grading/schema.yml

@@ -30,7 +30,7 @@ models:
         description: "The entity's display name with section, subsection, and unit prepended to the name. This provides additional context when looking at block names and can help data consumers understand which block they are analyzing"
       - name: grade_type
         description: "The type of object graded"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["course", "subsection", "problem"]
         data_type: Nullable(String)
@@ -91,7 +91,7 @@ models:
       - name: approving_state
         data_type: string
         description: "The most recent approving_state of the learner's grade"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["passed", "failed"]
 
@@ -149,7 +149,7 @@ models:
         description: "The mode of enrollment"
       - name: enrollment_status
         description: "Whether a learner is actively enrolled in a course"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["registered", "unregistered"]
       - name: course_grade

models/instance/schema.yml

@@ -49,9 +49,10 @@ models:
       - name: enrollment_status
         data_type: string
         description: "The type of enrollment event  (ex: registered, unregistered)"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values: [ "registered", "unregistered" ]
+              table: 'xapi.fact_instance_enrollments'
       - name: course_enrollment_mode_status_cnt
         data_type: int
         description: "The number of enrollment events for this mode that occurred in the given hour"

models/learners/schema.yml

@@ -27,7 +27,7 @@ models:
         description: "The mode of enrollment"
       - name: enrollment_status
         description: "Whether a learner is actively enrolled in a course"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["registered", "unregistered"]
       - name: course_grade

models/navigation/schema.yml

@@ -102,7 +102,7 @@ models:
       - name: rollup_name
         data_type: string
         description: "The level at which page views are counted"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["section", "subsection"]
       - name: block_name
@@ -234,7 +234,7 @@ models:
       - name: content_level
         data_type: string
         description: "The level at which page views are counted"
-        tests:
+        data_tests:
           - accepted_values:
               values: ["section", "subsection"]
       - name: actor_id
@@ -287,12 +287,13 @@ models:
       - name: engagement_level
         data_type: string
         description: "The engagement level of the learner with the section"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values:
-                - 'No problems attempted yet'
-                - 'All problems attempted'
-                - 'At least one problem attempted'
+                - 'No pages viewed yet'
+                - 'All pages viewed'
+                - 'At least one page viewed'
+              table: 'xapi.section_page_engagement'
 
   - name: subsection_page_engagement
     description: "A record per course per subsection per learner with their engagement level"
@@ -312,9 +313,10 @@ models:
       - name: engagement_level
         data_type: string
         description: "The engagement level of the learner with the subsection"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values:
                 - 'No pages viewed yet'
                 - 'All pages viewed'
                 - 'At least one page viewed'
+              table: 'xapi.subsection_page_engagement'

models/problems/schema.yml

@@ -30,12 +30,12 @@ models:
         description: "The xAPI actor identifier"
       - name: success
         description: "The result of the last submission"
-        tests:
+        data_tests:
           - not_null
         data_type: Bool
       - name: attempts
         description: "The number of attempts made"
-        tests:
+        data_tests:
           - not_null
         data_type: Int16
       - name: num_hints_displayed
@@ -361,7 +361,7 @@ models:
       - name: section_subsection_problem_engagement
         data_type: string
         description: "The engagement level of the learner with the section/subsection"
-        tests:
+        data_tests:
           - accepted_values:
               values:
                 - 'No problems attempted yet'
@@ -488,12 +488,13 @@ models:
       - name: engagement_level
         data_type: string
         description: "The engagement level of the learner with the section"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values:
                 - 'No problems attempted yet'
                 - 'All problems attempted'
                 - 'At least one problem attempted'
+              table: 'xapi.section_problem_engagement'
 
   - name: subsection_problem_engagement
     description: "A record per course per subsection per learner with their engagement level"
@@ -513,9 +514,10 @@ models:
       - name: engagement_level
         data_type: string
         description: "The engagement level of the learner with the subsection"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values:
                 - 'No problems attempted yet'
                 - 'All problems attempted'
                 - 'At least one problem attempted'
+              table: 'xapi.subsection_problem_engagement'

models/video/schema.yml

@@ -225,7 +225,7 @@ models:
       - name: content_level
         data_type: string
         description: "The content level of the video"
-        tests:
+        data_tests:
           - accepted_values:
               values:
                 - 'section'
@@ -236,7 +236,7 @@ models:
       - name: section_subsection_video_engagement
         data_type: string
         description: "The engagement level of the learner with the video"
-        tests:
+        data_tests:
           - accepted_values:
               values:
                 - 'No videos viewed yet'
@@ -326,12 +326,13 @@ models:
       - name: engagement_level
         data_type: string
         description: "The engagement level of the learner with the section"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values:
                 - 'No videos viewed yet'
                 - 'All videos viewed'
                 - 'At least one video viewed'
+              table: 'xapi.section_video_engagement'
 
   - name: subsection_video_engagement
     description: "A record per course per subsection per learner with their engagement level"
@@ -351,46 +352,10 @@ models:
       - name: engagement_level
         data_type: string
         description: "The engagement level of the learner with the subsection"
-        tests:
-          - accepted_values:
+        data_tests:
+          - accepted_values_xapi:
               values:
                 - 'No videos viewed yet'
                 - 'All videos viewed'
                 - 'At least one video viewed'
-
-  - name: watched_video_segments
-    description: "A dataset with one record per learner per video segment watched in a course"
-    columns:
-      - name: org
-        data_type: string
-        description: "The organization that the course belongs to"
-      - name: course_key
-        data_type: string
-        description: "The course key for the course"
-      - name: actor_id
-        data_type: string
-        description: "The xAPI actor identifier"
-      - name: video_id
-        data_type: string
-        description: "The xAPI object identifier"
-      - name: start_position
-        data_type: int64
-        description: "The start position of the segment"
-      - name: end_position
-        data_type: int64
-        description: "The end position of the segment"
-      - name: started_at
-        data_type: datetime
-        description: "The time the video segment was started"
-      - name: ended_at
-        data_type: datetime
-        description: "The time the video segment was ended"
-      - name: emission_time
-        data_type: datetime
-        description: "The time the event was emitted"
-      - name: end_type
-        data_type: string
-        description: "The type of event that ended the video segment"
-      - name: video_duration
-        data_type: int64
-        description: "The duration of the video in seconds"
+              table: 'xapi.subsection_video_engagement'

package-lock.yml

@@ -1,6 +1,6 @@
 packages:
-- package: dbt-labs/codegen
-  version: 0.11.0
-- package: dbt-labs/dbt_utils
-  version: 1.1.0
-sha1_hash: 97b4306bc75da556cd002412ddf08f036472221b
+  - package: dbt-labs/codegen
+    version: 0.12.1
+  - package: dbt-labs/dbt_utils
+    version: 1.1.1
+sha1_hash: d974113b0f072cce35300077208f38581075ab40

tests/generic/test_accepted_values_xapi.sql

@@ -0,0 +1,34 @@
+{% test accepted_values_xapi(model, column_name, values, table, quote=True) %}
+
+with all_values as (
+
+    select distinct
+        {{ column_name }} as value_field
+
+    from {{ table }}
+
+),
+
+validation_errors as (
+
+    select
+        value_field
+
+    from all_values
+    where value_field not in (
+        {% for value in values -%}
+            {% if quote -%}
+            '{{ value }}'
+            {%- else -%}
+            {{ value }}
+            {%- endif -%}
+            {%- if not loop.last -%},{%- endif %}
+        {%- endfor %}
+        )
+
+)
+
+select *
+from validation_errors
+
+{% endtest %}