Merge pull request #70 from openedx/cag/user-information

feat: join user_pii data with reports

models/completion/fact_completions.sql

@@ -48,8 +48,14 @@ select
         when scaled_progress >= 0.1 and scaled_progress < 0.2
         then '10-19%'
         else '0-9%'
-    end as completion_bucket
+    end as completion_bucket,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from completions
 join {{ ref("course_names") }} courses on completions.course_key = courses.course_key
 left join
     {{ ref("course_block_names") }} blocks on completions.entity_id = blocks.location
+left outer join
+    {{ ref("dim_user_pii") }} users
+    on toUUID(completions.actor_id) = users.external_user_id

models/completion/schema.yml

@@ -38,6 +38,15 @@ models:
       - name: completion_bucket
         description: "A displayable value of progress sorted into 10% buckets. Useful for grouping progress together to show high-level learner performance"
         data_type: String
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: completion_events
     description: "A materialized view for xAPI events related to course completions"

models/enrollment/fact_enrollments.sql

@@ -18,6 +18,11 @@ select
     courses.course_run as course_run,
     enrollments.actor_id as actor_id,
     enrollments.enrollment_mode as enrollment_mode,
-    enrollments.enrollment_status as enrollment_status
+    enrollments.enrollment_status as enrollment_status,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from enrollments
 join {{ ref("course_names") }} courses on enrollments.course_key = courses.course_key
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/enrollment/schema.yml

@@ -31,6 +31,15 @@ models:
           - accepted_values:
               values: ["registered", "unregistered"]
         data_type: String
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: enrollment_events
     description: "A materialized view for xAPI events related to course enrollment"

models/forum/fact_forum_interactions.sql

@@ -7,6 +7,11 @@ select
     courses.course_run as course_run,
     forum.object_id as object_id,
     forum.actor_id as actor_id,
-    forum.verb_id as verb_id
+    forum.verb_id as verb_id,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from {{ ref("forum_events") }} forum
 join {{ ref("course_names") }} courses on (forum.course_key = courses.course_key)
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/forum/schema.yml

@@ -31,6 +31,15 @@ models:
       - name: verb_id
         data_type: LowCardinality(String)
         description: "The xAPI verb identifier"
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: forum_events
     description: "One record per forum event"

models/grading/fact_grades.sql

@@ -41,7 +41,12 @@ select
     grades.grade_type as grade_type,
     grades.actor_id as actor_id,
     grades.scaled_score as scaled_score,
-    {{ get_bucket("scaled_score") }} as grade_bucket
+    {{ get_bucket("scaled_score") }} as grade_bucket,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from grades
 join {{ ref("course_names") }} courses on grades.course_key = courses.course_key
 left join {{ ref("course_block_names") }} blocks on grades.entity_id = blocks.location
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/grading/fact_student_status.sql

@@ -8,7 +8,10 @@ select
     enrollment_mode,
     enrollment_status,
     course_grade as course_grade,
-    {{ get_bucket("course_grade") }} as grade_bucket
+    {{ get_bucket("course_grade") }} as grade_bucket,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from {{ ref("fact_enrollment_status") }} fes
 left join
     {{ ref("fact_learner_course_status") }} lg
@@ -24,3 +27,5 @@ join
     {{ ref("course_names") }} courses
     on fes.org = courses.org
     and fes.course_key = courses.course_key
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/grading/schema.yml

@@ -43,6 +43,15 @@ models:
       - name: grade_bucket
         description: "A displayable value of grades sorted into 10% buckets. Useful for grouping grades together to show high-level learner performance"
         data_type: String
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: fact_learner_course_grade
     description: "One record per learner per course for the most recent grade"
@@ -149,3 +158,12 @@ models:
       - name: grade_bucket
         data_type: string
         description: "A displayable value of grades sorted into 10% buckets. Useful for grouping grades together to show high-level learner performance"
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"

models/navigation/fact_navigation.sql

@@ -10,11 +10,16 @@ select
     blocks.display_name_with_location as block_name_with_location,
     navigation.object_type as object_type,
     navigation.starting_position as starting_position,
-    navigation.ending_point as ending_point
+    navigation.ending_point as ending_point,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from {{ ref("navigation_events") }} navigation
 join
     {{ ref("dim_course_blocks") }} blocks
     on (
         navigation.course_key = blocks.course_key
         and navigation.block_id = blocks.block_id
     )
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/navigation/fact_navigation_completion.sql

@@ -5,6 +5,7 @@ with
             date(emission_time) as visited_on,
             org,
             course_key,
+            course_name,
             course_run,
             {{ section_from_display("block_name_with_location") }} as section_number,
             {{ subsection_from_display("block_name_with_location") }}
@@ -15,15 +16,19 @@ with
     )
 
 select
-    visits.visited_on,
-    visits.org,
-    visits.course_key,
-    visits.course_run,
-    pages.section_with_name,
-    pages.subsection_with_name,
-    pages.page_count,
-    visits.actor_id,
-    visits.block_id
+    visits.visited_on as visited_on,
+    visits.org as org,
+    visits.course_key as course_key,
+    visits.course_name as course_name,
+    visits.course_run as course_run,
+    pages.section_with_name as section_with_name,
+    pages.subsection_with_name as subsection_with_name,
+    pages.page_count as page_count,
+    visits.actor_id as actor_id,
+    visits.block_id as block_id,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from visited_subsection_pages visits
 join
     {{ ref("int_pages_per_subsection") }} pages
@@ -33,3 +38,5 @@ join
         and visits.section_number = pages.section_number
         and visits.subsection_number = pages.subsection_number
     )
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/navigation/fact_navigation_dropoff.sql

@@ -64,7 +64,10 @@ select
     page_views.rollup_name as rollup_name,
     blocks.display_name_with_location as block_name,
     page_views.actor_id as actor_id,
-    page_views.total_views as total_views
+    page_views.total_views as total_views,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from page_views
 join
     blocks
@@ -73,3 +76,5 @@ join
         and page_views.course_key = blocks.course_key
         and page_views.hierarchy_location = blocks.hierarchy_location
     )
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/navigation/schema.yml

@@ -74,6 +74,15 @@ models:
       - name: ending_point
         data_type: string
         description: "The tab in the unit navigation bar that the learner selected to navigate to"
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: fact_navigation_dropoff
     description: "A view for analyzing the number of page visits per learner per section and subsection"
@@ -102,6 +111,15 @@ models:
       - name: total_views
         data_type: uint64
         description: "The total number of times a learner viewed pages in this section or subsection on a given day"
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: fact_navigation_completion
     description: "A view for analyzing how many pages a learner has visited in a section or subsection"
@@ -115,9 +133,9 @@ models:
       - name: course_key
         data_type: string
         description: "The course identifier"
-      - name: course_run
+      - name: course_name
         data_type: string
-        description: "The course run for the course"
+        description: "The course name"
       - name: course_run
         data_type: string
         description: "The course run for the course"
@@ -136,6 +154,15 @@ models:
       - name: block_id
         data_type: string
         description: "The ID of the specific page visited"
+      - name: username
+        data_type: String
+        description: "The username of the learner"
+      - name: name
+        data_type: String
+        description: "The full name of the learner"
+      - name: email
+        data_type: String
+        description: "The email address of the learner"
 
   - name: int_pages_per_subsection
     description: "A view for analyzing the number of pages in each subsection"

models/problems/fact_learner_problem_summary.sql

@@ -49,8 +49,13 @@ select
     coalesce(any(success), false) as success,
     coalesce(any(attempts), 0) as attempts,
     sum(num_hints_displayed) as num_hints_displayed,
-    sum(num_answers_displayed) as num_answers_displayed
+    sum(num_answers_displayed) as num_answers_displayed,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from results_with_hints
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id
 group by
     org,
     course_key,
@@ -59,4 +64,7 @@ group by
     problem_id,
     problem_name,
     problem_name_with_location,
-    actor_id
+    actor_id,
+    username,
+    name,
+    email

models/problems/fact_problem_engagement.sql

@@ -15,16 +15,19 @@ with
     )
 
 select
-    attempts.attempted_on,
-    attempts.org,
-    attempts.course_key,
-    attempts.course_run,
-    problems.section_with_name,
-    problems.subsection_with_name,
-    problems.item_count,
-    attempts.actor_id,
-    attempts.problem_id,
-    attempts.graded
+    attempts.attempted_on as attempted_on,
+    attempts.org as org,
+    attempts.course_key as course_key,
+    attempts.course_run as course_run,
+    problems.section_with_name as section_with_name,
+    problems.subsection_with_name as subsection_with_name,
+    problems.item_count as item_count,
+    attempts.actor_id as actor_id,
+    attempts.problem_id as problem_id,
+    attempts.graded as graded,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from attempted_subsection_problems attempts
 join
     {{ ref("int_problems_per_subsection") }} problems
@@ -34,3 +37,5 @@ join
         and attempts.section_number = problems.section_number
         and attempts.subsection_number = problems.subsection_number
     )
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id

models/problems/fact_problem_responses.sql

@@ -30,14 +30,19 @@ select
     responses.responses as responses,
     responses.success as success,
     responses.attempts as attempts,
-    responses.interaction_type as interaction_type
+    responses.interaction_type as interaction_type,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from responses
 join
     {{ ref("dim_course_blocks") }} blocks
     on (
         responses.course_key = blocks.course_key
         and responses.problem_id = blocks.block_id
     )
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id
 group by
     -- multi-part questions include an extra record for the response to the first
     -- part of the question. this group by clause eliminates the duplicate record
@@ -55,4 +60,7 @@ group by
     success,
     attempts,
     graded,
-    interaction_type
+    interaction_type,
+    username,
+    name,
+    email

models/problems/fact_problem_responses_extended.sql

@@ -24,7 +24,10 @@ select
     results.success as success,
     results.attempts as attempts,
     results.graded as graded,
-    results.interaction_type as interaction_type
+    results.interaction_type as interaction_type,
+    users.username as username,
+    users.name as name,
+    users.email as email
 from problem_results results
 join
     {{ ref("int_problems_per_subsection") }} problems
@@ -34,3 +37,5 @@ join
         and results.section_number = problems.section_number
         and results.subsection_number = problems.subsection_number
     )
+left outer join
+    {{ ref("dim_user_pii") }} users on toUUID(actor_id) = users.external_user_id