Merge pull request #32 from SoryRawyer/rds/add-extended-block-name-docs

feat: add block name with location to models (FC-0033)

models/base/dim_course_blocks.sql

@@ -4,7 +4,8 @@ select
     courses.course_name as course_name,
     courses.course_run as course_run,
     blocks.location as block_id,
-    blocks.block_name as block_name
+    blocks.block_name as block_name,
+    blocks.display_name_with_location as display_name_with_location
 from
     {{ source('event_sink', 'course_block_names') }} blocks
     join {{ source('event_sink', 'course_names')}} courses

models/base/schema.yml

@@ -0,0 +1,21 @@
+version: 2
+
+models:
+  - name: dim_course_blocks
+    description: "A denormalized table of course block information"
+    columns:
+      - name: org
+        data_type: String
+      - name: course_key
+        data_type: String
+      - name: course_name
+        data_type: String
+      - name: course_run
+        data_type: String
+      - name: block_id
+        data_type: String
+      - name: block_name
+        data_type: String
+      - name: display_name_with_location
+        data_type: String
+        description: "The block'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"

models/base/sources.yml

@@ -85,7 +85,7 @@ sources:
           - name: org
           - name: verb_id
           - name: scaled_score
-      
+
       - name: completions_events
         identifier: "{{ env_var('ASPECTS_COMPLETION_EVENTS_TABLE', 'completion_events') }}"
         columns:
@@ -117,6 +117,8 @@ sources:
           - name: location
           - name: block_name
           - name: course_key
+          - name: graded
+          - name: display_name_with_location
 
       - name: course_names
         columns:

models/completion/fact_completions.sql

@@ -23,6 +23,7 @@ select
     courses.course_run as course_run,
     completions.entity_id as entity_id,
     if(blocks.block_name != '', blocks.block_name, courses.course_name) as entity_name,
+    if(blocks.block_name != '', blocks.display_name_with_location, null) as entity_name_with_location,
     completions.actor_id as actor_id,
     cast(completions.scaled_progress as Float) as scaled_progress,
     case

models/completion/schema.yml

@@ -2,19 +2,32 @@ version: 2
 
 models:
   - name: fact_completions
+    database: "{{ env_var('DBT_PROFILE_TARGET_DATABASE', 'reporting') }}"
     description: "One record per completion events for component"
     columns:
       - name: emission_time
         description: "Timestamp, to the second, of when this event was emitted"
+        data_type: DateTime64(3)
       - name: org
+        data_type: String
       - name: course_key
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: entity_id
         description: "The block ID or course key for the graded entity"
+        data_type: String
       - name: entity_name
+        data_type: String
+      - name: entity_name_with_location
+        data_type: Nullable(String)
       - name: actor_id
-      - name: progress_percent
+        data_type: String
+      - name: scaled_progress
         description: "A ratio between 0 and 1, inclusive, of the learner's progress"
+        data_type: Float32
       - 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

models/enrollment/schema.yml

@@ -6,13 +6,20 @@ models:
     columns:
       - name: emission_time
         description: "Timestamp, to the second, of when this event was emitted"
+        data_type: DateTime
       - name: org
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: actor_id
+        data_type: String
       - name: enrollment_mode
+        data_type: LowCardinality(String)
       - name: enrollment_status
         description: "Whether a learner is actively enrolled in a course"
         tests:
           - accepted_values:
               values: ["registered", "unregistered"]
+        data_type: String

models/forum/schema.yml

@@ -0,0 +1,24 @@
+version: 2
+
+models:
+  - name: fact_forum_interactions
+    description: "One record per forum interaction"
+    columns:
+      - name: event_id
+        data_type: UUID
+      - name: emission_time
+        data_type: DateTime64(3)
+      - name: org
+        data_type: String
+      - name: course_key
+        data_type: String
+      - name: course_name
+        data_type: String
+      - name: course_run
+        data_type: String
+      - name: object_id
+        data_type: String
+      - name: actor_id
+        data_type: String
+      - name: verb_id
+        data_type: LowCardinality(String)

models/grading/fact_grades.sql

@@ -27,6 +27,7 @@ select
     courses.course_run as course_run,
     grades.entity_id as entity_id,
     if(blocks.block_name != '', blocks.block_name, courses.course_name) as entity_name,
+    if(blocks.block_name != '', blocks.display_name_with_location, null) as entity_name_with_location,
     grades.grade_type as grade_type,
     grades.actor_id as actor_id,
     cast(grades.scaled_score as Float) as scaled_score,

models/grading/schema.yml

@@ -6,20 +6,33 @@ models:
     columns:
       - name: emission_time
         description: "Timestamp, to the second, of when this event was emitted"
+        data_type: DateTime64(3)
       - name: org
+        data_type: String
       - name: course_key
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: entity_id
         description: "The block ID or course key for the graded entity"
+        data_type: String
       - name: entity_name
+        data_type: String
+      - name: entity_name_with_location
+        data_type: Nullable(String)
       - name: grade_type
         description: "The type of object graded"
         tests:
           - accepted_values:
               values: ["course", "subsection", "problem"]
+        data_type: Nullable(String)
       - name: actor_id
+        data_type: String
       - name: scaled_score
         description: "A ratio between 0 and 1, inclusive, of the learner's grade"
+        data_type: Float32
       - 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

models/problems/fact_learner_problem_summary.sql

@@ -8,6 +8,7 @@ with results_with_hints as (
         course_run,
         problem_id,
         problem_name,
+        problem_name_with_location,
         actor_id,
         success,
         attempts,
@@ -22,6 +23,7 @@ with results_with_hints as (
         course_run,
         problem_id,
         problem_name,
+        problem_name_with_location,
         actor_id,
         null as success,
         null as attempts,
@@ -47,6 +49,7 @@ select
     course_run,
     problem_id,
     problem_name,
+    problem_name_with_location,
     actor_id,
     coalesce(any(success), false) as success,
     coalesce(any(attempts), 0) as attempts,
@@ -61,4 +64,5 @@ group by
     course_run,
     problem_id,
     problem_name,
+    problem_name_with_location,
     actor_id

models/problems/fact_problem_responses.sql

@@ -22,6 +22,7 @@ select
     blocks.course_run as course_run,
     responses.problem_id as problem_id,
     blocks.block_name as problem_name,
+    blocks.display_name_with_location as problem_name_with_location,
     responses.actor_id as actor_id,
     responses.responses as responses,
     responses.success as success,

models/problems/int_problem_hints.sql

@@ -24,6 +24,7 @@ select
     blocks.course_run as course_run,
     hints.problem_id as problem_id,
     blocks.block_name as problem_name,
+    blocks.display_name_with_location as problem_name_with_location,
     hints.actor_id as actor_id,
     hints.help_type as help_type
 from

models/problems/int_problem_results.sql

@@ -71,6 +71,7 @@ select
     course_run,
     problem_id,
     problem_name,
+    problem_name_with_location,
     actor_id,
     responses,
     success,

models/problems/schema.yml

@@ -5,39 +5,65 @@ models:
     description: "One record per learner per problem in a course"
     columns:
       - name: org
+        data_type: String
       - name: course_key
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: problem_id
+        data_type: String
       - name: problem_name
+        data_type: String
+      - name: problem_name_with_location
+        data_type: String
       - name: actor_id
+        data_type: String
       - name: success
         description: "The result of the last submission"
         tests:
           - not_null
+        data_type: Bool
       - name: attempts
         description: "The number of attempts made"
         tests:
           - not_null
+        data_type: Int16
       - name: num_hints_displayed
         description: "The number of times a learner asked for a hint"
+        data_type: UInt64
       - name: num_answers_displayed
         description: "The number of times a learner requested the answers for the problem"
+        data_type: UInt64
 
   - name: fact_problem_responses
     description: "One record for each submitted response to a problem"
     columns:
       - name: emission_time
+        data_type: DateTime
       - name: org
+        data_type: String
       - name: course_key
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: problem_id
+        data_type: String
       - name: problem_name
+        data_type: String
+      - name: problem_name_with_location
+        data_type: String
       - name: actor_id
+        data_type: String
       - name: responses
         description: "The responses for this submission. If a problem has multiple parts, values for all parts will be in this field"
+        data_type: String
       - name: success
         description: "Boolean indicating whether the responses were correct"
+        data_type: Bool
       - name: attempts
         description: "Number indicating which attempt this was"
+        data_type: Int16

models/video/fact_transcript_usage.sql

@@ -20,6 +20,7 @@ select
     blocks.course_run as course_run,
     transcripts.video_id as video_id,
     blocks.block_name as video_name,
+    blocks.display_name_with_location as video_name_with_location,
     transcripts.actor_id as actor_id
 from
     transcripts

models/video/fact_video_plays.sql

@@ -21,6 +21,7 @@ select
     blocks.course_run as course_run,
     plays.video_id as video_id,
     blocks.block_name as video_name,
+    blocks.display_name_with_location as video_name_with_location,
     plays.actor_id as actor_id
 from
     plays

models/video/schema.yml

@@ -5,22 +5,42 @@ models:
     description: "One record for each time a learner played a video"
     columns:
       - name: emission_time
+        data_type: DateTime
       - name: org
+        data_type: String
       - name: course_key
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: video_id
+        data_type: String
       - name: video_name
+        data_type: String
+      - name: video_name_with_location
+        data_type: String
       - name: actor_id
+        data_type: String
 
   - name: fact_transcript_usage
     description: "One record for each time a transcript or closed caption was enabled"
     columns:
       - name: emission_time
+        data_type: DateTime
       - name: org
+        data_type: String
       - name: course_key
+        data_type: String
       - name: course_name
+        data_type: String
       - name: course_run
+        data_type: String
       - name: video_id
+        data_type: String
       - name: video_name
+        data_type: String
+      - name: video_name_with_location
+        data_type: String
       - name: actor_id
+        data_type: String

packages.yml

@@ -1,5 +1,5 @@
 packages:
   - package: dbt-labs/codegen
-    version: 0.9.0
+    version: 0.11.0
   - package: dbt-labs/dbt_utils
     version: 1.1.0