DQ Changes for Streamlit

integration_tests/dbt_project.yml

@@ -8,7 +8,7 @@ vars:
   error_empty_seeds: true
   ## Use this variable to run the project with synthetic data loaded as seeds
   # otherwise set to false and set the input vars below
-  use_synthetic_data: false
+  use_synthetic_data: true
 
   ## Update these vars to use your own data as input, do not comment out
   # enabled logic has been added to the sources config

models/data_quality/final/data_quality__analytics_checks_summary.sql

@@ -22,7 +22,7 @@ with unioned_data as (
 
 select
   data_quality_check
-  , result_count
+  , coalesce(result_count,0) as result_count
   , coalesce(normally_zero ,1) as normally_zero
   , '{{ var('tuva_last_run')}}' as tuva_last_run
 from unioned_data

models/data_quality/final/data_quality__claim_date_trends.sql

@@ -150,13 +150,13 @@ with date_stage as(
 
 select
     cast(all_date.year_month as {{ dbt.type_int() }} ) as year_month
-    , claim_start.result_count as claim_start_date
-    , claim_end.result_count as claim_end_date
-    , admission_date.result_count as admission_date
-    , discharge_date.result_count as discharge_date
-    , med_paid_date.result_count as medical_paid_date
-    , dispensing_date.result_count as dispensing_date
-    , pharm_paid_date.result_count as pharmacy_paid_date
+    , coalesce(claim_start.result_count,0) as claim_start_date
+    , coalesce(claim_end.result_count,0) as claim_end_date
+    , coalesce(admission_date.result_count,0) as admission_date
+    , coalesce(discharge_date.result_count,0) as discharge_date
+    , coalesce(med_paid_date.result_count,0) as medical_paid_date
+    , coalesce(dispensing_date.result_count,0) as dispensing_date
+    , coalesce(pharm_paid_date.result_count,0) as pharmacy_paid_date
     , '{{ var('tuva_last_run')}}' as tuva_last_run
 from all_date_range all_date
 left join date_stage claim_start

models/data_quality/intermediate/data_quality__chronic_conditions_prevalence.sql

@@ -41,10 +41,10 @@ cross join total_patients
 select
     ref_data.analytics_concept
     , coalesce(results.condition, ref_data.analytics_measure) as analytics_measure
-    , results.patients
-    , results.condition_rank as value_rank
-    , results.percent_of_total as data_source_value
+    , coalesce(results.patients,0) as patients
+    , coalesce(results.percent_of_total,0) as data_source_value
     , ref_data.analytics_value
+    , coalesce(results.condition_rank,0) as value_rank
     , ref_data.value_rank as medicare_lds_condition_rank
     , '{{ var('tuva_last_run') }}' as tuva_last_run
 from {{ ref('data_quality__reference_mart_analytics') }}  ref_data

models/data_quality/intermediate/data_quality__dx_and_px.sql

@@ -407,37 +407,37 @@ with unpivot_diagnosis as(
 
 , final as (
     select cast(data_quality_check as {{ dbt.type_string() }} ) as data_quality_check
-    ,result_count
+    , cast( result_count as {{ dbt.type_int() }}) as result_count
     from missing_primary_dx
 
     union all
 
     select cast(data_quality_check as {{ dbt.type_string() }} ) as data_quality_check
-    ,result_count
+    , cast( result_count as {{ dbt.type_int() }}) as result_count
     from invalid_primary_dx
 
     union all
 
     select cast(data_quality_check as {{ dbt.type_string() }} ) as data_quality_check
-    ,result_count
+    , cast( result_count as {{ dbt.type_int() }}) as result_count
     from multiple_primary_dx
 
     union all
 
     select cast(data_quality_check as {{ dbt.type_string() }} ) as data_quality_check
-    ,result_count
+    , cast( result_count as {{ dbt.type_int() }}) as result_count
     from invalid_secondary_dx
 
     union all
 
     select cast(data_quality_check as {{ dbt.type_string() }} ) as data_quality_check
-    ,result_count
+    , cast( result_count as {{ dbt.type_int() }}) as result_count
     from claims_with_secondary_dx
 
     union all
 
     select cast(data_quality_check as {{ dbt.type_string() }} ) as data_quality_check
-    ,result_count
+    , cast( result_count as {{ dbt.type_int() }}) as result_count
     from invalid_procedure
 )
 

models/data_quality/intermediate/data_quality__encounters_missing_groups.sql

@@ -19,9 +19,12 @@ with expected_groups as (
 )
 
 select
-    e.encounter_group as missing_encounter_group
+    a.encounter_group
+    , case
+        when a.encounter_group is null then 'missing'
+      else 'populated'
+    end as missing_encounter_group
     , '{{ var('tuva_last_run') }}' as tuva_last_run
 from expected_groups e
-    left join actual_groups a
-        on e.encounter_group = a.encounter_group
-where a.encounter_group is null
+left join actual_groups a
+    on e.encounter_group = a.encounter_group