turn supervision_officer_attribute_sessions into supervision_staff_at…

…tribute_sessions (Recidiviz/recidiviz-data#29335)

## Description of the change

Renamed the file and view, and added WHERE clauses to downstream views
to do the `role_type` filtering that
`supervision_officer_attribute_sessions` was doing. This allows us to
more easily query staff information for users who don't have an ingested
role_type (for example, getting information for specialists who are not
technically officers into the workflows supervision_staff_record).

Will post the sandbox prefix once it's done loading!

## Type of change

> All pull requests must have at least one of the following labels
applied (otherwise the PR will fail):

| Label | Description |
|-----------------------------
|-----------------------------------------------------------------------------------------------------------
|
| Type: Bug | non-breaking change that fixes an issue |
| Type: Feature | non-breaking change that adds functionality |
| Type: Breaking Change | fix or feature that would cause existing
functionality to not work as expected |
| Type: Non-breaking refactor | change addresses some tech debt item or
prepares for a later change, but does not change functionality |
| Type: Configuration Change | adjusts configuration to achieve some end
related to functionality, development, performance, or security |
| Type: Dependency Upgrade | upgrades a project dependency - these
changes are not included in release notes |

## Related issues

Closes Recidiviz/recidiviz-data#29066

## Checklists

### Development

**This box MUST be checked by the submitter prior to merging**:
- [x] **Double- and triple-checked that there is no Personally
Identifiable Information (PII) being mistakenly added in this pull
request**

These boxes should be checked by the submitter prior to merging:
- [ ] Tests have been written to cover the code changed/added as part of
this pull request

### Code review

These boxes should be checked by reviewers prior to merging:

- [ ] This pull request has a descriptive title and information useful
to a reviewer
- [ ] Potential security implications or infrastructural changes have
been considered, if relevant

GitOrigin-RevId: 0fd8c4ae7e5b19e95705af59e7ac9f57393a81cf

recidiviz/aggregated_metrics/misc_aggregated_metrics.py

@@ -145,11 +145,12 @@ def _query_template_and_format_args(
         FROM
             `{{project_id}}.aggregated_metrics.supervision_officer_aggregated_metrics_materialized` a
         INNER JOIN
-            `{{project_id}}.sessions.supervision_officer_attribute_sessions_materialized` b
+            `{{project_id}}.sessions.supervision_staff_attribute_sessions_materialized` b
         ON
             a.state_code = b.state_code
             AND a.officer_id = b.officer_id
-            AND a.end_date BETWEEN b.start_date AND {nonnull_end_date_exclusive_clause("b.end_date_exclusive")},
+            AND a.end_date BETWEEN b.start_date AND {nonnull_end_date_exclusive_clause("b.end_date_exclusive")}
+            AND "SUPERVISION_OFFICER" IN UNNEST(b.role_type_array),
         
         UNNEST(supervisor_staff_id_array) AS supervisor_staff_id
     )

recidiviz/calculator/query/state/views/analyst_data/models/metric_unit_of_analysis_type.py

@@ -243,7 +243,10 @@ def get_index_columns_query_string(self, prefix: Optional[str] = None) -> str:
     (
         MetricUnitOfObservationType.SUPERVISION_OFFICER,
         MetricUnitOfAnalysisType.SUPERVISION_OFFICER,
-    ): """SELECT * FROM `{project_id}.sessions.supervision_officer_attribute_sessions_materialized`""",
+    ): """
+SELECT * FROM `{project_id}.sessions.supervision_staff_attribute_sessions_materialized`
+WHERE "SUPERVISION_OFFICER" IN UNNEST(role_type_array)
+""",
     (
         MetricUnitOfObservationType.SUPERVISION_OFFICER,
         MetricUnitOfAnalysisType.SUPERVISION_OFFICE,
@@ -252,14 +255,17 @@ def get_index_columns_query_string(self, prefix: Optional[str] = None) -> str:
     supervision_office_id AS office,
     supervision_district_id AS district,
 FROM
-    `{project_id}.sessions.supervision_officer_attribute_sessions_materialized`""",
+    `{project_id}.sessions.supervision_staff_attribute_sessions_materialized`
+WHERE "SUPERVISION_OFFICER" IN UNNEST(role_type_array)
+""",
     (
         MetricUnitOfObservationType.SUPERVISION_OFFICER,
         MetricUnitOfAnalysisType.SUPERVISION_DISTRICT,
     ): """SELECT
     *, supervision_district_id AS district,
 FROM
-    `{project_id}.sessions.supervision_officer_attribute_sessions_materialized`
+    `{project_id}.sessions.supervision_staff_attribute_sessions_materialized`
+WHERE "SUPERVISION_OFFICER" IN UNNEST(role_type_array)
 """,
     (
         MetricUnitOfObservationType.SUPERVISION_OFFICER,
@@ -268,13 +274,17 @@ def get_index_columns_query_string(self, prefix: Optional[str] = None) -> str:
     *, 
     supervisor_staff_id AS unit_supervisor,
 FROM
-    `{project_id}.sessions.supervision_officer_attribute_sessions_materialized`,
+    `{project_id}.sessions.supervision_staff_attribute_sessions_materialized`,
     UNNEST(supervisor_staff_id_array) AS supervisor_staff_id
+WHERE "SUPERVISION_OFFICER" IN UNNEST(role_type_array)
 """,
     (
         MetricUnitOfObservationType.SUPERVISION_OFFICER,
         MetricUnitOfAnalysisType.STATE_CODE,
-    ): """SELECT * FROM `{project_id}.sessions.supervision_officer_attribute_sessions_materialized`""",
+    ): """
+SELECT * FROM `{project_id}.sessions.supervision_staff_attribute_sessions_materialized`
+WHERE "SUPERVISION_OFFICER" IN UNNEST(role_type_array)
+""",
 }
 
 UNIT_OF_ANALYSIS_STATIC_ATTRIBUTE_COLS_QUERY_DICT: Dict[

recidiviz/calculator/query/state/views/outliers/staff_query_template.py

@@ -72,12 +72,13 @@ def staff_query_template(role: str) -> str:
         supervisor_external_id,
         attrs.specialized_caseload_type_primary AS specialized_caseload_type,
     FROM ({source_tbl}) supervision_staff
-    INNER JOIN `{{project_id}}.sessions.supervision_officer_attribute_sessions_materialized` attrs
+    INNER JOIN `{{project_id}}.sessions.supervision_staff_attribute_sessions_materialized` attrs
         ON attrs.state_code = supervision_staff.state_code AND attrs.officer_id = supervision_staff.external_id 
     LEFT JOIN UNNEST(attrs.supervisor_staff_external_id_array) AS supervisor_external_id
     INNER JOIN `{{project_id}}.normalized_state.state_staff` staff 
         ON attrs.staff_id = staff.staff_id AND attrs.state_code = staff.state_code
     WHERE staff.state_code = '{state}' 
+      AND "SUPERVISION_OFFICER" IN UNNEST(attrs.role_type_array)
       {f"AND {config.supervision_staff_exclusions}" if config.supervision_staff_exclusions else ""}
     -- Get the staff's attributes from the most recent session
     QUALIFY ROW_NUMBER() OVER(PARTITION BY attrs.state_code, attrs.officer_id ORDER BY COALESCE(attrs.end_date_exclusive, "9999-01-01") DESC) = 1

recidiviz/calculator/query/state/views/sessions/sessions_views.py

@@ -177,9 +177,6 @@
 from recidiviz.calculator.query.state.views.sessions.supervision_level_sessions import (
     SUPERVISION_LEVEL_SESSIONS_VIEW_BUILDER,
 )
-from recidiviz.calculator.query.state.views.sessions.supervision_officer_attribute_sessions import (
-    SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_BUILDER,
-)
 from recidiviz.calculator.query.state.views.sessions.supervision_officer_inferred_location_sessions import (
     SUPERVISION_OFFICER_INFERRED_LOCATION_SESSIONS_VIEW_BUILDER,
 )
@@ -189,6 +186,9 @@
 from recidiviz.calculator.query.state.views.sessions.supervision_projected_completion_date_spans import (
     SUPERVISION_PROJECTED_COMPLETION_DATE_SPANS_VIEW_BUILDER,
 )
+from recidiviz.calculator.query.state.views.sessions.supervision_staff_attribute_sessions import (
+    SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_BUILDER,
+)
 from recidiviz.calculator.query.state.views.sessions.supervision_super_sessions import (
     SUPERVISION_SUPER_SESSIONS_VIEW_BUILDER,
 )
@@ -343,7 +343,7 @@
     SUPERVISION_LEVEL_SESSIONS_VIEW_BUILDER,
     SUPERVISION_OFFICER_INFERRED_LOCATION_SESSIONS_VIEW_BUILDER,
     SUPERVISION_OFFICER_SESSIONS_VIEW_BUILDER,
-    SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_BUILDER,
+    SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_BUILDER,
     SUPERVISION_UNIT_SUPERVISOR_SESSIONS_VIEW_BUILDER,
     SUPERVISION_SUPER_SESSIONS_VIEW_BUILDER,
     SUPERVISION_TOOL_ACCESS_SESSIONS_VIEW_BUILDER,

recidiviz/calculator/query/state/views/sessions/supervision_officer_attribute_sessions.py → recidiviz/calculator/query/state/views/sessions/supervision_staff_attribute_sessions.py

@@ -30,17 +30,15 @@
 from recidiviz.utils.environment import GCP_PROJECT_STAGING
 from recidiviz.utils.metadata import local_project_id_override
 
-SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_NAME = (
-    "supervision_officer_attribute_sessions"
-)
+SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_NAME = "supervision_staff_attribute_sessions"
 
-SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_DESCRIPTION = """
+SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_DESCRIPTION = """
 View that preprocesses state staff periods to extract relevant attributes and external id's.
 """
 
 # All dictionary values below should specify a list of values by which to sort rows for deduplication.
 # All columns referenced in a given list should be queryable within the `sub_sessions_dedup` cte below.
-_SUPERVISION_OFFICER_ATTRIBUTES_NO_OVERLAPS: Dict[str, List[str]] = {
+_SUPERVISION_STAFF_ATTRIBUTES_NO_OVERLAPS: Dict[str, List[str]] = {
     "supervision_district_id": [],
     "supervision_district_name": [],
     "supervision_office_id": [],
@@ -52,7 +50,7 @@
     "supervision_office_id_inferred": [],
 }
 
-_SUPERVISION_OFFICER_ATTRIBUTES_WITH_OVERLAPS: Dict[str, List[str]] = {
+_SUPERVISION_STAFF_ATTRIBUTES_WITH_OVERLAPS: Dict[str, List[str]] = {
     "role_subtype": ["COALESCE(role_subtype_priority, 99)"],
     "role_type": [],
     "specialized_caseload_type": [],
@@ -63,7 +61,7 @@
     "supervisor_staff_id": ["supervisor_staff_external_id", "supervisor_staff_id"],
 }
 
-SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_QUERY_TEMPLATE = f"""
+SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_QUERY_TEMPLATE = f"""
 WITH all_staff_attribute_periods AS (
     -- location periods
     SELECT
@@ -217,12 +215,12 @@
         end_date AS end_date_exclusive,
         -- Apply an arbitrary dedup to attributes that we don't expect to overlap, mostly as an added protection
         {generate_largest_value_query_fragment(
-            table_columns_with_priority_columns=_SUPERVISION_OFFICER_ATTRIBUTES_NO_OVERLAPS, 
+            table_columns_with_priority_columns=_SUPERVISION_STAFF_ATTRIBUTES_NO_OVERLAPS, 
             partition_columns=["state_code", "staff_id", "start_date"],
         )},
         -- For attributes that might have overlap, dedup via the configured priority order and suffix with "_primary"
         {generate_largest_value_query_fragment(
-            table_columns_with_priority_columns=_SUPERVISION_OFFICER_ATTRIBUTES_WITH_OVERLAPS, 
+            table_columns_with_priority_columns=_SUPERVISION_STAFF_ATTRIBUTES_WITH_OVERLAPS, 
             partition_columns=["state_code", "staff_id", "start_date"],
             column_suffix="_primary"
         )},
@@ -247,7 +245,7 @@
         {list_to_query_string(
             [
                 f"ARRAY_AGG(DISTINCT {attr} IGNORE NULLS) AS {attr}_array"
-                for attr in _SUPERVISION_OFFICER_ATTRIBUTES_WITH_OVERLAPS
+                for attr in _SUPERVISION_STAFF_ATTRIBUTES_WITH_OVERLAPS
             ]
         )}
     FROM
@@ -260,7 +258,7 @@
 SELECT
     b.external_id AS officer_id,
     a.*,
-    {list_to_query_string([f"c.{attr}_array" for attr in _SUPERVISION_OFFICER_ATTRIBUTES_WITH_OVERLAPS])},
+    {list_to_query_string([f"c.{attr}_array" for attr in _SUPERVISION_STAFF_ATTRIBUTES_WITH_OVERLAPS])},
 FROM
     sub_sessions_dedup a
 LEFT JOIN
@@ -271,19 +269,17 @@
     attribute_arrays c
 USING
     (state_code, staff_id, start_date)
-WHERE
-    "SUPERVISION_OFFICER" IN UNNEST(role_type_array)
 """
 
-SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_BUILDER = SimpleBigQueryViewBuilder(
+SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_BUILDER = SimpleBigQueryViewBuilder(
     dataset_id=SESSIONS_DATASET,
-    view_id=SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_NAME,
-    view_query_template=SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_QUERY_TEMPLATE,
-    description=SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_DESCRIPTION,
+    view_id=SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_NAME,
+    view_query_template=SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_QUERY_TEMPLATE,
+    description=SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_DESCRIPTION,
     clustering_fields=["state_code", "staff_id"],
     should_materialize=True,
 )
 
 if __name__ == "__main__":
     with local_project_id_override(GCP_PROJECT_STAGING):
-        SUPERVISION_OFFICER_ATTRIBUTE_SESSIONS_VIEW_BUILDER.build_and_print()
+        SUPERVISION_STAFF_ATTRIBUTE_SESSIONS_VIEW_BUILDER.build_and_print()

recidiviz/calculator/query/state/views/sessions/supervision_unit_supervisor_sessions.py

@@ -55,13 +55,14 @@
         a.start_date,
         a.end_date_exclusive,
     FROM
-        `{{project_id}}.sessions.supervision_officer_attribute_sessions_materialized` a,
+        `{{project_id}}.sessions.supervision_staff_attribute_sessions_materialized` a,
     UNNEST(supervisor_staff_id_array) AS supervisor_staff_id
     INNER JOIN
         `{{project_id}}.normalized_state.state_staff` b
     ON
         a.state_code = b.state_code
         AND supervisor_staff_id = b.staff_id
+    WHERE "SUPERVISION_OFFICER" IN UNNEST(a.role_type_array)
 )
 ,
 overlapping_spans AS (

recidiviz/calculator/query/state/views/workflows/firestore/supervision_staff_record.py

@@ -127,7 +127,7 @@
                 attrs.supervisor_staff_external_id_array[SAFE_OFFSET(0)] AS supervisor_external_id,
                 attrs.supervisor_staff_external_id_array AS supervisor_external_ids,
             FROM full_query
-            LEFT JOIN `{{project_id}}.sessions.supervision_officer_attribute_sessions_materialized` attrs
+            LEFT JOIN `{{project_id}}.sessions.supervision_staff_attribute_sessions_materialized` attrs
                 ON full_query.id = attrs.officer_id
                 AND full_query.state_code = attrs.state_code
                 AND {today_between_start_date_and_nullable_end_date_clause("start_date", "end_date_exclusive")}