[PULL REQUEST] add in military employment

python/employment.py

@@ -274,6 +274,29 @@ def _get_jobs_inputs(year: int) -> dict[str, pd.DataFrame]:
                     "year": year,
                 },
             )
+        # Get military employment data and append to control_totals
+        with open(utils.SQL_FOLDER / "employment/get_military_employment.sql") as file:
+            jobs_inputs["military_emp"] = pd.read_sql_query(
+                sql=sql.text(file.read()),
+                con=con,
+                params={
+                    "run_id": utils.RUN_ID,
+                    "year": year,
+                },
+            )
+
+        military_control_totals = (
+            jobs_inputs["military_emp"]
+            .groupby(["run_id", "year", "industry_code", "metric"], as_index=False)[
+                "value"
+            ]
+            .sum()
+        )[["run_id", "year", "industry_code", "metric", "value"]]
+
+        jobs_inputs["control_totals"] = pd.concat(
+            [jobs_inputs["control_totals"], military_control_totals],
+            ignore_index=True,
+        )
 
     return jobs_inputs
 
@@ -311,12 +334,20 @@ def _validate_jobs_inputs(jobs_inputs: dict[str, pd.DataFrame]) -> None:
         null={},
     )
     tests.validate_data(
-        "QCEW control totals",
+        "Military employment data",
+        jobs_inputs["military_emp"],
+        row_count={"key_columns": {"mgra"}},
+        negative={},
+        null={},
+    )
+    tests.validate_data(
+        "Jobs control totals",
         jobs_inputs["control_totals"],
         row_count={"key_columns": {"industry_code"}},
         negative={},
         null={},
     )
+
 
 
 def _create_jobs_output(
@@ -341,6 +372,10 @@ def _create_jobs_output(
             _distribute_self_emp_to_mgra(
                 jobs_inputs["B24080"], jobs_inputs["xref_bg_to_mgra"]
             ),
+            # Include military employment at MGRA level
+            jobs_inputs["military_emp"][
+                ["run_id", "year", "mgra", "industry_code", "value"]
+            ],
         ],
         ignore_index=True,
     ).sort_values(by=["mgra", "industry_code"])

python/tests.py

@@ -41,7 +41,7 @@
         # and 722 3-digit naics code. Self employment data does not natively have a
         # naics code so it is therefore assigned to 'SE' as the naics codes are being
         # treated as strings.
-        "industry_code": 22,
+        "industry_code": 23,
     },
     "series": {
         15: {

sql/employment/get_military_employment.sql

@@ -0,0 +1,38 @@
+/* 
+This query grabs the Military Active Duty (Job) Data and assigns counts to MGRA15.
+This will assign 0 to MGRAs where there is no Military Jobs
+*/
+
+-- Initialize parameters -----------------------------------------------------
+DECLARE @run_id INTEGER = :run_id;
+DECLARE @year INTEGER = :year;
+
+
+-- Send error message if no data exists --------------------------------------
+IF NOT EXISTS (
+    SELECT TOP (1) *
+    FROM [ws].[fact].[MILITARY_EMPLOYMENT]
+    WHERE [year] = @year
+)
+BEGIN
+    THROW 50000, 'Military Active duty data does not exist.', 1;
+END
+ELSE
+BEGIN
+
+-- Get MGRA Military Active Duty Counts ------------------------------------- 
+    SELECT
+        @run_id AS [run_id],
+        @year AS [year],
+        [mgra],
+        'MIL' AS [industry_code],
+        'jobs' AS [metric],
+        COALESCE(SUM([site_active_duty]), 0) AS [value]
+    FROM [inputs].[mgra]
+    LEFT OUTER JOIN [ws].[fact].[MILITARY_EMPLOYMENT]
+        ON [MILITARY_EMPLOYMENT].[shape].STWithin([mgra].[shape]) = 1
+        AND [run_id] = @run_id AND [year] = @year
+    WHERE [run_id] = @run_id 
+    GROUP BY [mgra]
+    ORDER BY [mgra]
+END