Adding category count to BE signals (#1486)

Added category count to downloadable data and backend signals.

data/data-pipeline/data_pipeline/content/config/csv.yml

@@ -17,6 +17,9 @@ fields:
   - score_name: Total threshold criteria exceeded
     label: Total threshold criteria exceeded
     format: int64
+  - score_name: Total categories exceeded
+    label: Total categories exceeded
+    format: int64
   - score_name: Definition M (communities)
     label: Identified as disadvantaged
     format: bool

data/data-pipeline/data_pipeline/content/config/excel.yml

@@ -22,6 +22,9 @@ sheets:
       - score_name: Total threshold criteria exceeded
         label: Total threshold criteria exceeded
         format: int64
+      - score_name: Total categories exceeded
+        label: Total categories exceeded
+        format: int64
       - score_name: Definition M (communities)
         label: Identified as disadvantaged
         format: bool

data/data-pipeline/data_pipeline/etl/score/constants.py

@@ -187,6 +187,7 @@ TILES_SCORE_COLUMNS = {
     field_names.LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD: "LMILHSE",
     field_names.UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD: "ULHSE",
     field_names.THRESHOLD_COUNT: "TC",
+    field_names.CATEGORY_COUNT: "CC",
     field_names.ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD: "IAULHSE",
     field_names.ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD: "IAPLHSE",
     field_names.ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD: "IALMILHSE",

data/data-pipeline/data_pipeline/score/field_names.py

@@ -591,6 +591,7 @@ LOW_READING_LOW_HS_EDUCATION_FIELD = (
 )
 
 THRESHOLD_COUNT = "Total threshold criteria exceeded"
+CATEGORY_COUNT = "Total categories exceeded"
 
 FPL_200_SERIES = "Is low income?"
 FPL_200_AND_COLLEGE_ATTENDANCE_SERIES = (

data/data-pipeline/data_pipeline/score/score_m.py

@@ -832,6 +832,7 @@ class ScoreM(Score):
             field_names.M_HEALTH,
             field_names.M_WORKFORCE,
         ]
+        self.df[field_names.CATEGORY_COUNT] = self.df[factors].sum(axis=1)
         self.df[field_names.SCORE_M_COMMUNITIES] = self.df[factors].any(axis=1)
 
         # Note: this is purely used for comparison tool analysis, and can be removed at a later date. - LMB.