Add tribal overlap to downloads (#1907)

* Add tribal data to downloads (#1904)

* Update test pickle with current cols (#1904)

* Remove text of tribe names from GeoJSON (#1904)

* Update test data (#1904)

* Add tribal overlap to smoketests (#1904)

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

@@ -380,3 +380,12 @@ fields:
 - score_name: Income data has been estimated based on neighbor income
   label: Income data has been estimated based on geographic neighbor income
   format: bool
+- score_name: Number of Tribal areas within Census tract
+  label: Number of Tribal areas within Census tract
+  format: int64
+- score_name: Names of Tribal areas within Census tract
+  label: Names of Tribal areas within Census tract
+  format: string
+- score_name: Percent of the Census tract that is within Tribal areas
+  label: Percent of the Census tract that is within Tribal areas
+  format: percentage

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

@@ -384,3 +384,12 @@ sheets:
       - score_name: Income data has been estimated based on neighbor income
         label: Income data has been estimated based on geographic neighbor income
         format: bool
+      - score_name: Number of Tribal areas within Census tract
+        label: Number of Tribal areas within Census tract
+        format: int64
+      - score_name: Names of Tribal areas within Census tract
+        label: Names of Tribal areas within Census tract
+        format: string
+      - score_name: Percent of the Census tract that is within Tribal areas
+        label: Percent of the Census tract that is within Tribal areas
+        format: percentage

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

@@ -379,6 +379,10 @@ TILES_SCORE_COLUMNS = {
     field_names.PERCENT_AGE_UNDER_10: "AGE_10",
     field_names.PERCENT_AGE_10_TO_64: "AGE_MIDDLE",
     field_names.PERCENT_AGE_OVER_64: "AGE_OLD",
+    field_names.COUNT_OF_TRIBAL_AREAS_IN_TRACT: "TA_COUNT",
+    field_names.PERCENT_OF_TRIBAL_AREA_IN_TRACT: "TA_PERC",
+    
+
 }
 
 # columns to round floats to 2 decimals
@@ -452,4 +456,5 @@ TILES_SCORE_FLOAT_COLUMNS = [
     field_names.ELIGIBLE_FUDS_BINARY_FIELD_NAME,
     field_names.AML_BOOLEAN,
     field_names.HISTORIC_REDLINING_SCORE_EXCEEDED,
+    field_names.PERCENT_OF_TRIBAL_AREA_IN_TRACT
 ]

data/data-pipeline/data_pipeline/tests/score/fixtures.py

@@ -215,3 +215,16 @@ def national_tract_df():
         low_memory=False,
         header=None,
     )
+
+
+@pytest.fixture()
+def tribal_overlap():
+    tribal_overlap = (
+        constants.DATA_PATH / "dataset" / "tribal_overlap" / "usa.csv"
+    )
+
+    return pd.read_csv(
+        tribal_overlap,
+        dtype={GEOID_TRACT_FIELD: "string"},
+        low_memory=False,
+    )

data/data-pipeline/data_pipeline/tests/score/test_output.py

@@ -27,6 +27,7 @@ from .fixtures import (
     census_2010_df,
     hrs_df,
     national_tract_df,
+    tribal_overlap,
 )
 
 
@@ -249,6 +250,7 @@ def test_data_sources(
     census_decennial_df,
     census_2010_df,
     hrs_df,
+    tribal_overlap,
 ):
     data_sources = {
         key: value for key, value in locals().items() if key != "final_score_df"