Territories in the 65th percentile of low income are added is disadvantaged

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

@@ -2,22 +2,20 @@
 import pandas as pd
 import pytest
 from data_pipeline.config import settings
+from data_pipeline.etl.score import constants
 from data_pipeline.etl.score.etl_score import ScoreETL
 from data_pipeline.score import field_names
+from data_pipeline.score.score_narwhal import ScoreNarwhal
 from data_pipeline.utils import get_module_logger
 
+
 logger = get_module_logger(__name__)
 
+TEST_DATA_FOLDER = settings.APP_ROOT / "tests" / "score" / "test_utils" / "data"
 
 @pytest.fixture
 def toy_score_df(scope="module"):
-    return pd.read_csv(
-        settings.APP_ROOT
-        / "tests"
-        / "score"
-        / "test_utils"
-        / "data"
-        / "test_drop_tracts_from_percentile.csv",
+    return pd.read_csv(TEST_DATA_FOLDER / "test_drop_tracts_from_percentile.csv",
         dtype={field_names.GEOID_TRACT_FIELD: str},
     )
 
@@ -83,3 +81,44 @@ def test_drop_all_tracts(toy_score_df):
         toy_score_df,
         drop_tracts=toy_score_df[field_names.GEOID_TRACT_FIELD].to_list(),
     ), "Percentile in score fails when we drop all tracts"
+
+
+def test_mark_territory_dacs():
+    test_data = pd.read_csv(TEST_DATA_FOLDER / "test_mark_territory_dacs.csv",
+        dtype={field_names.GEOID_TRACT_FIELD: str},
+    )
+    # Sanity check on the input data
+    assert not test_data[field_names.SCORE_N_COMMUNITIES].all()
+
+    scorer = ScoreNarwhal(test_data)
+    scorer._mark_territory_dacs()
+    territory_filter = test_data[field_names.GEOID_TRACT_FIELD].str.startswith(tuple(constants.TILES_ISLAND_AREA_FIPS_CODES))
+    # Check territories are set to true
+    expected_new_dacs_filter = (
+        test_data[field_names.GEOID_TRACT_FIELD].isin(['60050951100', '66010951100', '69110001101', '78010990000'])
+    )
+    assert test_data.loc[expected_new_dacs_filter, field_names.SCORE_N_COMMUNITIES].all()
+    # Non-territories are still false
+    assert not test_data.loc[~expected_new_dacs_filter, field_names.SCORE_N_COMMUNITIES].all()
+
+
+def test_mark_poverty_flag():
+    test_data = pd.read_csv(TEST_DATA_FOLDER / "test_mark_poverty_flag.csv",
+        dtype={field_names.GEOID_TRACT_FIELD: str},
+    )
+    # Sanity check on the input data
+    assert not test_data[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED].all()
+
+    scorer = ScoreNarwhal(test_data)
+    scorer._mark_poverty_flag()
+    expected_low_income_filter = (
+        test_data[field_names.GEOID_TRACT_FIELD].isin(['36087011302', '66010951100', '78010990000'])
+    )
+    # Three tracts are set to true
+    assert (
+        test_data[expected_low_income_filter][field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED].all()
+    )
+    # Everything else is false
+    assert (
+        not test_data[~expected_low_income_filter][field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED].all()
+    )

data/data-pipeline/data_pipeline/tests/score/test_utils/data/test_mark_poverty_flag.csv

@@ -0,0 +1,8 @@
+GEOID10_TRACT,Percentage households below 200% of federal poverty line in 2009,"Percent of individuals below 200% Federal Poverty Line, imputed and adjusted","Percent of individuals below 200% Federal Poverty Line, imputed and adjusted (percentile)",Is low income (imputed and adjusted)?
+01071950300,,0.1,0.1,False
+36087011302,,0.7,0.7,False
+72119130701,,0.5,0.5,False
+60050951100,0.1,,,False
+66010951100,0.7,,,False
+69110001100,0.5,,,False
+78010990000,0.9,,,False

data/data-pipeline/data_pipeline/tests/score/test_utils/data/test_mark_territory_dacs.csv

@@ -0,0 +1,9 @@
+GEOID10_TRACT,Is low income (imputed and adjusted)?,Definition N (communities)
+01071950300,True,False
+36087011302,False,False
+72119130701,True,False
+60050951100,True,False
+66010951100,True,False
+69110001100,False,False
+69110001101,True,False
+78010990000,True,False