publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 08:01:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add FEMA risk index to score file (#687)

Browse source 
* Add to score file
This commit is contained in:
Lucas Merrill Brown 2021-09-15 13:31:32 -05:00 • committed by GitHub
commit 1c0d87d84b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 68 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

24
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -66,6 +66,11 @@ class ScoreETL(ExtractTransformLoad):
# DOE energy burden
self.ENERGY_BURDEN_FIELD_NAME = "Energy burden"
# FEMA Risk Index
self.RISK_INDEX_EXPECTED_ANNUAL_LOSS_SCORE_FIELD_NAME = (
"FEMA Risk Index Expected Annual Loss Score"
)
# There's another aggregation level (a second level of "buckets").
self.AGGREGATION_POLLUTION: str = "Pollution Burden"
self.AGGREGATION_POPULATION: str = "Population Characteristics"
@ -85,6 +90,7 @@ class ScoreETL(ExtractTransformLoad):
self.census_acs_median_incomes_df: pd.DataFrame
self.cdc_life_expectancy_df: pd.DataFrame
self.doe_energy_burden_df: pd.DataFrame
self.national_risk_index_df: pd.DataFrame
def data_sets(self) -> list:
# Define a named tuple that will be used for each data set input.
@ -186,6 +192,11 @@ class ScoreETL(ExtractTransformLoad):
renamed_field=self.ENERGY_BURDEN_FIELD_NAME,
bucket=None,
),
DataSet(
input_field=self.RISK_INDEX_EXPECTED_ANNUAL_LOSS_SCORE_FIELD_NAME,
renamed_field=self.RISK_INDEX_EXPECTED_ANNUAL_LOSS_SCORE_FIELD_NAME,
bucket=None,
),
# The following data sets have buckets, because they're used in Score C
DataSet(
input_field="CANCER",
@ -365,6 +376,16 @@ class ScoreETL(ExtractTransformLoad):
low_memory=False,
)
# Load FEMA national risk index data
national_risk_index_csv = (
self.DATA_PATH / "dataset" / "national_risk_index_2020" / "usa.csv"
)
self.national_risk_index_df = pd.read_csv(
national_risk_index_csv,
dtype={self.GEOID_FIELD_NAME: "string"},
low_memory=False,
)
def _join_cbg_dfs(self, census_block_group_dfs: list) -> pd.DataFrame:
logger.info("Joining Census Block Group dataframes")
census_block_group_df = functools.reduce(
@ -630,6 +651,7 @@ class ScoreETL(ExtractTransformLoad):
self.census_df,
self.housing_and_transportation_df,
self.census_acs_median_incomes_df,
self.national_risk_index_df,
]
census_block_group_df = self._join_cbg_dfs(census_block_group_dfs)
@ -638,7 +660,7 @@ class ScoreETL(ExtractTransformLoad):
self.hud_housing_df,
self.cdc_places_df,
self.cdc_life_expectancy_df,
self.doe_energy_burden_df
self.doe_energy_burden_df,
]
census_tract_df = self._join_tract_dfs(census_tract_dfs)