Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for TIGER years 2000 and 2009-2023 (incl.) #129

Merged
merged 1 commit into from
Jul 8, 2024
+132 −95
Merged

Add support for TIGER years 2000 and 2009-2023 (incl.) #129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
63 changes: 24 additions & 39 deletions doc/devlog/2024-05-03.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,13 @@
"\n",
"_Author: Tyler Coles_\n",
"\n",
"Testing our us_census functions for loading canonical sets of IDs for Census granularities from state to block group for the years 2000, 2010, and 2020.\n",
"Testing our us_census functions for loading canonical sets of IDs for Census granularities from state to block group for all supported TIGER years (2000 and 2009-2023).\n",
"\n",
"Since this is our source of truth for these delineations, we want to make sure we're getting complete data. One thing we can test is that at each level of granularity (above block group) each node should contain at least one child node. That is every state should contain a county, every county a tract, and every tract a block group. Otherwise we know something is missing.\n",
"\n",
"(This may seem like a trivial test, but in fact it discovered that my original assumptions about how TIGER provides the data were invalid and has already saved us from bugs!)"
"(This may seem like a trivial test, but in fact it discovered that my original assumptions about how TIGER provides the data were invalid and has already saved us from bugs!)\n",
"\n",
"WARNING: this will take a very long time if you don't have the TIGER files cached."
]
},
{
Expand All @@ -22,13 +24,14 @@
"outputs": [],
"source": [
"import epymorph.geography.us_census as c\n",
"import epymorph.geography.us_tiger as t\n",
"\n",
"\n",
"class Fail(Exception):\n",
" pass\n",
"\n",
"\n",
"def test_year(year: c.CensusYear) -> None:\n",
"def test_year(year: int) -> None:\n",
" # 1. test that we have 52 states\n",
" states = c.get_us_states(year).geoid\n",
"\n",
Expand Down Expand Up @@ -80,46 +83,28 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Census year 2020 passed!\n"
]
}
],
"source": [
"test_year(2020)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Census year 2010 passed!\n"
]
}
],
"source": [
"test_year(2010)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Census year 2000 passed!\n"
"Census year 2000 passed!\n",
"Census year 2009 passed!\n",
"Census year 2010 passed!\n",
"Census year 2011 passed!\n",
"Census year 2012 passed!\n",
"Census year 2013 passed!\n",
"Census year 2014 passed!\n",
"Census year 2015 passed!\n",
"Census year 2016 passed!\n",
"Census year 2017 passed!\n",
"Census year 2018 passed!\n",
"Census year 2019 passed!\n",
"Census year 2020 passed!\n",
"Census year 2021 passed!\n",
"Census year 2022 passed!\n",
"Census year 2023 passed!\n"
]
}
],
"source": [
"test_year(2000)"
"for year in t.TIGER_YEARS:\n",
" test_year(year)"
]
}
],
Expand Down
17 changes: 11 additions & 6 deletions epymorph/geo/adrio/census/adrio_census.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,8 @@

from epymorph.data_shape import Shapes
from epymorph.data_type import CentroidDType
from epymorph.error import DataResourceException, GeoValidationException
from epymorph.error import (DataResourceException, GeographyError,
GeoValidationException)
from epymorph.geo.adrio.adrio import ADRIO, ADRIOMaker
from epymorph.geo.spec import TimePeriod, Year
from epymorph.geography.us_census import (BLOCK_GROUP, COUNTY, STATE, TRACT,
Expand All @@ -22,7 +23,7 @@
StateScopeAll, TractScope)
from epymorph.geography.us_tiger import (get_block_groups_geo,
get_counties_geo, get_states_geo,
get_tracts_geo)
get_tracts_geo, is_tiger_year)
from epymorph.simulation import AttributeDef, geo_attrib


Expand Down Expand Up @@ -197,18 +198,22 @@ def fetch_acs5(self, variables: list[str], scope: CensusScope, year: int) -> Dat
def fetch_sf(self, scope: CensusScope) -> GeoDataFrame:
"""Utility function to fetch shape files from Census for specified regions."""
# call appropriate pygris function based on granularity and sort result
scope_year = scope.year
if not is_tiger_year(scope_year):
raise GeographyError(f"Unsupported year: {scope_year}")

match scope:
case StateScopeAll() | StateScope():
df = get_states_geo(year=scope.year)
df = get_states_geo(year=scope_year)

case CountyScope():
df = get_counties_geo(year=scope.year)
df = get_counties_geo(year=scope_year)

case TractScope():
df = get_tracts_geo(year=scope.year)
df = get_tracts_geo(year=scope_year)

case BlockGroupScope():
df = get_block_groups_geo(year=scope.year)
df = get_block_groups_geo(year=scope_year)

case _:
raise DataResourceException("Unsupported query.")
Expand Down
Loading
Loading