In [1]:
%load_ext autoreload
%autoreload 2
from synthpop.census_helpers import Census
from synthpop import categorizer as cat
import pandas as pd
import numpy as np
import os
pd.set_option('display.max_columns', 500)
In [2]:
c = Census(os.environ["CENSUS"])
In [3]:
income_columns = ['B19001_0%02dE'%i for i in range(1, 18)]
vehicle_columns = ['B08201_0%02dE'%i for i in range(1, 7)]
workers_columns = ['B08202_0%02dE'%i for i in range(1, 6)]
families_columns = ['B11001_001E', 'B11001_002E']
block_group_columns = income_columns + families_columns
tract_columns = vehicle_columns + workers_columns
h_acs = c.block_group_and_tract_query(block_group_columns,
tract_columns, "06", "075",
merge_columns=['tract', 'county', 'state'],
block_group_size_attr="B11001_001E",
tract_size_attr="B08201_001E",
tract="030600")
h_acs
Out[3]:
In [4]:
population = ['B01001_001E']
sex = ['B01001_002E', 'B01001_026E']
race = ['B02001_0%02dE'%i for i in range(1,11)]
male_age_columns = ['B01001_0%02dE'%i for i in range(3,26)]
female_age_columns = ['B01001_0%02dE'%i for i in range(27,50)]
all_columns = population + sex + race + male_age_columns + female_age_columns
p_acs = c.block_group_query(all_columns, "06", "075", tract="030600")
p_acs
Out[4]:
In [5]:
puma = c.tract_to_pums("06", "075", "030600")
In [6]:
p_pums = c.download_population_pums("06", puma)
p_pums.head(5)
Out[6]:
In [7]:
h_pums = c.download_household_pums("06", puma)
h_pums.head(5)
Out[7]:
In [8]:
h_acs_cat = cat.categorize(h_acs, {
("households", "total"): "B11001_001E",
("children", "yes"): "B11001_002E",
("children", "no"): "B11001_001E - B11001_002E",
("income", "lt35"): "B19001_002E + B19001_003E + B19001_004E + "
"B19001_005E + B19001_006E + B19001_007E",
("income", "gt35-lt100"): "B19001_008E + B19001_009E + "
"B19001_010E + B19001_011E + B19001_012E"
"+ B19001_013E",
("income", "gt100"): "B19001_014E + B19001_015E + B19001_016E"
"+ B19001_017E",
("cars", "none"): "B08201_002E",
("cars", "one"): "B08201_003E",
("cars", "two or more"): "B08201_004E + B08201_005E + B08201_006E",
("workers", "none"): "B08202_002E",
("workers", "one"): "B08202_003E",
("workers", "two or more"): "B08202_004E + B08202_005E"
}, index_cols=['NAME'])
h_acs_cat
Out[8]:
In [9]:
assert np.all(cat.sum_accross_category(h_acs_cat) < 2)
In [10]:
p_acs_cat = cat.categorize(p_acs, {
("population", "total"): "B01001_001E",
("age", "19 and under"): "B01001_003E + B01001_004E + B01001_005E + "
"B01001_006E + B01001_007E + B01001_027E + "
"B01001_028E + B01001_029E + B01001_030E + "
"B01001_031E",
("age", "20 to 35"): "B01001_008E + B01001_009E + B01001_010E + "
"B01001_011E + B01001_012E + B01001_032E + "
"B01001_033E + B01001_034E + B01001_035E + "
"B01001_036E",
("age", "35 to 60"): "B01001_013E + B01001_014E + B01001_015E + "
"B01001_016E + B01001_017E + B01001_037E + "
"B01001_038E + B01001_039E + B01001_040E + "
"B01001_041E",
("age", "above 60"): "B01001_018E + B01001_019E + B01001_020E + "
"B01001_021E + B01001_022E + B01001_023E + "
"B01001_024E + B01001_025E + B01001_042E + "
"B01001_043E + B01001_044E + B01001_045E + "
"B01001_046E + B01001_047E + B01001_048E + "
"B01001_049E",
("race", "white"): "B02001_002E",
("race", "black"): "B02001_003E",
("race", "asian"): "B02001_005E",
("race", "other"): "B02001_004E + B02001_006E + B02001_007E + "
"B02001_008E",
("sex", "male"): "B01001_002E",
("sex", "female"): "B01001_026E"
}, index_cols=['NAME'])
p_acs_cat
Out[10]:
In [11]:
assert np.all(cat.sum_accross_category(p_acs_cat) < 2)
In [12]:
p_acs_cat.iloc[0].transpose()
Out[12]:
In [13]:
def age_cat(r):
if r.AGEP <= 19: return "19 and under"
elif r.AGEP <= 35: return "20 to 35"
elif r.AGEP <= 60: return "35 to 60"
return "above 60"
def race_cat(r):
if r.RAC1P == 1: return "white"
elif r.RAC1P == 2: return "black"
elif r.RAC1P == 6: return "asian"
return "other"
def sex_cat(r):
if r.SEX == 1: return "male"
return "female"
_, jd_persons = cat.joint_distribution(
p_pums,
cat.category_combinations(p_acs_cat.columns),
{"age": age_cat, "race": race_cat, "sex": sex_cat}
)
jd_persons
Out[13]:
In [14]:
def cars_cat(r):
if r.VEH == 0: return "none"
elif r.VEH == 1: return "one"
return "two or more"
def children_cat(r):
if r.NOC > 0: return "yes"
return "no"
def income_cat(r):
if r.FINCP > 100000: return "gt100"
elif r.FINCP > 35000: return "gt35-lt100"
return "lt35"
def workers_cat(r):
if r.WIF == 3: return "two or more"
elif r.WIF == 2: return "two or more"
elif r.WIF == 1: return "one"
return "none"
_, jd_households = cat.joint_distribution(
h_pums,
cat.category_combinations(h_acs_cat.columns),
{"cars": cars_cat, "children": children_cat,
"income": income_cat, "workers": workers_cat}
)
jd_households
Out[14]:
In [16]:
"TBD"
Out[16]:
In [ ]: