from synthpop.recipes.starter import Starter
from synthpop.synthesizer import synthesize_all
import pandas as pd
import os
import sys
state_abbr = sys.argv[1]
county_name = sys.argv[2]
starter = Starter(os.environ["CENSUS"], state_abbr, county_name)
if len(sys.argv) > 3:
state, county, tract, block_group = sys.argv[3:]
indexes = [
pd.Series([state, county, tract, block_group],
index=["state", "county", "tract", "block group"])
]
else:
indexes = None
households, people, fit_quality = synthesize_all(starter, indexes=indexes)
for geo, qual in fit_quality.items():
print 'Geography: {} {} {} {}'.format(geo.state, geo.county, geo.tract,
geo.block_group)
# print ' household chisq: {}'.format(qual.household_chisq)
# print ' household p: {}'.format(qual.household_p)
print ' people chisq: {}'.format(qual.people_chisq)
print ' people p: {}'.format(qual.people_p)
def synthesize_county(county):
starter = Starter(os.environ["CENSUS"], "CO", county)
synthetic_population = synthesize_all(starter)
return synthetic_population
def synthesize_county(county):
starter = Starter(os.environ["CENSUS"], "CO", county)
synthetic_population = synthesize_all(starter)
return synthetic_population
from synthpop.recipes.starter import Starter
from synthpop.synthesizer import synthesize_all
import pandas as pd
import os
import sys
state_abbr = sys.argv[1]
county_name = sys.argv[2]
starter = Starter(os.environ["CENSUS"], state_abbr, county_name)
if len(sys.argv) > 3:
state, county, tract, block_group = sys.argv[3:]
indexes = [pd.Series(
[state, county, tract, block_group],
index=["state", "county", "tract", "block group"])]
else:
indexes = None
households, people, fit_quality = synthesize_all(starter, indexes=indexes)
for geo, qual in fit_quality.items():
print 'Geography: {} {} {} {}'.format(
geo.state, geo.county, geo.tract, geo.block_group)
# print ' household chisq: {}'.format(qual.household_chisq)
# print ' household p: {}'.format(qual.household_p)
print ' people chisq: {}'.format(qual.people_chisq)
print ' people p: {}'.format(qual.people_p)
def synthesize_counties(counties):
for county in counties:
starter = Starter(os.environ["CENSUS"], "RI", county)
synthesize_all(starter)
def synth_test():
starter = Starter(os.environ["CENSUS"], "WA", "King County")
ind = pd.Series(["53", "33", "100", "2006"], index=["state", "county", "tract", "block group"])
households, persons, fit = synthesize_all(starter, indexes=[ind])
pass
def synthesize_region(num_geogs=None):
starter = Starter(os.environ["CENSUS"], "WA")
households, persons, fit = synthesize_all(starter, num_geogs=num_geogs)
return (households, persons)
print parser.format_help()
sys.exit(2)
if match.group(3) == None:
taz_set.add(int(match.group(1)))
else:
assert(int(match.group(3)) > int(match.group(1)))
taz_set.update(range(int(match.group(1)), int(match.group(3))+1))
print "taz_set = [%s]" % str(taz_set)
# enable_logging()
starter_hh = SFCTAStarterHouseholds(parser_args.census_api_key,
parser_args.controls_csv, taz_set,
parser_args.PUMA_data_dir, parser_args.fips_file,
write_households_csv="households.csv",
write_persons_csv="persons.csv")
households, people, fit_quality = synthesize_all(starter_hh, indexes=None)
gq_start_hhid = starter_hh.start_hhid
gq_start_persid = starter_hh.start_persid
# close the file
del starter_hh
starter_gq = SFCTAStarterGroupQuarters(parser_args.census_api_key,
parser_args.controls_csv, taz_set,
parser_args.PUMA_data_dir, parser_args.fips_file,
write_households_csv="households.csv",
write_persons_csv="persons.csv",
write_append=True,
start_hhid=gq_start_hhid,
start_persid=gq_start_persid)
households_gq, people_gq, fit_quality_gq = synthesize_all(starter_gq, indexes=None)
# close the file
# %load_ext autoreload
# %autoreload 2
from synthpop.recipes.starter2 import Starter
from synthpop.synthesizer import synthesize_all, enable_logging
import os
import pandas as pd
enable_logging()
# setting API Key
os.environ["CENSUS"] = "d95e144b39e17f929287714b0b8ba9768cecdc9f"
starter = Starter(os.environ["CENSUS"], "NC", "Mecklenburg County")
ind = pd.Series(["37", "119", "005706", "4"],
index=["state", "county", "tract", "block group"])
output = synthesize_all(starter, indexes=[ind])
output.to_csv("data/test_synth_output.csv")
