def get_pop_details(self,
pop,
dir,
title_prefix,
location,
state_location,
country_location,
decimal=3):
os.makedirs(dir, exist_ok=True)
# want default age brackets and to see that they line up with the average contacts by age bracket created
age_brackets = spdd.get_census_age_brackets(self.datadir, location,
state_location,
country_location)
age_brackets_labels = [
str(age_brackets[b][0]) + '-' + str(age_brackets[b][-1])
for b in sorted(age_brackets.keys())
]
for setting_code in ['H', 'W', 'S']:
average_contacts = utilities.get_average_contact_by_age(
pop, self.datadir, setting_code=setting_code, decimal=decimal)
fmt = f'%.{str(decimal)}f'
# print(f"expected contacts by age for {code}:\n", average_contacts)
utilities.plot_array(
average_contacts,
datadir=self.figDir,
testprefix=
f"{self.n}_seed_{self.seed}_{setting_code}_average_contacts",
expect_label='Expected' if self.generateBaseline else 'Test',
names=age_brackets_labels,
xlabel_rotation=50)
sc.savejson(os.path.join(
dir,
f"{self.n}_seed_{self.seed}_{setting_code}_average_contact.json"
),
dict(enumerate(average_contacts.tolist())),
indent=2)
for method in ['density', 'frequency']:
matrix = sp.calculate_contact_matrix(pop, method, setting_code)
brackets = spdd.get_census_age_brackets(
self.datadir, location, state_location, country_location)
ageindex = spb.get_age_by_brackets_dic(brackets)
agg_matrix = spb.get_aggregate_matrix(matrix, ageindex)
textfile = os.path.join(
dir,
f"{self.n}_seed_{self.seed}_{setting_code}_{method}_contact_matrix.csv"
)
np.savetxt(textfile, agg_matrix, delimiter=",", fmt=fmt)
fig = sp.plot_contacts(pop,
setting_code=setting_code,
density_or_frequency=method,
do_show=False)
fig.savefig(
os.path.join(
self.figDir,
f"{self.n}_seed_{self.seed}_{setting_code}_{method}_contact_matrix.png"
))
def get_average_contact_by_age(pop,
datadir,
location="seattle_metro",
state_location="Washington",
country_location="usa",
setting_code="H",
decimal=3):
"""
Helper method to get average contacts by age brackets
Args:
pop : population dictionary
datadir : data directory to look up reference data
state_location : state location
country_location : country location
setting_code : contact layer code, can be "H", "W", "S"
decimal : digits for rounding, default to 3
Returns:
numpy.ndarray: A numpy array with average contacts by age brackets.
"""
brackets = spdd.get_census_age_brackets(datadir, location, state_location,
country_location)
ageindex = spb.get_age_by_brackets_dic(brackets)
total = np.zeros(len(brackets))
contacts = np.zeros(len(brackets))
for p in pop.values():
total[ageindex[p["age"]]] += 1
contacts[ageindex[p["age"]]] += len(p["contacts"][setting_code])
average = np.round(np.divide(contacts, total), decimals=decimal)
return average
def test_seattle_age_brackets(self):
"""
Test for method get_census_age_brackets and get_age_by_brackets. It
calls helper method verify_age_bracket_dictionary_correct for
verification.
Returns:
None
"""
self.is_debugging = False
age_brackets = spdd.get_census_age_brackets(
datadir=sp.settings.datadir,
state_location="Washington",
country_location="usa",
use_default=False
)
age_brackets_json = {}
for k in age_brackets:
age_brackets_json[k] = age_brackets[k].tolist()
if self.is_debugging:
with open(f"DEBUG_{self._testMethodName}_age_brackets.json", "w") as outfile:
json.dump(age_brackets_json, outfile, indent=4)
age_by_brackets = sp.get_age_by_brackets(
age_brackets=age_brackets
)
self.verify_age_bracket_dictionary_correct(age_by_brackets)
def get_pop_contact_matrix(pop, layer, method):
"""
Args:
pop (pop object) : population, either synthpops.pop.Pop, covasim.people.People, or dict
layer (str) : name of the physical contact layer: H for households, S for schools, W for workplaces, C for community or other
method: (str) : density or frequency
Returns:
array: contact matrix
"""
age_brackets = spdd.get_census_age_brackets(**pop.loc_pars)
matrix = sp.calculate_contact_matrix(pop.popdict, method, layer)
ageindex = spb.get_age_by_brackets(age_brackets)
agg_matrix = spb.get_aggregate_matrix(matrix, ageindex)
return agg_matrix
def test_seattle_age_brackets(self):
self.is_debugging = False
age_brackets = spdd.get_census_age_brackets(
datadir=sp.datadir,
state_location="Washington",
country_location="usa",
use_default=False)
age_brackets_json = {}
for k in age_brackets:
age_brackets_json[k] = age_brackets[k].tolist()
if self.is_debugging:
with open(f"DEBUG_{self._testMethodName}_age_brackets.json",
"w") as outfile:
json.dump(age_brackets_json, outfile, indent=4)
age_by_brackets_dic = sphh.get_age_by_brackets_dic(
age_brackets=age_brackets)
self.verify_age_bracket_dictionary_correct(age_by_brackets_dic)
def get_pop_average_contacts_by_brackets(pop, layer, decimal=3):
"""
get population contact counts by age brackets and save the results as json files and plots
Args:
pop (pop object) : population, either synthpops.pop.Pop, covasim.people.People, or dict
layer (str) : name of the physical contact layer: H for households, S for schools, W for workplaces, C for community or other
decimal (int) : rounding precision for average contact calculation
Returns:
dict: a dictionary where index is the age bracket and value is the percentage of contact
"""
# want default age brackets and to see that they line up with the average contacts by age bracket created
age_brackets = spdd.get_census_age_brackets(**pop.loc_pars)
average_contacts = []
for k in age_brackets:
degree_df = sp.count_layer_degree(pop, layer=layer, ages=age_brackets[k])
people_in_ages = sp.filter_people(pop, ages=age_brackets[k])
average_contacts.append(
0 if len(degree_df) == 0 else np.round(degree_df.sum(axis=0)['degree'] / len(people_in_ages),
decimals=decimal))
return dict(enumerate(average_contacts))
def process_long_term_care_facility_rates_by_age(datadir, state_location,
country_location):
"""
Process the National Long Term Care Providers state data tables from 2016 to
get the estimated user rates by age.
Args:
datadir (string) : file path to the data directory
state_location (string) : name of the state
country_location (string) : name of the country the state is in
Returns:
dict: A dictionary with the estimated rates of Long Term Care Facility
usage by age for the state in 2016.
"""
year = 2016 # use 2016 data to match the year of data for the LTCF state data table
acs_period = 1 # using ACS 1 year estimates
part = 2 # which part of the LTCF state data table to use
ltcf_df = data_distributions_legacy.get_usa_long_term_care_facility_data(
datadir, state_location, country_location, part=part)
ltcf_age_bracket_keys = [
'Under 65', '65–74', '75–84', '85 and over'
] # age brackets as defined by National LTCF Providers survey
facility_keys = [
'Nursing home',
'Residential care community',
# 'Hospice', # Hospice users are often cared for in their own homes so it may not be appropriate to include them in facility resident numbers.
]
facility_users = {}
# 2016 state wide age breakdown of LTCF users
facility_user_age_percentage = {}
for fk in facility_keys:
facility_users[fk] = {}
facility_user_age_percentage[fk] = {}
facility_users[fk]['Total'] = int(ltcf_df[
ltcf_df.iloc[:, 0] == 'Number of users2, 5'][fk].values[0].replace(
',', ''))
for ab in ltcf_age_bracket_keys:
facility_user_age_percentage[fk][ab] = float(
ltcf_df[ltcf_df.iloc[:, 0] == ab][fk].values[0].replace(
',', '')) / 100.
# 2016 state wide total LTCF users by facility type and age brackets
for fk in facility_keys:
for ab in ltcf_age_bracket_keys:
facility_users[fk][ab] = facility_users[fk][
'Total'] * facility_user_age_percentage[fk][ab]
# map the LTCF users age groups to the census age groups
age_group_mapping = {
'Under 65': '60-64',
'65–74': '65-74',
'75–84': '75-84',
'85 and over': '85-100'
}
age_brackets = spdata.get_census_age_brackets(
datadir,
state_location=state_location,
country_location=country_location,
nbrackets=18)
age_by_brackets_dic = spb.get_age_by_brackets_dic(age_brackets)
brackets_in_range_mapping = {}
for ab in ltcf_age_bracket_keys:
sa, ea = age_group_mapping[ab].split('-')
sa, ea = int(sa), int(ea)
age_range = np.arange(sa, ea + 1)
brackets_in_range = set()
for a in age_range:
b = age_by_brackets_dic[a]
brackets_in_range.add(b)
brackets_in_range_mapping[ab] = sorted(brackets_in_range.copy())
# 2016 state population size
population_size = process_us_census_population_size(
datadir, state_location, state_location, country_location, year,
acs_period)
# 2016 state age distribution (18 age brackets)
age_bracket_distr, age_brackets = process_us_census_age_counts(
datadir, state_location, state_location, country_location, year,
acs_period)
age_bracket_distr = spb.norm_dic(age_bracket_distr)
age_bracket_count = {}
for b in sorted(age_bracket_distr.keys()):
age_bracket_count[b] = population_size * age_bracket_distr[b]
# 2016 state age count for the LTCF data defined age brackets
state_older_age_counts = {}
for ab in ltcf_age_bracket_keys:
state_older_age_counts[ab] = 0
for b in brackets_in_range_mapping[ab]:
state_older_age_counts[
ab] += age_bracket_distr[b] * population_size
# calculate the percent using facilities by the LTCF data age brackets
ltcf_rates_by_age = dict.fromkeys(np.arange(101), 0)
for ab in ltcf_age_bracket_keys:
ltcf_rates_by_age[ab] = np.sum(
[facility_users[fk][ab]
for fk in facility_keys]) / state_older_age_counts[ab]
for b in brackets_in_range_mapping[ab]:
for a in age_brackets[b]:
ltcf_rates_by_age[a] = ltcf_rates_by_age[ab].copy()
for ab in ltcf_age_bracket_keys:
ltcf_rates_by_age.pop(ab, None)
return ltcf_rates_by_age