def test_make_contacts_with_facilities_from_microstructure(location='seattle_metro', state_location='Washington',
country_location='usa', Npop=1000):
# First generate microstructure with facilities
sp.generate_microstructure_with_facilities(datadir, location, state_location, country_location,
Npop, school_enrollment_counts_available=False,
write=False, plot=False, return_popdict=True)
# sp.generate_microstructure_with_facilities(datadir, location, state_location,
# country_location, n, sheet_name='United States of America',
# use_two_group_reduction=False, average_LTCF_degree=20, ltcf_staff_age_min=20, ltcf_staff_age_max=60,
# school_enrollment_counts_available=False, with_school_types=False, school_mixing_type='random', average_class_size=20, inter_grade_mixing=0.1,
# average_student_teacher_ratio=20, average_teacher_teacher_degree=3, teacher_age_min=25, teacher_age_max=75,
# average_student_all_staff_ratio=15, average_additional_staff_degree=20, staff_age_min=20, staff_age_max=75,
# verbose=False, plot=False, write=False, return_popdict=False, use_default=False):
# Then make contacts
popdict = sp.make_contacts_with_facilities_from_microstructure(datadir, location, state_location, country_location,
Npop)
contains_age = 74
contains_sex = 1
uids = popdict.keys()
assert contains_age in uids
assert contains_sex in uids
return popdict
def test_make_contacts_with_facilities_from_microstructure(location='seattle_metro', state_location='Washington',
country_location='usa', Npop=1000):
# First generate microstructure with facilities
sp.generate_microstructure_with_facilities(datadir, location, state_location, country_location,
Npop, school_enrollment_counts_available=True,
write=True, plot=False, return_popdict=True)
# Then make contacts
popdict = sp.make_contacts_with_facilities_from_microstructure(datadir, location, state_location, country_location,
Npop)
contains_age = 74
contains_sex = 1
uids = popdict.keys()
assert contains_age in uids
assert contains_sex in uids
return popdict
def test_generate_microstructures_with_facilities():
popdict = sp.generate_microstructure_with_facilities(
datadir,
location,
state_location,
country_location,
n,
write=write,
plot=False,
return_popdict=return_popdict)
assert (len(popdict) is not None)
return popdict
def test_generate_microstructures_with_non_teaching_staff():
# # generate and write to file
population1 = sp.generate_microstructure_with_facilities(
datadir,
location=location,
state_location=state_location,
country_location=country_location,
n=n,
use_two_group_reduction=use_two_group_reduction,
average_LTCF_degree=average_LTCF_degree,
ltcf_staff_age_min=ltcf_staff_age_min,
ltcf_staff_age_max=ltcf_staff_age_max,
with_school_types=with_school_types,
school_mixing_type=school_mixing_type,
average_class_size=average_class_size,
inter_grade_mixing=inter_grade_mixing,
average_student_teacher_ratio=average_student_teacher_ratio,
average_teacher_teacher_degree=average_teacher_teacher_degree,
teacher_age_min=teacher_age_min,
teacher_age_max=teacher_age_max,
average_student_all_staff_ratio=average_student_all_staff_ratio,
average_additional_staff_degree=average_additional_staff_degree,
staff_age_min=staff_age_min,
staff_age_max=staff_age_max,
write=write,
plot=plot,
return_popdict=return_popdict,
use_default=use_default)
# # # read in from file
population2 = sp.make_contacts_with_facilities_from_microstructure(
datadir,
location=location,
state_location=state_location,
country_location=country_location,
n=n,
use_two_group_reduction=use_two_group_reduction,
average_LTCF_degree=average_LTCF_degree,
with_school_types=with_school_types,
school_mixing_type=school_mixing_type,
average_class_size=average_class_size,
inter_grade_mixing=inter_grade_mixing,
average_student_teacher_ratio=average_student_teacher_ratio,
average_teacher_teacher_degree=average_teacher_teacher_degree,
average_student_all_staff_ratio=average_student_all_staff_ratio,
average_additional_staff_degree=average_additional_staff_degree)
# # generate on the fly
sc.tic()
population3 = sp.make_population(
n=n,
generate=True,
with_facilities=True,
use_two_group_reduction=use_two_group_reduction,
average_LTCF_degree=average_LTCF_degree,
ltcf_staff_age_min=ltcf_staff_age_min,
ltcf_staff_age_max=ltcf_staff_age_max,
with_school_types=with_school_types,
school_mixing_type=school_mixing_type,
average_class_size=average_class_size,
inter_grade_mixing=inter_grade_mixing,
average_student_teacher_ratio=average_student_teacher_ratio,
average_teacher_teacher_degree=average_teacher_teacher_degree,
teacher_age_min=teacher_age_min,
teacher_age_max=teacher_age_max,
with_non_teaching_staff=with_non_teaching_staff,
average_student_all_staff_ratio=average_student_all_staff_ratio,
average_additional_staff_degree=average_additional_staff_degree,
staff_age_min=staff_age_min,
staff_age_max=staff_age_max,
rand_seed=rand_seed)
sc.toc()
sp.check_all_residents_are_connected_to_staff(population3)
return population1, population2, population3
def make_population(n=None, max_contacts=None, generate=None, with_industry_code=False, with_facilities=False,
use_two_group_reduction=True, average_LTCF_degree=20, ltcf_staff_age_min=20, ltcf_staff_age_max=60,
with_school_types=False, school_mixing_type='random', average_class_size=20, inter_grade_mixing=0.1,
average_student_teacher_ratio=20, average_teacher_teacher_degree=3, teacher_age_min=25, teacher_age_max=75,
with_non_teaching_staff=False,
average_student_all_staff_ratio=15, average_additional_staff_degree=20, staff_age_min=20, staff_age_max=75,
rand_seed=None):
'''
Make a full population network including both people (ages, sexes) and contacts using Seattle, Washington data.
Args:
n (int) : The number of people to create.
max_contacts (dict) : A dictionary for maximum number of contacts per layer: keys must be "W" (work).
generate (bool) : If True, generate a new population. Else, look for cached population and if those are not available, generate a new population.
with_industry_code (bool) : If True, assign industry codes for workplaces, currently only possible for cached files of populations in the US.
with_facilities (bool) : If True, create long term care facilities, currently only available for locations in the US.
use_two_group_reduction (bool) : If True, create long term care facilities with reduced contacts across both groups.
average_LTCF_degree (float) : default average degree in long term care facilities.
ltcf_staff_age_min (int) : Long term care facility staff minimum age.
ltcf_staff_age_max (int) : Long term care facility staff maximum age.
with_school_types (bool) : If True, creates explicit school types.
school_mixing_type (str or dict) : The mixing type for schools, 'random', 'age_clustered', or 'age_and_class_clustered' if string, and a dictionary of these by school type otherwise.
average_class_size (float) : The average classroom size.
inter_grade_mixing (float) : The average fraction of mixing between grades in the same school for clustered school mixing types.
average_student_teacher_ratio (float) : The average number of students per teacher.
average_teacher_teacher_degree (float) : The average number of contacts per teacher with other teachers.
teacher_age_min (int) : The minimum age for teachers.
teacher_age_max (int) : The maximum age for teachers.
with_non_teaching_staff (bool) : If True, includes non teaching staff.
average_student_all_staff_ratio (float) : The average number of students per staff members at school (including both teachers and non teachers).
average_additional_staff_degree (float) : The average number of contacts per additional non teaching staff in schools.
staff_age_min (int) : The minimum age for non teaching staff.
staff_age_max (int) : The maximum age for non teaching staff.
rand_seed (int) : Start point random sequence is generated from.
Returns:
network (dict): A dictionary of the full population with ages and connections.
'''
log.debug('make_population()')
if rand_seed is not None:
sp.set_seed(rand_seed)
default_n = 10000
default_max_contacts = {'W': 20} # this can be anything but should be based on relevant average number of contacts for the population under study
if n is None:
n = default_n
n = int(n)
if n not in popsize_choices:
if generate is False:
choicestr = ', '.join([str(choice) for choice in popsize_choices])
errormsg = f'If generate=False, number of people must be one of {choicestr}, not {n}'
raise ValueError(errormsg)
else:
generate = True # If n not found in popsize_choices and generate was not False, generate a new population.
# Default to False, unless LTCF are requested
if generate is None:
if with_facilities:
generate = True
else:
generate = False
max_contacts = sc.mergedicts(default_max_contacts, max_contacts)
country_location = 'usa'
state_location = 'Washington'
location = 'seattle_metro'
sheet_name = 'United States of America'
options_args = {}
options_args['use_microstructure'] = True
options_args['use_industry_code'] = with_industry_code
options_args['use_long_term_care_facilities'] = with_facilities
options_args['use_two_group_reduction'] = use_two_group_reduction
options_args['with_school_types'] = with_school_types
options_args['with_non_teaching_staff'] = with_non_teaching_staff
network_distr_args = {}
network_distr_args['Npop'] = int(n)
network_distr_args['average_LTCF_degree'] = average_LTCF_degree
network_distr_args['average_class_size'] = average_class_size
network_distr_args['average_student_teacher_ratio'] = average_student_teacher_ratio
network_distr_args['average_teacher_teacher_degree'] = average_teacher_teacher_degree
network_distr_args['inter_grade_mixing'] = inter_grade_mixing
network_distr_args['average_student_all_staff_ratio'] = average_student_all_staff_ratio
network_distr_args['average_additional_staff_degree'] = average_additional_staff_degree
network_distr_args['school_mixing_type'] = school_mixing_type
# Heavy lift 1: make the contacts and their connections
if not generate:
log.debug('Not generating a new population')
# must read in from file, will fail if the data has not yet been generated
population = sp.make_contacts(location=location, state_location=state_location,
country_location=country_location, sheet_name=sheet_name,
options_args=options_args,
network_distr_args=network_distr_args)
else:
log.debug('Generating a new population...')
if with_facilities and with_industry_code:
errormsg = f'Requesting both long term care facilities and industries by code is not supported yet.'
raise ValueError(errormsg)
elif with_facilities:
population = sp.generate_microstructure_with_facilities(sp.datadir, location=location, state_location=state_location, country_location=country_location, n=n, sheet_name=sheet_name,
use_two_group_reduction=use_two_group_reduction, average_LTCF_degree=average_LTCF_degree, ltcf_staff_age_min=ltcf_staff_age_min, ltcf_staff_age_max=ltcf_staff_age_max,
with_school_types=with_school_types, school_mixing_type=school_mixing_type, average_class_size=average_class_size, inter_grade_mixing=inter_grade_mixing,
average_student_teacher_ratio=average_student_teacher_ratio, average_teacher_teacher_degree=average_teacher_teacher_degree, teacher_age_min=teacher_age_min, teacher_age_max=teacher_age_max,
average_student_all_staff_ratio=average_student_all_staff_ratio, average_additional_staff_degree=average_additional_staff_degree, staff_age_min=staff_age_min, staff_age_max=staff_age_max,
return_popdict=True, trimmed_size_dic=max_contacts)
else:
population = sp.generate_synthetic_population(n, sp.datadir, location=location, state_location=state_location, country_location=country_location, sheet_name=sheet_name,
with_school_types=with_school_types, school_mixing_type=school_mixing_type, average_class_size=average_class_size, inter_grade_mixing=inter_grade_mixing,
average_student_teacher_ratio=average_student_teacher_ratio, average_teacher_teacher_degree=average_teacher_teacher_degree, teacher_age_min=teacher_age_min, teacher_age_max=teacher_age_max,
average_student_all_staff_ratio=average_student_all_staff_ratio, average_additional_staff_degree=average_additional_staff_degree, staff_age_min=staff_age_min, staff_age_max=staff_age_max,
return_popdict=True, trimmed_size_dic=max_contacts,
)
# Semi-heavy-lift 2: trim them to the desired numbers
# population = sp.trim_contacts(population, trimmed_size_dic=max_contacts, use_clusters=False)
# Change types
for key, person in population.items():
for layerkey in population[key]['contacts'].keys():
population[key]['contacts'][layerkey] = list(population[key]['contacts'][layerkey])
log.debug('make_population(): done.')
return population
def test_create_reduced_contacts_with_group_types():
n = 1001
average_LTCF_degree = 20
# First create contact_networks_facilities
# set write to False and instead use return_popdict = True to get a population dict
popdict = sp.generate_microstructure_with_facilities(
datadir,
location,
state_location,
country_location,
n,
school_enrollment_counts_available=True,
write=False,
plot=False,
return_popdict=True)
# Make 2 groups of contacts
# Facility contacts - use generating function so that data can be generated as needed to run this test
contacts_group_1 = sp.generate_microstructure_with_facilities(
datadir,
location,
state_location,
country_location,
n,
plot=False,
verbose=False,
write=False,
return_popdict=True,
use_two_group_reduction=False,
average_LTCF_degree=20)
# List of ids for group_1 facility contacts
contacts_group_1_list = list(contacts_group_1.keys())
# Home contacts
network_distr_args = {
'average_degree': average_LTCF_degree,
'network_type': 'poisson_degree',
'directed': True
}
contacts_group_2 = sp.make_contacts_generic(
popdict, network_distr_args=network_distr_args)
# List of ids for group_2 home contacts
contacts_group_2_list = list(contacts_group_2.keys())
# Now reduce contacts
reduced_contacts = sp.create_reduced_contacts_with_group_types(
popdict,
contacts_group_1_list,
contacts_group_2_list,
'LTCF',
average_degree=average_LTCF_degree,
force_cross_edges=True)
assert len(reduced_contacts) * 2 == len(contacts_group_1_list) + len(
contacts_group_2_list)
for i in popdict:
person = reduced_contacts[i]
if person['snf_res'] == 1:
contacts = person['contacts']['LTCF']
staff_contacts = [
j for j in contacts if popdict[j]['snf_staff'] == 1
]
if len(staff_contacts) == 0:
errormsg = f'At least one LTCF or Skilled Nursing Facility resident has no contacts with staff members.'
raise ValueError(errormsg)
return reduced_contacts
def make_population(n=None,
max_contacts=None,
generate=None,
with_industry_code=False,
with_facilities=False,
use_two_group_reduction=True,
average_LTCF_degree=20,
rand_seed=None):
'''
Make a full population network including both people (ages, sexes) and contacts using Seattle, Washington cached data.
Args:
n (int) : The number of people to create.
max_contacts (dict) : A dictionary for maximum number of contacts per layer: keys must be "S" (school) and/or "W" (work).
generate (bool) : If True, first look for cached population files and if those are not available, generate new population
with_industry_code (bool) : If True, assign industry codes for workplaces, currently only possible for cached files of populations in the US
with_facilities (bool) : If True, create long term care facilities
use_two_group_reduction (bool) : If True, create long term care facilities with reduced contacts across both groups
average_LTCF_degree (int) : default average degree in long term care facilities
Returns:
network (dict): A dictionary of the full population with ages and connections.
'''
if rand_seed is not None:
sp.set_seed(rand_seed)
default_n = 10000
default_max_contacts = {
'S': 20,
'W': 20
} # this can be anything but should be based on relevant average number of contacts for the population under study
if n is None:
n = default_n
n = int(n)
if n not in popsize_choices:
if generate is False:
choicestr = ', '.join([str(choice) for choice in popsize_choices])
errormsg = f'If generate=False, number of people must be one of {choicestr}, not {n}'
raise ValueError(errormsg)
else:
generate = True # If not found, generate
# Default to False, unless LTCF are requested
if generate is None:
if with_facilities:
generate = True
else:
generate = False
max_contacts = sc.mergedicts(default_max_contacts, max_contacts)
country_location = 'usa'
state_location = 'Washington'
location = 'seattle_metro'
sheet_name = 'United States of America'
options_args = {
'use_microstructure': True,
'use_industry_code': with_industry_code,
'use_long_term_care_facilities': with_facilities,
'use_two_group_reduction': use_two_group_reduction,
'average_LTCF_degree': average_LTCF_degree
}
network_distr_args = {'Npop': int(n)}
# Heavy lift 1: make the contacts and their connections
if not generate:
# must read in from file, will fail if the data has not yet been generated
population = sp.make_contacts(location=location,
state_location=state_location,
country_location=country_location,
options_args=options_args,
network_distr_args=network_distr_args)
else:
# make a new network on the fly
if with_facilities and with_industry_code:
errormsg = f'Requesting both long term care facilities and industries by code is not supported yet.'
raise ValueError(errormsg)
elif with_facilities:
population = sp.generate_microstructure_with_facilities(
sp.datadir,
location=location,
state_location=state_location,
country_location=country_location,
n=n,
return_popdict=True,
use_two_group_reduction=use_two_group_reduction,
average_LTCF_degree=average_LTCF_degree)
else:
population = sp.generate_synthetic_population(
n,
sp.datadir,
location=location,
state_location=state_location,
country_location=country_location,
sheet_name=sheet_name,
plot=False,
return_popdict=True)
# Semi-heavy-lift 2: trim them to the desired numbers
population = sp.trim_contacts(population,
trimmed_size_dic=max_contacts,
use_clusters=False)
# Change types
for key, person in population.items():
for layerkey in population[key]['contacts'].keys():
population[key]['contacts'][layerkey] = list(
population[key]['contacts'][layerkey])
return population
n = int(n)
# # # generate and write to file
population = sp.generate_microstructure_with_facilities(
datadir,
location=location,
state_location=state_location,
country_location=country_location,
n=n,
use_two_group_reduction=use_two_group_reduction,
average_LTCF_degree=average_LTCF_degree,
ltcf_staff_age_min=ltcf_staff_age_min,
ltcf_staff_age_max=ltcf_staff_age_max,
with_school_types=with_school_types,
school_mixing_type=school_mixing_type,
average_class_size=average_class_size,
inter_grade_mixing=inter_grade_mixing,
average_student_teacher_ratio=average_student_teacher_ratio,
average_teacher_teacher_degree=average_teacher_teacher_degree,
teacher_age_min=teacher_age_min,
teacher_age_max=teacher_age_max,
average_student_all_staff_ratio=average_student_all_staff_ratio,
average_additional_staff_degree=average_additional_staff_degree,
staff_age_min=staff_age_min,
staff_age_max=staff_age_max,
write=write,
plot=plot,
return_popdict=return_popdict,
use_default=use_default)
# # # read in from file
population = sp.make_contacts_with_facilities_from_microstructure(
