def test_main():
# Get US surge data
us_surge = Surge()
# Set parameters
us_surge.end_date = '5/15/20' # set end date wanted
us_surge.ignore_last_n_days = 0 # allow for data repo to be corrected/updated
us_surge.min_n_cases_abs = 500 # min # of absolute cases for analysis
us_surge.deaths_100k_minimum = 41 # US death per 100,000 for Chronic Lower Respiratory Diseases per year: 41 (2019)
print('')
print('# of states/distric: ', len(us_surge.names))
print('# of days: ', us_surge.dates.shape[0])
# Fit data to all states
fit_data = us_surge.multi_fit_data(verbose=True,
plot=True,
save_plots=True)
# Plot all data in one plot
us_surge.plot_multi_fit_data(fit_data, 'experimental', save=True)
# Plot all fit data in one plot
us_surge.plot_multi_fit_data(fit_data, 'fit', save=True)
# Create clustering bins based on surge period
bins = us_surge.clustering(fit_data, 2, 'surge_period')
print('')
print('*****************************************************************')
print(' Bins ')
print('*****************************************************************')
for k in sorted(bins.keys()):
print(' Bin %i %s' % (k, bins[k]))
# Use bins to create groups of states based on surge period
state_groups = dict()
for (sort_key, data) in fit_data:
state = data[0]
param_vec = data[3]
key = us_surge.get_bin_id(sort_key, bins)
if key in state_groups:
state_groups[key].append(state)
else:
state_groups[key] = list()
state_groups[key].append(state)
state_groups = [
state_groups[k] for k in sorted(state_groups.keys(), reverse=False)
]
print('')
print('*****************************************************************')
print(' Country Groups ')
print('*****************************************************************')
for g in state_groups:
print(' Group %i %s' % (state_groups.index(g), g))
assert len(state_groups) == 7
assert state_groups[0] == ['New York', 'Virginia']
assert state_groups[1] == ['Massachusetts', 'Connecticut', 'Michigan']
assert state_groups[2] == [
'New Jersey', 'Pennsylvania', 'Louisiana', 'Minnesota', 'Maryland'
]
assert state_groups[3] == ['North Carolina', 'Indiana']
assert state_groups[4] == [
'Florida', 'Georgia', 'Wisconsin', 'Missouri', 'Colorado', 'Ohio'
]
assert state_groups[5] == ['Illinois', 'California', 'Washington']
assert state_groups[6] == ['Alabama', 'Mississippi']
# Plot the normalized surge for groups of states
us_surge.plot_group_fit_data(state_groups, fit_data, save=True)
# Plot the surge period for all grouped states
us_surge.plot_group_surge_periods(fit_data, bins, save=True)
def test_main():
# Get US surge data
g_surge = Surge('global')
# Set parameters
g_surge.end_date = '5/15/20' # set end date wanted
g_surge.ignore_last_n_days = 0 # allow for data repo to be corrected/updated
g_surge.min_n_cases_abs = 2500 # min # of absolute cases for analysis
print('# of countries: ', g_surge.cases.shape[1])
print('# of days: ', g_surge.cases.shape[0])
# Fit data to all states
fit_data = g_surge.multi_fit_data(blocked_list=['China'],
verbose=True,
plot=True,
save_plots=True)
# Plot all data in one plot
g_surge.plot_multi_fit_data(fit_data, 'experimental', save=True)
# Plot all fit data in one plot
g_surge.plot_multi_fit_data(fit_data, 'fit', save=True)
# Create clustering bins based on surge period
bins = g_surge.clustering(fit_data, 2, 'surge_period')
print('')
print('*****************************************************************')
print(' Bins ')
print('*****************************************************************')
for k in sorted(bins.keys()):
print(' Bin %i %s' % (k, bins[k]))
# Use bins to create groups of countries based on surge period
country_groups = dict()
for (sort_key, data) in fit_data:
country = data[0]
param_vec = data[3]
key = g_surge.get_bin_id(sort_key, bins)
if key in country_groups:
country_groups[key].append(country)
else:
country_groups[key] = list()
country_groups[key].append(country)
country_groups = [
country_groups[k] for k in sorted(country_groups.keys(), reverse=False)
]
print('')
print('*****************************************************************')
print(' Country Groups ')
print('*****************************************************************')
for g in country_groups:
print(' Group %i %s' % (country_groups.index(g), g))
assert len(country_groups) == 6
assert country_groups[0] == ['Belgium', 'France']
assert country_groups[1] == ['Germany', 'Turkey']
assert country_groups[2] == [
'Spain', 'Netherlands', 'United Kingdom', 'Canada'
]
assert country_groups[3] == ['Ecuador', 'Sweden']
assert country_groups[4] == ['US', 'Italy']
assert country_groups[5] == ['Iran']
# Plot the normalized surge for groups of countries
g_surge.plot_group_fit_data(country_groups, fit_data, save=True)
# Plot the surge period for all grouped states
g_surge.plot_group_surge_periods(fit_data, bins, save=True)
def main():
# Get US surge data
g_surge = Surge('global')
# Set parameters
g_surge.end_date = '4/20/20' # set end date wanted
g_surge.end_date = None # get all the data available
g_surge.ignore_last_n_days = 2 # allow for data repo to be corrected/updated
g_surge.min_n_cases_abs = 2500 # min # of absolute cases for analysis
print('# of countries: ', g_surge.cases.shape[1])
print('# of days: ', g_surge.cases.shape[0])
# Fit data to all states
fit_data = g_surge.multi_fit_data(blocked_list=['China'],
verbose=True,
plot=True,
save_plots=True)
# Plot all data in one plot
g_surge.plot_multi_fit_data(fit_data, 'experimental', save=True)
# Plot all fit data in one plot
g_surge.plot_multi_fit_data(fit_data, 'fit', save=True)
# Create clustering bins based on surge period
bins = g_surge.clustering(fit_data, 2, 'surge_period')
print('')
print('*****************************************************************')
print(' Bins ')
print('*****************************************************************')
for k in sorted(bins.keys()):
print(' Bin %i %s' % (k, bins[k]))
# Use bins to create groups of countries based on surge period
country_groups = dict()
for (sort_key, data) in fit_data:
country = data[0]
param_vec = data[3]
key = g_surge.get_bin_id(sort_key, bins)
if key in country_groups:
country_groups[key].append(country)
else:
country_groups[key] = list()
country_groups[key].append(country)
country_groups = [
country_groups[k] for k in sorted(country_groups.keys(), reverse=False)
]
print('')
print('*****************************************************************')
print(' Country Groups ')
print('*****************************************************************')
for g in country_groups:
print(' Group %i %s' % (country_groups.index(g), g))
# Plot the normalized surge for groups of countries
g_surge.plot_group_fit_data(country_groups, fit_data, save=True)
# Plot the surge period for all grouped states
g_surge.plot_group_surge_periods(fit_data, bins, save=True)
def main():
# Get US surge data
sub_locale = 'North Carolina'
c_surge = Surge(locale='US',sub_locale=sub_locale)
print('')
print('State : ',sub_locale)
print('# of counties: ',len(c_surge.names))
# Set parameters
c_surge.end_date = '4/20/20' # set end date wanted
c_surge.end_date = None # get all the data available
c_surge.ignore_last_n_days = 2 # allow for data repo to be corrected/updated
c_surge.min_n_cases_abs = 25 # min # of absolute cases for analysis
c_surge.deaths_100k_minimum = 41 # US death per 100,000 for Chronic Lower Respiratory Diseases per year: 41 (2019)
# Fit data to all counties/cities
fit_data = c_surge.multi_fit_data(verbose=True, plot=True, save_plots=True)
print('# of fittings done = ',len(fit_data))
# Plot all data in one plot
c_surge.plot_multi_fit_data( fit_data, 'experimental', save=True )
if len(fit_data) == 0:
print('Done here...')
return
# Plot all fit data in one plot
c_surge.plot_multi_fit_data( fit_data, 'fit', save=True )
# Create clustering bins based on surge period
bins = c_surge.clustering(fit_data,2,'surge_period')
print('')
print('*****************************************************************')
print(' Bins ')
print('*****************************************************************')
for k in sorted(bins.keys()):
print(' Bin %i %s'%(k,bins[k]))
# Use bins to create groups of counties/cities based on surge period
county_groups = dict()
for (sort_key,data) in fit_data:
county = data[0]
param_vec = data[3]
key = c_surge.get_bin_id(sort_key,bins)
if key in county_groups:
county_groups[key].append(county)
else:
county_groups[key] = list()
county_groups[key].append(county)
county_groups = [ county_groups[k] for k in
sorted(county_groups.keys(),reverse=False) ]
print('')
print('*****************************************************************')
print(' County Groups ')
print('*****************************************************************')
for g in county_groups:
print(' Group %i %s'%(county_groups.index(g),g))
# Plot the normalized surge for groups of counties
c_surge.plot_group_fit_data( county_groups, fit_data, save=True )
# Plot the surge period for all grouped counties
c_surge.plot_group_surge_periods( fit_data, bins, save=True )
def main():
# Get US surge data
us_surge = Surge()
# Set parameters
us_surge.end_date = '4/20/20' # set end date wanted
us_surge.end_date = None # get all the data available
us_surge.ignore_last_n_days = 2 # allow for data repo to be corrected/updated
us_surge.min_n_cases_abs = 500 # min # of absolute cases for analysis
us_surge.deaths_100k_minimum = 41 # US death per 100,000 for Chronic Lower Respiratory Diseases per year: 41 (2019)
print('')
print('# of states/distric: ', len(us_surge.names))
print('# of days: ', us_surge.dates.shape[0])
# Fit data to all states
fit_data = us_surge.multi_fit_data(verbose=True,
plot=True,
save_plots=True)
# Plot all data in one plot
us_surge.plot_multi_fit_data(fit_data, 'experimental', save=True)
# Plot all fit data in one plot
us_surge.plot_multi_fit_data(fit_data, 'fit', save=True)
# Create clustering bins based on surge period
bins = us_surge.clustering(fit_data, 2, 'surge_period')
print('')
print('*****************************************************************')
print(' Bins ')
print('*****************************************************************')
for k in sorted(bins.keys()):
print(' Bin %i %s' % (k, bins[k]))
# Use bins to create groups of states based on surge period
state_groups = dict()
for (sort_key, data) in fit_data:
state = data[0]
param_vec = data[3]
key = us_surge.get_bin_id(sort_key, bins)
if key in state_groups:
state_groups[key].append(state)
else:
state_groups[key] = list()
state_groups[key].append(state)
state_groups = [
state_groups[k] for k in sorted(state_groups.keys(), reverse=False)
]
print('')
print('*****************************************************************')
print(' Country Groups ')
print('*****************************************************************')
for g in state_groups:
print(' Group %i %s' % (state_groups.index(g), g))
# Plot the normalized surge for groups of states
us_surge.plot_group_fit_data(state_groups, fit_data, save=True)
# Plot the surge period for all grouped states
us_surge.plot_group_surge_periods(fit_data, bins, save=True)
def main():
# Get US surge data
us_surge = Surge()
#states = [ a for (a,b) in
# sorted( zip(us_surge.names, us_surge.cases[-1,:]),
# key = lambda entry: entry[1], reverse=True )]
# Set parameters
us_surge.end_date = '4/20/20' # set end date wanted
us_surge.end_date = None # get all the data available
us_surge.ignore_last_n_days = 2 # allow for data repo to be corrected/updated
us_surge.min_n_cases_abs = 500 # min # of absolute cases for analysis
us_surge.deaths_100k_minimum = 41 # US death per 100,000 for Chronic Lower Respiratory Diseases per year: 41 (2019)
print('')
print('# of states/distric: ', len(us_surge.names))
print('# of days: ', us_surge.dates.shape[0])
# Fit data to all states of fully-evolved surge
fit_data = us_surge.multi_fit_data() # silent
states = list()
print('')
for (i, (sort_key, data)) in enumerate(fit_data):
name = data[0]
states.append(name)
print('%2i) %15s: surge period %1.2f [day]' % (i, name, sort_key))
surge_periods = list() # collect surge period of all counties/towns
total_n_counties = 0 # count all counties/towns inspected w/ nonzero cases
for state in states:
print('')
print(
'***************************************************************')
print(' ', state)
print(
'***************************************************************')
c_surge = Surge(locale='US', sub_locale=state)
print('# of counties: ', len(c_surge.names))
(ids, ) = np.where(c_surge.cases[-1, :] > 0)
total_n_counties += ids.size
# Set parameters
c_surge.end_date = '4/20/20' # set end date wanted
c_surge.end_date = None # get all the data available
c_surge.ignore_last_n_days = 2 # allow for data repo to be corrected/updated
c_surge.min_n_cases_abs = 100 # min # of absolute cases for analysis
c_surge.deaths_100k_minimum = 41 # US death per 100,000 for Chronic Lower Respiratory Diseases per year: 41 (2019)
# Fit data to all counties/cities
fit_data = c_surge.multi_fit_data(verbose=False,
plot=True,
save_plots=True)
print('# of fittings done = ', len(fit_data))
if len(fit_data) == 0:
continue
print('')
for (sort_key, data) in fit_data:
name = data[0]
surge_periods.append(sort_key)
print('%15s: surge period %1.2f [day]' % (name, sort_key))
# Create clustering bins based on surge period
bins = c_surge.clustering(fit_data, 2, 'surge_period')
print('')
print(
'----------------------------------------------------------------')
print(
' Bins ')
print(
'----------------------------------------------------------------')
for k in sorted(bins.keys()):
print(' Bin %i %s' % (k, bins[k]))
# Use bins to create groups of counties/cities based on surge period
county_groups = dict()
for (sort_key, data) in fit_data:
county = data[0]
param_vec = data[3]
key = c_surge.get_bin_id(sort_key, bins)
if key in county_groups:
county_groups[key].append(county)
else:
county_groups[key] = list()
county_groups[key].append(county)
county_groups = [
county_groups[k]
for k in sorted(county_groups.keys(), reverse=False)
]
print('')
print(
'----------------------------------------------------------------')
print(
' County Groups ')
print(
'----------------------------------------------------------------')
for g in county_groups:
print(' Group %i %s' % (county_groups.index(g), g))
# Plot the surge period for all grouped counties
c_surge.plot_group_surge_periods(fit_data, bins, save=True)
print('')
print('')
print('Total # of counties/towns with surge period = ', len(surge_periods))
print('Average surge period %1.2f [day], std %1.2f' %
(np.mean(np.array(surge_periods)), np.std(np.array(surge_periods))))
print('Total # of inspected counties/towns w/ non-zero cases = %4i' %
total_n_counties)