def probe(filename, column, what):
deprivation = getDeprivation(filename, column, what)
print what
print ' Highest'
for k in sorted(rate.keys(), key=lambda k: deprivation[k],
reverse=True)[:10]:
print ' {:32s}: {:.2f}'.format(codes[k], deprivation[k])
print ' Lowest'
for k in sorted(rate.keys(), key=lambda k: deprivation[k],
reverse=False)[:10]:
print ' {:32s}: {:.2f}'.format(codes[k], deprivation[k])
y = np.array([100.0 * rate[k] for k in rate.keys()])
x = np.array([deprivation[k] for k in rate.keys()])
c = [
UKCovid19Data.colorsByRegion[UKCovid19Data.whichRegion(k)]
for k in rate.keys()
]
fig = plt.figure(figsize=(8, 6))
plt.scatter(x, y, color=c, alpha=0.8)
r = scipy.stats.linregress(x, y)
gradient, intercept, r_value, p_value, std_err = r
rx = np.linspace(min(x), max(x), 100)
ry = gradient * rx + intercept
plt.plot(rx, ry, color='tab:red', label='Linear regression')
coef = np.polyfit(x, y, 2)
qy = coef[2] + coef[1] * rx + coef[0] * rx**2
plt.plot(rx, qy, color='tab:green', label='Quadratic best fit')
ax = plt.gca()
vals = ax.get_yticks()
ax.set_yticklabels(['{:,.1f}%'.format(x) for x in vals])
plt.ylabel('Daily % increase rate\n({} to {})'.format(dates[0], dates[-1]))
plt.xlabel(what)
plt.title('Deprivation: {}\nr={:.3f}'.format(what, r_value))
regionsUsed = sorted(
list(set([UKCovid19Data.whichRegion(k) for k in rate.keys()])))
handles, labels = ax.get_legend_handles_labels()
handles.extend([
matplotlib.patches.Patch(color=UKCovid19Data.colorsByRegion[k],
label=k) for k in regionsUsed
])
plt.legend(handles=handles, loc='upper left', prop={'size': 6})
distutils.dir_util.mkpath('output')
plt.savefig('output/deprivation-{}.png'.format(
filename.replace('(%)', 'percentage')),
dpi=96)
correlation[what] = r_value
def plot(x,y,c,w,s,interesting):
fig=plt.figure(figsize=(8,6))
plt.scatter(x,y,s=s,color=c,alpha=0.8)
# Unweighted regression line
r=scipy.stats.linregress(x,y)
gradient,intercept,r_value,p_value,std_err=r
print 'Unweighted',gradient,intercept
rx=np.linspace(min(x),max(x),100)
ry=gradient*rx+intercept
plt.plot(rx,ry,color='tab:orange',label='Linear regression (unweighted)')
# Weighted regression line
coef=np.polyfit(x,y,1,w=w)
print 'Weighted',coef[0],coef[1]
ry=coef[1]+coef[0]*rx # Highest power first
plt.plot(rx,ry,color='tab:red',label='Linear regression (weighted by total votes)')
rw=corr(x,y,w)
ax=plt.gca()
vals=ax.get_yticks()
ax.set_yticklabels(['{:,.1f}%'.format(x) for x in vals])
vals=ax.get_xticks()
ax.set_xticklabels(['{:,.1f}%'.format(x) for x in vals])
regionsUsed=sorted(list(set([UKCovid19Data.whichRegion(k) for k in interesting])))
handles,labels = ax.get_legend_handles_labels()
handles.extend([matplotlib.patches.Patch(color=UKCovid19Data.colorsByRegion[k],label=k) for k in regionsUsed])
plt.legend(handles=handles,loc='upper left',prop={'size':6})
return r.rvalue,rw
regionsUsed=sorted(list(set([UKCovid19Data.whichRegion(k) for k in interesting])))
handles,labels = ax.get_legend_handles_labels()
handles.extend([matplotlib.patches.Patch(color=UKCovid19Data.colorsByRegion[k],label=k) for k in regionsUsed])
plt.legend(handles=handles,loc='upper left',prop={'size':6})
return r.rvalue,rw
plots=[('England',7,'England'),(None,7,'England, Scotland and Wales')] #,('Scotland',7,'Scotland'),('Wales',5,'Wales')
for p in range(len(plots)):
what=plots[p]
print what[2]
window=what[1]
timeseries,dates,codes=UKCovid19Data.getUKCovid19Data(what[0],window+1,None) # Need 8 days to get 7 growth rates.
print len(timeseries),'timeseries'
for c in timeseries.keys():
print ' ',c,codes[c],timeseries[c]
interesting=frozenset(timeseries.keys())
codeRewrites=UKCovid19Data.getUKCodeRewrites(interesting)
votesTotal,votesLeave=getVotesLeave(codeRewrites,interesting)
# Couple of fixups to census data
codeRewrites['E06000048']='E06000057' # Northumberland
codeRewrites['E08000020']='E08000037' # Gateshead
populationTotal,populationAged=getDemographics(codeRewrites,interesting)
oldies={k:populationAged[k]/populationTotal[k] for k in populationTotal.keys()}
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import distutils.dir_util
import math
import numpy as np
import UKCovid19Data
for what in [('England', 7, None), ('Scotland', 7, None), ('Wales', 7, None),
(None, 7, None)]:
timeseries, days, codes = UKCovid19Data.getUKCovid19Data(
what[0], what[1] + 1, what[2])
print '------'
print what[0], days[0], days[-1], len(days)
assert len(days) == what[1] + 1
print 'Top 20 case counts'
for k in sorted(timeseries, key=lambda k: timeseries[k][-1],
reverse=True)[:20]:
print ' {:32s}: {:d}'.format(codes[k], int(timeseries[k][-1]))
print
window = what[1]
growth = {
k: (timeseries[k][-1] / timeseries[k][-1 - window])**(1.0 / window)
for k in timeseries if timeseries[k][-1 - window] > 0.0
def probe(filename,column,what,lowerTierPopulation):
income,population=getIncome(filename,column,what,lowerTierPopulation)
print what
for k in rate.keys():
if not k in income:
print 'No income for',k,codes[k]
print ' Highest'
for k in sorted(rate.keys(),key=lambda k: income[k],reverse=True)[:10]:
print ' {:32s}: {:.2f}'.format(codes[k],income[k])
print ' Lowest'
for k in sorted(rate.keys(),key=lambda k: income[k],reverse=False)[:10]:
print ' {:32s}: {:.2f}'.format(codes[k],income[k])
interesting=sorted(rate.keys(),key=lambda k: population[k],reverse=True)
y=np.array([100.0*rate[k] for k in interesting])
x=np.array([income[k] for k in interesting])
c=[UKCovid19Data.colorsByRegion[UKCovid19Data.whichRegion(k)] for k in interesting]
w=np.array([population[k] for k in interesting])
s=np.sqrt(w/50.0)
fig=plt.figure(figsize=(8,6))
plt.scatter(x,y,color=c,alpha=0.8,s=s)
r=scipy.stats.linregress(x,y)
gradient,intercept,r_value,p_value,std_err=r
rx=np.linspace(min(x),max(x),100)
ry=gradient*rx+intercept
plt.plot(rx,ry,color='tab:orange',label='Linear regression (unweighted)')
coef=np.polyfit(x,y,1,w=w)
ry=coef[1]+coef[0]*rx
plt.plot(rx,ry,color='tab:red',label='Linear regression (weighted)')
rw=corr(x,y,w)
coef=np.polyfit(x,y,2,w=w)
qy=coef[2]+coef[1]*rx+coef[0]*rx**2
plt.plot(rx,qy,color='tab:green',label='Quadratic best fit (weighted)')
ax=plt.gca()
vals=ax.get_yticks()
ax.set_yticklabels(['{:,.1f}%'.format(x) for x in vals])
plt.ylabel('Daily % increase rate\n({} to {})'.format(dates[0],dates[-1]))
plt.xlabel(what)
# plt.xscale('symlog') # Meh.
regionsUsed=sorted(list(set([UKCovid19Data.whichRegion(k) for k in interesting])))
handles,labels = ax.get_legend_handles_labels()
handles.extend([matplotlib.patches.Patch(color=UKCovid19Data.colorsByRegion[k],label=k) for k in regionsUsed])
plt.legend(handles=handles,loc='upper right',prop={'size':6})
plt.title('England, Scotland and Wales UTLAs: {}\nr={:.3f} (weighted), r={:.3f} (unweighted),'.format(filename,rw,r_value))
distutils.dir_util.mkpath('output')
plt.savefig('output/income-{}.png'.format(filename),dpi=96)
correlation[what]=r_value
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import scipy.stats
import UKCovid19Data
def cov(x, y, w):
return np.sum(w * (x - np.average(x, weights=w)) * (y - np.average(y, weights=w))) / np.sum(w)
def corr(x, y, w):
return cov(x, y, w) / np.sqrt(cov(x, x, w) * cov(y, y, w))
window=7
timeseries,dates,codes=UKCovid19Data.getUKCovid19Data(None,window+1,None) # Need 8 days to get 7 growth rates.
print '***',dates
interesting=frozenset(timeseries.keys())
codeRewrites=UKCovid19Data.getUKCodeRewrites(interesting)
rate={k:(timeseries[k][-1]/timeseries[k][-1-window])**(1.0/(window))-1.0 for k in timeseries.keys() if timeseries[k][-1-window]>0.0}
for k in sorted(rate.keys(),key=lambda k: rate[k],reverse=True):
print k,codes[k],rate[k]
def getLowerTierPopulation():
csvfile=open('data/income/Population-Table 1.csv','rb')
reader=csv.reader(csvfile)
# at
# https://www.gov.uk/government/statistics/english-indices-of-deprivation-2019
import csv
import distutils.dir_util
import math
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import scipy.stats
import UKCovid19Data
window = 7
timeseries, dates, codes = UKCovid19Data.getUKCovid19Data(
'England', window + 1, None) # Need 8 days to get 7 growth rates.
rate = {
k: (timeseries[k][-1] / timeseries[k][-1 - window])**(1.0 / (window)) - 1.0
for k in timeseries.keys() if timeseries[k][-1 - window] > 0.0
}
for k in sorted(rate.keys(), key=lambda k: rate[k], reverse=True):
print k, codes[k], rate[k]
def getDeprivation(filename, column, what):
csvfile = open('data/deprivation/{}-Table 1.csv'.format(filename), 'rb')
reader = csv.reader(csvfile)
firstRow = True
fig = plt.figure(figsize=(16, 9))
mdayslo = None
mdayshi = None
texts = []
totalbase = 0.0
numbase = 0
for what in [
('England', None, datetime.date(2020, 3, 8)),
('Scotland', None, datetime.date(2020, 3, 8)),
('Wales', None, datetime.date(2020, 3, 21))
]: # TODO: Northern Ireland data starts 26th March... but gappy 28th&29th?
timeseries, days, codes = UKCovid19Data.getUKCovid19Data(
*what, skip=set(['E06000017']))
mdays = [mdates.date2num(d) for d in days]
z = 0
for k in sorted(timeseries.keys(),
key=lambda k: timeseries[k][-1],
reverse=False
): # Plot highest current case counts with higher z
cases = np.array([y for y in timeseries[k]])
if chart == 4 or chart == 5:
cases = active(cases)
assert len(days) == len(cases)
areas[lad].add(pcon)
areas[lad].add(ward)
if pcon in interesting:
areas[pcon].add(pcon)
areas[pcon].add(ward)
if ward in interesting:
areas[ward].add(ward)
return dict(areas)
window = 7
timeseries, dates, codes = UKCovid19Data.getUKCovid19Data(
'England', window + 1, None)
rate = {
k: (timeseries[k][-1] / timeseries[k][-1 - window])**(1.0 / (window)) - 1.0
for k in timeseries.keys() if timeseries[k][-1 - window] > 0.0
}
interesting = frozenset(rate.keys())
print len(interesting), 'interesting areas (from growth rate)'
areas = getAreas(interesting)
rawvotes = {2017: getRawVotes(2017), 2019: getRawVotes(2019)}
votes = {2017: {}, 2019: {}}
for year in [2017, 2019]:
for c in interesting: