def MakeFigures():
pops = populations.Process()
print len(pops)
cdf = Cdf.MakeCdfFromList(pops, 'populations')
myplot.Cdf(cdf,
root='populations',
title='City/Town Populations',
xlabel='population',
ylabel='CDF',
legend=False)
myplot.Cdf(cdf,
root='populations_logx',
title='City/Town Populations',
xlabel='population',
ylabel='CDF',
xscale='log',
legend=False)
myplot.Cdf(cdf,
root='populations_loglog',
complement=True,
title='City/Town Populations',
xlabel='population',
ylabel='Complementary CDF',
yscale='log',
xscale='log',
legend=False)
t = [math.log(x) for x in pops]
t.sort()
rankit.MakeNormalPlot(t, 'populations_rankit')
def main():
#cdf, place = total_percentile_rank(results)
speeds = relay.GetSpeeds(results)
speed = relay.ConvertPaceToSpeed('6:53')
cdf = Cdf.MakeCdfFromList(speeds)
print cdf.Prob(speed),'speed'
print convert_speeds_to_time(speed),'time'
myplot.Cdf(cdf)
myplot.Show()
speeds_old = GetSpeeds_M4049(results)
cdf_old = Cdf.MakeCdfFromList(speeds_old)
rank = cdf_old.Prob(speed)
print rank,'rank', speed,'speed'
print convert_speeds_to_time(speed),'time'
myplot.Cdf(cdf_old)
myplot.Show()
speeds_5059 = GetSpeeds_M5059(results)
cdf_5059 = Cdf.MakeCdfFromList(speeds_5059)
future_speed = cdf_5059.Value(rank)
print future_speed,'speed'
print convert_speeds_to_time(future_speed),'time'
myplot.Cdf(cdf_5059)
myplot.Show()
fspeeds = GetSpeeds_F2039(results)
cdf_female = Cdf.MakeCdfFromList(fspeeds)
fspeed = cdf_female.Value(rank)
print fspeed,'speed'
print convert_speeds_to_time(fspeed),'time'
myplot.Cdf(cdf_female)
myplot.Show()
def MakeFigure():
fp = open('babyboom.dat')
# skip to the beginning of the data
for line in fp:
if line.find('START DATA') != -1:
break
# read a list of times
times = []
for line in fp:
t = line.split()
time = int(t[-1])
times.append(time)
# compute interarrival times
diffs = [times[0]]
for i in range(len(times)-1):
diff = times[i+1] - times[i]
diffs.append(diff)
n = len(diffs)
mu = thinkstats.Mean(diffs)
print 'mean interarrival time', mu
cdf = Cdf.MakeCdfFromList(diffs, 'actual')
sample = [random.expovariate(1/mu) for i in range(n)]
model = Cdf.MakeCdfFromList(sample, 'model')
myplot.Cdf(cdf)
myplot.Save(root='interarrivals',
title='Time between births',
xlabel='minutes',
ylabel='CDF',
legend=False,
formats=['eps', 'png', 'pdf'])
myplot.Cdfs([cdf, model], complement=True)
myplot.Save(root='interarrivals_model',
title='Time between births',
xlabel='minutes',
ylabel='Complementary CDF',
yscale='log',
formats=['eps', 'png', 'pdf'])
pyplot.subplots_adjust(bottom=0.11)
myplot.Cdf(cdf, complement=True)
myplot.Save(root='interarrivals_logy',
title='Time between births',
xlabel='minutes',
ylabel='Complementary CDF',
yscale='log',
legend=False,
formats=['eps', 'png', 'pdf'])
def main():
data_dir = '../chap1/'
preg = survey.Pregnancies()
preg.ReadRecords(data_dir)
cdf = weight_cdf(preg)
myplot.Cdf(cdf)
myplot.show()
sample = Sample(cdf, 1000)
cdf_sample = Cdf.MakeCdfFromList(sample)
myplot.Cdf(cdf_sample)
myplot.Show()
def main(script, *args):
data = ReadIncomeFile()
hist, pmf, cdf = MakeIncomeDist(data)
# plot the CDF on a log-x scale
myplot.Cdf(cdf, root='income_logx', xscale='log')
# plot the complementary CDF on a log-log scale
myplot.Cdf(cdf,
root='income_loglog',
complement=True,
xscale='log',
yscale='log',
show=True)
def observe_data(l, name=None, show=False):
cdf = pmf = None
if isinstance(l, list):
cdf = Cdf.MakeCdfFromList(l,name+' cdf')
pmf = Pmf.MakePmfFromList(l, name+' pmf')
elif isinstance(l, Pmf.Pmf):
pmf = l
cdf = Cdf.MakeCdfFromPmf(l)
if name is None: name = pmf.name
elif isinstance(l, Cdf.Cdf):
cdf = l
if name is None: name = cdf.name
else:
raise Exception('input parameter type is wrong')
v_25, median, v_75 = cdf.Percentile(25), cdf.Percentile(50), cdf.Percentile(75)
mean = cdf.Mean()
print('%s: 1/4:%4.2f(%4.2f), 1/2:%4.2f(mean-median:%4.2f), mean:%4.2f, 3/4:%4.2f(%4.2f)' % \
(name, v_25, median-v_25, median, mean-median, mean, v_75,v_75-median))
if show:
if pmf is not None:
myplot.Pmf(pmf)
myplot.Show()
myplot.Cdf(cdf)
myplot.Show()
def main():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
# plot the distribution of actual speeds
pmf = Pmf.MakePmfFromList(speeds, 'actual speeds')
# myplot.Clf()
# myplot.Hist(pmf)
# myplot.Save(root='observed_speeds',
# title='PMF of running speed',
# xlabel='speed (mph)',
# ylabel='probability')
# plot the biased distribution seen by the observer
biased = BiasPmf(pmf, 7.5, name='observed speeds')
myplot.Clf()
myplot.Hist(biased)
myplot.Save(root='observed_speeds',
title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
cdf = Cdf.MakeCdfFromPmf(biased)
myplot.Clf()
myplot.Cdf(cdf)
myplot.show(root='observed_speeds_cdf',
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='cumulative probability')
def PlotAges(resp):
"""Plot the distribution of ages."""
ages = [r.age for r in resp.records]
cdf = Cdf.MakeCdfFromList(ages)
myplot.Clf()
myplot.Cdf(cdf)
myplot.Show()
def main():
# Exercise 3.6
myBirthWeight = 163
table = survey.Pregnancies()
table.ReadRecords()
unfilteredLiveBirthWeights = [(p.birthwgt_lb, p.birthwgt_oz)
for p in table.records if p.outcome == 1]
liveBirthWeights = [
lbs * 16 + oz for lbs, oz in unfilteredLiveBirthWeights
if type(lbs) == int and type(oz) == int and lbs * 16 + oz <= 200
]
liveBirthWeightsCdf = Cdf.MakeCdfFromList(liveBirthWeights,
name="live birth weights")
print("My birth weight percentile rank (vs all births): %d" %
(100 * liveBirthWeightsCdf.Prob(myBirthWeight)))
unfilteredNotFirstLiveBirthWeights = [(p.birthwgt_lb, p.birthwgt_oz)
for p in table.records
if p.outcome == 1 and p.birthord != 1
]
notFirstLiveBirthWeights = [
lbs * 16 + oz for lbs, oz in unfilteredNotFirstLiveBirthWeights
if type(lbs) == int and type(oz) == int and lbs * 16 + oz <= 200
]
notFirstLiveBirthWeightsCdf = Cdf.MakeCdfFromList(
notFirstLiveBirthWeights, name="not first live birth weights")
print("My birth weight percentile rank (vs first births): %d" %
(100 * notFirstLiveBirthWeightsCdf.Prob(myBirthWeight)))
myplot.Cdf(notFirstLiveBirthWeightsCdf)
myplot.Show(title="not first live birth weight CDF",
xlabel="birth weight oz",
ylabel="probability")
def process(data):
# Hist 分布图
hist = Pmf.MakeHistFromList(data, name='hist')
myplot.Hist(hist, color='blue')
myplot.Show()
# Pmf 分布图
pmf = Pmf.MakePmfFromHist(hist, name='pmf')
myplot.Pmf(pmf, color='yellow')
myplot.Show()
myplot.Clf()
# 实际数据的CDF分布图
cdf = Cdf.MakeCdfFromList(data, name='loafs')
myplot.Cdf(cdf)
mu, var = thinkstats.MeanVar(data)
sigma = math.sqrt(var)
print("mu = %.3f, sigma = %.3f" % (mu, sigma))
# 正态分布
xs = normal_sample(len(data), mu, sigma) # xs = data
ys = [erf.NormalCdf(x, mu=mu, sigma=sigma) for x in xs]
myplot.Scatter(xs, ys, color='red', label='sample')
myplot.Show()
def main():
babies = BabyBoom.Babies()
babies.ReadRecords(data_dir='res', n=None)
lastmin = 0
interval = []
for item in babies.records:
interval.append(item.minutes - lastmin)
lastmin = item.minutes
cdf = Cdf.MakeCdfFromList(interval, name='baby interval')
myplot.Cdf(cdf, complement=False, transform=None)
myplot.Show()
# y轴取log(CCDF) : CCDF(X) = 1 - CDF(X)
myplot.Clf()
myplot.Cdf(cdf, complement=True, yscale='log')
myplot.Show()
def main():
sz, alph, exem = 1000, 1.7, 100
lst = paretovariate(sz, alph, exem)
lst_cdf = Cdf.MakeCdfFromList(lst)
myplot.Clf()
myplot.Cdf(lst_cdf, complement=True, xscale='log', yscale='log')
myplot.Show(title='CCDF of {0} random paretovariates'.format(sz))
def MakeCdfs(lens):
cdf = Cdf.MakeCdfFromList(lens, 'slashdot')
myplot.Clf()
myplot.Cdf(cdf)
myplot.Save(root='slashdot.logx',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log')
myplot.Clf()
myplot.Cdf(cdf, complement=True)
myplot.Save(root='slashdot.loglog',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log',
yscale='log')
def MakeFigures(pool, firsts, others):
"""Creates several figures for the book."""
# CDF of all ages
myplot.Clf()
myplot.Cdf(pool.age_cdf)
myplot.Save(root='agemodel_age_cdf',
title="Distribution of mother's age",
xlabel='age (years)',
ylabel='CDF',
legend=False)
# CDF of all weights
myplot.Clf()
myplot.Cdf(pool.weight_cdf)
myplot.Save(root='agemodel_weight_cdf',
title="Distribution of birth weight",
xlabel='birth weight (oz)',
ylabel='CDF',
legend=False)
# plot CDFs of birth ages for first babies and others
myplot.Clf()
myplot.Cdfs([firsts.age_cdf, others.age_cdf])
myplot.Save(root='agemodel_age_cdfs',
title="Distribution of mother's age",
xlabel='age (years)',
ylabel='CDF')
myplot.Clf()
myplot.Cdfs([firsts.weight_cdf, others.weight_cdf])
myplot.Save(root='agemodel_weight_cdfs',
title="Distribution of birth weight",
xlabel='birth weight (oz)',
ylabel='CDF')
# make a scatterplot of ages and weights
ages, weights = GetAgeWeight(pool)
pyplot.clf()
#pyplot.scatter(ages, weights, alpha=0.2)
pyplot.hexbin(ages, weights, cmap=matplotlib.cm.gray_r)
myplot.Save(root='agemodel_scatter',
xlabel='Age (years)',
ylabel='Birth weight (oz)',
legend=False)
def PlotPosteriorMeans(d, name):
"""Plots the CDF of the means of the posteriors.
d: map from code to posterior Suite
name: label for the cdf
"""
means = [item.Mean() for item in d.itervalues()]
cdf = thinkbayes.MakeCdfFromList(means, name=name)
myplot.Cdf(cdf)
def CheckCdf2():
"""Compare chi2 values from the simulation with a chi-squared dist."""
df = 3
t = [SimulateChi2() for i in range(1000)]
t2 = [scipy.stats.chi2.cdf(x, df) for x in t]
cdf = Cdf.MakeCdfFromList(t2)
myplot.Cdf(cdf)
myplot.Show()
def main():
list = [100 * random.random() for i in range(1000)]
pmf = Pmf.MakePmfFromList(list, name='pfm')
cdf = Cdf.MakeCdfFromList(list, name='cdf')
myplot.Pmf(pmf)
myplot.Show()
myplot.Clf()
myplot.Cdf(cdf)
myplot.Show()
def main():
#Exercise 3.5
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
speedsCdf = Cdf.MakeCdfFromList(speeds, "race speeds")
mplt.Cdf(speedsCdf)
mplt.show(title="Race Speed CDF",
xlabel="speed in mph",
ylabel="probability")
def PlotPosterior(self, root=None, clf=False):
if root: clf = True
posterior = self.Cdf()
myplot.Cdf(posterior,
root=root,
clf=clf,
xlabel='# of taxa',
ylabel='prob',
legend=False)
def MakeExample():
"""Make a simple example CDF."""
t = [2, 1, 3, 2, 5]
cdf = Cdf.MakeCdfFromList(t)
myplot.Cdf(cdf,
root='example_cdf',
title='CDF',
xlabel='x',
ylabel='CDF(x)',
axis=[0, 6, 0, 1],
legend=False)
def Q2(results):
results.sort()
# print(results)
cdf = Cdf.MakeCdfFromList(results, name='cdf')
myplot.Cdf(cdf)
myplot.Show()
p = [0.95, 0.99]
for i in p:
significant_value = cdf.Value(i)
print("p:%4.2f significant_value = %d" % (i, significant_value))
pass
def CheckCdf():
"""
"""
xs, ys = Chi2Cdf(df=3, high=15)
pyplot.plot(xs, ys)
t = [SimulateChi2() for i in range(1000)]
cdf = Cdf.MakeCdfFromList(t)
myplot.Cdf(cdf)
myplot.Show()
def main():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
# plot the distribution of actual speeds
cdf = Cdf.MakeCdfFromList(speeds, 'speeds')
myplot.Cdf(cdf,
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='probability',
show=True)
def PlotMarginals(suite):
"""Plot the marginal distributions for a 2-D joint distribution."""
pmf_m, pmf_s = ComputeMarginals(suite)
pyplot.clf()
pyplot.figure(1, figsize=(7, 4))
pyplot.subplot(1, 2, 1)
cdf_m = Cdf.MakeCdfFromPmf(pmf_m, 'mu')
myplot.Cdf(cdf_m)
pyplot.xlabel('Mean height (cm)')
pyplot.ylabel('CDF')
pyplot.subplot(1, 2, 2)
cdf_s = Cdf.MakeCdfFromPmf(pmf_s, 'sigma')
myplot.Cdf(cdf_s)
pyplot.xlabel('Std Dev height (cm)')
pyplot.ylabel('CDF')
myplot.Save(root='bayes_height_marginals_%s' % suite.name)
def main():
pareto = paretovariate(1, 0.5)
cdf = Cdf.MakeCdfFromList(pareto)
myplot.Cdf(cdf)
myplot.show()
ccdf = ccdf_list(cdf)
plt = myplot.pyplot
plt.plot(cdf.Values(), ccdf)
plt.xscale('log')
plt.yscale('log')
plt.show()
def main(script, *args):
data = ReadIncomeFile()
hist, pmf, cdf = MakeIncomeDist(data)
# plot the CDF on a log-x scale
myplot.Clf()
myplot.Cdf(cdf)
myplot.Save(root='income_logx',
xscale='log',
xlabel='income',
ylabel='CDF')
# plot the complementary CDF on a log-log scale
myplot.Clf()
myplot.Cdf(cdf, complement=True)
myplot.Save(root='income_loglog',
complement=True,
xscale='log',
yscale='log',
xlabel='income',
ylabel='complementary CDF')
def MakeFigures(pool, firsts, others):
"""Creates several figures for the book."""
# plot PMFs of birth weights for first babies and others
myplot.Clf()
myplot.Hist(firsts.weight_pmf, linewidth=0, color='blue')
myplot.Hist(others.weight_pmf, linewidth=0, color='orange')
myplot.Save(root='nsfg_birthwgt_pmf',
title='Birth weight PMF',
xlabel='weight (ounces)',
ylabel='probability')
# plot CDFs of birth weights for first babies and others
myplot.Clf()
myplot.Cdf(firsts.weight_cdf, linewidth=2, color='blue')
myplot.Cdf(others.weight_cdf, linewidth=2, color='orange')
myplot.Save(root='nsfg_birthwgt_cdf',
title='Birth weight CDF',
xlabel='weight (ounces)',
ylabel='probability',
axis=[0, 200, 0, 1])
def main():
"""when k=1 weibull would be liner"""
weibull = weibullvariate(1, 1)
cdf = Cdf.MakeCdfFromList(weibull)
myplot.Cdf(cdf)
myplot.show()
ccdf = ccdf_list(cdf)
plt = myplot.pyplot
plt.plot(cdf.Values(), ccdf)
#plt.xscale('log')
plt.yscale('log')
plt.show()
def main():
# Exercise 3.9
table = survey.Pregnancies()
table.ReadRecords()
unfilteredLiveBirthWeights = [(p.birthwgt_lb, p.birthwgt_oz)
for p in table.records if p.outcome == 1]
liveBirthWeights = [
lbs * 16 + oz for lbs, oz in unfilteredLiveBirthWeights
if type(lbs) == int and type(oz) == int and lbs * 16 + oz <= 200
]
liveBirthWeightsCdf = Cdf.MakeCdfFromList(liveBirthWeights,
name="live birth weights")
samepleListLiveBirthWeights = sample(liveBirthWeightsCdf, 1000)
myplot.Cdf(Cdf.MakeCdfFromList(samepleListLiveBirthWeights))
myplot.show(title="CDF of live births resampled")
# Exercise 3.10
randomList = [random.random() for x in range(1000)]
myplot.Pmf(Pmf.MakePmfFromList(randomList))
myplot.show(title="random pmf")
myplot.Cdf(Cdf.MakeCdfFromList(randomList))
myplot.Show(title="random cdf")
def main():
# 通过公式计算F(X)
lamb = 1 / 32.6
xs = sorted([random.expovariate(lamb) for i in range(43)])
ys = [1 - pow(math.e, -lamb * x) for x in xs]
myplot.Plot(xs, ys, label='formular')
# 通过累计统计F(X) ---> 经验CDF
cdf = Cdf.MakeCdfFromList(xs, name='expovariate')
print("mu = ", cdf.Mean())
print("median = ", cdf.Percentile(50))
myplot.Cdf(cdf, complement=False, transform=None)
myplot.Show()
