def Main():
Ratio()
return
pmf1 = Pmf.Pmf()
for x in range(0, 101):
pmf1.Set(x, 1)
pmf1.Normalize()
pmf2 = TrianglePrior()
# plot the priors
myplot.Clf()
myplot.Pmfs([pmf1, pmf2])
myplot.Save(root='simple_coin_both_prior',
title='Biased coin',
xlabel='x',
ylabel='Probability')
RunUpdate(pmf1)
RunUpdate(pmf2)
# plot the posterior distributions
myplot.Clf()
myplot.Pmfs([pmf1, pmf2])
myplot.Save(root='simple_coin_both_post',
title='Biased coin',
xlabel='x',
ylabel='Probability')
def Main():
truth = ReadTruth()
truth_map = {}
for pcode, label in truth:
truth_map[pcode] = label
labels = ReadLabels()
photo_map, labeler_map = MakeObjects(labels)
RunUpdates(photo_map, labeler_map, labels)
yes = []
no = []
for pcode, photo in photo_map.iteritems():
if pcode in truth_map:
mean = photo.Mean()
if truth_map[pcode] == '1':
yes.append(mean)
else:
no.append(mean)
myplot.Clf()
cdf_yes = thinkbayes.MakeCdfFromList(yes, name='yes')
cdf_no = thinkbayes.MakeCdfFromList(no, name='no')
myplot.Cdfs([cdf_yes, cdf_no])
myplot.Show()
return
myplot.Clf()
PlotPosteriorMeans(photo_map, 'photos')
PlotPosteriorMeans(labeler_map, 'labelers')
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 main():
resp = brfss.Respondents()
resp.ReadRecords(data_dir='res')
d = resp.SummarizeHeight()
man_d = d[1]
lady_d = d[2]
# 男性的mu, var, sigma, 变异系数CV
man_mu, man_var = thinkstats.TrimmedMeanVar(man_d)
man_sigma = math.sqrt(man_var)
man_cv = man_sigma/man_mu
print("man: mu = %.3f, var = %.3f, sigma = %.3f, cv = %.3f" % (man_mu, man_var, man_sigma, man_cv))
# 女性的mu, var, sigma, 变异系数CV
lady_mu, lady_var = thinkstats.TrimmedMeanVar(lady_d)
lady_sigma = math.sqrt(lady_var)
lady_cv = lady_sigma/lady_mu
print("lady: mu = %.3f, var = %.3f, sigma = %.3f, cv = %.3f" % (lady_mu, lady_var, lady_sigma, lady_cv))
# 男性, 女性Hist分布
man_hist = Pmf.MakeHistFromList(man_d, name='man hist')
myplot.Hist(man_hist)
myplot.Show()
myplot.Clf()
lady_hist = Pmf.MakeHistFromList(lady_d, name='lady hist')
myplot.Hist(lady_hist)
myplot.Show()
myplot.Clf()
# 男性, 女性Pmf分布
man_pmf = Pmf.MakePmfFromHist(man_hist, name='man pmf')
myplot.Pmf(man_pmf)
myplot.Show()
myplot.Clf()
lady_pmf = Pmf.MakePmfFromHist(lady_hist, name='lady pmf')
myplot.Pmf(lady_pmf)
myplot.Show()
myplot.Clf()
# 男性/女性Cdf累积分布
man_cdf = Cdf.MakeCdfFromPmf(man_pmf, name='man cdf')
lady_cdf = Cdf.MakeCdfFromPmf(lady_pmf, name='lady cdf')
myplot.Cdfs((man_cdf, lady_cdf), complement=False, transform=None)
myplot.Show()
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 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():
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 Resample(cdf, n=10000):
sample = cdf.Sample(n)
new_cdf = Cdf.MakeCdfFromList(sample, 'resampled')
myplot.Clf()
myplot.Cdfs([cdf, new_cdf])
myplot.Save(root='resample_cdf',
title='CDF',
xlabel='weight in oz',
ylabel='CDF(x)')
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():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
pmf = Pmf.MakePmfFromList(speeds, 'actual speeds')
observed = BiasPmf(pmf, 7.5, 'observed speeds')
myplot.Clf()
myplot.Hist(observed)
myplot.Show(title='observed speeds',
xlabel='speed (mph)',
ylabel='probability')
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 MakeExample():
"""Make a simple example CDF."""
t = [2, 1, 3, 2, 5]
cdf = Cdf.MakeCdfFromList(t)
myplot.Clf()
myplot.Cdf(cdf)
myplot.Save(root='example_cdf',
title='CDF',
xlabel='x',
ylabel='CDF(x)',
axis=[0, 6, 0, 1],
legend=False)
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 MakeFigures(exam, alice, bob):
formats = ['png']
myplot.Pmf(exam.prior, label='prior')
myplot.Save(root='sat_prior', formats=formats, xlabel='p', ylabel='PMF')
myplot.Clf()
myplot.Pmfs([alice, bob])
myplot.Save(root='sat_posterior',
formats=formats,
xlabel='p',
ylabel='PMF')
def MakeFigures():
pops = populations.ReadData()
print len(pops)
cdf = Cdf.MakeCdfFromList(pops, 'populations')
myplot.Clf()
myplot.Cdf(cdf)
myplot.Save(root='populations',
title='City/Town Populations',
xlabel='population',
ylabel='CDF',
legend=False)
myplot.Clf()
myplot.Cdf(cdf)
myplot.Save(root='populations_logx',
title='City/Town Populations',
xlabel='population',
ylabel='CDF',
xscale='log',
legend=False)
myplot.Clf()
myplot.Cdf(cdf, complement=True)
myplot.Save(root='populations_loglog',
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 PlotCdfs(samples):
"""Make CDFs showing the distribution of outliers."""
cdfs = []
for label, sample in samples.iteritems():
outliers = [x for x in sample if x < 150]
cdf = Cdf.MakeCdfFromList(outliers, label)
cdfs.append(cdf)
myplot.Clf()
myplot.Cdfs(cdfs)
myplot.Save(root='bayes_height_cdfs',
title='CDF of height',
xlabel='Reported height (cm)',
ylabel='CDF')
def MakeFigures(pmf, biased_pmf):
"""Makes figures showing the CDF of the biased and unbiased PMFs"""
cdf = Cdf.MakeCdfFromPmf(pmf, 'unbiased')
print('unbiased median', cdf.Percentile(50))
print('percent < 100', cdf.Prob(100))
print('percent < 1000', cdf.Prob(1000))
biased_cdf = Cdf.MakeCdfFromPmf(biased_pmf, 'biased')
print('biased median', biased_cdf.Percentile(50))
myplot.Clf()
myplot.Cdfs([cdf, biased_cdf])
myplot.Save(root='slashdot.logx',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log')
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 CmpNormalModelWithDataSample():
firsts, others, babies = Babies.PartitionBabies()
weights = Babies.GetWightList(babies)
pmf = Pmf.MakePmfFromList(weights)
mu = pmf.Mean()
var = pmf.Var(mu)
sigma = math.sqrt(var)
print("mu = {}, var = {}, sigma = {}".format(mu, var, sigma))
# 经验分布, 数据
cdf = Cdf.MakeCdfFromPmf(pmf, name='data')
myplot.cdf(cdf)
# u, sigma --> 误差函数计算 模型
xs, yy = pmf.Render()
ys = [erf.NormalCdf(x, mu, sigma) for x in xs]
myplot.Plot(xs, ys, label='Model')
myplot.Show()
myplot.Clf()
def MakeFigure(xmin=100, alpha=1.7, mu=150, sigma=25):
"""Makes a figure showing the CDF of height in ParetoWorld.
Compared to a normal distribution.
xmin: parameter of the Pareto distribution
alpha: parameter of the Pareto distribution
mu: parameter of the Normal distribution
sigma: parameter of the Normal distribution
"""
t1 = [xmin * random.paretovariate(alpha) for i in range(10000)]
cdf1 = Cdf.MakeCdfFromList(t1, name='pareto')
t2 = [random.normalvariate(mu, sigma) for i in range(10000)]
cdf2 = Cdf.MakeCdfFromList(t2, name='normal')
myplot.Clf()
myplot.Cdfs([cdf1, cdf2])
myplot.Save(root='pareto_world2',
title='Pareto World',
xlabel='height (cm)',
ylabel='CDF')
# Example 3-10
import random, Pmf, Cdf, myplot
size = 10000
lst = [random.random() for i in range(size)]
lst_pmf = Pmf.MakePmfFromList(lst)
lst_cdf = Cdf.MakeCdfFromList(lst)
myplot.Clf()
myplot.Pmf(lst_pmf)
myplot.Show(title='PMF of {0} randoms'.format(size))
myplot.Clf()
myplot.Cdf(lst_cdf)
myplot.Show(title='CDF of {0} randoms'.format(size))
# yes, the distribution is uniform
