def MakeFigures(pool, firsts, others):
"""Creates several figures for the book."""
bar_options = [
dict(linewidth=0, color='blue'),
dict(linewidth=0, color='orange')
]
# plot PMFs of birth weights for first babies and others
myplot.Hists([firsts.weight_pmf, others.weight_pmf],
root='nsfg_birthwgt_pmf',
bar_options=bar_options,
title='Birth weight PMF',
xlabel='weight (ounces)',
ylabel='probability')
plot_options = [
dict(linewidth=2, color='blue'),
dict(linewidth=2, color='orange')
]
# plot CDFs of birth weights for first babies and others
myplot.Cdfs([firsts.weight_cdf, others.weight_cdf],
root='nsfg_birthwgt_cdf',
plot_options=plot_options,
title='Birth weight CDF',
xlabel='weight (ounces)',
ylabel='probability',
axis=[0, 200, 0, 1])
def testGeneratePrevalence(self):
sample = 'ab'
prior = Pmf.MakePmfFromList(range(1, 4))
meta = rarefaction.MetaHypo(prior, sample)
for taxon in sample:
meta.Update(taxon)
k = 3
taxon = 'other'
iters = 1000
plot = False
hypos = meta.GetHypos()
for hypo, prob in hypos.Items():
self.assertAlmostEquals(prob, 0.4) if hypo.k==2 else 0
self.assertAlmostEquals(prob, 0.6) if hypo.k==3 else 0
if hypo.k != k or not plot:
continue
# check the distribution of generated prevalences
ps = [hypo.GeneratePrevalence().Prob(taxon) for i in xrange(iters)]
cdf = Cdf.MakeCdfFromList(ps)
# compare to what the distribution is supposed to be
dist = hypo.Get(taxon)
ps2 = [dist.Random() for i in xrange(iters)]
cdf2 = Cdf.MakeCdfFromList(ps2)
myplot.Cdfs([cdf, cdf2], show=True)
def main():
# Exercise 5.6
sample_size=365
for n in range(1,6):
distribution = []
for _ in range(sample_size):
distribution.append(get_bread(n))
print(np.mean(distribution), np.std(distribution))
found_distribution = []
for _ in range(sample_size):
found_distribution.append(int(get_bread(4)))
print('picking 4 loaves: mu={} sigma={}'.format(np.mean(found_distribution),np.std(found_distribution)))
expected_distribution = np.random.normal(np.mean(found_distribution), np.std(found_distribution), sample_size)
myplot.Cdfs(cdfs=(Cdf.MakeCdfFromList(found_distribution), Cdf.MakeCdfFromList(expected_distribution)))
myplot.show()
plt.hist(found_distribution, normed=True, bins=20, label='found')
plt.hist(expected_distribution, normed=True, bins=20, alpha=.75, label='expected')
plt.ylabel('Probability')
plt.xlabel('Bread Weight')
plt.legend()
plt.show()
# Exercise 5.7
men_heights = np.random.normal(loc=178, scale=59.4, size=99999)
women_heights = np.random.normal(loc=163, scale=52.8, size=99999)
pairs = zip(men_heights, women_heights)
l = [w>m for m, w in pairs]
print('In {}% of the pairs the woman will be taller than the man'.format(sum(l)/len(l)*100.0))
def PlotDiffs(groups, low, high, root):
"""Plots the CDF of diffs for each group.
Args:
low, high: range of diffs to include
root: string filename root
"""
diff_list = []
for gender, res in groups.iteritems():
diffs = ComputeDiffs(res, low=low, high=high)
diff_list.append((gender, diffs))
print 'PlotDiffs', gender, len(diffs)
cdfs = []
for name, diffs in diff_list:
cdf = Cdf.MakeCdfFromList(diffs, name=name)
cdfs.append(cdf)
options = [dict(linewidth=2) for cdf in cdfs]
myplot.Cdfs(cdfs,
xlabel='time - qualifying time (min)',
ylabel='P(difference < x)',
plot_options=options,
root=root)
def plot_accident_cdfs():
"""Plots CDF of accident counts for the control and treatment areas.
Before and after the date CAWS was deployed (known to be November 1996).
"""
cdfs = []
for label in ['control', 'treatment']:
print label
filename = label + '_data.csv'
col_dict = process_merged_file(filename)
# November 15, 1996
before, after = split_col_dict(col_dict, 1780)
print 'before'
cdf = accident_cdf(before, 'accidents')
cdf.name = label + ' before'
cdfs.append(cdf)
print 'after'
cdf = accident_cdf(after, 'accidents')
cdf.name = label + ' after'
cdfs.append(cdf)
myplot.Cdfs(cdfs,
root='caws.poisson',
transform='exponential',
title='CCDF of Accident Counts',
xlabel='Number of accidents',
ylabel='Complementary CDF')
def PlotCdfs():
"""Plots distribution of ability for different number of factors.
After 100000 people:
n max value
50 0.333842852938
10 0.6483317765470
5 0.837633976492
1 0.983619459771
"""
cdfs = []
for n in [50, 10, 5, 1]:
pmf, data = WorldRecord(m=10000, n=n)
cdf = Cdf.MakeCdfFromPmf(pmf, name='n=%d' % n)
print n, max(cdf.Values())
cdfs.append(cdf)
options = dict(linewidth=2)
plot_options = [options] * len(cdfs)
myplot.Cdfs(cdfs,
root='world_record_cdfs',
plot_options=plot_options,
title='Distribution of potential',
xlabel='potential',
ylabel='CDF')
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 MakeFigure():
frac1 = 0.8
frac2 = 1 - frac1
xs, ys = RenderPdf(1170, 179)
pmf1 = Pmf.MakePmfFromDict(dict(zip(xs, ys)), name='blue')
xs, ys = RenderPdf(995, 167)
pmf2 = Pmf.MakePmfFromDict(dict(zip(xs, ys)), name='green')
myplot.Pmfs(
[pmf1, pmf2],
root='normal1',
xlabel='CLA score',
ylabel='PDF',
)
pmf1.Normalize(frac1)
pmf2.Normalize(frac2)
ymax = max(pmf1.MaxLike(), pmf2.MaxLike())
ymax = 0.003
pyplot.clf()
threshes = [1200, 1300, 1400, 1500, 1570]
for thresh in threshes:
myplot.Plot([thresh, thresh], [0, ymax],
clf=False,
line_options=dict(color='gray', alpha=0.5, linewidth=1))
plot_options = [
dict(color='blue', linewidth=2),
dict(color='green', linewidth=2)
]
myplot.Pmfs(
[pmf1, pmf2],
plot_options=plot_options,
clf=False,
root='normal2',
xlabel='CLA score',
ylabel='PDF',
)
cdf1 = Cdf.MakeCdfFromPmf(pmf1)
cdf2 = Cdf.MakeCdfFromPmf(pmf2)
for thresh in threshes:
p1 = frac1 * (1 - cdf1.Prob(thresh))
p2 = frac2 * (1 - cdf2.Prob(thresh))
den = p1 + p2
rep1 = p1 / den
rep2 = p2 / den
print thresh, den, rep1, rep2
return
myplot.Cdfs([cdf1, cdf2], root='normal2', xlabel='', ylabel='', title='')
def Resample(cdf, n=10000):
sample = cdf.Sample(n)
new_cdf = Cdf.MakeCdfFromList(sample, 'resampled')
myplot.Cdfs([cdf, new_cdf],
root='resample_cdf',
title='CDF',
xlabel='weight in oz',
ylabel='CDF(x)')
def main(): all_recs = cyb_records.Stats() all_recs.ReadRecords() print 'Number of total stats', len(all_recs.records) cdf = CdfPerDay(all_recs.records) myplot.Cdfs(cdf) myplot.Show(title="CDF: daily usage of machines at the YMCA", xlabel = 'Distance (in m / day)', ylabel = 'Percentile')
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 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():
all_recs = cyb_records.Stats()
all_recs.ReadRecords()
print 'Number of total stats', len(all_recs.records)
cdf = CdfPerMachine(all_recs.records)
myplot.Cdfs(cdf)
myplot.Show(title="CDF of cardio machine average distances",
xlabel='Average Distances',
ylabel='Probability')
def main():
firsts, others, babies = Babies.PartitionBabies()
cdf0 = Cdf.MakeCdfFromList(Babies.GetWightList(babies), name='cdf0')
print("Sample(cdf, 10) : ", Sample(cdf0, 10))
d1 = WeightRandomSample(cdf0, 100)
cdf1 = Cdf.MakeCdfFromList(d1, name='cdf1')
d2 = WeightRandomSample(cdf0, 1000)
cdf2 = Cdf.MakeCdfFromList(d2, name='cdf2')
myplot.Cdfs([cdf0, cdf1, cdf2], complement=False, transform=None)
myplot.Show()
def MakeFigure(xmin=100, alpha=1.7, mu=150, sigma=25):
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.Cdfs([cdf1, cdf2],
root='pareto_world2',
title='Pareto World',
xlabel='height (cm)',
ylabel='CDF')
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 main():
firsts, others, babies = Babies.PartitionBabies()
cdf_babies = Cdf.MakeCdfFromList(Babies.GetWightList(babies),
name='babies')
cdf_firsts = Cdf.MakeCdfFromList(Babies.GetWightList(firsts),
name='firsts')
cdf_others = Cdf.MakeCdfFromList(Babies.GetWightList(others),
name='others')
print("babies percentile rank: ", 100 * cdf_babies.Prob(mywt))
print("firsts percentile rank: ", 100 * cdf_firsts.Prob(mywt))
print("others percentile rank: ", 100 * cdf_others.Prob(mywt))
myplot.Cdfs([cdf_babies, cdf_firsts, cdf_others])
myplot.Show()
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.Cdfs([cdf, biased_cdf],
root='slashdot.logx',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log')
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 main():
results = ReadResults()
speeds = GetSpeeds(results)
pmf = Pmf.MakePmfFromList(speeds, 'speeds')
myplot.Pmf(pmf)
myplot.Show(title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
import Cdf
cdf = Cdf.MakeCdfFromList(speeds, 'speeds')
myplot.Cdf(cdf)
myplot.Show()
myplot.Cdfs(cdf)
myplot.Show()
def Main(script):
# read 'em and sort 'em
birthdays = ReadBirthdays()
birthdays.sort()
# compute the intervals in days
deltas = Diff(birthdays)
days = [inter.days for inter in deltas]
# make and plot the CCDF on a log scale.
cdf = Cdf.MakeCdfFromList(days, name='intervals')
myplot.Cdfs([cdf],
'intervals',
xlabel='days',
ylabel='ccdf',
yscale='log',
complement=True)
def PlotPrevalence(self, root=None, clf=False, n=6):
"""Looks up the PMFs for a given taxon and plots them."""
if root: clf = True
cdfs = []
for taxon in lowercase[:n]:
pmf = self.GetPrevalence(taxon)
cdf = Cdf.MakeCdfFromPmf(pmf)
cdfs.append(cdf)
median = cdf.Percentile(50)
ci = cdf.Percentile(5), cdf.Percentile(95)
print taxon, median, ci
myplot.Cdfs(cdfs,
root=root,
clf=clf,
xlabel='prevalence',
ylabel='prob')
def MakeFigures(pool, firsts, others):
"""Creates several figures for the book."""
# plot CDFs of birth ages for first babies and others
line_options = [dict(linewidth=0.5), dict(linewidth=0.5)]
myplot.Cdfs([firsts.age_cdf, others.age_cdf],
root='nsfg_age_cdf',
line_options=line_options,
title="Mother's age CDF",
xlabel='age (years)',
ylabel='probability')
# 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='age_scatter',
xlabel='Age (years)',
ylabel='Birth weight (oz)',
legend=False)
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')
def PlotDiffs(half_diffs, diffs):
half_cdf = Cdf.MakeCdfFromList(half_diffs, 'half')
cdf = Cdf.MakeCdfFromList(diffs, 'full')
options = dict(linewidth=2)
myplot.Cdfs([half_cdf, cdf],
xlabel='time - qualifying time (min)',
ylabel='CDF',
plot_options=[options, options],
root='marathon_cdf')
diffs = [int(x) for x in diffs]
half_diffs = [int(x) for x in half_diffs]
pmf = Pmf.MakePmfFromList(diffs, 'full')
half_pmf = Pmf.MakePmfFromList(half_diffs, 'half')
myplot.Pmfs([half_pmf, pmf],
xlabel='time - qualifying time (min)',
ylabel='PMF',
plot_options=[options, options],
root='marathon_pmf')
#!/usr/bin/python3
# -*- coding: utf-8 -*-
import math
import Babies
import Cdf
import myplot
import thinkstats
import erf
if __name__ == "__main__":
firsts, others, babies = Babies.PartitionBabies()
preglengths = Babies.GetPregnacyList(babies)
mu = thinkstats.Mean(preglengths)
sigma = math.sqrt(thinkstats.Var(preglengths, mu))
print("mu = %.3f sigma = %.3f" % (mu, sigma))
cdf0 = Cdf.MakeCdfFromList(preglengths, name='cdf0')
ys = [erf.NormalCdf(x, mu=mu, sigma=sigma) for x in preglengths]
cdf1 = Cdf.Cdf(preglengths, ys, 'cdf1')
myplot.Cdf(cdf1, complement=False, transform=None)
myplot.Cdfs([cdf0, cdf1], complement=False, transform=None)
myplot.Show()
# TODO wrong
License: GNU GPLv3 http://www.gnu.org/licenses/gpl.html
"""
import math
import random
import matplotlib.pyplot as pyplot
import Cdf
import myplot
import Pmf
cdfs = []
allbday = []
for i in range(10):
n = 30
t = [random.randrange(365) for i in range(n)]
t.sort()
pmf = Pmf.Pmf()
for i in range(len(t) - 1):
x = t[i + 1] - t[i]
pmf.Incr(x)
allbday.append(x)
cdf = Cdf.MakeCdfFromPmf(pmf)
cdfs.append(cdf)
cdf = Cdf.MakeCdfFromList(allbday, 'all')
cdfs.append(cdf)
myplot.Cdfs(cdfs, root='birthday', transform='exponential')
# Example 3-9
import survey, Cdf, myplot
def Sample(cdf, n):
#return [cdf.Value(random.random()) for i in range(n)]
#return random.sample(Cdf.Values(), n)
return [cdf.Random() for i in range(n)]
table = survey.Pregnancies()
table.ReadRecords()
births = [rec for rec in table.records if rec.outcome == 1]
weights = [x.birthwgt_lb for x in births if x.birthwgt_lb < 97]
weights_cdf = Cdf.MakeCdfFromList(weights, 'birth weights')
sample = Sample(weights_cdf, 10000)
sample_cdf = Cdf.MakeCdfFromList(sample, 'sample weights')
myplot.Clf()
myplot.Cdfs( (weights_cdf, sample_cdf) )
myplot.Show(title='CDF of all birth weights',
xlabel='weight (lbs)',
ylabel='cumulative probability')
