def main():
import myplot
pmf = Pmf.MakePmfFromList([1, 2, 3, 3, 4, 4, 5, 5, 5, 6, 6, 7])
remain = PmfRemainingLifeTime(pmf, age=4)
myplot.Hist(pmf)
myplot.Show()
myplot.Hist(remain)
myplot.Show()
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():
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 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():
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():
firsts, others, babies = Babies.PartitionBabies()
d = Babies.GetPregnacyList(babies)
hist = Pmf.MakeHistFromList(d, name='pregnacylist')
myplot.Hist(hist)
myplot.Show()
g1 = Skewness(d)
gp = PearsonSkewness(d)
print("g1 = %.3f, gp = %.3f" % (g1, gp))
skewness.show_skewness(l=d, name='pregnancy skewness')
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():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
pmf = Pmf.MakePmfFromList(speeds, 'speeds')
pmf = BiasPmf(7,pmf)
myplot.Hist(pmf)
#myplot.Show(title='PMF of observed speed',
# xlabel='speed (mph)',
# ylabel='probability')
myplot.Save(
formats=['png'],
root='runner',
title='PMF of observed speed',
xlabel='speed (mph)',
ylabel='probability')
def main():
ran = generate_random_sample(1000)
pmf = Pmf.MakePmfFromList(ran)
cdf = Cdf.MakeCdfFromPmf(pmf)
myplot.Cdf(cdf)
myplot.show()
myplot.scatter(*cdf.Render())
myplot.show()
myplot.Hist(pmf)
myplot.show()
myplot.Pmf(pmf)
myplot.show()
def __init__(self):
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
self.speeds = speeds
self.pmf = Pmf.MakePmfFromList(speeds)
def BiasedPmf(self, speed):
new_pmf = self.pmf.Copy()
for other_speed,p in new_pmf.Items():
diff = abs(other_speed - speed)
new_pmf.Mult(other_speed, diff)
new_pmf.Normalize()
return new_pmf
if __name__ == '__main__':
r = RelayPmf()
biased = r.BiasedPmf(7.5)
print "Variance", biased.Var()
print "Mean", biased.Mean()
myplot.Clf()
myplot.Hist(biased)
myplot.Save(root='observed_speeds',
title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
def main(name, data_dir='.'):
hist = Pmf.MakeHistFromList([1, 2, 2, 3, 5])
print(hist.Freq(2))
myplot.Hist(hist)
myplot.Show()
def MakeHistogram(table):
lengths = [record.prglength for record in table.records]
hist = Pmf.MakeHistFromList(lengths, name='pregnancy length')
myplot.Hist(hist, show=True, xlabel='weeks', ylabel='count')