def _resample(cdf, n=10000):
sample = cdf._sample(n)
new_cdf = _13_Cdf._make_cdf_from_list(sample, 'resampled')
_05_myplot._clf()
_05_myplot._cdfs([cdf, new_cdf])
_05_myplot._save(root='resample_cdf',
title='CDF',
xlabel='weight in oz',
ylabel='CDF(x)')
def _plot_cdfs(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 = _13_Cdf._make_cdf_from_list(outliers, label)
cdfs.append(cdf)
_05_myplot._clf()
_05_myplot._cdfs(cdfs)
_05_myplot._save(root='bayes_height_cdfs',
title='CDF of height',
xlabel='Reported height (cm)',
ylabel='CDF')
def _make_figures(pmf, biased_pmf):
"""Makes figures showing the CDF of the biased and unbiased PMFs"""
cdf = _13_Cdf._make_cdf_from_pmf(pmf, 'unbiased')
print('unbiased median', cdf._percentile(50))
print('percent < 100', cdf._prob(100))
print('percent < 1000', cdf._prob(1000))
biased_cdf = _13_Cdf._make_cdf_from_pmf(biased_pmf, 'biased')
print('biased median', biased_cdf._percentile(50))
_05_myplot._clf()
_05_myplot._cdfs([cdf, biased_cdf])
_05_myplot._save(root='slashdot.logx',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log')
def _make_figures(pool, firsts, others):
"""Creates several figures for the book."""
# CDF of all ages
_05_myplot._clf()
_05_myplot._cdf(pool.age_cdf)
_05_myplot._save(root='agemodel_age_cdf',
title="Distribution of mother's age",
xlabel='age (years)',
ylabel='CDF',
legend=False)
# CDF of all weights
_05_myplot._clf()
_05_myplot._cdf(pool.weight_cdf)
_05_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
_05_myplot._clf()
_05_myplot._cdfs([firsts.age_cdf, others.age_cdf])
_05_myplot._save(root='agemodel_age_cdfs',
title="Distribution of mother's age",
xlabel='age (years)',
ylabel='CDF')
_05_myplot._clf()
_05_myplot._cdfs([firsts.weight_cdf, others.weight_cdf])
_05_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 = _get_age_weight(pool)
pyplot.clf()
# pyplot.scatter(ages, weights, alpha=0.2)
pyplot.hexbin(ages, weights, cmap=matplotlib.cm.gray_r)
_05_myplot._save(root='agemodel_scatter',
xlabel='Age (years)',
ylabel='Birth weight (oz)',
legend=False)
def _make_figure(xmin=100, alpha=1.7, mu=150, sigma=25):
"""
Makes a figure showing the CDF of height in ParetoWorld.
Compared to a normal distribution.
Args:
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 = _13_Cdf._make_cdf_from_list(t1, name='pareto')
t2 = [random.normalvariate(mu, sigma) for i in range(10000)]
cdf2 = _13_Cdf._make_cdf_from_list(t2, name='normal')
_05_myplot._clf()
_05_myplot._cdfs([cdf1, cdf2])
_05_myplot._save(root='pareto_world2',
title='Pareto World',
xlabel='height (cm)',
ylabel='CDF')