def main():
results = _10_relay._read_results()
speeds = _10_relay._get_speeds(results)
# plot the distribution of actual speeds
pmf = _04_Pmf._make_pmf_from_list(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 = _bias_pmf(pmf, 7.5, name='observed speeds')
_05_myplot._clf()
_05_myplot._hist(biased)
_05_myplot._save(root='observed_speeds',
title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
cdf = _13_Cdf._make_cdf_from_pmf(biased)
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._save(root='observed_speeds_cdf',
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='cumulative probability')
def _plot_ages(resp):
"""Plot the distribution of ages."""
ages = [r.age for r in resp.records]
cdf = _13_Cdf._make_cdf_from_list(ages)
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._show()
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 _make_example():
"""Make a simple example CDF."""
t = [2, 1, 3, 2, 5]
cdf = _13_Cdf._make_cdf_from_list(t)
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._save(root='example_cdf',
title='CDF',
xlabel='x',
ylabel='CDF(x)',
axis=[0, 6, 0, 1],
legend=False)
def _log_cdf_time_interval():
timeInterval = _calc_time_interval()
pmf = _04_Pmf._make_pmf_from_list(timeInterval, "baby birth interval")
cdf = _13_Cdf._make_cdf_from_pmf(pmf, "baby birth interval")
_05_myplot._clf()
_05_myplot._cdf(cdf, complement=True, xscale="linear", yscale="log")
_05_myplot._save(
root="baby_birth_interval_logccdf",
title="LogCCDF of baby birth interval",
xlabel="interval(minutes)",
ylabel="LogCCdf",
)
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_cdfs(lens):
cdf = _13_Cdf._make_cdf_from_list(lens, 'slashdot')
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._save(root='slashdot.logx',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log')
_05_myplot._clf()
_05_myplot._cdf(cdf, complement=True)
_05_myplot._save(root='slashdot.loglog',
xlabel='Number of friends/foes',
ylabel='CDF',
xscale='log',
yscale='log')
def _make_figures(pool, firsts, others):
"""Creates several figures for the book."""
# plot PMFs of birth weights for first babies and others
_05_myplot._clf()
_05_myplot._hist(firsts.weight_pmf, linewidth=0, color='blue')
_05_myplot._hist(others.weight_pmf, linewidth=0, color='orange')
_05_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
_05_myplot._clf()
_05_myplot._cdf(firsts.weight_cdf, linewidth=2, color='blue')
_05_myplot._cdf(others.weight_cdf, linewidth=2, color='orange')
_05_myplot._save(root='nsfg_birthwgt_cdf',
title='Birth weight CDF',
xlabel='weight (ounces)',
ylabel='probability',
axis=[0, 200, 0, 1])
def _cdf_time_interval():
timeInterval = _calc_time_interval()
pmf = _04_Pmf._make_pmf_from_list(timeInterval, "baby birth interval")
_05_myplot._clf()
_05_myplot._hist(pmf)
_05_myplot._save(
root="baby_birth_interval_pmf",
title="PMF of baby birth interval",
xlabel="interval(minutes)",
ylabel="probability",
)
cdf = _13_Cdf._make_cdf_from_pmf(pmf)
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._save(
root="baby_birth_interval_cdf",
title="CDF of baby birth interval",
xlabel="interval(minutes)",
ylabel="cumulative probability",
)
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')
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_figures():
pops = _21_populations._read_data()
print(len(pops))
cdf = _13_Cdf._make_cdf_from_list(pops, 'populations')
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._save(root='populations',
title='City/Town Populations',
xlabel='population',
ylabel='CDF',
legend=False)
_05_myplot._clf()
_05_myplot._cdf(cdf)
_05_myplot._save(root='populations_logx',
title='City/Town Populations',
xlabel='population',
ylabel='CDF',
xscale='log',
legend=False)
_05_myplot._clf()
_05_myplot._cdf(cdf, complement=True)
_05_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()
_17_rankit._make_normal_plot(t, 'populations_rankit')