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 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 _check_cdf2():
"""Compare chi2 values from the simulation with a chi-squared dist."""
df = 3
t = [_simulate_chi2() for i in range(1000)]
t2 = [scipy.stats.chi2.cdf(x, df) for x in t]
cdf = _13_Cdf._make_cdf_from_list(t2)
_05_myplot._cdf(cdf)
_05_myplot._show()
def main():
results = _10_relay._read_results()
speeds = _10_relay._get_speeds(results)
# plot the distribution of actual speeds
cdf = _13_Cdf._make_cdf_from_list(speeds, 'speeds')
_05_myplot._cdf(cdf)
_05_myplot._save(root='relay_cdf',
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='probability')
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 _check_cdf():
"""Compare chi2 values from simulation with chi2 distributions."""
for df in [1, 2, 3]:
xs, ys = _chi2_cdf(df=df, high=15)
pyplot.plot(xs, ys, label=df)
t = [_simulate_chi2() for i in range(1000)]
cdf = _13_Cdf._make_cdf_from_list(t)
_05_myplot._cdf(cdf)
_05_myplot._save(root='khan3',
xlabel='chi2 value',
ylabel="CDF",
formats=['png'])
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."""
# 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 _plot_marginals(suite):
"""Plot the marginal distributions for a 2-D joint distribution."""
pmf_m, pmf_s = _compute_marginals(suite)
pyplot.clf()
pyplot.figure(1, figsize=(7, 4))
pyplot.subplot(1, 2, 1)
cdf_m = _13_Cdf._make_cdf_from_pmf(pmf_m, 'mu')
_05_myplot._cdf(cdf_m)
pyplot.xlabel('Mean height (cm)')
pyplot.ylabel('CDF')
pyplot.subplot(1, 2, 2)
cdf_s = _13_Cdf._make_cdf_from_pmf(pmf_s, 'sigma')
_05_myplot._cdf(cdf_s)
pyplot.xlabel('Std Dev height (cm)')
pyplot.ylabel('CDF')
_05_myplot._save(root='bayes_height_marginals_%s' % suite.name)
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 _plot_coef_variation(suites):
"""
Plot the posterior distributions for CV.
Args:
suites: map from label to Pmf of CVs.
"""
pyplot.clf()
pmfs = {}
for label, suite in suites.iteritems():
pmf = _compute_coef_variation(suite)
cdf = _13_Cdf._make_cdf_from_pmf(pmf, label)
_05_myplot._cdf(cdf)
pmfs[label] = pmf
_05_myplot._save(root='bayes_height_cv',
title='Coefficient of variation',
xlabel='cv',
ylabel='CDF')
print('female bigger', _prob_bigger(pmfs['female'], pmfs['male']))
print('male bigger', _prob_bigger(pmfs['male'], pmfs['female']))
def main(script):
# read 'em and sort 'em
birthdays = _read_birthdays()
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 = _13_Cdf._make_cdf_from_list(days, name='intervals')
scale = _05_myplot._cdf(cdf, transform='exponential')
_05_myplot._save(root='intervals',
xlabel='days',
ylabel='ccdf',
**scale)
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')
