def MakeNormalPlot(weights):
"""Generates a normal probability plot of birth weights.
weights: sequence
"""
mean, var = thinkstats2.TrimmedMeanVar(weights, p=0.01)
std = math.sqrt(var)
xs = [-5, 5]
xs, ys = thinkstats2.FitLine(xs, mean, std)
thinkplot.Plot(xs, ys, color='0.8', label='model')
xs, ys = thinkstats2.NormalProbability(weights)
thinkplot.Plot(xs, ys, label='weights')
def main(filename='mystery0.dat'):
data = ReadFile(filename)
cdf = thinkstats2.Cdf(data)
thinkplot.PrePlot(rows=2, cols=3)
thinkplot.SubPlot(1)
thinkplot.Cdf(cdf)
thinkplot.Config(title='linear')
thinkplot.SubPlot(2)
scale = thinkplot.Cdf(cdf, xscale='log')
thinkplot.Config(title='logx', **scale)
thinkplot.SubPlot(3)
scale = thinkplot.Cdf(cdf, transform='exponential')
thinkplot.Config(title='expo', **scale)
thinkplot.SubPlot(4)
xs, ys = thinkstats2.NormalProbability(data)
thinkplot.Plot(xs, ys)
thinkplot.Config(title='normal')
thinkplot.SubPlot(5)
scale = thinkplot.Cdf(cdf, transform='pareto')
thinkplot.Config(title='pareto', **scale)
thinkplot.SubPlot(6)
scale = thinkplot.Cdf(cdf, transform='weibull')
thinkplot.Config(title='weibull', **scale)
thinkplot.Show(legend=False)
def ResampleSurvival(resp, iters=101):
"""Resamples respondents and estimates the survival function.
resp: DataFrame of respondents
iters: number of resamples
"""
_, sf = EstimateMarriageSurvival(resp)
thinkplot.Plot(sf)
low, high = resp.agemarry.min(), resp.agemarry.max()
ts = np.arange(low, high, 1 / 12.0)
ss_seq = []
for _ in range(iters):
sample = thinkstats2.ResampleRowsWeighted(resp)
_, sf = EstimateMarriageSurvival(sample)
ss_seq.append(sf.Probs(ts))
low, high = thinkstats2.PercentileRows(ss_seq, [5, 95])
thinkplot.FillBetween(ts, low, high, color='gray', label='90% CI')
thinkplot.Save(root='survival3',
xlabel='age (years)',
ylabel='prob unmarried',
xlim=[12, 46],
ylim=[0, 1],
formats=FORMATS)
def EstimateMarriageSurvivalByDecade(groups, **options):
"""Groups respondents by decade and plots survival curves.
groups: GroupBy object
"""
thinkplot.PrePlot(len(groups))
for _, group in groups:
_, sf = EstimateMarriageSurvival(group)
thinkplot.Plot(sf, **options)
def AddLabelsByDecade(groups, **options):
"""Draws fake points in order to add labels to the legend.
groups: GroupBy object
"""
thinkplot.PrePlot(len(groups))
for name, _ in groups:
label = '%d0s' % name
thinkplot.Plot([15], [1], label=label, **options)
def MakeFigures(df):
"""Plots the CDF of income in several forms.
"""
xs, ps = df.income.values, df.ps.values
cdf = SmoothCdf(xs, ps, label='data')
cdf_log = SmoothCdf(np.log10(xs), ps, label='data')
# linear plot
thinkplot.Cdf(cdf)
thinkplot.show(root='hinc_linear', xlabel='household income', ylabel='CDF')
# pareto plot
# for the model I chose parameters by hand to fit the tail
xs, ys = thinkstats2.RenderParetoCdf(xmin=55000,
alpha=2.5,
low=0,
high=250000)
thinkplot.Plot(xs, 1 - ys, label='model', color='0.8')
thinkplot.Cdf(cdf, complement=True)
thinkplot.show(root='hinc_pareto',
xlabel='log10 household income',
ylabel='CCDF',
xscale='log',
yscale='log')
# lognormal plot
# for the model I estimate mu and sigma using
# percentile-based statistics
median = cdf_log.Percentile(50)
iqr = cdf_log.Percentile(75) - cdf_log.Percentile(25)
std = iqr / 1.349
# choose std to match the upper tail
std = 0.35
print(median, std)
xs, ps = thinkstats2.RenderNormalCdf(median, std, low=3.5, high=5.5)
thinkplot.Plot(xs, ps, label='model', color='0.8')
thinkplot.Cdf(cdf_log)
thinkplot.show(root='hinc_normal',
xlabel='log10 household income',
ylabel='CDF')
def MakeNormalPlot(weights, term_weights):
"""Generates a normal probability plot of birth weights."""
mean, var = thinkstats2.TrimmedMeanVar(weights, p=0.01)
std = math.sqrt(var)
xs = [-4, 4]
fxs, fys = thinkstats2.FitLine(xs, mean, std)
thinkplot.Plot(fxs, fys, linewidth=4, color='0.8')
thinkplot.PrePlot(2)
xs, ys = thinkstats2.NormalProbability(weights)
thinkplot.Plot(xs, ys, label='all live')
xs, ys = thinkstats2.NormalProbability(term_weights)
thinkplot.Plot(xs, ys, label='full term')
thinkplot.Save(root='analytic_birthwgt_normal',
title='Normal probability plot',
xlabel='Standard deviations from mean',
ylabel='Birth weight (lbs)')
def PlotMarriageData(resp):
"""Plots hazard and survival functions.
resp: DataFrame of respondents
"""
hf, sf = EstimateMarriageSurvival(resp)
thinkplot.PrePlot(rows=2)
thinkplot.Plot(hf)
thinkplot.Config(ylabel='hazard', legend=False)
thinkplot.SubPlot(2)
thinkplot.Plot(sf)
thinkplot.Save(root='survival2',
xlabel='age (years)',
ylabel='prob unmarried',
ylim=[0, 1],
legend=False,
formats=FORMATS)
return sf
def MakeParetoCdf2():
"""Generates a plot of the CDF of height in Pareto World."""
xmin = 100
alpha = 1.7
xs, ps = thinkstats2.RenderParetoCdf(xmin, alpha, 0, 1000.0, n=100)
thinkplot.Plot(xs, ps)
thinkplot.Save(root='analytic_pareto_height',
title='Pareto CDF',
xlabel='height (cm)',
ylabel='CDF',
legend=False)
def PlotSurvival(complete):
"""Plots survival and hazard curves.
complete: list of complete lifetimes
"""
thinkplot.PrePlot(3, rows=2)
cdf = thinkstats2.Cdf(complete, label='cdf')
sf = MakeSurvivalFromCdf(cdf, label='survival')
print(cdf[13])
print(sf[13])
thinkplot.Plot(sf)
thinkplot.Cdf(cdf, alpha=0.2)
thinkplot.Config()
thinkplot.SubPlot(2)
hf = sf.MakeHazardFunction(label='hazard')
print(hf[39])
thinkplot.Plot(hf)
thinkplot.Config(ylim=[0, 0.75])
def PlotHazard(complete, ongoing):
"""Plots the hazard function and survival function.
complete: list of complete lifetimes
ongoing: list of ongoing lifetimes
"""
# plot S(t) based on only complete pregnancies
sf = MakeSurvivalFromSeq(complete)
thinkplot.Plot(sf, label='old S(t)', alpha=0.1)
thinkplot.PrePlot(2)
# plot the hazard function
hf = EstimateHazardFunction(complete, ongoing)
thinkplot.Plot(hf, label='lams(t)', alpha=0.5)
# plot the survival function
sf = hf.MakeSurvival()
thinkplot.Plot(sf, label='S(t)')
thinkplot.Show(xlabel='t (weeks)')
def MakeParetoCdf():
"""Generates a plot of the Pareto CDF."""
xmin = 0.5
thinkplot.PrePlot(3)
for alpha in [2.0, 1.0, 0.5]:
xs, ps = thinkstats2.RenderParetoCdf(xmin, alpha, 0, 10.0, n=100)
thinkplot.Plot(xs, ps, label=r'$\alpha=%g$' % alpha)
thinkplot.Save(root='analytic_pareto_cdf',
title='Pareto CDF',
xlabel='x',
ylabel='CDF')
def MakeExpoCdf():
"""Generates a plot of the exponential CDF."""
thinkplot.PrePlot(3)
for lam in [2.0, 1, 0.5]:
xs, ps = thinkstats2.RenderExpoCdf(lam, 0, 3.0, 50)
label = r'$\lambda=%g$' % lam
thinkplot.Plot(xs, ps, label=label)
thinkplot.Save(root='analytic_expo_cdf',
title='Exponential CDF',
xlabel='x',
ylabel='CDF')
def PlotRemainingLifetime(sf1, sf2):
"""Plots remaining lifetimes for pregnancy and age at first marriage.
sf1: SurvivalFunction for pregnancy length
sf2: SurvivalFunction for age at first marriage
"""
thinkplot.PrePlot(cols=2)
rem_life1 = sf1.RemainingLifetime()
thinkplot.Plot(rem_life1)
thinkplot.Config(title='remaining pregnancy length',
xlabel='weeks',
ylabel='mean remaining weeks')
thinkplot.SubPlot(2)
func = lambda pmf: pmf.Percentile(50)
rem_life2 = sf2.RemainingLifetime(filler=np.inf, func=func)
thinkplot.Plot(rem_life2)
thinkplot.Config(title='years until first marriage',
ylim=[0, 15],
xlim=[11, 31],
xlabel='age (years)',
ylabel='median remaining years')
thinkplot.Save(root='survival6', formats=FORMATS)
def PlotPredictionsByDecade(groups, **options):
"""Groups respondents by decade and plots survival curves.
groups: GroupBy object
"""
hfs = []
for _, group in groups:
hf, sf = EstimateMarriageSurvival(group)
hfs.append(hf)
thinkplot.PrePlot(len(hfs))
for i, hf in enumerate(hfs):
if i > 0:
hf.Extend(hfs[i - 1])
sf = hf.MakeSurvival()
thinkplot.Plot(sf, **options)
def PlotConditionalSurvival(durations):
"""Plots conditional survival curves for a range of t0.
durations: list of durations
"""
pmf = thinkstats2.Pmf(durations)
times = [8, 16, 24, 32]
thinkplot.PrePlot(len(times))
for t0 in times:
sf = ConditionalSurvival(pmf, t0)
label = 't0=%d' % t0
thinkplot.Plot(sf, label=label)
thinkplot.Show()
def MakeNormalModel(weights):
"""Plots a CDF with a Normal model.
weights: sequence
"""
cdf = thinkstats2.Cdf(weights, label='weights')
mean, var = thinkstats2.TrimmedMeanVar(weights)
std = math.sqrt(var)
print('n, mean, std', len(weights), mean, std)
xmin = mean - 4 * std
xmax = mean + 4 * std
xs, ps = thinkstats2.RenderNormalCdf(mean, std, xmin, xmax)
thinkplot.Plot(xs, ps, label='model', linewidth=4, color='0.8')
thinkplot.Cdf(cdf)
def MakeExampleNormalPlot():
"""Generates a sample normal probability plot.
"""
n = 1000
thinkplot.PrePlot(3)
mus = [0, 1, 5]
sigmas = [1, 1, 2]
for mu, sigma in zip(mus, sigmas):
sample = np.random.normal(mu, sigma, n)
xs, ys = thinkstats2.NormalProbability(sample)
label = '$\mu=%d$, $\sigma=%d$' % (mu, sigma)
thinkplot.Plot(xs, ys, label=label)
thinkplot.Save(root='analytic_normal_prob_example',
title='Normal probability plot',
xlabel='standard normal sample',
ylabel='sample values')
def MakeNormalCdf():
"""Generates a plot of the normal CDF."""
thinkplot.PrePlot(3)
mus = [1.0, 2.0, 3.0]
sigmas = [0.5, 0.4, 0.3]
for mu, sigma in zip(mus, sigmas):
xs, ps = thinkstats2.RenderNormalCdf(mu=mu,
sigma=sigma,
low=-1.0,
high=4.0)
label = r'$\mu=%g$, $\sigma=%g$' % (mu, sigma)
thinkplot.Plot(xs, ps, label=label)
thinkplot.Save(root='analytic_normal_cdf',
title='Normal CDF',
xlabel='x',
ylabel='CDF',
loc=2)
def MakeNormalModel(weights):
"""Plot the CDF of birthweights with a normal model."""
# estimate parameters: trimming outliers yields a better fit
mu, var = thinkstats2.TrimmedMeanVar(weights, p=0.01)
print('Mean, Var', mu, var)
# plot the model
sigma = math.sqrt(var)
print('Sigma', sigma)
xs, ps = thinkstats2.RenderNormalCdf(mu, sigma, low=0, high=12.5)
thinkplot.Plot(xs, ps, label='model', color='0.8')
# plot the data
cdf = thinkstats2.Cdf(weights, label='data')
thinkplot.PrePlot(1)
thinkplot.Cdf(cdf)
thinkplot.Save(root='analytic_birthwgt_model',
title='Birth weights',
xlabel='birth weight (lbs)',
ylabel='CDF')
