def MakeFigures(df):
"""Generates CDFs and normal prob plots for weights and log weights."""
weights = df.wtkg2.dropna()
log_weights = np.log10(weights)
# plot weights on linear and log scales
thinkplot.PrePlot(cols=2)
MakeNormalModel(weights)
thinkplot.Config(xlabel='adult weight (kg)', ylabel='CDF')
thinkplot.SubPlot(2)
MakeNormalModel(log_weights)
thinkplot.Config(xlabel='adult weight (log10 kg)')
thinkplot.Save(root='brfss_weight')
# make normal probability plots on linear and log scales
thinkplot.PrePlot(cols=2)
MakeNormalPlot(weights)
thinkplot.Config(xlabel='z', ylabel='weights (kg)')
thinkplot.SubPlot(2)
MakeNormalPlot(log_weights)
thinkplot.Config(xlabel='z', ylabel='weights (log10 kg)')
thinkplot.Save(root='brfss_weight_normal')
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 MakeBabyBoom():
"""Plot CDF of interarrival time on log and linear scales.
"""
# compute the interarrival times
df = ReadBabyBoom()
diffs = df.minutes.diff()
cdf = thinkstats2.Cdf(diffs, label='actual')
thinkplot.PrePlot(cols=2)
thinkplot.Cdf(cdf)
thinkplot.Config(xlabel='minutes', ylabel='CDF', legend=False)
thinkplot.SubPlot(2)
thinkplot.Cdf(cdf, complement=True)
thinkplot.Config(xlabel='minutes',
ylabel='CCDF',
yscale='log',
legend=False)
thinkplot.Save(root='analytic_interarrivals', legend=False)
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 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 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)