def PlotJointDist(self):
"""Makes a pcolor plot of the age-size joint distribution."""
thinkplot.Clf()
joint = self.cache.GetDistAgeSize()
thinkplot.Contour(joint, contour=False, pcolor=True)
thinkplot.Save(root='kidney8',
formats=FORMATS,
axis=[0, 41, -0.7, 1.31],
yticks=MakeLogTicks([0.2, 0.5, 1, 2, 5, 10, 20]),
xlabel='ages',
ylabel='diameter (cm, log scale)')
def MakePlots(player1, player2):
"""Generates two plots.
price1 shows the priors for the two players
price2 shows the distribution of diff for the two players
"""
# plot the prior distribution of price for both players
thinkplot.Clf()
thinkplot.PrePlot(num=2)
pmf1 = player1.PmfPrice()
pmf1.label = 'showcase 1'
pmf2 = player2.PmfPrice()
pmf2.label = 'showcase 2'
thinkplot.Pdfs([pmf1, pmf2])
thinkplot.Save(root='price1',
xlabel='price ($)',
ylabel='PDF',
formats=FORMATS)
# plot the historical distribution of underness for both players
thinkplot.Clf()
thinkplot.PrePlot(num=2)
cdf1 = player1.CdfDiff()
cdf1.label = 'player 1'
cdf2 = player2.CdfDiff()
cdf2.label = 'player 2'
print('Player median', cdf1.Percentile(50))
print('Player median', cdf2.Percentile(50))
print('Player 1 overbids', player1.ProbOverbid())
print('Player 2 overbids', player2.ProbOverbid())
thinkplot.Cdfs([cdf1, cdf2])
thinkplot.Save(root='price2',
xlabel='diff ($)',
ylabel='CDF',
formats=FORMATS)
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='alpha=%g' % alpha)
thinkplot.Save(root='analytic_pareto_cdf',
title='Pareto CDF',
xlabel='x',
ylabel='CDF')
def main():
hypos = xrange(1, 1001)
suite = Train(hypos)
suite.Update(60)
print(suite.Mean())
thinkplot.PrePlot(1)
thinkplot.Pmf(suite)
thinkplot.Save(root='train1',
xlabel='Number of trains',
ylabel='Probability',
formats=['pdf', 'eps'])
def PlotSuites(suites, root):
"""Plots two suites.
suite1, suite2: Suite objects
root: string filename to write
"""
thinkplot.Clf()
thinkplot.PrePlot(len(suites))
thinkplot.Pmfs(suites)
thinkplot.Save(root=root,
xlabel='x',
ylabel='Probability',
formats=['pdf', 'eps'])
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 main(name):
thinkstats2.RandomSeed(18)
transactions = ReadData()
dailies = GroupByQualityAndDay(transactions)
PlotDailies(dailies)
RunModels(dailies)
PrintSerialCorrelations(dailies)
MakeAcfPlot(dailies)
name = 'high'
daily = dailies[name]
PlotLinearModel(daily, name)
PlotRollingMean(daily, name)
PlotFilled(daily, name)
years = np.linspace(0, 5, 101)
thinkplot.Scatter(daily.years, daily.ppg, alpha=0.1, label=name)
PlotPredictions(daily, years)
xlim = years[0] - 0.1, years[-1] + 0.1
thinkplot.Save(root='timeseries4',
title='predictions',
xlabel='years',
xlim=xlim,
ylabel='price per gram ($)')
name = 'medium'
daily = dailies[name]
thinkplot.Scatter(daily.years, daily.ppg, alpha=0.1, label=name)
PlotIntervals(daily, years)
PlotPredictions(daily, years)
xlim = years[0] - 0.1, years[-1] + 0.1
thinkplot.Save(root='timeseries5',
title='predictions',
xlabel='years',
xlim=xlim,
ylabel='price per gram ($)')
def ComputeSkewnesses():
def VertLine(x, y):
thinkplot.Plot([x, x], [0, y], color='0.6', linewidth=1)
live, firsts, others = first.MakeFrames()
data = live.totalwgt_lb.dropna()
print('Birth weight')
mean, median = Summarize(data)
y = 0.35
VertLine(mean, y)
thinkplot.Text(mean - 0.15, 0.1 * y, 'mean', horizontalalignment='right')
VertLine(median, y)
thinkplot.Text(median + 0.1, 0.1 * y, 'median', horizontalalignment='left')
pdf = thinkstats2.EstimatedPdf(data)
thinkplot.Pdf(pdf, label='birth weight')
thinkplot.Save(root='density_totalwgt_kde', xlabel='lbs', ylabel='PDF')
df = brfss.ReadBrfss(nrows=None)
data = df.wtkg2.dropna()
print('Adult weight')
mean, median = Summarize(data)
y = 0.02499
VertLine(mean, y)
thinkplot.Text(mean + 1, 0.1 * y, 'mean', horizontalalignment='left')
VertLine(median, y)
thinkplot.Text(median - 1.5,
0.1 * y,
'median',
horizontalalignment='right')
pdf = thinkstats2.EstimatedPdf(data)
thinkplot.Pdf(pdf, label='adult weight')
thinkplot.Save(root='density_wtkg2_kde',
xlabel='kg',
ylabel='PDF',
xlim=[0, 200])
def ScatterPlot(root, heights, weights, alpha=1.0):
"""Make a scatter plot and save it.
root: string filename root
heights: sequence of float
weights: sequence of float
alpha: float
"""
thinkplot.Scatter(heights, weights, alpha=alpha)
thinkplot.Save(root=root,
xlabel='Height (cm)',
ylabel='Weight (kg)',
axis=[140, 210, 20, 200],
legend=False)
def PlotPriorDist(pmf):
"""Plot the prior distribution of p_correct.
pmf: prior
"""
thinkplot.Clf()
thinkplot.PrePlot(num=1)
cdf1 = thinkbayes.MakeCdfFromPmf(pmf, 'prior')
thinkplot.Cdf(cdf1)
thinkplot.Save(root='sat_prior',
xlabel='p_correct',
ylabel='CDF',
formats=['pdf', 'eps'])
def HexBin(root, heights, weights, bins=None):
"""Make a hexbin plot and save it.
root: string filename root
heights: sequence of float
weights: sequence of float
bins: 'log' or None for linear
"""
thinkplot.HexBin(heights, weights, bins=bins)
thinkplot.Save(root=root,
xlabel='Height (cm)',
ylabel='Weight (kg)',
axis=[140, 210, 20, 200],
legend=False)
def PlotPmfs(self, root='redline0'):
"""Plots the computed Pmfs.
root: string
"""
pmfs = ScaleDists([self.pmf_z, self.pmf_zb], 1.0 / 60)
thinkplot.Clf()
thinkplot.PrePlot(2)
thinkplot.Pmfs(pmfs)
thinkplot.Save(root=root,
xlabel='Time (min)',
ylabel='CDF',
formats=FORMATS)
def main():
suite = Train(range(0, 101))
trainNum = [6, 10, 20, 12, 15, 19, 4, 10]
# suite.Update(60)
for TN in trainNum:
suite.Update(TN)
suite.Print()
thinkplot.PrePlot(1)
thinkplot.Pmf(suite)
thinkplot.Save(root='train_self1',
xlabel='Number of trains',
ylabel='Probability',
formats=['pdf'])
def main():
PlotMarriageData()
return
preg = nsfg.ReadFemPreg()
print('Number of pregnancies', len(preg))
complete = preg.query('outcome in [1, 3, 4]').prglngth
print('Number of complete pregnancies', len(complete))
ongoing = preg[preg.outcome == 6].prglngth
print('Number of ongoing pregnancies', len(ongoing))
PlotSurvival(complete)
thinkplot.Save(root='survival1', xlabel='t (weeks)')
def main(script):
thinkstats2.RandomSeed(17)
live, firsts, others = first.MakeFrames()
live = live.dropna(subset=['agepreg', 'totalwgt_lb'])
BinnedPercentiles(live)
ages = live.agepreg
weights = live.totalwgt_lb
print('thinkstats2 Corr', thinkstats2.Corr(ages, weights))
print('thinkstats2 SpearmanCorr', thinkstats2.SpearmanCorr(ages, weights))
ScatterPlot(ages, weights, alpha=0.1)
thinkplot.Save(root='chap07scatter1', legend=False, formats=['jpg'])
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)
median = ParetoMedian(xmin, alpha)
thinkplot.Save(root='analytic_pareto_height',
title='Pareto CDF',
xlabel='height (cm)',
ylabel='CDF',
legend=False)
def MakePlot(self, root='redline3'):
"""Plot the CDFs.
root: string
"""
# observed gaps
cdf_prior_x = self.prior_x.MakeCdf()
cdf_post_x = self.post_x.MakeCdf()
cdf_y = self.pmf_y.MakeCdf()
cdfs = ScaleDists([cdf_prior_x, cdf_post_x, cdf_y], 1.0 / 60)
thinkplot.Clf()
thinkplot.PrePlot(3)
thinkplot.Cdfs(cdfs)
thinkplot.Save(root=root,
xlabel='Time (min)',
ylabel='CDF',
formats=FORMATS)
pmfs = self.prior_x, self.post_x
pmfs = ScaleDists(pmfs, 1.0 / 60)
thinkplot.PrePlot(3)
thinkplot.Pmfs(pmfs)
thinkplot.Save(root=root + 'a',
xlabel='Time (min)',
ylabel='Probability',
formats=FORMATS)
pmfs = self.prior_x, self.post_x, self.pmf_y
pmfs = ScaleDists(pmfs, 1.0 / 60)
thinkplot.PrePlot(3)
thinkplot.Pmfs(pmfs)
thinkplot.Save(root=root + 'b',
xlabel='Time (min)',
ylabel='Probability',
formats=FORMATS)
def main():
thinkstats2.RandomSeed(17)
preg = nsfg.ReadFemPreg()
sf1 = PlotPregnancyData(preg)
# make the plots based on Cycle 6
resp6 = ReadFemResp2002()
sf2 = PlotMarriageData(resp6)
ResampleSurvival(resp6)
PlotRemainingLifetime(sf1, sf2)
# read Cycles 5 and 7
resp5 = ReadFemResp1995()
resp7 = ReadFemResp2010()
# plot resampled survival functions by decade
resps = [resp5, resp6, resp7]
PlotResampledByDecade(resps)
thinkplot.Save(root='survival4',
xlabel='age (years)',
ylabel='prob unmarried',
xlim=[13, 45],
ylim=[0, 1],
formats=FORMATS)
# plot resampled survival functions by decade, with predictions
PlotResampledByDecade(resps, predict_flag=True, omit=[5])
thinkplot.Save(root='survival5',
xlabel='age (years)',
ylabel='prob unmarried',
xlim=[13, 45],
ylim=[0, 1],
formats=FORMATS)
def PlotOutliers(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 = thinkbayes.MakeCdfFromList(outliers, label)
cdfs.append(cdf)
thinkplot.Clf()
thinkplot.Cdfs(cdfs)
thinkplot.Save(root='variability_cdfs',
title='CDF of height',
xlabel='Reported height (cm)',
ylabel='CDF')
def main():
print "1"
hockey1 = Hockey()
# print(type(hockey1))
thinkplot.PrePlot(1)
thinkplot.Pmf(hockey1)
thinkplot.Save(root='hockey_self2_prior',
xlabel='',
ylabel='Probability',
formats=['pdf'])
print(hockey1.Values())
for hypo in hockey1.Values():
print(hockey1.Likelihood(2, hypo))
hockey1.UpdateSet([0, 2, 4, 3, 8])
thinkplot.Pmf(hockey1)
thinkplot.Save(root='hockey_self2_posterior',
xlabel='',
ylabel='Probability',
formats=['pdf'])
print("No error, everything worked fine")
def main():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
# plot the distribution of actual speeds
pmf = thinkstats2.MakePmfFromList(speeds, 'actual speeds')
# plot the biased distribution seen by the observer
biased = BiasPmf(pmf, 7.5, name='observed speeds')
thinkplot.Hist(biased)
thinkplot.Save(root='observed_speeds',
title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
cdf = thinkstats2.MakeCdfFromPmf(biased)
thinkplot.Clf()
thinkplot.Cdf(cdf)
thinkplot.Save(root='observed_speeds_cdf',
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='cumulative probability')
def MakeGenderPlot(filename='heri14.csv'):
"""Generates a plot with the data, a fitted model, and error bars."""
pyplot.clf()
data = ReadData(filename)
men = GetColumn(data, 6)
ts, ys = RenderColumn(men)
pyplot.plot(ts, ys, 'b-', linewidth=3, alpha=0.7, label='men')
women = GetColumn(data, 11)
ts, ys = RenderColumn(women)
pyplot.plot(ts, ys, 'g-', linewidth=3, alpha=0.7, label='women')
thinkplot.Save(root='heri14.3',
formats=FORMATS,
title='',
xlabel='',
ylabel='Preferred religion None (%)',
axis=[1967, UPPER, 0, 28])
del men[1969]
del women[1969]
ts, ds = DiffColumns(men, women)
MakePlot(ts, ds, model='ys ~ ts')
pyplot.plot(ts, ds, color='purple', linewidth=3, alpha=0.7,
label='Gender gap')
thinkplot.Save(root='heri14.4',
formats=FORMATS,
title='',
xlabel='',
ylabel='Percentage points',
axis=[1967, UPPER, 0, 6])
def PlotQuadraticModel(daily, name):
model, results = RunQuadraticModel(daily)
regression.SummarizeResults(results)
timeseries.PlotFittedValues(model, results, label=name)
thinkplot.Save(root='Output_Timeseries1',
title='Fitted Val',
xlabel='yr',
xlim=[-0.2, 4],
ylabel='price per gram ($)')
timeseries.PlotResidualPercentiles(model, results)
thinkplot.Save(root='Output_Timeseries2',
title='Residual',
xlabel='yr',
ylabel='price per gram ($)')
years = np.linspace(0, 10, 200)
thinkplot.Scatter(daily.years, daily.ppg, alpha=0.1, label=name)
timeseries.PlotPredictions(daily, years, func=RunQuadraticModel)
thinkplot.Save(root='Output_Timeseries3',
title='Predict',
xlabel='yr',
xlim=[years[0]-0.1, years[-1]+0.1],
ylabel='price per gram ($)')
def ResampleDivorceCurveByDecade(resps):
"""Plots divorce curves for each birth cohort.
resps: list of respondent DataFrames
"""
for i in range(41):
samples = [thinkstats2.ResampleRowsWeighted(resp) for resp in resps]
sample = pandas.concat(samples, ignore_index=True)
groups = sample.groupby('decade')
if i == 0:
survival.AddLabelsByDecade(groups, alpha=0.7)
EstimateSurvivalByDecade(groups, alpha=0.1)
thinkplot.Save(root='survival7', xlabel='years', axis=[0, 28, 0, 1])
def PlotSuites(suites, root):
"""Plots two suites.
suite1, suite2: Suite objects
root: string filename to write
"""
formats = ['pdf', 'png']
thinkplot.Clf()
thinkplot.PrePlot(len(suites))
thinkplot.Pmfs(suites)
thinkplot.Save(root=root,
xlabel='Percentage of Active Female Users',
ylabel='Probability',
formats=formats,
legend=True)
def MakePmfPlot(alpha = 10):
"""Plots Pmf of location for a range of betas."""
locations = range(0, 31)
betas = [10, 20, 40]
thinkplot.PrePlot(num=len(betas))
for beta in betas:
pmf = MakeLocationPmf(alpha, beta, locations)
pmf.name = 'beta = %d' % beta
thinkplot.Pdf(pmf)
thinkplot.Save('paintball1',
xlabel='Distance',
ylabel='Prob',
formats=FORMATS)
def PlotPregnancyData(preg):
"""Plots survival and hazard curves based on pregnancy lengths.
preg:
"""
complete = preg.query('outcome in [1, 3, 4]').prglngth
print('Number of complete pregnancies', len(complete))
ongoing = preg[preg.outcome == 6].prglngth
print('Number of ongoing pregnancies', len(ongoing))
PlotSurvival(complete)
thinkplot.Save(root='survival1', xlabel='t (weeks)', formats=FORMATS)
hf = EstimateHazardFunction(complete, ongoing)
sf = hf.MakeSurvival()
return sf
def main():
pmf_dice = Pmf()
pmf_dice.Set(Die(6),2)
pmf_dice.Set(Die(8),3)
pmf_dice.Set(Die(12),1)
pmf_dice.Set(Die(20),1)
mix = Pmf()
for die, weight in pmf_dice.Items():
for outcome, prob in die.Items():
mix.Incr(outcome, weight*prob)
mix.Normalize()
thinkplot.PrePlot(1)
thinkplot.Pmf(mix)
thinkplot.Save(root='dice_Mix_self3',xlabel='',ylabel='Probability',formats=['pdf'])
def main():
ps = numpy.linspace(0, 1, 101)
bill = Billiards(ps)
bill.Update((5, 3))
thinkplot.Pdf(bill)
thinkplot.Save(root='billiards1',
xlabel='probability of win',
ylabel='PDF',
formats=['png'])
bayes_result = ProbWinMatch(bill)
print(thinkbayes.Odds(1-bayes_result))
mle = 5 / 8
freq_result = (1-mle)**3
print(thinkbayes.Odds(1-freq_result))
def TestSample(live):
"""Plots the distribution of weights against a random sample.
live: DataFrame for live births
"""
weights = live.totalwgt_lb
cdf = thinkstats2.Cdf(weights, label='totalwgt_lb')
sample = cdf.Sample(1000)
sample_cdf = thinkstats2.Cdf(sample, label='sample')
thinkplot.PrePlot(2)
thinkplot.Cdfs([cdf, sample_cdf])
thinkplot.Save(root='cumulative_sample',
xlabel='weight (pounds)',
ylabel='CDF')
