def ClassSizes():
"""Generate PMFs of observed and actual class size.
"""
# start with the actual distribution of class sizes from the book
d = {7: 8, 12: 8, 17: 14, 22: 4, 27: 6, 32: 12, 37: 8, 42: 3, 47: 2}
# form the pmf
pmf = thinkstats2.Pmf(d, label='actual')
print('mean', pmf.Mean())
print('var', pmf.Var())
# compute the biased pmf
biased_pmf = BiasPmf(pmf, label='observed')
print('mean', biased_pmf.Mean())
print('var', biased_pmf.Var())
# unbias the biased pmf
unbiased_pmf = UnbiasPmf(biased_pmf, label='unbiased')
print('mean', unbiased_pmf.Mean())
print('var', unbiased_pmf.Var())
# plot the Pmfs
thinkplot.PrePlot(2)
thinkplot.Pmfs([pmf, biased_pmf])
thinkplot.Save(root='class_size1',
xlabel='class size',
ylabel='PMF',
axis=[0, 52, 0, 0.27])
def MakePlot(self, root='redline2'):
"""Plots the computed CDFs.
root: string
"""
print 'Mean z', self.pmf_z.Mean() / 60
print 'Mean zb', self.pmf_zb.Mean() / 60
print 'Mean y', self.pmf_y.Mean() / 60
cdf_z = self.pmf_z.MakeCdf()
cdf_zb = self.pmf_zb.MakeCdf()
cdf_y = self.pmf_y.MakeCdf()
cdfs = ScaleDists([cdf_z, cdf_zb, cdf_y], 1.0 / 60)
thinkplot.Clf()
thinkplot.PrePlot(3)
thinkplot.Cdfs(cdfs)
thinkplot.Save(root=root,
xlabel='Time (min)',
ylabel='CDF',
formats=FORMATS)
root += 'a'
pmfs = self.pmf_z, self.pmf_zb, self.pmf_y
pmfs = ScaleDists(pmfs, 1.0 / 60)
thinkplot.PrePlot(3)
thinkplot.Pmfs(pmfs)
thinkplot.Save(root=root,
xlabel='Time (min)',
ylabel='Probability',
formats=FORMATS)
def ClassSizes():
# start with the actual distribution of class sizes from the book
d = {
7: 8,
12: 8,
17: 14,
22: 4,
27: 6,
32: 12,
37: 8,
42: 3,
47: 2,
}
# form the pmf
pmf = thinkstats2.MakePmfFromDict(d, 'actual')
print 'mean', pmf.Mean()
print 'var', pmf.Var()
# compute the biased pmf
biased_pmf = BiasPmf(pmf, 'observed')
print 'mean', biased_pmf.Mean()
print 'var', biased_pmf.Var()
# unbias the biased pmf
unbiased_pmf = UnbiasPmf(biased_pmf, 'unbiased')
print 'mean', unbiased_pmf.Mean()
print 'var', unbiased_pmf.Var()
# plot the Pmfs
thinkplot.Pmfs([pmf, biased_pmf])
thinkplot.Show(xlabel='Class size', ylabel='PMF')
def MakeStep(greq, less):
axis = [0, 50, 0, 0.6]
greqpmf = thinkstats2.Pmf(greq.prglngth, label='greater/equal to 30')
lesspmf = thinkstats2.Pmf(less.prglngth, label='less than 30')
thinkplot.Pmfs([greqpmf, lesspmf])
thinkplot.Config(xlabel='Pregnancy length(weeks)', axis=axis)
thinkplot.Show()
def MakePrice1(player1, player2):
""" plot the prior distribution of price for both players"""
thinkplot.Clf()
thinkplot.PrePlot(num=2)
pmf1 = player1.PmfPrice()
pmf1.name = 'showcase 1'
pmf2 = player2.PmfPrice()
pmf2.name = 'showcase 2'
thinkplot.Pmfs([pmf1, pmf2])
def CH7_4(show = 1):
"""
混合分布
"""
suite1, suite2 = CH7_3(0)
# 均值:
mu1 = suite1.Mean()
mu2 = suite2.Mean()
print("Mean1: ", mu1)
print("Mean2: ", mu2)
if show:
# 使用均值, 计算泊松分布 (下一场比赛进球分布)
pos1 = thinkbayes.MakePoissonPmf(mu1, 10, step=1)
pos2 = thinkbayes.MakePoissonPmf(mu2, 10, step=1)
thinkplot.Clf()
thinkplot.PrePlot(num=2)
thinkplot.Pmfs([pos1, pos2])
thinkplot.Show(title='Poisson', xlabel='Goals per game', ylabel='Probability')
# 混合分布
def _MixPmf(suite):
high = 10
metapmf = thinkbayes.Pmf()
for lam, prob in suite.Items():
pmf = thinkbayes.MakePoissonPmf(lam, high, step=1)
metapmf.Set(pmf, y=prob)
return thinkbayes.MakeMixture(metapmf, name='mix')
mix1 = _MixPmf(suite1)
mix2 = _MixPmf(suite2)
if show:
thinkplot.Clf()
thinkplot.PrePlot(num=2)
thinkplot.Pmfs([mix1, mix2])
thinkplot.Show(title='Mixture', xlabel='Goals per game', ylabel='Probability')
return mix1, mix2
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.Show(xlabel='Heads probability', ylabel='PMF')
def PlotBeliefs(self, root):
"""Plots prior and posterior beliefs.
root: string filename root for saved figure
"""
thinkplot.Clf()
thinkplot.PrePlot(num=2)
thinkplot.Pmfs([self.prior, self.posterior])
thinkplot.Save(root=root,
xlabel='price ($)',
ylabel='PMF',
formats=FORMATS)
def MakeStep(male, female):
axis = [0, 800, 0, 0.1]
malepmf = thinkstats2.Pmf(male.alcwknd, label='Male')
femalepmf = thinkstats2.Pmf(female.alcwknd, label='Female')
thinkplot.Pmfs([malepmf, femalepmf])
thinkplot.Config(xlabel='Alcohol Consumption (grams)',
ylabel='PMF',
axis=axis,
title='Weekend Alcohol Consumption')
thinkplot.Show()
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 plot_bar_step(first_pmf, other_pmf):
"""PrePlot takes optional parameters rows and cols to make a grid of figures for bar grapg"""
width = 0.5
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(first_pmf, align="left", width=width)
thinkplot.Hist(other_pmf, align="right", width=width)
thinkplot.Config(xlabel="weeks",
ylabel="probability",
axis=[27, 46, 0, 0.6])
#for step graph
thinkplot.PrePlot(2)
thinkplot.SubPlot(2)
thinkplot.Pmfs([first_pmf, other_pmf])
thinkplot.Show(xlabel="weeks", axis=[27, 46, 0, 0.6])
def main():
results = ReadResults()
speeds = GetSpeeds(results)
speeds = BinData(speeds, 3, 12, 100)
pmf = thinkstats2.Pmf(speeds, 'speeds')
pmf2 = ObservedPmf(pmf, 7.5)
thinkplot.PrePlot(2)
thinkplot.Pmfs([pmf, pmf2])
thinkplot.Show(title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
def main():
## extract data
results = ReadResults()
speeds = GetSpeeds(results)
speeds = BinData(speeds, 3, 12, 100)
## make and plot pmfs
pmf = thinkstats2.Pmf(speeds, 'speeds')
observed_pmf = ObservedPmf(pmf, label='observed')
thinkplot.PrePlot(2)
thinkplot.Pmfs([pmf, observed_pmf])
thinkplot.Show(xlabel='speed (mph)', axis=[4, 12, 0, 0.1])
def pmf_stuff(width, x_low, x_high, third, pmf_one, pmf_two, label,
y_axis_scale):
width = width
axis = [x_low, x_high, third, y_axis_scale]
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(pmf_one, align='right', width=width)
thinkplot.Hist(pmf_two, align='left', width=width)
thinkplot.Config(xlabel=label, ylabel='PMF', axis=axis)
thinkplot.PrePlot(2)
thinkplot.SubPlot(2)
thinkplot.Pmfs([pmf_one, pmf_two])
thinkplot.Config(xlabel=label, ylabel='PMF', axis=axis)
thinkplot.Show()
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 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():
results = ReadResults()
speeds = GetSpeeds(results)
speeds = BinData(speeds, 3, 12, 100)
pmf = thinkstats2.Pmf(speeds, 'speeds')
pmf_biased = ObservedPmf(pmf, 7, 'biased speeds')
thinkplot.PrePlot(2)
thinkplot.Pmfs([pmf, pmf_biased])
thinkplot.Show(title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability',
axis=[0, 13, 0, 0.27])
def main():
p1 = thinkbayes2.MakeNormalPmf(0, 1, 3, n=101)
p1.label = 'p1'
p2 = p1.Copy(label='p2')
q1 = thinkbayes2.MakeNormalPmf(0, 1, 3, n=101)
q1.label = 'q1'
q2 = q1.Copy(label='q2')
p1, q1 = Update(p1, q1, True)
p1, q2 = Update(p1, q2, True)
p2, q1 = Update(p2, q1, True)
p2, q2 = Update(p2, q2, False)
thinkplot.PrePlot(num=4, rows=2)
thinkplot.Pmfs([p1, p2])
thinkplot.Config(legend=True)
thinkplot.SubPlot(2)
thinkplot.Pmfs([q1, q2])
thinkplot.Show()
print('Prob p1 > p2', p1 > p2)
print('Prob q1 > q2', q1 > q2)
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 main():
exam = Exam()
alice = Sat(exam)
alice.name = 'alice'
alice.Update(780)
bob = Sat(exam)
bob.name = 'bob'
bob.Update(760)
print 'Prob Alice is "smarter":', PmfProbGreater(alice, bob)
print 'Prob Bob is "smarter":', PmfProbGreater(bob, alice)
thinkplot.Pmfs([alice, bob])
thinkplot.Show(xlabel='x', ylabel='Probability')
def MakeFigures(firsts, others):
"""Plot Pmfs of pregnancy length.
firsts: DataFrame
others: DataFrame
"""
# plot the PMFs
first_pmf = thinkstats2.Pmf(firsts.prglngth, label='first')
other_pmf = thinkstats2.Pmf(others.prglngth, label='other')
width = 0.45
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(first_pmf, align='right', width=width)
thinkplot.Hist(other_pmf, align='left', width=width)
thinkplot.Config(xlabel='weeks',
ylabel='probability',
axis=[27, 46, 0, 0.6])
thinkplot.PrePlot(2)
thinkplot.SubPlot(2)
thinkplot.Pmfs([first_pmf, other_pmf])
thinkplot.Save(root='probability_nsfg_pmf',
xlabel='weeks',
axis=[27, 46, 0, 0.6])
# plot the differences in the PMFs
weeks = range(35, 46)
diffs = []
for week in weeks:
p1 = first_pmf.Prob(week)
p2 = other_pmf.Prob(week)
diff = 100 * (p1 - p2)
diffs.append(diff)
thinkplot.Bar(weeks, diffs)
thinkplot.Save(root='probability_nsfg_diffs',
title='Difference in PMFs',
xlabel='weeks',
ylabel='percentage points',
legend=False)
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.name = 'showcase 1'
pmf2 = player2.PmfPrice()
pmf2.name = 'showcase 2'
thinkplot.Pmfs([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.name = 'player 1'
cdf2 = player2.CdfDiff()
cdf2.name = '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 CH6_2(price1, price2):
"""
两组展览品的价格分布
"""
thinkplot.Clf()
thinkplot.PrePlot(num=2)
# 因为price变量值没有重复的, 所以PMF绘图是看不出什么的.
# price1_pmf = thinkbayes.MakePmfFromList(price1, name='showcase1')
# price2_pmf = thinkbayes.MakePmfFromList(price2, name='showcase2')
price1_max = max(price1)
price2_max = max(price2)
price_max = max(price1_max, price2_max)
xs = numpy.linspace(0, price_max + 100, num=150)
price1_pdf = thinkbayes.EstimatedPdf(price1)
price2_pdf = thinkbayes.EstimatedPdf(price2)
price1_pmf = price1_pdf.MakePmf(xs, name='showcase1')
price2_pmf = price2_pdf.MakePmf(xs, name='showcase2')
thinkplot.Pmfs([price1_pmf, price2_pmf])
thinkplot.Show(xlabel='price $', ylabel='PMF')
firsts = tmp[tmp.birthord == 1]
others = tmp[tmp.birthord != 1]
first_pmf = thinkstats2.Pmf(firsts.prglngth)
others_pmf = thinkstats2.Pmf(others.prglngth)
# %%
# 棒グラフ表示
width = 0.45
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(first_pmf, align='right', width=width)
thinkplot.Hist(others_pmf, align='left', width=width)
thinkplot.Config(xlabl='week', ylabel='probability', axis=[27, 46, 0, 0.6])
thinkplot.show()
# %%
# ステップ関数表示
thinkplot.PrePlot(2)
thinkplot.Pmfs([first_pmf, others_pmf])
thinkplot.show(xlabl='week', ylabel='probability', axis=[27, 46, 0, 0.6])
# %% [markdown]
# ## 3.3 その他の可視化
# %%
# 差を棒グラフで表示
weeks = range(35, 46)
diffs = []
for week in weeks:
p1 = first_pmf.Prob(week)
p2 = others_pmf.Prob(week)
diff = 100 * (p1 - p2)
diffs.append(diff)
thinkplot.Bar(weeks, diffs)
# %% [markdown]
#Scenario 1 : Compare pmf of daily time spent for male vs female male_ds=advertisement_data[advertisement_data.Male==1] female_ds=advertisement_data[advertisement_data.Male==0] male_pmf = thinkstats2.Pmf(male_ds.Daily_Time_Spent, label='male') female_pmf = thinkstats2.Pmf(female_ds.Daily_Time_Spent, label='female') #Plot pmf of daily time spent for male and female width=20 axis = [30, 90, 0, 0.01] thinkplot.PrePlot(2) #thinkplot.SubPlot(2) thinkplot.Pmfs([male_pmf, female_pmf]) thinkplot.Config(xlabel='Daily Time Spent in Minutes', axis=axis) thinkplot.show() #Scenario 2: Compare pmf of daily time spent for age group 18-29 Vs 30-39 bins = [18, 30, 40, 50, 60, 70, 120] labels = ['18-29', '30-39', '40-49', '50-59', '60-69', '70+'] advertisement_data['agerange'] = pd.cut(advertisement_data.Age, bins, labels = labels,include_lowest = True) age_grp_30_to_39_ds=advertisement_data[advertisement_data.agerange=='30-39'] age_grp_18_to_29_ds=advertisement_data[advertisement_data.agerange=='18-29'] age_grp_30_to_39_pmf = thinkstats2.Pmf(age_grp_30_to_39_ds.Daily_Time_Spent, label='30-39') age_grp_18_to_29_pmf = thinkstats2.Pmf(age_grp_18_to_29_ds.Daily_Time_Spent, label='18-29')
# Exploratory Analysis of the Data # In[25]: width=0.45 axis = [27, 46, 0, 0.6] thinkplot.PrePlot(2, cols=2) thinkplot.Hist(timeduration_pmf, align='right', width=width) thinkplot.Hist(temperature_pmf, align='left', width=width) thinkplot.Config(xlabel='Time Duration comparison against Temperature)', ylabel='PMF', axis=axis) thinkplot.PrePlot(2) thinkplot.SubPlot(2) thinkplot.Pmfs([timeduration_pmf, temperature_pmf]) thinkplot.Config(xlabel='Point in Time duration (temperature)', axis=axis) # Additional Exploratory Analysis # In[26]: df.temperature.mean() #62.999 df.tripduration.mean() #11.44 mode(df.month) #8, People ride the most in August mode(df.week) #30 #People rode the most the 30th week of the month mode(df.day) #1, people rode the most on the first of the month mode(df.hour) #17, people mostly ride at 5PM
# NSFG respondent variable NUMKDHH to construction the actual distribution for the
# number of children under 18 in the household
resp = nsfg.ReadFemResp()
pmf = thinkstats2.Pmf(resp.numkdhh, label='actual')
# computer the biased distributoin we would see if surveyed the children and asked them how
# many children including themselves are under 18 in their household
def BiasPmf(pmf, label):
new_pmf = pmf.Copy(label=label)
for x, p in pmf.Items():
new_pmf.Mult(x, x)
new_pmf.Normalize()
return new_pmf
#plot actual and observed distributions
biased_pmf = BiasPmf(pmf, label='observed')
thinkplot.PrePlot(2)
thinkplot.Pmfs([pmf, biased_pmf])
thinkplot.Config(xlabel='Number of children', ylabel='pmf')
thinkplot.show()
# compute their means
print('The actual mean is: ', "{:.2f}".format(pmf.Mean()))
print('The biased mean is: ', "{:.2f}".format(biased_pmf.Mean()))
others = live[live.birthord != 1]
first_pmf = thinkstats2.Pmf(firsts.prglngth)
other_pmf = thinkstats2.Pmf(others.prglngth)
## Make comparison plot
width = 0.45
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(first_pmf, align='right', width=width)
thinkplot.Hist(other_pmf, align='left', width=width)
thinkplot.Config(xlabel='weeks',
ylabel='probability',
axis=[27, 46, 0, 0.6])
thinkplot.PrePlot(2)
thinkplot.SubPlot(2)
thinkplot.Pmfs([first_pmf, other_pmf])
thinkplot.Show(xlabel='weeks', axis=[27, 46, 0, 0.6])
## Make bar chart comparison
diffs = []
weeks = range(35, 46)
for week in weeks:
p1 = first_pmf[week]
p2 = other_pmf[week]
diff = (p1 - p2) * 100
diffs.append(diff)
thinkplot.Bar(weeks, diffs)
thinkplot.Show(xlabel='weeks', ylabel='diff - %')
## Class size paradox
# In[54]: thinkplot.Pmf(flfindistdfpmf) thinkplot.Pmf(vfindistdfpmf) # In[55]: thinkplot.PrePlot(2) thinkplot.subplot(2) #axis = [0, 800, 0, 0.0005] thinkplot.Pmfs([flfindistdfpmf,vfindistdfpmf ]) thinkplot.Show(xlabel = 'Total Revenue', ylabel = 'PMF') # # Lets plot PMF of log transformed columns # In[56]: findistdf.columns # In[57]: lgflfindistdfpmf = thinkstats2.Pmf(flfindistdf['lg_TOTALREV'], label='FLORIDA')
import nsfg
import thinkstats2
import thinkplot
import probability
p = nsfg.ReadFemResp()
act_pmf = thinkstats2.Pmf(p.numkdhh, label='actual')
print(act_pmf)
bias_pmf = probability.BiasPmf(act_pmf, label='observed')
print(bias_pmf)
print('Mean number of children, actual: ', act_pmf.Mean())
print('Mean number of children, biased: ', bias_pmf.Mean())
fig = thinkplot.Pmfs([act_pmf, bias_pmf])
#thinkplot.show(xlabel='No. of Children', ylabel='pmf')
thinkplot.SaveFormat(root = 'act_vs_biased',
fmt = 'png',
xlabel = 'No. of Children',
ylabel = 'pmf')
