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 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
MakePrice1(player1, player2)
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 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')
n = len(diffs)
lam = 44 / 24 * 60.0
sample = [random.expovariate(lam) for _ in range(n)]
model = thinkstats2.Cdf(sample, label='model')
thinkplot.PrePlot(2)
thinkplot.Cdfs([cdf, model], complement=True)
thinkplot.Save(root='analytic_interarrivals_model',
title='Time between births',
xlabel='minutes',
ylabel='CCDF',
yscale='log')
def main():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
speeds = relay.BinData(speeds, 3, 12, 100)
# plot the distribution of actual speeds
pmf = thinkstats2.Pmf(speeds, 'actual speeds')
# plot the biased distribution seen by the observer
biased = ObservedPmf(pmf, 7.5, label='observed speeds')
thinkplot.Pmf(biased)
thinkplot.Save(root='observed_speeds',
title='PMF of running speed',
xlabel='speed (mph)',
ylabel='PMF')
cdf = thinkstats2.Cdf(pmf)
cdf_biased = thinkstats2.Cdf(biased)
thinkplot.PrePlot(2)
thinkplot.Cdfs([cdf, cdf_biased])
thinkplot.Save(root='observed_speeds_cdf',
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='CDF')
def MakeCdfs(male, female):
malecdf = thinkstats2.Cdf(male.alcwknd, label='Male')
femalecdf = thinkstats2.Cdf(female.alcwknd, label='Female')
thinkplot.PrePlot(2)
thinkplot.Cdfs([malecdf, femalecdf])
thinkplot.Config(xlabel='Alcohol Consumed (grams)',
ylabel='CDF',
title='Weekend Alcohol Consumption')
thinkplot.Show()
def MakeCdfs(male, female):
malecdf = thinkstats2.Cdf(male.totalwgt_lb, label='Male')
femalecdf = thinkstats2.Cdf(female.totalwgt_lb, label='Female')
thinkplot.PrePlot(2)
thinkplot.Cdfs([malecdf, femalecdf])
thinkplot.Config(xlabel='Baby Weight (Lbs)',
ylabel='CDF',
title='Baby Weights')
thinkplot.Show()
def MakeFigures(pool, firsts, others):
"""Creates several figures for the book."""
# CDF of all ages
thinkplot.Clf()
thinkplot.Cdf(pool.age_cdf)
thinkplot.Save(root='agemodel_age_cdf',
title="Distribution of mother's age",
xlabel='age (years)',
ylabel='CDF',
legend=False)
# CDF of all weights
thinkplot.Clf()
thinkplot.Cdf(pool.weight_cdf)
thinkplot.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
thinkplot.Clf()
thinkplot.Cdfs([firsts.age_cdf, others.age_cdf])
thinkplot.Save(root='agemodel_age_cdfs',
title="Distribution of mother's age",
xlabel='age (years)',
ylabel='CDF')
thinkplot.Clf()
thinkplot.Cdfs([firsts.weight_cdf, others.weight_cdf])
thinkplot.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 = GetAgeWeight(pool)
thinkplot.clf()
thinkplot.Scatter(ages, weights, alpha=0.2)
thinkplot.Save(root='agemodel_scatter',
xlabel='Age (years)',
ylabel='Birth weight (oz)',
legend=False)
def MakePrice2(player1, player2):
""" 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'
thinkplot.Cdfs([cdf1, cdf2])
def MakeCdfs(greq, less):
greqcdf = thinkstats2.Cdf(greq.totalwgt_lb, label='greater/equal to 30')
lesscdf = thinkstats2.Cdf(less.totalwgt_lb, label='less than 30')
thinkplot.PrePlot(2)
thinkplot.Cdfs([greqcdf, lesscdf])
thinkplot.Config(xlabel='Weight (lbs)', ylabel='CDF')
thinkplot.Show()
print 'Greater/equal to 30 50th percentile:', greqcdf.Percentile(50)
print 'Less than 30 50th percentile:', lesscdf.Percentile(50)
def TestSample(live):
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')
def CH6_5(diff1, diff2):
"""
两组展品的出价差的CDF累计分布
"""
thinkplot.Clf()
thinkplot.PrePlot(num=2)
diff1_cdf = thinkbayes.MakeCdfFromList(diff1, name='diff1')
diff2_cdf = thinkbayes.MakeCdfFromList(diff2, name='diff2')
thinkplot.Cdfs([diff1_cdf, diff2_cdf])
thinkplot.Show(xlabel='diff $', ylabel="CDF")
# 计算CDF(diff <= 0), 判断选手是否偏向低估商品
print(diff1_cdf.Prob(0), diff2_cdf.Prob(0))
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 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')
def PlotPosteriors(self, other):
"""Plots posterior distributions of efficacy.
self, other: Sat objects.
"""
thinkplot.Clf()
thinkplot.PrePlot(num=2)
cdf1 = thinkbayes2.Cdf(self, label='posterior %d' % self.score)
cdf2 = thinkbayes2.Cdf(other, label='posterior %d' % other.score)
thinkplot.Cdfs([cdf1, cdf2])
thinkplot.Save(xlabel='efficacy',
ylabel='CDF',
axis=[0, 4.6, 0.0, 1.0],
root='sat_posteriors_eff',
formats=['pdf', 'eps'])
def TestCorrelation(cdf):
"""Tests the correlated generator.
Makes sure that the sequence has the right distribution and correlation.
"""
n = 10000
rho = 0.4
rdt_seq = CorrelatedGenerator(cdf, rho)
xs = [rdt_seq.next() for _ in range(n)]
rho2 = correlation.SerialCorr(xs)
print(rho, rho2)
cdf2 = thinkbayes.MakeCdfFromList(xs)
thinkplot.Cdfs([cdf, cdf2])
thinkplot.Show()
def MakePlot(self, root='redline1'):
"""Plot the prior and posterior CDF of passengers arrival rate.
root: string
"""
thinkplot.Clf()
thinkplot.PrePlot(2)
# convert units to passengers per minute
prior = self.prior_lam.MakeCdf().Scale(60)
post = self.post_lam.MakeCdf().Scale(60)
thinkplot.Cdfs([prior, post])
thinkplot.Save(root=root,
xlabel='Arrival rate (passengers / min)',
ylabel='CDF',
formats=FORMATS)
def compareAlaskaAirlinesCdf(alaska, others):
"""Create CDF to compare Alaska Airlines versus other airlines
Per JD Power: Among traditional carriers, Alaska Airlines ranks highest for the 12th consecutive year
https://www.jdpower.com/business/press-releases/2019-north-america-airline-satisfaction-study
"""
# plot CDFs of arrival delays for alaska airlines and others
alaska_cdf = thinkstats2.Cdf(alaska.ARRIVAL_DELAY, label='Alaska Airlines')
other_cdf = thinkstats2.Cdf(others.ARRIVAL_DELAY, label='other')
thinkplot.PrePlot(2)
thinkplot.Cdfs([alaska_cdf, other_cdf])
# thinkplot.Show(xlabel='arrival delay (min)', ylabel='CDF', axis=[-20, 40, 0, 1])
thinkplot.Save(root='AlaskaAirlines_ArrivalDelay_cdf',
title='Arrival delay',
xlabel='arrival delay (min)',
ylabel='CDF',
axis=[-20, 40, 0, 1])
def MakeFigures(live, firsts, others):
"""Creates several figures for the book.
live: DataFrame
firsts: DataFrame
others: DataFrame
"""
first_wgt = firsts.totalwgt_lb
first_wgt_dropna = first_wgt.dropna()
print('Firsts', len(first_wgt), len(first_wgt_dropna))
#assert len(first_wgt_dropna) == 4381
other_wgt = others.totalwgt_lb
other_wgt_dropna = other_wgt.dropna()
print('Others', len(other_wgt), len(other_wgt_dropna))
#assert len(other_wgt_dropna) == 4706
first_pmf = thinkstats2.Pmf(first_wgt_dropna, label='first')
other_pmf = thinkstats2.Pmf(other_wgt_dropna, label='other')
width = 0.4 / 16
# plot PMFs of birth weights for first babies and others
thinkplot.PrePlot(2)
thinkplot.Hist(first_pmf, align='right', width=width)
thinkplot.Hist(other_pmf, align='left', width=width)
thinkplot.Save(root='cumulative_birthwgt_pmf',
title='Birth weight',
xlabel='weight (pounds)',
ylabel='PMF')
# plot CDFs of birth weights for first babies and others
first_cdf = thinkstats2.Cdf(firsts.totalwgt_lb, label='first')
other_cdf = thinkstats2.Cdf(others.totalwgt_lb, label='other')
thinkplot.PrePlot(2)
thinkplot.Cdfs([first_cdf, other_cdf])
thinkplot.Save(root='cumulative_birthwgt_cdf',
title='Birth weight',
xlabel='weight (pounds)',
ylabel='CDF',
axis=[0, 12.5, 0, 1]
)
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)
def PlotConditionalCdfs(self):
"""Plots the cdf of ages for each bucket."""
buckets = [7.0, 16.0, 23.0, 27.0]
# 2.01, 4.95 cm, 9.97 cm, 14.879 cm
names = ['2 cm', '5 cm', '10 cm', '15 cm']
cdfs = []
for bucket, name in zip(buckets, names):
cdf = self.cache.ConditionalCdf(bucket, name)
cdfs.append(cdf)
thinkplot.Clf()
thinkplot.PrePlot(num=len(cdfs))
thinkplot.Cdfs(cdfs)
thinkplot.Save(root='kidney6',
title='Distribution of age for several diameters',
formats=FORMATS,
xlabel='tumor age (years)',
ylabel='CDF',
loc=4)
def PlotPosteriors():
thinkbayes.RandomSeed(18)
data1 = FakeData(100, 0.03)
data2 = FakeData(100, 0.05)
pmf1 = MakePosterior(data1, name="headline a")
pmf2 = MakePosterior(data2, name="headline b")
lt = pmf1 < pmf2
eq = pmf1 == pmf2
gt = pmf1 > pmf2
print lt + eq / 2
print gt + eq / 2
cdf1 = pmf1.MakeCdf()
cdf2 = pmf2.MakeCdf()
thinkplot.PrePlot(num=2)
thinkplot.Cdfs([cdf1, cdf2])
thinkplot.Show(axis=[0, 0.2, 0, 1])
width=0.45 thinkplot.PrePlot(2, cols=2) thinkplot.Hist(wins_pmf, align='right', width=width) thinkplot.Hist(runs_pmf, align='left', width=width) thinkplot.Config(xlabel='Result', ylabel='PMF') # In[30]: # Building the CDFs of both the wins and the runs wins_cdf = thinkstats2.Cdf(wins, label='Wins') runs_cdf = thinkstats2.Cdf(runs, label='Runs') thinkplot.PrePlot(2) thinkplot.Cdfs([wins_cdf, runs_cdf]) thinkplot.Config(xlabel='Result', ylabel='CDF') # In[32]: (data.W.values) # I will use these numpy arrays later, that's why i created them here. # In[34]: (data.R.values) # In[46]:
# anim = viewer.animate(frames=100)
# # plt.show()
RandomSeed(17)
env = Sugarscape(50,
num_agents=250,
min_lifespan=60,
max_lifespan=100,
replace=True)
cdfs = []
for i in range(5):
[env.step() for i in range(100)]
cdf = Cdf(agent.sugar for agent in env.agents)
cdfs.append(cdf)
thinkplot.preplot(cols=2)
thinkplot.Cdfs(cdfs[:-1], color='gray', alpha=0.3)
thinkplot.Cdf(cdfs[-1])
thinkplot.config(xlabel='Wealth', ylabel='CDF')
thinkplot.bigger_text()
thinkplot.subplot(2)
thinkplot.Cdfs(cdfs[:-1], color='gray', alpha=0.3)
thinkplot.Cdf(cdfs[-1])
thinkplot.config(xlabel='Wealth', ylabel='CDF', xscale='log')
thinkplot.bigger_text()
thinkplot.save('chap09-4')
thinkplot.show(xlabel='weeks', ylabel='CDF')
#%%
print("10% {0} weeks".format(cdf.Value(0.1)))
print("90% {0} weeks".format(cdf.Value(0.9)))
#%% [markdown]
# ## 4.5 CDFを比較する
#%%
first_cdf = thinkstats2.Cdf(firsts.totalwgt_lb, label='first')
other_cdf = thinkstats2.Cdf(others.totalwgt_lb, label='other')
thinkplot.PrePlot(2)
thinkplot.Cdfs([first_cdf, other_cdf])
thinkplot.Show(xlabel='weight (pounds)', ylabel='CDF')
#%% [markdown]
# ## 4.6 パーセンタイル派生統計量
# - 中央値(median)：50位パーセンタイル値
# - 四分位範囲(interquartile range, IQR)：75位 - 25位パーセンタイル値
# - 分位数(quantiles)：CDFにおいて等間隔で表現される統計量
#%% [markdown]
# ## 4.7 乱数
#%%
import numpy as np
weights = live.totalwgt_lb
axis = [10000, 70000, 0, 0.01] thinkplot.PrePlot(2) #thinkplot.SubPlot(2) thinkplot.Pmfs([clicked_pmf, nonclicked_pmf]) thinkplot.Config(xlabel='Area Income', axis=axis) thinkplot.show() ############################################################################ #############################Section 3 -CDF################################# ############################################################################ age_grp_30_to_39_cdf = thinkstats2.Cdf(age_grp_30_to_39_ds.Daily_Time_Spent, label='30-39') age_grp_18_to_29_cdf = thinkstats2.Cdf(age_grp_18_to_29_ds.Daily_Time_Spent, label='18-29') thinkplot.PrePlot(2) thinkplot.Cdfs([age_grp_30_to_39_cdf, age_grp_18_to_29_cdf]) thinkplot.Config(xlabel='Daily Time Spent in minutes', ylabel='CDF') thinkplot.show() male_cdf = thinkstats2.Cdf(male_ds.Daily_Time_Spent, label='male') female_cdf = thinkstats2.Cdf(female_ds.Daily_Time_Spent, label='female') thinkplot.PrePlot(2) thinkplot.Cdfs([male_cdf, female_cdf]) thinkplot.Config(xlabel='Daily Time Spent in minutes', ylabel='CDF') thinkplot.show() ################################################################################################## ############################# Section 4 -Analytical Distribution #################################
from code import *
import thinkplot
y2 = y1.flatten()
pmf_scores = thinkstats2.Pmf(y2)
thinkplot.Hist(pmf_scores)
thinkplot.Config(xlabel='Runs Scored', ylabel='probability', axis=[0, 20, 0, 0.3])
cdf_scores = thinkstats2.Cdf(y2, label='Runs Scored')
cdf_ld = thinkstats2.Cdf(X3['bat_LD%'], label='Line Drives')
cdf_pop = thinkstats2.Cdf(X3['bat_POP%'], label='Pop Ups')
cdf_gb = thinkstats2.Cdf(X3['bat_GB%'], label='Ground Balls')
thinkplot.PrePlot(4)
thinkplot.Cdfs([cdf_scores, cdf_ld, cdf_pop, cdf_gb])
thinkplot.Show(xlabel='balls in play (%)', ylabel='CDF')
# Visualizing data in One Dimension (1-D)
import matplotlib.pyplot as plt
y.hist(bins=15, color='steelblue', edgecolor='black', linewidth=1.0,
xlabelsize=8, ylabelsize=8, grid=False)
plt.tight_layout(rect=(0, 15, 0, 15))
# visualizing one of the continuous, numeric attributes
# Histogram
fig = plt.figure(figsize = (10,4))
title = fig.suptitle("Runs", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.1)
ax = fig.add_subplot(1,1, 1)
def WeightDiffInFirstOther(first, other):
first_cdf = thinkstats2.Cdf(first.totalwgt_lb, label='First')
other_cdf = thinkstats2.Cdf(other.totalwgt_lb, label='Other')
thinkplot.PrePlot(2)
thinkplot.Cdfs([first_cdf, other_cdf])
thinkplot.Show(xlabel='Weight (pounds)', ylabel='CDF')
thinkplot.Config(xlabel='trip duration (minutes)', ylabel='CDF', loc='upper left') # In[33]: chilly_tripduration_cdf = thinkstats2.Cdf(chilly_df.tripduration, label='chilly trip duration') thinkplot.Cdf(chilly_tripduration_cdf) thinkplot.Config(xlabel='trip duration (minutes)', ylabel='CDF', loc='upper left') # In[34]: #comparison thinkplot.Cdfs([chilly_tripduration_cdf,warm_tripduration_cdf]) thinkplot.Show(xlabel='trip duration (minutes)',ylabel='CDF') # By comparing colder and warmer temperatures with their duration, we can see that chilly bike rides are slightly shorter than warmer bike rides # Analytical Distribution # In[35]: #NORMAL CDF to for visual thinkplot.PrePlot(3) mus = [1.0, 2.0, 3.0] sigmas = [0.5, 0.4, 0.3]
over_three_hr = moving_time[moving_time > 10800]
less_three_hr = moving_time[moving_time <= 10800]
pmf_more = thinkstats2.Pmf(over_three_hr, label="More Than Three HR")
pmf_less = thinkstats2.Pmf(less_three_hr, label='Less Than Three HR')
pmf_stuff(1, 8000, 22000, 0, pmf_more, pmf_less, 'Ride Length (Min)', 0.02)
########### PART SIX ############
cdf = thinkstats2.Cdf(moving_time, label='Moving Time')
thinkplot.Cdf(cdf)
thinkplot.Show(xlabel='Moving Time in Min', ylabel='CDF')
more_cdf = thinkstats2.Cdf(over_one_hr, label='Over Than One Hr')
less_cdf = thinkstats2.Cdf(less_one_hr, label='Less Than One Hr')
thinkplot.PrePlot(2)
thinkplot.Cdfs([more_cdf, less_cdf])
thinkplot.Show(xlabel='Moving Time (Min)', ylabel='CDF')
########### PART SEVEN ############
avg_watts = average_watts.dropna()
def MakeNormalModel(data, label):
cdf = thinkstats2.Cdf(data, label=label)
mean, var = thinkstats2.TrimmedMeanVar(data)
std = np.sqrt(var)
print('n, mean, std', len(data), mean, std)
xmin = mean - 4 * std
xmax = mean + 4 * std
