def testPmfProbLess(self):
pmf = thinkbayes.MakePmfFromList([1, 2, 2, 3, 3, 3, 4, 4, 4, 4])
p = pmf.ProbLess(3)
self.assertAlmostEquals(p, 0.3)
p = pmf < 4
self.assertAlmostEquals(p, 0.6)
p = pmf < pmf
self.assertAlmostEquals(p, 0.35)
p = pmf > pmf
self.assertAlmostEquals(p, 0.35)
p = pmf <= pmf
self.assertAlmostEquals(p, 0.65)
p = pmf >= pmf
self.assertAlmostEquals(p, 0.65)
p = pmf == pmf
self.assertAlmostEquals(p, 0.3)
p = pmf != pmf
self.assertAlmostEquals(p, 0.7)
def RunLoop(gap_times, nums, lam=0.0333):
"""Runs the basic analysis for a range of num_passengers.
gap_times: sequence of float
nums: sequence of values for num_passengers
lam: arrival rate in passengers per second
Returns: WaitMixtureEstimator
"""
global UPPER_BOUND
UPPER_BOUND = 4000
thinkplot.Clf()
RandomSeed(18)
# resample gap_times
n = 220
cdf_z = thinkbayes.MakeCdfFromList(gap_times)
sample_z = cdf_z.Sample(n)
pmf_z = thinkbayes.MakePmfFromList(sample_z)
# compute the biased pmf and add some long delays
cdf_zp = BiasPmf(pmf_z).MakeCdf()
sample_zb = cdf_zp.Sample(n) + [1800, 2400, 3000]
# smooth the distribution of zb
pdf_zb = thinkbayes.EstimatedPdf(sample_zb)
xs = MakeRange(low=60)
pmf_zb = pdf_zb.MakePmf(xs)
# unbias the distribution of zb and make wtc
pmf_z = UnbiasPmf(pmf_zb)
wtc = WaitTimeCalculator(pmf_z)
probs = []
for num_passengers in nums:
ete = ElapsedTimeEstimator(wtc, lam, num_passengers)
# compute the posterior prob of waiting more than 15 minutes
cdf_y = ete.pmf_y.MakeCdf()
prob = 1 - cdf_y.Prob(900)
probs.append(prob)
# thinkplot.Cdf(ete.pmf_y.MakeCdf(name=str(num_passengers)))
thinkplot.Plot(nums, probs)
thinkplot.Save(
root='redline5',
xlabel='Num passengers',
ylabel='P(y > 15 min)',
formats=FORMATS,
)
def __init__(self, xs, pcounts, passenger_data):
self.xs = xs
self.pcounts = pcounts
self.passenger_data = passenger_data
self.wait_times = [y for _k1, y, _k2 in passenger_data]
self.pmf_y = thinkbayes.MakePmfFromList(self.wait_times, name="y")
dirichlet = GapDirichlet2(self.xs)
dirichlet.params /= 1.0
dirichlet.Preload(self.pcounts)
dirichlet.params /= 20.0
self.prior_zb = dirichlet.PredictivePmf(self.xs, name="prior zb")
for k1, y, _k2 in passenger_data:
dirichlet.Update((k1, y))
self.pmf_mean_zb = dirichlet.PmfMeanZb()
self.post_zb = dirichlet.PredictivePmf(self.xs, name="post zb")
self.post_z = UnbiasPmf(self.post_zb, name="post z")
def SampleSum(dists, n):
pmf = thinkbayes.MakePmfFromList(RandomSum(dists) for i in xrange(n))
return pmf
def PmfMeanZb(self):
"""Makes the Pmf of mean zb.
Values stored in mean_zbs.
"""
return thinkbayes.MakePmfFromList(self.mean_zbs)
def sampleMax(dists, n):
pmf = thinkbayes.MakePmfFromList(RandomMax(dists) for i in xrange(n))
return pmf
def SampleMax(dists, n):
return thinkbayes.MakePmfFromList([RandomMax(dists) for x in range(n)])
351.0,
286.0,
373.0,
232.0,
393.0,
745.0,
636.0,
758.0,
]
#print(OBSERVED_GAP_TIMES)
print "cumulated data number :", len(OBSERVED_GAP_TIMES)
#OBSERVED_GAP_TIMES = OBSERVED_GAP_TIMES/60 # this is not working...
for i in xrange(0, len(OBSERVED_GAP_TIMES)):
OBSERVED_GAP_TIMES[i] = OBSERVED_GAP_TIMES[i] / 60
#print(OBSERVED_GAP_TIMES)
cdf_z = thinkbayes.MakeCdfFromList(OBSERVED_GAP_TIMES)
sample_z = cdf_z.Sample(220)
pmf_z = thinkbayes.MakePmfFromList(sample_z)
#pmf_z = scipy.stats.gaussian_kde(sample_z)
thinkplot.Clf()
thinkplot.preplot(2)
thinkplot.Clf()
thinkplot.Pmf(pmf_z)
thinkplot.Save(root='chapter8_self1',
xlabel='',
ylabel='Probability',
formats=['pdf'])
def addTeam( self, team, this_team, rest_of_league ):
this_x_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( this_team.X ) )
this_y_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( this_team.Y ) )
other_x_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( rest_of_league.X ) )
other_y_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( rest_of_league.Y ) )
self.addCDFs( team, this_x_cdf, this_y_cdf, other_x_cdf, other_y_cdf )
