def MakeFigure():
frac1 = 0.8
frac2 = 1 - frac1
xs, ys = RenderPdf(1170, 179)
pmf1 = Pmf.MakePmfFromDict(dict(zip(xs, ys)), name='blue')
xs, ys = RenderPdf(995, 167)
pmf2 = Pmf.MakePmfFromDict(dict(zip(xs, ys)), name='green')
myplot.Pmfs(
[pmf1, pmf2],
root='normal1',
xlabel='CLA score',
ylabel='PDF',
)
pmf1.Normalize(frac1)
pmf2.Normalize(frac2)
ymax = max(pmf1.MaxLike(), pmf2.MaxLike())
ymax = 0.003
pyplot.clf()
threshes = [1200, 1300, 1400, 1500, 1570]
for thresh in threshes:
myplot.Plot([thresh, thresh], [0, ymax],
clf=False,
line_options=dict(color='gray', alpha=0.5, linewidth=1))
plot_options = [
dict(color='blue', linewidth=2),
dict(color='green', linewidth=2)
]
myplot.Pmfs(
[pmf1, pmf2],
plot_options=plot_options,
clf=False,
root='normal2',
xlabel='CLA score',
ylabel='PDF',
)
cdf1 = Cdf.MakeCdfFromPmf(pmf1)
cdf2 = Cdf.MakeCdfFromPmf(pmf2)
for thresh in threshes:
p1 = frac1 * (1 - cdf1.Prob(thresh))
p2 = frac2 * (1 - cdf2.Prob(thresh))
den = p1 + p2
rep1 = p1 / den
rep2 = p2 / den
print thresh, den, rep1, rep2
return
myplot.Cdfs([cdf1, cdf2], root='normal2', xlabel='', ylabel='', title='')
def Main():
Ratio()
return
pmf1 = Pmf.Pmf()
for x in range(0, 101):
pmf1.Set(x, 1)
pmf1.Normalize()
pmf2 = TrianglePrior()
# plot the priors
myplot.Clf()
myplot.Pmfs([pmf1, pmf2])
myplot.Save(root='simple_coin_both_prior',
title='Biased coin',
xlabel='x',
ylabel='Probability')
RunUpdate(pmf1)
RunUpdate(pmf2)
# plot the posterior distributions
myplot.Clf()
myplot.Pmfs([pmf1, pmf2])
myplot.Save(root='simple_coin_both_post',
title='Biased coin',
xlabel='x',
ylabel='Probability')
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 = Pmf.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
myplot.Pmfs([pmf, biased_pmf, unbiased_pmf])
myplot.Show(xlabel='Class size', ylabel='PMF')
def main(script):
# make an exam object with data from the 2010 SAT
exam = Exam()
# look up Alice's raw score
alice = 780
alice_correct = exam.GetRawScore(alice)
print 'Alice raw score', alice_correct
# display the distribution of raw scores for the population
alice_dist = exam.GetPrior()
alice_dist.name = 'alice'
coin.Update(alice_dist, (53, 1))
#myplot.Pmf(alice_dist, show=True)
# look up Alice's raw score
bob = 760
bob_correct = exam.GetRawScore(bob)
print 'Bob raw score', bob_correct
# display the distribution of raw scores for the population
bob_dist = exam.GetPrior()
bob_dist.name = 'bob'
coin.Update(bob_dist, (52, 2))
myplot.Pmfs([alice_dist, bob_dist], show=True)
print ProbBigger(alice_dist, bob_dist)
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 = Pmf.MakePmfFromDict(d, 'actual')
print 'mean', pmf.Mean()
print 'var', pmf.Var()
biased = BiasPmf(pmf, name='biased')
print 'mean', biased.Mean()
print 'var', biased.Var()
# plot the actual pmf
myplot.Pmfs([pmf, biased], show=True, xlabel='Class size', ylabel='PMF')
def create_error_pmf():
all_events = cyb_records.Events()
all_events.ReadRecords()
all_records = all_events.records
my_pmfs = Pmf_errors(all_records)
myplot.Pmfs(my_pmfs)
myplot.Show(title="PDF of different types of errors Per Machine",
xlabel='Error Codes',
ylabel='Probability')
def PlotPMF(records, machine_filter=[]):
pmfs = []
errors = GetErrorsPerWeek(records, machine_filter)
for key in errors.keys():
if SumErrors(errors.get(key)) > 10:
pmf = Pmf.MakeHistFromDict(errors.get(key), key)
pmfs.append(pmf)
myplot.Pmfs(pmfs)
myplot.Show(title="Histogram: Error Rate per Week",
xlabel='Date',
ylabel='Errors per week')
def MakeFigures(exam, alice, bob):
formats = ['png']
myplot.Pmf(exam.prior, label='prior')
myplot.Save(root='sat_prior', formats=formats, xlabel='p', ylabel='PMF')
myplot.Clf()
myplot.Pmfs([alice, bob])
myplot.Save(root='sat_posterior',
formats=formats,
xlabel='p',
ylabel='PMF')
def main():
distro = {7: 8, 12: 8, 17: 14, 22: 4, 27: 6, 32: 12, 37: 8, 42: 3, 47: 2}
pmf = Pmf.MakePmfFromDict(distro, 'actual')
biased_pmf = BiasPmf(pmf, 'observed')
unbiased_pmf = UnbiasPmf(pmf, 'unbiased')
for p in [pmf, biased_pmf, unbiased_pmf]:
print p.name, "mean = {:.3f}".format(p.Mean())
print p.name, "var = {:.3f}".format(p.Var())
myplot.Pmfs([pmf, biased_pmf])
myplot.Show(xlabel='Class Size', ylabel='PMF')
def RelativeRisk(first, others, week=38):
first_cond = ConditionOnWeeks(first.pmf, week, 'first babies')
other_cond = ConditionOnWeeks(others.pmf, week, 'others')
risk.ComputeRelativeRisk(first_cond, other_cond)
return
myplot.Pmfs(
[first_cond, other_cond],
xlabel='weeks',
ylabel=r'Prob{x $=$ weeks | x $\geq$ weeks}',
title='Conditional Probability',
show=True,
)
def main():
all_recs = cyb_records.Events()
all_recs.ReadRecords()
print 'Number of total stats', len(all_recs.records)
pmfs = []
errors = GetErrorsPerWeek(all_recs.records)
for key in errors.keys():
if SumErrors(errors.get(key)) > 10:
pmf = Pmf.MakeHistFromDict(errors.get(key), key)
pmfs.append(pmf)
myplot.Pmfs(pmfs)
myplot.Show(
title="Histogram: Error Rate per Week for All Treadmills | 2014-04-17",
xlabel='Date',
ylabel='Errors per week')
def main():
prior = MakeUniformSuite(0.0, 1.0, 101)
post1 = prior.Copy(name='post1')
evidence = 1,1
Update(post1, evidence)
print 'P(two heads)', TwoUp(post1)
post2 = prior.Copy(name='post2')
evidence = 49, 49
Update(post2, evidence)
print 'P(two heads)', TwoUp(post2)
# plot the posterior distributions
myplot.Pmfs([prior, post1, post2],
root='kasser',
xlabel='P(heads)',
ylabel='Probability',
show=True)
def main():
print 'pae', 0.3 / (0.3 + 3.0 / 13)
doorA = MakeUniformSuite(0.0, 1.0, 101, name='Door A')
evidence = 3, 2
Update(doorA, evidence)
doorC = MakeUniformSuite(0.0, 1.0, 101, name='Door C')
evidence = 3, 10
Update(doorC, evidence)
print TotalProbability(doorA, doorC, ProbWinning)
# plot the posterior distributions
myplot.Pmfs([doorA, doorC])
myplot.Save(root='blinky',
formats=['pdf', 'png'],
title='Probability of blinking',
xlabel='P(blink)',
ylabel='Posterior probability')
def main():
all_recs = cyb_records.Events()
all_recs.ReadRecords()
print 'Number of total stats', len(all_recs.records)
ErrorNames = {"0x80100009": "Watchdog", \
"0x80100008": "Approaching over-temp", \
"0x80100005": "Communication issue", \
"0x80100007": "Controller foldback", \
"0x80200062": "Unknown"}
pmfs = []
errors = GetErrorsPerWeek(all_recs.records)
for key in errors.keys():
if SumErrors(errors.get(key)) > 30:
pmf = Pmf.MakeHistFromDict(errors.get(key), ErrorNames.get(key))
pmfs.append(pmf)
myplot.Pmfs(pmfs)
myplot.Show(title="Histogram: errors rate | 2014-04-08",
xlabel='Date',
ylabel='Errors per week')
def PlotDiffs(half_diffs, diffs):
half_cdf = Cdf.MakeCdfFromList(half_diffs, 'half')
cdf = Cdf.MakeCdfFromList(diffs, 'full')
options = dict(linewidth=2)
myplot.Cdfs([half_cdf, cdf],
xlabel='time - qualifying time (min)',
ylabel='CDF',
plot_options=[options, options],
root='marathon_cdf')
diffs = [int(x) for x in diffs]
half_diffs = [int(x) for x in half_diffs]
pmf = Pmf.MakePmfFromList(diffs, 'full')
half_pmf = Pmf.MakePmfFromList(half_diffs, 'half')
myplot.Pmfs([half_pmf, pmf],
xlabel='time - qualifying time (min)',
ylabel='PMF',
plot_options=[options, options],
root='marathon_pmf')
