def Test(expected, observed, num_trials=1000, stir=-1):
"""Run a simulation to estimate the p-value of the observed values.
Args:
expected: Hist of expected values
observed: Hist of observed values
num_trials: how many simulations to run
stir: how much to stir the simulated vat of nuts
(-1 means perfect mixing)
Returns:
float p-value
"""
# compute the chi-squared stat
threshold = ChiSquared(expected, observed)
print 'chi-squared', threshold
print 'simulated %d trials' % num_trials
chi2s = []
count = 0.0
num_nuts = observed.Total()
cdf = thinkstats2.MakeCdfFromHist(expected)
for _ in range(num_trials):
simulated = SimulateSample(expected, cdf, num_nuts, stir=stir)
chi2 = ChiSquared(expected, simulated)
chi2s.append(chi2)
if chi2 >= threshold:
count += 1
print 'max chi2', max(chi2s)
pvalue = count / num_trials
print 'p-value', pvalue
return pvalue
def testCdf(self):
t = [1, 2, 2, 3, 5]
pmf = thinkstats2.Pmf(t)
hist = thinkstats2.Hist(t)
cdf = thinkstats2.Cdf(pmf)
self.assertEqual(len(str(cdf)), 37)
self.assertEqual(cdf[0], 0)
self.assertAlmostEqual(cdf[1], 0.2)
self.assertAlmostEqual(cdf[2], 0.6)
self.assertAlmostEqual(cdf[3], 0.8)
self.assertAlmostEqual(cdf[4], 0.8)
self.assertAlmostEqual(cdf[5], 1)
self.assertAlmostEqual(cdf[6], 1)
xs = range(7)
ps = cdf.Probs(xs)
for p1, p2 in zip(ps, [0, 0.2, 0.6, 0.8, 0.8, 1, 1]):
self.assertAlmostEqual(p1, p2)
self.assertEqual(cdf.Value(0), 1)
self.assertEqual(cdf.Value(0.1), 1)
self.assertEqual(cdf.Value(0.2), 1)
self.assertEqual(cdf.Value(0.3), 2)
self.assertEqual(cdf.Value(0.4), 2)
self.assertEqual(cdf.Value(0.5), 2)
self.assertEqual(cdf.Value(0.6), 2)
self.assertEqual(cdf.Value(0.7), 3)
self.assertEqual(cdf.Value(0.8), 3)
self.assertEqual(cdf.Value(0.9), 5)
self.assertEqual(cdf.Value(1), 5)
ps = np.linspace(0, 1, 11)
xs = cdf.ValueArray(ps)
self.assertTrue((xs == [1, 1, 1, 2, 2, 2, 2, 3, 3, 5, 5]).all())
np.random.seed(17)
xs = cdf.Sample(7)
self.assertListEqual(xs.tolist(), [2, 2, 1, 1, 3, 3, 3])
# when you make a Cdf from a Pdf, you might get some floating
# point representation error
self.assertEqual(len(cdf), 4)
self.assertAlmostEqual(cdf.Prob(2), 0.6)
self.assertAlmostEqual(cdf[2], 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromPmf(pmf)
self.assertEqual(len(cdf), 4)
self.assertAlmostEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromItems(pmf.Items())
self.assertEqual(len(cdf), 4)
self.assertAlmostEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(pmf.d)
self.assertEqual(len(cdf), 4)
self.assertAlmostEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromDict(pmf.d)
self.assertEqual(len(cdf), 4)
self.assertAlmostEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(hist)
self.assertEqual(len(cdf), 4)
self.assertEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromHist(hist)
self.assertEqual(len(cdf), 4)
self.assertEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(t)
self.assertEqual(len(cdf), 4)
self.assertEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromList(t)
self.assertEqual(len(cdf), 4)
self.assertEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(Counter(t))
self.assertEqual(len(cdf), 4)
self.assertEqual(cdf.Prob(2), 0.6)
self.assertEqual(cdf.Value(0.6), 2)
cdf2 = cdf.Copy()
self.assertEqual(cdf2.Prob(2), 0.6)
self.assertEqual(cdf2.Value(0.6), 2)
def testCdf(self):
t = [1, 2, 2, 3, 5]
pmf = thinkstats2.Pmf(t)
hist = thinkstats2.Hist(t)
cdf = thinkstats2.Cdf(pmf)
self.assertEquals(len(str(cdf)), 40)
# when you make a Cdf from a Pdf, you might get some floating
# point representation error
self.assertEquals(len(cdf), 4)
self.assertAlmostEquals(cdf.Prob(2), 0.6)
self.assertAlmostEquals(cdf[2], 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromPmf(pmf)
self.assertEquals(len(cdf), 4)
self.assertAlmostEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(pmf.Items())
self.assertEquals(len(cdf), 4)
self.assertAlmostEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromItems(pmf.Items())
self.assertEquals(len(cdf), 4)
self.assertAlmostEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(pmf.d)
self.assertEquals(len(cdf), 4)
self.assertAlmostEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromDict(pmf.d)
self.assertEquals(len(cdf), 4)
self.assertAlmostEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(hist)
self.assertEquals(len(cdf), 4)
self.assertEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromHist(hist)
self.assertEquals(len(cdf), 4)
self.assertEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(t)
self.assertEquals(len(cdf), 4)
self.assertEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.MakeCdfFromList(t)
self.assertEquals(len(cdf), 4)
self.assertEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf = thinkstats2.Cdf(Counter(t))
self.assertEquals(len(cdf), 4)
self.assertEquals(cdf.Prob(2), 0.6)
self.assertEquals(cdf.Value(0.6), 2)
cdf2 = cdf.Copy()
self.assertEquals(cdf2.Prob(2), 0.6)
self.assertEquals(cdf2.Value(0.6), 2)