def test_zero_integer(self):
"""Test vose_sampler.ProbDistribution.alias_generation against a size
defined by zero. """
words = vose_sampler.get_words(valid_folder + "small.txt")
word_dist = vose_sampler.sample2dist(words)
VA_words = vose_sampler.VoseAlias(word_dist)
self.assertRaisesRegexp(SystemExit, nonnegative_integer_error + "0", VA_words.sample_n, 0)
def test_negative_integer(self):
"""Test vose_sampler.VoseAlias.alias_generation against a size
specified by a negative integer. """
words = vose_sampler.get_words(valid_folder + "small.txt")
word_dist = vose_sampler.sample2dist(words)
VA_words = vose_sampler.VoseAlias(word_dist)
self.assertRaisesRegexp(SystemExit, nonnegative_integer_error + "-1", VA_words.sample_n, -1)
def test_output_create_dist(self):
"""Test vose_sampler.ProbDistribution.create_dist to ensure it correctly
produces a uniform distribution for a list of words representing a standard die. """
numbers_dist = vose_sampler.sample2dist(["one","two","three","four","five","six"])
VA_numbers = vose_sampler.VoseAlias(numbers_dist)
actual = VA_numbers.dist
prob = Decimal(1)/Decimal(6)
expected = {"one":prob, "two":prob, "three":prob, "four":prob, "five":prob, "six":prob}
self.assertEqual(actual, expected)
def test_output_alias_generation(self):
"""Test vose_sampler.ProbDistribution.alias_generation to ensure it
generates words with same distribution as the original corpus. This
performs a 2-sided hypothesis test at the 1% significance level, that:
H_0: observed proportion a randomly selected word is equal to the
proportion seen in the original corpus (i.e. p_original == p_observed)
H_1: p_original != p_observed
"""
print(
"WARNING: There is a random element to test_output_alias_generation\n\
so it is likely to occasionally fail, nonetheless if the alias_generation\n\
method is working correctly failures will be very rare (testing at alpha=0.01\n\
implies we should expect a Type I error about 1% of the time).")
# Construct a ProbDistribution
words = vose_sampler.get_words(valid_folder + "small.txt")
word_dist = vose_sampler.sample2dist(words)
VA_words = vose_sampler.VoseAlias(word_dist)
# Generate sample and calculate the number of observations for a randomly selected word
word = random.choice(list(VA_words.dist))
n = 1000
t = 0
for i in range(n):
if VA_words.alias_generation() == word:
t += 1
# Compute the p-value
p_original = VA_words.dist[word]
p_low = math.fsum(
[self.dbinom(x, n, p_original) for x in range(t, n + 1)])
p_high = math.fsum(
[self.dbinom(x, n, p_original) for x in range(t + 1)])
p = 2 * min(p_low, p_high)
# Do not accept H_0 if p <= alpha
alpha = 0.01
self.assertGreater(p, alpha)