def test_transform(self):
dist = StatsCounter({
'of': 0.20,
'the': 0.50,
'that': 0.10,
'from': 0.20
})
dist = dist.transform(lambda word, prob: word.startswith('t'))
assert dist == StatsCounter({True: 0.6, False: 0.4})
def test_normalize(self):
pdist = StatsCounter({1: 1, 2: 2, 3: 1}).normalize()
assert pdist == {
1: 0.25,
2: 0.50,
3: 0.25,
}
def _get_revision_word_dist(self, page_title, revid):
""""""
revids_to_word_dist = self.ctitle_to_revids_to_word_dist[page_title]
if revid in revids_to_word_dist:
return revids_to_word_dist[revid]
text = self._get_revision_text(page_title, revid)
text = [word.lower() for word in wordpunct_tokenize(text)
if word.lower() not in STOPWORDS and word.lower() not in PUNCTUATION]
pdist = StatsCounter(text).normalize()
revids_to_word_dist[revid] = pdist
return pdist
def test_rank(etree):
k = measure(etree.xpath('//body//*/..'))
rv = rank(k)
assert list(rv)[0] == (etree.xpath('//article')[0],
StatsCounter(['div'] * 9))
def test_measure(etree):
rv = measure(etree.xpath('//div/..'))
uv = [(node.tag, metric) for node, metric in rv]
assert uv == [('article', StatsCounter(['div'] * 9))]
def __init__(self, *args, **kwargs):
StatsCounter.__init__(self, *args, **kwargs)
def test_get_weighted_random_value(self): wrv = StatsCounter(a=10, b=3).get_weighted_random_value() assert wrv == "a" or "b"
class TestStatsCounter:
counter_ints = StatsCounter({str(s):s for s in range(1000)})
def test_mean_int(self):
m = self.counter_ints.mean()
d = 499500/1000
assert m == d
def test_median_low(self):
m = self.counter_ints.median_low()
assert m == 499
def test_median_high(self, ):
m = self.counter_ints.median_high()
assert m == 500
def test_median_grouped(self, ):
m = self.counter_ints.median_grouped()
assert m == 499.5
def test_mode(self):
with raises(stats.StatisticsError):
self.counter_ints.mode()
def test_variance(self):
m = self.counter_ints.variance()
assert m == 83416.66666666667
def test_stdev(self, ):
m = self.counter_ints.stdev()
assert m == 288.8194360957494
def test_pvariance(self):
m = self.counter_ints.pvariance()
assert m == 83333.25
def test_pstdev(self, ):
m = self.counter_ints.pstdev()
assert m == 288.6749902572095
def test_argmax(self):
m = self.counter_ints.argmax()
assert m == '999'
def test_max(self):
m = self.counter_ints.max()
assert m == 999
def test_normalize(self):
pdist = StatsCounter({1: 1, 2: 2, 3: 1}).normalize()
assert pdist == {
1: 0.25,
2: 0.50,
3: 0.25,
}
def test_get_weighted_random_value(self):
wrv = StatsCounter(a=10, b=3).get_weighted_random_value()
assert wrv == "a" or "b"
def test_transform(self):
dist = StatsCounter({
'of': 0.20,
'the': 0.50,
'that': 0.10,
'from': 0.20
})
dist = dist.transform(lambda word, prob: word.startswith('t'))
assert dist == StatsCounter({True: 0.6, False: 0.4})
def measure(nodes):
return [(node, StatsCounter([child.tag for child in node]))
for node in nodes]