def test_windiff(self):
h = []
h.append(("5 words sentence of data.", 0))
h.append(("short.", 1))
h.append(("extra segmented sen.", 1))
h.append(("last and very very very very very long sen.", 1))
gold = []
gold.append(("5 words sentence of data.", 1))
gold.append(("short.", 1))
gold.append(("extra segmented sen.", 0))
gold.append(("last and very very very very very long sen.", 1))
gold = accuracy.get_seg_boundaries(gold)
h = accuracy.get_seg_boundaries(h)
window_size = 3
acc = accuracy.win_diff(gold, h, window_size = window_size)
self.assertEquals(float(acc), 0.6)
window_size = 5
expected = float(1)- float(8) / 13
acc = accuracy.win_diff(gold, h, window_size=window_size)
self.assertEquals("{0:.5f}".format(float(acc)), "{0:.5f}".format(expected))
def test_pk_perefct_seg(self):
sentences_class = []
sentences_class.append(("first sen is 5 words.", 0))
sentences_class.append(("sec sen.", 0))
sentences_class.append(("third sen is a very very very long sentence.", 1))
sentences_class.append(("the forth one is single segment.", 1))
gold = accuracy.get_seg_boundaries(sentences_class)
h = accuracy.get_seg_boundaries(sentences_class)
# with specified window size
for window_size in range(1, 15, 1):
acc = accuracy.pk(gold, h, window_size=window_size)
self.assertEquals(acc, 1)
# with default window size
acc = accuracy.pk(gold, h)
self.assertEquals(acc, 1)
def test_get_boundaries2(self):
sentences_class = []
sentences_class.append(("first sen is 5 words.", 0))
sentences_class.append(("sec sen.", 0))
sentences_class.append(("third sen is a very very very long sentence.", 1))
sentences_class.append(("the forth one is single segment.", 1))
expected = [16, 6]
result = accuracy.get_seg_boundaries(sentences_class)
for i, num in enumerate(result):
self.assertTrue(num == expected[i])
def test_pk_false_neg(self):
h = []
h.append(("5 words sentence of data.", 0))
h.append(("2 sentences same seg.", 1))
gold = []
gold.append(("5 words sentence of data.", 1))
gold.append(("2 sentences same seg.", 1))
gold = accuracy.get_seg_boundaries(gold)
h = accuracy.get_seg_boundaries(h)
window_size = 3
comparison_count = 6
# with default window size
acc = accuracy.pk(gold, h)
self.assertEquals(acc, window_size / comparison_count)
window_size = 4
acc = accuracy.pk(gold, h)
self.assertEquals(acc, window_size / comparison_count)
def test_get_boundaries(self):
sentences_class = []
sentences_class.append(("first sen.", 1))
sentences_class.append(("sec sen.", 1))
sentences_class.append(("third sen.", 0))
sentences_class.append(("forth sen.", 1))
sentences_class.append(("fifth sen.", 0))
sentences_class.append(("sixth sen.", 0))
sentences_class.append(("seventh sen.", 1))
expected = [2, 2, 4, 6]
result = accuracy.get_seg_boundaries(sentences_class)
for i, num in enumerate(result):
self.assertTrue(num == expected[i])