def test_parse_csv():
Iris = DataFile('iris.csv').read()
assert parse_csv(Iris)[0] == [5.1, 3.5, 1.4, 0.2, 'setosa']
def __init__(self, board=None):
if BoggleFinder.wordlist is None:
BoggleFinder.wordlist = Wordlist(DataFile("EN-text/wordlist.txt"))
self.found = {}
if board:
self.set_board(board)
def test_text_models():
flatland = DataFile("EN-text/flatland.txt").read()
wordseq = words(flatland)
P1 = UnigramTextModel(wordseq)
P2 = NgramTextModel(2, wordseq)
P3 = NgramTextModel(3, wordseq)
# The most frequent entries in each model
assert P1.top(10) == [(2081, 'the'), (1479, 'of'), (1021, 'and'),
(1008, 'to'), (850, 'a'), (722, 'i'), (640, 'in'),
(478, 'that'), (399, 'is'), (348, 'you')]
assert P2.top(10) == [(368, ('of', 'the')), (152, ('to', 'the')),
(152, ('in', 'the')), (86, ('of', 'a')),
(80, ('it', 'is')), (71, ('by', 'the')),
(68, ('for', 'the')), (68, ('and', 'the')),
(62, ('on', 'the')), (60, ('to', 'be'))]
assert P3.top(10) == [(30, ('a', 'straight', 'line')),
(19, ('of', 'three', 'dimensions')),
(16, ('the', 'sense', 'of')),
(13, ('by', 'the', 'sense')),
(13, ('as', 'well', 'as')),
(12, ('of', 'the', 'circles')),
(12, ('of', 'sight', 'recognition')),
(11, ('the', 'number', 'of')),
(11, ('that', 'i', 'had')), (11, ('so', 'as', 'to'))]
assert isclose(P1['the'], 0.0611, rel_tol=0.001)
assert isclose(P2['of', 'the'], 0.0108, rel_tol=0.01)
assert isclose(P3['', '', 'but'], 0.0, rel_tol=0.001)
assert isclose(P3['', '', 'but'], 0.0, rel_tol=0.001)
assert isclose(P3['so', 'as', 'to'], 0.000323, rel_tol=0.001)
assert P2.cond_prob.get(('went', )) is None
assert P3.cond_prob['in', 'order'].dictionary == {'to': 6}
test_string = 'unigram'
wordseq = words(test_string)
P1 = UnigramTextModel(wordseq)
assert P1.dictionary == {('unigram'): 1}
test_string = 'bigram text'
wordseq = words(test_string)
P2 = NgramTextModel(2, wordseq)
assert (P2.dictionary == {
('', 'bigram'): 1,
('bigram', 'text'): 1
} or P2.dictionary == {
('bigram', 'text'): 1,
('', 'bigram'): 1
})
test_string = 'test trigram text'
wordseq = words(test_string)
P3 = NgramTextModel(3, wordseq)
assert ('', '', 'test') in P3.dictionary
assert ('', 'test', 'trigram') in P3.dictionary
assert ('test', 'trigram', 'text') in P3.dictionary
assert len(P3.dictionary) == 3
def test_rot13_decoding():
flatland = DataFile("EN-text/flatland.txt").read()
ring = ShiftDecoder(flatland)
msg = ring.decode(rot13('Hello, world!'))
assert msg == 'Hello, world!'
def test_shift_decoding():
flatland = DataFile("EN-text/flatland.txt").read()
ring = ShiftDecoder(flatland)
msg = ring.decode('Kyzj zj r jvtivk dvjjrxv.')
assert msg == 'This is a secret message.'
def _set_lang(lang):
with DataFile(ensure_res('.'.join((lang, 'lang'))), None, json) as data:
Text._data.update(data)