def test_minpair(unspecified_test_corpus):
calls = [({'segment_pairs':[('s','ʃ')],
'relative_count':True},0.125),
({'segment_pairs':[('s','ʃ')],
'relative_count':False},1),
({'segment_pairs':[('m','n')],
'relative_count':True},0.11111),
({'segment_pairs':[('m','n')],
'relative_count':False},1),
({'segment_pairs':[('e','o')],
'relative_count':True},0),
({'segment_pairs':[('e','o')],
'relative_count':False},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':True},0.14286),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':False},2),]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'type') as c:
for kwargs, v in calls:
print(kwargs)
assert(abs(minpair_fl(c, **kwargs)[0]-v) < 0.0001)
calls = [({'segment_pairs':[('s','ʃ')],
'relative_count':True},0.14286),
({'segment_pairs':[('s','ʃ')],
'relative_count':False},1),
({'segment_pairs':[('m','n')],
'relative_count':True},0),
({'segment_pairs':[('m','n')],
'relative_count':False},0),
({'segment_pairs':[('e','o')],
'relative_count':True},0),
({'segment_pairs':[('e','o')],
'relative_count':False},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':True},0.09091),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':False},1)]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'type', frequency_threshold = 3) as c:
for kwargs, v in calls:
print(kwargs)
assert(abs(minpair_fl(c, **kwargs)[0]-v) < 0.0001)
def test_minpair(unspecified_test_corpus):
calls = [({'segment_pairs':[('s','ʃ')],
'relative_count':True},0.125),
({'segment_pairs':[('s','ʃ')],
'relative_count':False},1),
({'segment_pairs':[('m','n')],
'relative_count':True},0.11111),
({'segment_pairs':[('m','n')],
'relative_count':False},1),
({'segment_pairs':[('e','o')],
'relative_count':True},0),
({'segment_pairs':[('e','o')],
'relative_count':False},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':True},0.14286),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':False},2),]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'type') as c:
for kwargs, v in calls:
print(kwargs)
assert(abs(minpair_fl(c, **kwargs)[0]-v) < 0.0001)
calls = [({'segment_pairs':[('s','ʃ')],
'relative_count':True},0.14286),
({'segment_pairs':[('s','ʃ')],
'relative_count':False},1),
({'segment_pairs':[('m','n')],
'relative_count':True},0),
({'segment_pairs':[('m','n')],
'relative_count':False},0),
({'segment_pairs':[('e','o')],
'relative_count':True},0),
({'segment_pairs':[('e','o')],
'relative_count':False},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':True},0.09091),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':False},1)]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'type', frequency_threshold = 3) as c:
for kwargs, v in calls:
print(kwargs)
assert(abs(minpair_fl(c, **kwargs)[0]-v) < 0.0001)
def test_minimal_pair_wordtokens(unspecified_discourse_corpus):
corpus = unspecified_discourse_corpus.lexicon
calls = [({'segment_pairs':[('s','ʃ')],
'relative_count':True},0.125),
({'segment_pairs':[('s','ʃ')],
'relative_count':False},1),
({'segment_pairs':[('m','n')],
'relative_count':True},0.11111),
({'segment_pairs':[('m','n')],
'relative_count':False},1),
({'segment_pairs':[('e','o')],
'relative_count':True},0),
({'segment_pairs':[('e','o')],
'relative_count':False},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':True},0.14286),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':False},2),]
with MostFrequentVariantContext(corpus, 'transcription', 'type') as c:
for kwargs, v in calls:
assert(abs(minpair_fl(c, **kwargs)[0]-v) < 0.0001)
calls = [({ 'segment_pairs':[('s','ʃ')],
'relative_count':True},0.14286),
({'segment_pairs':[('s','ʃ')],
'relative_count':False},1),
({'segment_pairs':[('m','n')],
'relative_count':True},0),
({'segment_pairs':[('m','n')],
'relative_count':False},0),
({'segment_pairs':[('e','o')],
'relative_count':True},0),
({'segment_pairs':[('e','o')],
'relative_count':False},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':True},0.09091),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')],
'relative_count':False},1)]
with MostFrequentVariantContext(corpus,
'transcription', 'type',frequency_threshold = 3) as c:
for kwargs, v in calls:
assert(abs(minpair_fl(c, **kwargs)[0]-v) < 0.0001)
def run(self):
if self.name == 'functional_load':
try:
results = minpair_fl(self.kwargs['corpus'],
self.kwargs['segment_pair'],
stop_check=self.kwargs['stop_check'],
call_back=self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name, e)
self.errorEncountered.emit(message)
return
elif self.name == 'string_similarity':
try:
results = string_similarity(
self.kwargs['corpus'],
self.kwargs['query'],
self.kwargs['algorithm'],
stop_check=self.kwargs['stop_check'],
call_back=self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name, e)
self.errorEncountered.emit(message)
return
elif self.name == 'phonotactic_probability':
try:
results = phonotactic_probability_vitevitch(
self.kwargs['corpus'],
self.kwargs['query'],
self.kwargs['sequence_type'],
probability_type=self.kwargs['probability_type'],
stop_check=self.kwargs['stop_check'],
call_back=self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name, e)
self.errorEncountered.emit(message)
return
elif self.name == 'kullback_leibler':
try:
results = KullbackLeibler(self.kwargs['corpus'],
self.kwargs['seg1'],
self.kwargs['seg2'],
self.kwargs['side'],
stop_check=self.kwargs['stop_check'],
call_back=self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name, e)
self.errorEncountered.emit(message)
return
else:
raise UnLuckyException(
'No analysis function called {} could be found'.format(
self.name))
def run(self):
if self.name == 'functional_load':
try:
results = minpair_fl(self.kwargs['corpus'], self.kwargs['segment_pair'],
stop_check = self.kwargs['stop_check'],
call_back = self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name,e)
self.errorEncountered.emit(message)
return
elif self.name == 'string_similarity':
try:
results = string_similarity(self.kwargs['corpus'], self.kwargs['query'], self.kwargs['algorithm'],
stop_check = self.kwargs['stop_check'],
call_back = self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name,e)
self.errorEncountered.emit(message)
return
elif self.name == 'phonotactic_probability':
try:
results = phonotactic_probability_vitevitch(self.kwargs['corpus'],self.kwargs['query'],
self.kwargs['sequence_type'],
probability_type=self.kwargs['probability_type'],
stop_check = self.kwargs['stop_check'],
call_back = self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name,e)
self.errorEncountered.emit(message)
return
elif self.name == 'kullback_leibler':
try:
results = KullbackLeibler(self.kwargs['corpus'], self.kwargs['seg1'], self.kwargs['seg2'], self.kwargs['side'],
stop_check = self.kwargs['stop_check'],
call_back = self.kwargs['call_back'])
self.dataReady.emit(results)
except Exception as e:
message = '{}:{}'.format(self.name,e)
self.errorEncountered.emit(message)
return
else:
raise UnLuckyException('No analysis function called {} could be found'.format(self.name))
def test_minimal_pair_wordtokens(unspecified_discourse_corpus):
corpus = unspecified_discourse_corpus.lexicon
calls = [
({
'segment_pairs': [('s', 'ʃ')],
'relative_count': True
}, 0.125),
({
'segment_pairs': [('s', 'ʃ')],
'relative_count': False
}, 1),
({
'segment_pairs': [('m', 'n')],
'relative_count': True
}, 0.11111),
({
'segment_pairs': [('m', 'n')],
'relative_count': False
}, 1),
({
'segment_pairs': [('e', 'o')],
'relative_count': True
}, 0),
({
'segment_pairs': [('e', 'o')],
'relative_count': False
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')],
'relative_count': True
}, 0.14286),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')],
'relative_count': False
}, 2),
]
with MostFrequentVariantContext(corpus, 'transcription', 'type') as c:
for kwargs, v in calls:
assert (abs(minpair_fl(c, **kwargs)[0] - v) < 0.0001)
calls = [({
'segment_pairs': [('s', 'ʃ')],
'relative_count': True
}, 0.14286), ({
'segment_pairs': [('s', 'ʃ')],
'relative_count': False
}, 1), ({
'segment_pairs': [('m', 'n')],
'relative_count': True
}, 0), ({
'segment_pairs': [('m', 'n')],
'relative_count': False
}, 0), ({
'segment_pairs': [('e', 'o')],
'relative_count': True
}, 0), ({
'segment_pairs': [('e', 'o')],
'relative_count': False
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')],
'relative_count': True
}, 0.09091),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')],
'relative_count': False
}, 1)]
with MostFrequentVariantContext(corpus,
'transcription',
'type',
frequency_threshold=3) as c:
for kwargs, v in calls:
assert (abs(minpair_fl(c, **kwargs)[0] - v) < 0.0001)
