def devoicer(self, words):
for i, word in enumerate(words):
c = word[-1]
segment = SegmentTable().get_segment_by_symbol(c)
new_features = deepcopy(segment.features)
new_features[Feature('voice', ('+', '-'))] = '-'
new_c = SegmentTable().get_segment_symbol_by_features(new_features)
if new_c:
words[i] = word[:-1] + new_c
def devoice(self, words):
for i, word in enumerate(words):
# if random.randint(1, 5) != 5:
# continue # chance of 5 to 1 of changing
c = word[-1]
segment = SegmentTable().get_segment_by_symbol(c)
new_features = deepcopy(segment.features)
new_features[Feature('voice', ('+', '-'))] = '-'
new_c = SegmentTable().get_segment_symbol_by_features(new_features)
if new_c:
words[i] = word[:-1] + new_c
def apply_noise(self, words):
total_to_noise = int(len(words) * self.noise_rate / 100)
segment_table = SegmentTable()
for i, word in enumerate(words[:total_to_noise]):
c = word[-1]
segment = segment_table.get_segment_by_symbol(c)
if not self._is_voiced_obstruent(segment):
continue
new_features = deepcopy(segment.features)
new_features[Feature('voice', ('+', '-'))] = '-'
new_c = segment_table.get_segment_symbol_by_features(new_features)
if new_c:
words[i] = word[:-1] + new_c
def __init__(self, feature_string_dict, role=None):
"""
:param feature_string_dict: dictionary of form {"cons": "+", "WB": True}
:param role: "target", "change", "left_context", or "right_context"
"""
feature_dict = dict()
self.role = role
self.kleene = False
self.word_boundary = False
self.morpheme_boundary = False
if WORD_BOUNDARY_FEATURE_NAME in feature_string_dict:
if feature_string_dict[
WORD_BOUNDARY_FEATURE_NAME] and self._is_context_bundle():
self.word_boundary = True
elif MORPHEME_BOUNDARY_FEATURE_NAME in feature_string_dict:
if feature_string_dict[
MORPHEME_BOUNDARY_FEATURE_NAME] and self._is_context_bundle(
):
self.morpheme_boundary = True
else:
for feature_name in feature_string_dict:
if feature_name is KLEENE_FEATURE_NAME:
if self._is_context_bundle(
) and configurations['CHANGE_KLEENE_VALUE']:
self.kleene = feature_string_dict[feature_name]
else:
feature = Feature(feature_name)
if not SegmentTable().is_valid_feature(feature):
raise ValueError(
u"{} not in segment_table".format(feature_name))
else:
feature_dict[feature] = feature_string_dict[
feature_name]
self.feature_dict = feature_dict
from rule import Rule
from rule_set import RuleSet
from segment_table import Segment, SegmentTable, Feature
simulation_number = 1
syll = Feature('syll')
cons = Feature('cons')
long = Feature('long')
bound = Feature('bound')
a = Segment('a', {syll: '+', cons: '-', long: '-', bound: '-'})
b = Segment('b', {syll: '-', cons: '+', long: '-', bound: '-'})
lengthening = Segment('Y', {syll: '-', cons: '-', long: '+', bound: '-'})
morpheme_boundary = Segment('B', {syll: '-', cons: '-', long: '-', bound: '+'})
segment_table = SegmentTable([a, b, lengthening, morpheme_boundary])
configurations_dict = \
{
"MUTATE_RULE_SET": 3,
"MUTATE_HMM": 1,
"COMBINE_EMISSIONS": 0,
"ADVANCE_EMISSION": 0,
"CLONE_STATE": 0,
"CLONE_EMISSION": 0,
"ADD_STATE": 0,
"REMOVE_STATE": 0,
"ADD_TRANSITION": 0,
from rule import Rule
from rule_set import RuleSet
from segment_table import Segment, SegmentTable, Feature
from copy import deepcopy
simulation_number = 1
cons = Feature('cons')
high = Feature('high')
labial = Feature('labial')
voiceless = Feature('voiceless')
bound = Feature('bound')
a = Segment('a', {cons: '-', high: '-', labial: '-', voiceless: '-', bound: '-'})
i = Segment('i', {cons: '-', high: '+', labial: '-', voiceless: '-', bound: '-'})
b = Segment('b', {cons: '+', high: '-', labial: '+', voiceless: '-', bound: '-'})
d = Segment('d', {cons: '+', high: '-', labial: '-', voiceless: '-', bound: '-'})
F = Segment('F', {cons: '-', high: '-', labial: '-', voiceless: '+', bound: '-'})
morpheme_boundary = Segment('B', {cons: '-', high: '-', labial: '-', voiceless: '-', bound: '+'})
segment_table = SegmentTable([a, i, b, d, F, morpheme_boundary])
configurations_dict = \
{
"MUTATE_RULE_SET": 2,
"MUTATE_HMM": 1,
"COMBINE_EMISSIONS": 0,
from rule import Rule
from rule_set import RuleSet
from segment_table import Segment, SegmentTable, Feature
simulation_number = 1
cons = Feature('cons')
a = Segment('a', {cons: '-'})
b = Segment('b', {cons: '+'})
segment_table = SegmentTable([a, b])
configurations_dict = \
{
"MUTATE_RULE_SET": 1,
"MUTATE_HMM": 1,
"COMBINE_EMISSIONS": 0,
"ADVANCE_EMISSION": 0,
"CLONE_STATE": 0,
"CLONE_EMISSION": 0,
"ADD_STATE": 0,
"REMOVE_STATE": 0,
"ADD_TRANSITION": 0,
"REMOVE_TRANSITION": 0,
"ADD_SEGMENT_TO_EMISSION": 0,
"REMOVE_SEGMENT_FROM_EMISSION": 1,
"CHANGE_SEGMENT_IN_EMISSION": 0,
"ADD_EMISSION_TO_STATE": 0,
def _is_voiced_obstruent(self, segment):
is_voiced = segment.features[Feature('voice', ('+', '-'))] == '+'
is_obstruent = segment.features[Feature('son', ('+', '-'))] == '-'
return is_voiced and is_obstruent
from rule import Rule
from rule_set import RuleSet
from segment_table import Segment, SegmentTable, Feature
from copy import deepcopy
simulation_number = 1
cons = Feature('cons')
high = Feature('high')
voice = Feature('voice', values=('-', '+', '0'))
bound = Feature('bound')
a = Segment('a', {cons: '-', high: '-', voice: '-', bound: '-'})
i = Segment('i', {cons: '-', high: '+', voice: '-', bound: '-'})
t = Segment('t', {cons: '+', high: '-', voice: '-', bound: '-'})
d = Segment('d', {cons: '+', high: '-', voice: '+', bound: '-'})
T = Segment('T', {cons: '+', high: '-', voice: '0', bound: '-'})
B = Segment('B', {cons: '-', high: '-', voice: '-', bound: '+'})
segment_table = SegmentTable([a, i, t, d, T, B])
configurations_dict = \
{
"MUTATE_RULE_SET": 1,
"MUTATE_HMM": 1,
"COMBINE_EMISSIONS": 0,
"ADVANCE_EMISSION": 0,
"CLONE_STATE": 0,
"CLONE_EMISSION": 0,