def __init__(self, posType="RAW"):
self.l = Locations()
self.mobypos = dict()
self.posdef = {
'N': 'Noun',
'p': 'Plural',
'h': 'Noun Phrase',
'V': 'Verb (usu participle)',
't': 'Verb (transitive)',
'i': 'Verb (intransitive)',
'A': 'Adjective',
'v': 'Adverb',
'C': 'Conjunction',
'P': 'Preposition',
'!': 'Interjection',
'r': 'Pronoun',
'D': 'Definite Article',
'I': 'Indefinite Article',
'o': 'Nominative',
'N/A': 'N/A',
'e': 'UNKNOWN'
}
self.loadRawPOS()
if "CONDENSED" in posType:
self.condensePOS()
def __init__(self, stressType, dictDirection="ORTH_TO_PHON"):
self.l = Locations()
self.myBASE = self.l.mybase
self.stressType = stressType
self.CMUDict = {}
self.arpaToKlatt = {}
self.loadArpaToKlatt()
# print "loading CMU Pronounciation dict"
self.translateDictToKlatt(dictDirection)
def __init__(self):
"""
"""
self.l = Locations()
self.phon = PhonologicalFromOrthographic()
self.mobypos = MobyPOS(self.l.mybase)
self.mremove = list(['Conjunction', 'Interjection', 'Pronoun',
'Preposition', 'Definite Article', 'Indefinite Article'])
self.elppos = EnglishLexiconProjectPOS()
self.closed = ClosedClass()
self.keep_as_is = set()
self.remove_not_representative = set()
self.keep_to_root = set()
self.inflect_to_root = dict()
def __init__(self):
# project specific file locations and variable names
self.l = Locations()
self.cv = CreateVariables()
self.cv.loadExperimentalVars()
self.r = ProxyAcqConvTrscr()
# all child words
self.c3 = self.cv.threeVars
self.c4 = self.cv.fourVars
self.c6 = self.cv.sixVars
# all adult words
self.a3 = self.cv.threeAdultVars
self.a4 = self.cv.fourAdultVars
self.a6 = self.cv.sixAdultVars
# all child with adjusted use
self.c3a = self.cv.threeVars[
self.cv.threeVars[self.cv.token_adult] > 0]
self.c4a = self.cv.fourVars[self.cv.fourVars[self.cv.token_adult] > 0]
self.c6a = self.cv.sixVars[self.cv.sixVars[self.cv.token_adult] > 0]
# child multisyllabic words and vars - all
self.m3a = self.cv.threeVars[self.cv.threeMultiAll]
self.m4a = self.cv.fourVars[self.cv.fourMultiAll]
self.m6a = self.cv.sixVars[self.cv.sixMultiAll]
# child multisyllabic words and vars - adult token > 0
self.m3 = self.cv.threeVars[self.cv.threeMulti]
self.m4 = self.cv.fourVars[self.cv.fourMulti]
self.m6 = self.cv.sixVars[self.cv.sixMulti]
# child CVC words and vars - adult token > 0
self.cvc3 = self.cv.threeVars[self.cv.threeCVC]
self.cvc4 = self.cv.fourVars[self.cv.fourCVC]
self.cvc6 = self.cv.sixVars[self.cv.sixCVC]
self.all_word_stats()
self.positive_control_stats()
self.multisyllabic_stats()
def __init__(self):
# project specific file locations and variable names
self.l = Locations()
self.findShape = Syllabifier('STRESS')
self.sim = SONSimilarity(list())
self.fau = ProxyAcqConvTrscr()
# labels for columns in pandas
self.orthographic = 'orthographic'
self.phonological = 'phonological'
self.syllables = 'syllables'
self.onset_nucleus = 'onset_nucleus'
self.onset_nucleus_coda = 'onset_nucleus_coda'
# indexes for numeric variables
self.length_syllables = 'length_syllables'
self.length_phonemes = 'length_phonemes'
self.str_pos = 'stressed_syll_position'
self.pct_child = 'percent_child'
self.pct_adult = 'percent_adult'
self.token_child = 'token_child'
self.token_adult = 'token_adult'
# SON and PHON neighborhood density
self.phon_n_density = 'SAD_density'
self.onset_nucleus_density = 'onset_nucleus_density'
self.onset_nucleus_coda_density = 'onset_nucleus_coda_density'
# PHON neighborhood frequency
self.son_frequency = 'SON_frequency'
self.sad_frequency_pct_raw = 'SAD_frequency_pct_child_raw'
# different ways of creating PACT values
self.fau_pct_tok_p1 = 'fau_poly1'
self.fau_pct_tok_p2 = 'fau_poly2'
self.fau_tok_tok_p1 = 'fau_token_poly1'
self.fau_tok_tok_p2 = 'fau_token_poly2'
self.fau_pct_pct_p1 = 'fau_pct_poly1'
self.fau_pct_pct_p2 = 'fau_pct_poly2'
def __init__(self):
""" Initializes needed modules, and creates child and adult lexicons"""
# project specific file locations and variable names
self.loc = Locations()
self.we = WordEvaluation()
self.we.load_evaluated_words()
self.phon = PhonologicalFromOrthographic()
# number of transcripts at each age
self.n3 = 747
self.n4 = 683
self.n6 = 696
# creating child lexicons from RWL and word evaluation
self.child3 = self.apply_word_evaluation(self.loc.threeChildSALT)
self.child4 = self.apply_word_evaluation(self.loc.fourChildSALT)
self.child6 = self.apply_word_evaluation(self.loc.sixChildSALT)
# creating adult lexicons from RWL and word evaluation
self.adult3 = self.apply_word_evaluation(self.loc.threeAdultSALT)
self.adult4 = self.apply_word_evaluation(self.loc.fourAdultSALT)
self.adult6 = self.apply_word_evaluation(self.loc.sixAdultSALT)
def __init__(self):
# project specific file locations and variable names
self.l = Locations()
self.cv = CreateVariables()
self.cv.loadExperimentalVars()
self.bootstrap_num = 1000
def __init__(self):
self.l = Locations()
self.location = self.l.english_lexicon_project
self.elp_pos = dict()
self.pos_map = self.load_pos_map()
self.loadPOSFromFile()
f = open(rwl_file, "r")
f.readline()
for line in f.readlines():
wordInfo = line.strip()
wordInfo = wordInfo.split(",")
#
orth_words[wordInfo[0].lower()]['TOKEN'] = wordInfo[3]
#
orth_words[wordInfo[0].lower()]['NUMCHILD'] = wordInfo[1]
f.close()
return orth_words
if __name__ == "__main__":
TEST = RootWordList()
L = Locations()
print('entries from three adult RWL',
len(TEST.orthographic_from_rwl(L.threeAdultSALT)))
print('entries from three child RWL',
len(TEST.orthographic_from_rwl(L.threeChildSALT)))
print('entries from four adult RWL',
len(TEST.orthographic_from_rwl(L.fourAdultSALT)))
print('entries from four child RWL',
len(TEST.orthographic_from_rwl(L.fourChildSALT)))
print('entries from six adult RWL',
len(TEST.orthographic_from_rwl(L.sixAdultSALT)))
print('entries from six child RWL',
len(TEST.orthographic_from_rwl(L.sixChildSALT)))
def __init__(self):
self.l = Locations()
self.myBASE = self.l.mybase
self.closedclass = set()
self.loadClosedClass()