def main():
words = uti.set_reader(os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_preprocessed.txt']))
roots = uti.set_reader(os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_preprocessed.txt']))
words_from_roots = {(word[:len(root)] + '+' + word[len(root):]).rstrip('+')
for word in words for root in roots
if word.startswith(root)}
uti.write_iter(words_from_roots, os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_dl_parsed_preprocessed.txt'
]))
words_from_roots_pl = ay_trans.pl_trans(words_from_roots)
uti.write_iter(words_from_roots_pl, os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_dl_parsed_pl.txt'
]))
words_from_roots_ej = {ay_trans.nth_transcribe(word, ay.ejectives) for word in words_from_roots}
uti.write_iter(words_from_roots_ej, os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_dl_parsed_preprocessed_ejectives.txt'
]))
words_from_roots_ej_pl = ay_trans.pl_trans(words_from_roots_ej)
uti.write_iter(words_from_roots_ej_pl, os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_dl_parsed_pl_ejectives.txt'
]))
def main():
# Reading in files
nk_orth_roots = uti.set_reader(os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'nk_roots_pretrans.txt')))
nk_orth_forms = uti.set_reader(os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'nk_forms_pretrans.txt')))
nk_orth_pars = uti.set_reader(os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'nk_forms_sep_pretrans.txt')))
# Transcribing & Writing
# Roots
nk_trans_roots = transcribe(nk_orth_roots, palatalize=True)
uti.write_iter(nk_trans_roots, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'Preprocessed', 'nk_roots_preprocessed.txt')))
nk_ipa_roots = ipa_trans(nk_trans_roots)
uti.write_iter(nk_ipa_roots, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'IPA', 'nk_roots_ipa.txt')))
nk_pl_roots = uti.pl_trans(nk_trans_roots)
uti.write_iter(nk_pl_roots, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'UCLAPL', 'nk_roots_pl.txt')))
# Word forms
nk_trans_forms = transcribe(nk_orth_forms, palatalize=True)
uti.write_iter(nk_trans_forms, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'Preprocessed', 'nk_forms_preprocessed.txt')))
nk_ipa_forms = ipa_trans(nk_trans_forms)
uti.write_iter(nk_ipa_forms, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'IPA', 'nk_forms_ipa.txt')))
nk_pl_forms = uti.pl_trans(nk_trans_forms)
uti.write_iter(nk_pl_forms, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'UCLAPL', 'nk_forms_pl.txt')))
# Parsed word forms
nk_trans_pars = transcribe(nk_orth_pars, palatalize=True)
uti.write_iter(nk_trans_pars, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'Preprocessed', 'nk_forms_sep_preprocessed.txt')))
nk_ipa_pars = ipa_trans(nk_trans_pars)
uti.write_iter(nk_ipa_pars, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'IPA', 'nk_forms_sep_ipa.txt')))
nk_pl_pars = uti.pl_trans(nk_trans_pars)
uti.write_iter(nk_pl_pars, os.path.join(*(
os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'UCLAPL', 'nk_forms_sep_pl.txt')))
def main():
roots, suffixes = delucca_reader(
os.path.join(*[os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_delucca_segmented.txt']))
uti.write_iter(roots, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca.txt']))
uti.write_iter(suffixes,os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_suffixes_delucca.txt']))
lowering_table = ay_trans.make_lowering_table()
roots_trans = ay_trans.transcribe(roots, lowering=lowering_table)
roots_pl = ay_trans.pl_trans(roots_trans)
roots_ipa = ay_trans.ipa_trans(roots_trans)
roots_trans_ej = {ay_trans.nth_transcribe(word, ay.ejectives) for word in roots_trans}
roots_ej_pl = ay_trans.pl_trans(roots_trans_ej)
suffixes_trans = ay_trans.transcribe(suffixes, lowering=lowering_table)
uti.write_iter(roots_trans, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_preprocessed.txt']))
uti.write_iter(roots_pl, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_pl.txt']))
uti.write_iter(roots_ipa, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_ipa.txt']))
uti.write_iter(suffixes_trans, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_suffixes_delucca_preprocessed.txt']))
uti.write_iter(roots_trans_ej, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_preprocessed_ejectives.txt']))
uti.write_iter(roots_ej_pl, os.path.join(*[
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_pl_ejectives.txt']))
ay_words = uti.set_reader(os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_preprocessed.txt']))
subcorpus = rid_of_starters(ay_words, roots_trans)
roots = set_stemmer(subcorpus, suffixes_trans, ay)
uti.write_iter(roots, os.path.join(*[
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_roots_from_wordforms_preprocessed.txt']))
def main():
ay_orth = uti.set_reader(
os.path.join(
*[os.pardir, "Aymara", "Outputs", "Aymara_words_no_sp_en.txt"]))
lowering_table = make_lowering_table()
ay_trans = transcribe(ay_orth, lowering=lowering_table)
uti.write_iter(
ay_trans,
os.path.join(*[
os.pardir, "Aymara", "Outputs", "Transcription",
"aymara_preprocessed.txt"
]))
ay_ipa = ipa_trans(ay_trans)
uti.write_iter(
ay_ipa,
os.path.join(*[
os.pardir, "Aymara", "Outputs", "Transcription", "aymara_ipa.txt"
]))
ay_pl = pl_trans(ay_trans)
uti.write_iter(
ay_pl,
os.path.join(*[
os.pardir, "Aymara", "Outputs", "Transcription", "aymara_pl.txt"
]))
ay_trans_ej = {nth_transcribe(wrd, ay.ejectives) for wrd in ay_trans}
uti.write_iter(
ay_trans_ej,
os.path.join(*[
os.pardir, "Aymara", "Outputs", "Transcription",
"aymara_preprocessed_ejectives.txt"
]))
ay_pl_ej = pl_trans(ay_trans_ej)
uti.write_iter(
ay_pl_ej,
os.path.join(*[
os.pardir, "Aymara", "Outputs", "Transcription",
"aymara_pl_ejectives.txt"
]))
def main():
sib_sib = {sib1 + sib2 for sib1 in nk.sibilants for sib2 in nk.sibilants}
nk_roots = {
word.replace(' ', '')
for word in uti.set_reader(
os.path.join(*(os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'Preprocessed', 'nk_roots_preprocessed.txt')))
}
nk_forms = {
word.replace(' ', '')
for word in uti.set_reader(
os.path.join(*(os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'Preprocessed', 'nk_forms_preprocessed.txt')))
}
nk_forms_parsed = {
word.replace(' ', '')
for word in uti.set_reader(
os.path.join(*(os.pardir, 'NkoreKiga', 'Outputs', 'Transcription',
'Preprocessed', 'nk_forms_sep_preprocessed.txt')))
}
nk_corpora = [nk_roots, nk_forms, nk_forms_parsed]
corp_names = ['roots', 'forms', 'formssep']
for i, corpus in enumerate(nk_corpora):
corp_name = corp_names[i]
# All trigrams
trigram_counts = cou.trigram_counter(corpus)
uti.write_dict(
trigram_counts,
os.path.join(*(os.pardir, 'NkoreKiga', 'Outputs', 'Counts', 'Raw',
'nk_counts_tri_{}.txt'.format(corp_name))))
# Sibilant tier
nk_ss_list, nk_ss_count = cou.count_many_substr(sib_sib,
corpus,
nk,
tier=nk.sibilants,
return_set=True)
nk_ss_count_formatted = {
key[0] + ' anything ' + key[1]: nk_ss_count[key]
for key in nk_ss_count.keys()
}
uti.write_dict(
nk_ss_count_formatted,
os.path.join(*(os.pardir, 'NkoreKiga', 'Outputs', 'Counts', 'Raw',
'nk_counts_sib_tier_{}.txt'.format(corp_name))))
nk_ss_fric_list, nk_ss_fric_count = cou.count_many_substr(
sib_sib, corpus, nk, tier=nk.sibilant_fricatives, return_set=True)
nk_ss_fric_count_formatted = {
key[0] + ' anything ' + key[1]: nk_ss_fric_count[key]
for key in nk_ss_fric_count.keys()
}
uti.write_dict(
nk_ss_fric_count_formatted,
os.path.join(
*(os.pardir, 'NkoreKiga', 'Outputs', 'Counts', 'Raw',
'nk_counts_sib_fric_tier_{}.txt'.format(corp_name))))
def main():
parsed_words = {
word.replace(' ', '')
for word in uti.set_reader(
os.path.join(*(os.pardir, 'Aymara', 'Inputs',
'ay_words_parsed.txt')))
}
trigrams_parsed = cou.trigram_counter(parsed_words)
uti.write_dict(
trigrams_parsed,
os.path.join(*(os.pardir, 'Aymara', 'Outputs', 'Counts', 'Raw',
'aymara_counts_seg_all_trigrams_parsed.txt')))
"""
words = uti.set_reader(os.path.join(*(
os.pardir, 'Aymara', 'Outputs', 'Transcription',
'aymara_preprocessed.txt')))
roots = uti.set_reader(os.path.join(*(
os.pardir, 'Aymara', 'Inputs', 'delucca',
'ay_roots_delucca_preprocessed.txt')))
ay_corpora = [words, roots]
ay_corpus_names = ['words', 'roots']
# Aymara sounds: Defining certain ngrams
precon_asp = {aspirate + consonant for aspirate in ay.aspirates for consonant in ay.consonants}
precon_ej = {ejective + consonant for ejective in ay.ejectives for consonant in ay.consonants}
precon_plain = {plain + consonant for plain in ay.plain_stops for consonant in ay.consonants}
precon_stops = precon_asp.union(precon_ej, precon_plain)
prevoc_asp = {aspirate + vowel for aspirate in ay.aspirates for vowel in ay.vowels}
prevoc_ej = {ejective + vowel for ejective in ay.ejectives for vowel in ay.vowels}
prevoc_plain = {plain + vowel for plain in ay.plain_stops for vowel in ay.vowels}
prevoc_stops = prevoc_asp.union(prevoc_ej, prevoc_plain)
cc = {c1 + c2 for c1 in ay.consonants for c2 in ay.consonants}
cvc = {c1 + v + c2 for c1 in ay.consonants for v in ay.vowels
for c2 in ay.consonants}
cvcv = {c1 + v + c2 + v2 for c1 in ay.consonants for v in ay.vowels
for c2 in ay.consonants for v2 in ay.vowels}
stop_v_stop = {stop1 + vowel + stop2
for stop1 in ay.stops for vowel in ay.vowels for stop2 in ay.stops}
asp_v_asp = {a1 + v + a2 for a1 in ay.aspirates for v in ay.vowels for a2 in ay.aspirates}
asp_v_ej = {a + v + e for a in ay.aspirates for v in ay.vowels for e in ay.ejectives}
asp_v_plain = {a + v + p for a in ay.aspirates for v in ay.vowels for p in ay.plain_stops}
ej_v_asp = {e + v + a for e in ay.ejectives for v in ay.vowels for a in ay.aspirates}
ej_v_ej = {e1 + v + e2 for e1 in ay.ejectives for v in ay.vowels for e2 in ay.ejectives}
ej_v_ej_het = {e1 + v + e2 for e1 in ay.ejectives for v in ay.vowels for e2 in ay.ejectives
if e1 != e2}
ej_v_plain = {e + v + p for e in ay.ejectives for v in ay.vowels for p in ay.plain_stops}
plain_v_asp = {p + v + a for p in ay.plain_stops for v in ay.vowels for a in ay.aspirates}
plain_v_ej = {p + v + e for p in ay.plain_stops for v in ay.vowels for e in ay.ejectives}
plain_v_plain = {p1 + v + p2 for p1 in ay.plain_stops for v in ay.vowels for p2 in ay.plain_stops}
ee_het = {e1 + e2 for e1 in ay.ejectives for e2 in ay.ejectives if e1 != e2}
# Counting
for i, corpus in enumerate(ay_corpora):
corpus_name = ay_corpus_names[i]
"""
"""
## Stops
unigram_counts = cou.count_many_substr(ay.sounds, corpus, ay)
unigram_counts['stops'] = sum(unigram_counts[key] for key in ay.stops)
unigram_counts['plain_stops'] = sum(unigram_counts[key] for key in ay.plain_stops)
unigram_counts['aspirates'] = sum(unigram_counts[key] for key in ay.aspirates)
unigram_counts['ejectives'] = sum(unigram_counts[key] for key in ay.ejectives)
unigram_counts['consonants'] = sum(unigram_counts[key] for key in ay.consonants)
unigram_counts['vowels'] = sum(unigram_counts[key] for key in ay.vowels)
unigram_counts['total'] = sum(unigram_counts.values())
uti.write_dict(unigram_counts, os.path.join(*(
os.pardir, 'Aymara', 'Outputs', 'Counts', 'Raw',
'aymara_counts_seg_all_unigram_{}.txt'.format(corpus_name))))
"""
"""
## Preceding environments for stops
precon_stop_counts = cou.count_many_substr(precon_stops, corpus, ay)
prevoc_stop_counts = cou.count_many_substr(prevoc_stops, corpus, ay)
stop_bigrams = {
'preconsonantal stops': sum(precon_stop_counts.values()),
'prevocalic stops': sum(prevoc_stop_counts.values()),
'total non-final stops': sum(precon_stop_counts.values()) + sum(prevoc_stop_counts.values())
}
stop_bigrams['preconsonantal aspirates'] \
= sum(precon_stop_counts[key] for key in precon_asp)
stop_bigrams['preconsonantal ejectives'] \
= sum(precon_stop_counts[key] for key in precon_ej)
stop_bigrams['preconsonantal plain stops'] \
= sum(precon_stop_counts[key] for key in precon_plain)
stop_bigrams['prevocalic aspirates'] \
= sum(prevoc_stop_counts[key] for key in prevoc_asp)
stop_bigrams['prevocalic ejectives'] \
= sum(prevoc_stop_counts[key] for key in prevoc_ej)
stop_bigrams['prevocalic plain stops'] \
= sum(prevoc_stop_counts[key] for key in prevoc_plain)
uti.write_dict(stop_bigrams, os.path.join(*(
os.pardir, 'Aymara', 'Outputs', 'Counts', 'Raw',
'aymara_counts_seg_all_env_{}.txt'.format(corpus_name))))
"""
"""
## Prevocalic stops initially or not
prevoc_stop_initial_counts = cou.count_many_substr(prevoc_stops, corpus, ay, initial=True)
prevoc_counts_wordpos = {
'initial prevocalic stops': sum(prevoc_stop_initial_counts.values()),
'medial prevocalic stops': sum(prevoc_stop_counts.values()) -
sum(prevoc_stop_initial_counts.values()),
'total prevocalic stops': sum(prevoc_stop_counts.values()),
'initial prevocalic aspirates': sum(prevoc_stop_initial_counts[key] for key in prevoc_asp),
'medial prevocialic aspirates': sum(prevoc_stop_counts[key] for key in prevoc_asp) -
sum(prevoc_stop_initial_counts[key] for key in prevoc_asp),
'total prevocalic aspirates': sum(prevoc_stop_counts[key] for key in prevoc_asp),
'initial prevocalic ejectives': sum(prevoc_stop_initial_counts[key] for key in prevoc_ej),
'medial prevocalic ejectives': sum(prevoc_stop_counts[key] for key in prevoc_ej) -
sum(prevoc_stop_initial_counts[key] for key in prevoc_ej),
'total prevocalic ejectives': sum(prevoc_stop_counts[key] for key in prevoc_ej),
'initial prevocalic plain stops': sum(prevoc_stop_initial_counts[key] for key in prevoc_plain),
'medial prevocalic plain stops': sum(prevoc_stop_counts[key] for key in prevoc_plain) -
sum(prevoc_stop_initial_counts[key] for key in prevoc_plain),
'total prevocalic plain stops': sum(prevoc_stop_counts[key] for key in prevoc_plain)
}
uti.write_dict(prevoc_counts_wordpos, os.path.join(*(
os.pardir, 'Aymara', 'Outputs', 'Counts', 'Raw',
'aymara_counts_seg_prevoc_wordpos_{}.txt'.format(corpus_name))))
"""
"""