def get_childes_files(
root_location, file_name
): # fetches the childes file in xml and parses it into utterances with speaker in [0] position
global ordered_utterance_list
corpus_root = nltk.data.find(root_location)
file_setup = CHILDESCorpusReaderX(corpus_root, file_name)
ordered_utterance_list = file_setup.sents()
return (ordered_utterance_list)
def get_childes_stemmed(root_location, file_name):
global ordered_utterance_list
stemmer = SnowballStemmer("english")
corpus_root = nltk.data.find(root_location, paths=['.'])
file_setup = CHILDESCorpusReaderX(corpus_root, file_name)
ordered_utterance_list = file_setup.sents()
for utterance in ordered_utterance_list:
for i in range(1, len(utterance) - 1):
utterance[i] = stemmer.stem(utterance[i])
return (ordered_utterance_list)
def get_childes_files(
root_location, file_name
): # fetches the childes file in xml and parses it into utterances with speaker in [0] position
global ordered_utterance_list
corpus_root = nltk.data.find(root_location, paths=['.'])
file_setup = CHILDESCorpusReaderX(corpus_root, file_name)
if extractRoles:
global writeRoleHeader
corpus_participants = file_setup.participants()
for this_corpus_participants in corpus_participants[:2]:
for key in sorted(this_corpus_participants.keys()):
dct = this_corpus_participants[key]
if writeRoleHeader:
wrf.write('docId,')
wrf.write(','.join([k for k in sorted(dct.keys())]) + '\n')
writeRoleHeader = False
wrf.write(file_name + ',')
wrf.write(','.join([dct[k]
for k in sorted(dct.keys())]) + '\n')
#return #comment this out eventually
ordered_utterance_list = file_setup.sents()
return (ordered_utterance_list)
def get_childes_files(root_location, file_name): # fetches the childes file in xml and parses it into utterances with speaker in [0] position global info_list corpus_root = nltk.data.find(root_location) file_setup = CHILDESCorpusReaderX(corpus_root, file_name) get_child_info(file_setup) return(info_list)