def matrix_output(self):
# produce Jelena style output format with matrix
pass
def qlc_output_format(self):
# produce counterpart \t concept \t language QLC output format
print("COUNTERPART"+"\t"+"ORTHO_PARSE"+"\t"+"CONCEPT"+"\t"+"LANGUAGE")
for counterpart, concept, language in self._wordlist_iterator:
if counterpart == "?" or counterpart == "NONE":
print(counterpart+"\t"+counterpart+"\t"+concept+"\t"+language)
continue
grapheme_parsed_counterpart_tuple = self.o.parse_string_to_graphemes_string(counterpart)
# skip shit that doesn't parse
if grapheme_parsed_counterpart_tuple[0] == False:
continue
ortho_parse = grapheme_parsed_counterpart_tuple[1]
print(counterpart+"\t"+ortho_parse+"\t"+concept+"\t"+language)
if __name__=="__main__":
from qlc.tokenizer import Tokenizer
from qlc import ngram
t = Tokenizer()
t.lingpy_output()
# words = t.get_qlc_tokenized_words()
# ngram.unigram_model(words)
ortho_parse = grapheme_parsed_counterpart_tuple[1]
print(language+"\t"+concept+"\t"+counterpart+"\t"+grapheme_parsed_counterpart_tuple[1])
def matrix_output(self):
# produce Jelena style output format with matrix
pass
def qlc_output_format(self):
# produce counterpart \t concept \t language QLC output format
print("COUNTERPART"+"\t"+"ORTHO_PARSE"+"\t"+"CONCEPT"+"\t"+"LANGUAGE")
for counterpart, concept, language in self._wordlist_iterator:
if counterpart == "?" or counterpart == "NONE":
print(counterpart+"\t"+counterpart+"\t"+concept+"\t"+language)
continue
grapheme_parsed_counterpart_tuple = self.o.parse_string_to_graphemes_string(counterpart)
# skip shit that doesn't parse
if grapheme_parsed_counterpart_tuple[0] == False:
continue
ortho_parse = grapheme_parsed_counterpart_tuple[1]
print(counterpart+"\t"+ortho_parse+"\t"+concept+"\t"+language)
if __name__=="__main__":
from qlc.tokenizer import Tokenizer
from qlc import ngram
t = Tokenizer()
t.qlc_output_format()
# words = t.get_qlc_tokenized_words()
# ngram.unigram_model(words)
