def trainRegexp(self, backoff):
self.split_into_folds()
for k in range(1, (self.folds + 1)):
train_sents = sum(self.foldlist[: (self.folds - 1)], [])
if self.option_tone == "tonal" and self.option_tag == "Affixes":
regex = RegexpTonalSA(backoff)
if self.option_tone == "tonal" and self.option_tag == "POS":
regex = RegexpTonal(backoff)
if self.option_tone == "nontonal" and self.option_tag == "Affixes":
regex = RegexpSA(backoff)
if self.option_tone == "nontonal" and self.option_tag == "POS":
regex = Regexp(backoff)
to_tag = [untag(i) for i in self.foldlist[self.folds - 1]]
self.regex_tagged += regex.tag_sents(to_tag)
self.org_tagged += self.foldlist[self.folds - 1]
self.foldlist = [self.foldlist[self.folds - 1]] + self.foldlist[: (self.folds - 1)]
self.regex = regex
self.regex_avg_acc = accuracy(sum(self.org_tagged, []), sum(self.regex_tagged, []))
print("Accuracy of concatenated regexp-tagged sentences: ", self.regex_avg_acc)
(self.regex_tagprecision, self.regex_tagrecall) = self.tagprecision_recall(
regex, self.regex_tagged, self.org_tagged
)
self.org_tagged = []
self.foldlist = []
for i in range(1, self.folds + 1):
self.foldlist.append(self.create_fold(i))
