def rank_sentences(self, dataset, document_column_name, **kwargs):
all_sentences = list(map(sent_tokenize, dataset[document_column_name]))
all_scores = [list(range(len(sentences)))[::-1] for sentences in all_sentences]
data = [
{"sentences": sentences, "scores": scores}
for sentences, scores in zip(all_sentences, all_scores)
]
return Baseline.append_column(dataset, data, self.name)
def rank_sentences(self, dataset, document_column_name, seed=42, **kwargs):
random.seed(seed)
all_sentences = list(map(sent_tokenize, dataset[document_column_name]))
scores = [[random.random() for sentence in sentences]
for sentences in all_sentences]
data = [{
"sentences": sentences,
"scores": scores
} for sentences, scores in zip(all_sentences, scores)]
return Baseline.append_column(dataset, data, self.name)
def rank_sentences(self, dataset, document_column_name, **kwargs):
all_sentences = []
all_scores = []
for document in tqdm(dataset[document_column_name]):
sentences, scores = self.run_single(document)
all_sentences.append(sentences)
all_scores.append(scores)
data = [{
"sentences": sentences,
"scores": scores
} for sentences, scores in zip(all_sentences, all_scores)]
return Baseline.append_column(dataset, data, self.name)