diff --git a/date_selection.py b/date_selection.py index de65c9fc1b75f34f8b35478fc2db8b18287ec799..dd53f0f7b5290d9691989c9f44dfd1b179611562 100644 --- a/date_selection.py +++ b/date_selection.py @@ -1,7 +1,7 @@ from collections import Counter -def select_dates_by_mention_count(articles, start_date, end_date): +def rank_dates_by_mention_count(articles, start_date, end_date): mention_count = Counter({}) for article in articles: for sentence in article['sentences']: diff --git a/timeline_generation.py b/timeline_generation.py index 80bb3e75f4cc701598f6f9f9959a01c38e5502f5..52824452dccb03e06572aacc4fa5843666e0665c 100644 --- a/timeline_generation.py +++ b/timeline_generation.py @@ -23,7 +23,7 @@ def make_timeline(articles, gold_timeline, keywords): # articles = dataset.filter_articles_by_keywords(articles, keywords) # select dates - ranked_dates = date_selection.select_dates_by_mention_count(articles, start_date, end_date) + ranked_dates = date_selection.rank_dates_by_mention_count(articles, start_date, end_date) # train TFIDF vectorizer on all sentences (not just the ones for this date) all_sentences = [sentence['text'] for article in articles for sentence in article['sentences']]