From df1cc4c84c37e5ff69f0d179fb2affb304eae515 Mon Sep 17 00:00:00 2001
From: vvye <ekaiser.hellwege@gmail.com>
Date: Sun, 12 Sep 2021 14:29:48 +0200
Subject: [PATCH] Remove keyword function
---
sentence_selection.py | 3 ---
summarization.py | 2 +-
util.py | 10 ----------
3 files changed, 1 insertion(+), 14 deletions(-)
diff --git a/sentence_selection.py b/sentence_selection.py
index 0931fae..eff8e44 100644
--- a/sentence_selection.py
+++ b/sentence_selection.py
@@ -1,7 +1,6 @@
from datetime import datetime, timedelta
from sklearn.metrics.pairwise import cosine_similarity
import numpy as np
-from scipy import sparse
import util
@@ -48,8 +47,6 @@ def candidate_sentences(articles, date, vectorizer):
def sentences_published_on_date(articles, date, tolerance_days, num_first_sentences):
- # implementation details are the same as ghalandari et al:
- # a sentence is not included in the final list if it also mentions any date at all
sentences = []
for article in articles:
pub_date = datetime.strptime(article['pub_date'], '%Y-%m-%d')
diff --git a/summarization.py b/summarization.py
index 8642ae3..141cf74 100644
--- a/summarization.py
+++ b/summarization.py
@@ -41,7 +41,7 @@ def summarize(sentences, vectorizer, keywords, num_sentences):
for i in sorted_indices:
remaining_indices.remove(i)
sentence = sentences[i]
- if not util.contains_any(sentence['text'], keywords):
+ if not any([kw.lower() in sentence['text'].lower() for kw in keywords]):
continue
if redundant(i, selected_indices, X):
continue
diff --git a/util.py b/util.py
index 4630ae7..3ba515b 100644
--- a/util.py
+++ b/util.py
@@ -1,5 +1,4 @@
import os
-import re
def subdirs(path):
@@ -10,15 +9,6 @@ def files(path, extension=None):
return [f for f in os.listdir(path) if os.path.isfile(path / f) and (extension is None or f.endswith(extension))]
-def contains_any(string, keywords):
- for keyword in keywords:
- # following ghalandari, don't account for word boundaries
- # if re.search(fr'\b{keyword.lower()}\b', string.lower()):
- if keyword.lower() in string.lower():
- return True
- return False
-
-
def avg(lst):
return sum(lst) / len(lst)
--
GitLab