julian.kunkel
/
thesis-anne
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

dict -> defaultdict

This commit is contained in:
Anne Lorenz 2018-10-18 11:16:19 +02:00
parent 36588ce72f
commit cd3a90101f
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
FilterKeywords.py
View File

@ -6,8 +6,7 @@ FilterKeywords searches for merger specific keywords
in an article and counts them. in an article and counts them.
''' '''
# toDo: dict ändern! from collections import defaultdict
import re import re
from nltk.stem.porter import PorterStemmer from nltk.stem.porter import PorterStemmer
@ -45,8 +44,8 @@ class FilterKeywords:
# remove duplicates # remove duplicates
keywords = set(keyword_list) keywords = set(keyword_list)
# counts keywords in article # counts keywords in article (default value: 0)
dict_keywords = {} dict_keywords = defaultdict(int)
# search for matchings in dictionary of input article # search for matchings in dictionary of input article
for key in dict_input.keys(): for key in dict_input.keys():
@ -54,10 +53,13 @@ class FilterKeywords:
for kword in keywords: for kword in keywords:
if re.match(kword, key): if re.match(kword, key):
# if match, increase value of matching key # if match, increase value of matching key
## DORIS: Hier könntest du ein defaultdict verwenden, https://www.accelebrate.com/blog/using-defaultdict-python/
if str(kword) in dict_keywords: if str(kword) in dict_keywords:
dict_keywords[str(kword)] += dict_input[key] dict_keywords[str(kword)] += dict_input[key]
else: else:
dict_keywords[str(kword)] = dict_input[key] dict_keywords[str(kword)] = dict_input[key]
return dict_keywords return dict_keywords
if __name__ == '__main__':
dict_test={'example':2, 'combined':5, 'sells':3}
print(FilterKeywords.search_keywords(dict_test))