ocertat/1article
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

add (review) to stopwords

Browse Source
This commit is contained in:
Mark Eaton
2026-05-16 00:18:12 -04:00
parent 17246ae9ec
commit f0e2e61269
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
parse.py
+7 -5
View File
@@ -7,6 +7,7 @@ from collections import Counter
from pprint import pprint from pprint import pprint
stop_words = [ stop_words = [
"(review)",
"of", "of",
"and", "and",
"the", "the",
@@ -62,7 +63,7 @@ def extract_journal_titles(data):
for row in data: for row in data:
if "(edited volume)" not in row[3]: if "(edited volume)" not in row[3]:
journal_titles.append(row[3]) journal_titles.append(row[3])
count_journal_titles = Counter(journal_titles).most_common(20) count_journal_titles = Counter(journal_titles).most_common(30)
pprint(count_journal_titles) pprint(count_journal_titles)
print("Total journals: " + str(len(set(journal_titles)))) print("Total journals: " + str(len(set(journal_titles))))
@@ -85,7 +86,7 @@ def extract_title_keywords(data):
def print_title_keywords(data): def print_title_keywords(data):
title_keywords = extract_title_keywords(data) title_keywords = extract_title_keywords(data)
title_keywords = [word[0] for word in title_keywords] title_keywords = [word[0] for word in title_keywords]
count_title_words = Counter(title_keywords).most_common(20) count_title_words = Counter(title_keywords).most_common(30)
pprint(count_title_words) pprint(count_title_words)
@@ -105,8 +106,9 @@ def names(data):
for name in name_parts: for name in name_parts:
name = name.rstrip(",") name = name.rstrip(",")
if name not in stop_words: if name not in stop_words:
names.append(name) if "." not in name:
count_names = Counter(names).most_common(20) names.append(name)
count_names = Counter(names).most_common(30)
pprint(count_names) pprint(count_names)
@@ -115,5 +117,5 @@ if __name__ == "__main__":
data = data[1:] data = data[1:]
extract_journal_titles(data) extract_journal_titles(data)
print_title_keywords(data) print_title_keywords(data)
names(data) # names(data)
histogram(data) histogram(data)