moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

testing gender and continent again

This commit is contained in:
Alejandro Moreo Fernandez 2024-04-12 12:03:38 +02:00
parent 8ad41b1d33
commit 8399552c8d
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Retrieval/commons.py
View File

@ -45,6 +45,8 @@ def load_json_sample(path, class_name, max_lines=-1):
obj = json.load(open(path, 'rt'))
keys = [f'{id}' for id in range(len(obj['text'].keys()))]
text = [obj['text'][id] for id in keys]
#print(list(obj.keys()))
#import sys; sys.exit(0)
classes = [obj[class_name][id] for id in keys]
if max_lines is not None and max_lines>0:
text = text[:max_lines]

4
Retrieval/fifth.py
View File

@ -112,11 +112,11 @@ def scape_latex(string):
Ks = [10, 50, 100, 250, 500, 1000, 2000]
# Ks = [500]
for CLASS_NAME in ['continent'] : #'years_category']: #['continent', 'first_letter_category']: #, 'gender', 'gender_category', 'occupations', 'source_countries', 'source_subcont_regions', 'years_category', 'relative_pageviews_category']:
for CLASS_NAME in ['gender_category'] : #'years_category']: #['continent', 'first_letter_category']: #, 'gender', 'gender_category', 'occupations', 'source_countries', 'source_subcont_regions', 'years_category', 'relative_pageviews_category']:
data_path = './' + CLASS_NAME
if CLASS_NAME in ['years_category', 'continent']:
if CLASS_NAME in ['years_category', 'continent', 'gender_category']:
train_path = join(data_path, 'train500PerGroup.json')
else:
train_path = join(data_path, 'train3000samples.json')