forked from nlp-psych/gender_data_assignment
-
Notifications
You must be signed in to change notification settings - Fork 0
/
bawe_gender_classifier.py
50 lines (42 loc) · 1.39 KB
/
bawe_gender_classifier.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
# detect author gender from essay corpus
from sklearn.model_selection import cross_val_score
from sklearn.naive_bayes import GaussianNB
import feature_extractor as fe
import numpy
import re
import sys
datadir = sys.argv[1]
genderlabfile = datadir + "/BAWE_balanced_subset.csv"
conffile = sys.argv[2]
def load_balanced_gender_labels():
'''
Read the gender labels file and return dictionary mapping student id
to gender
'''
meta_lines = [line.rstrip().split(',') for line in open(genderlabfile)]
gender_dict = {row[0]:row[1] for row in meta_lines[1:]}
return gender_dict
def load_essays(gender_dict):
essays = []
genderlabels = []
students = []
for student, gender in gender_dict.items():
with open('%s/%s.txt' % (datadir, student)) as f:
text = f.read()
text = re.sub('<[^<]+?>', '', text) # remove vestigial xml
essays.append(text)
genderlabels.append(gender)
students.append(student)
return essays, genderlabels, students
def load_conf_file():
conf = set(line.strip() for line in open(conffile))
return conf
def predict_gender(X, Y):
scores = cross_val_score(GaussianNB(), X, Y, scoring='accuracy', cv=10)
return scores.mean()
if __name__ == "__main__":
gender_dict = load_balanced_gender_labels()
essays, genderlabels, students = load_essays(gender_dict)
conf = load_conf_file()
features = fe.extract_features(essays, conf)
print (predict_gender(features, genderlabels))