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

update labeling

This commit is contained in:
Anne Lorenz 2019-01-15 10:37:07 +01:00
parent 035583584f
commit 6471a81196
3 changed files with 25576 additions and 773 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10001
data/interactive_labeling_round_30.csv Normal file
View File

File diff suppressed because one or more lines are too long

16343
src/2019-01-09-al-interactive-labeling.ipynb
View File

File diff suppressed because it is too large Load Diff

5
src/MNBInteractive.py
View File

@ -32,6 +32,7 @@ class MNBInteractive:
# split unlabeled data into text and label set # split unlabeled data into text and label set
# join title and text # join title and text
U = unlabeled_data['Title'] + '. ' + unlabeled_data['Text'] U = unlabeled_data['Title'] + '. ' + unlabeled_data['Text']
l = unlabeled_data['Label']
if sklearn_cv: if sklearn_cv:
cv = CountVectorizer() cv = CountVectorizer()
@ -87,13 +88,11 @@ class MNBInteractive:
# number of samples encountered for each class during fitting # number of samples encountered for each class during fitting
# this value is weighted by the sample weight when provided # this value is weighted by the sample weight when provided
# class_count = classifier.class_count_ class_count = classifier.class_count_
# classes in order used # classes in order used
classes = classifier.classes_ classes = classifier.classes_
class_count = classifier.class_count_
print('# MNB: ending multinomial naive bayes') print('# MNB: ending multinomial naive bayes')
# return classes and vector of class estimates # return classes and vector of class estimates