paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-07-30 18:27:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

Code style adjustments

Browse Source
This commit is contained in:
Jonas Winkler
2018-09-25 16:09:33 +02:00
parent 779ea6a015
commit 60618381f8
12 changed files with 94 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/documents/classifier.py Normal file → Executable file
View File

@@ -87,7 +87,7 @@ class DocumentClassifier(object):
# Step 2: vectorize data
logging.getLogger(__name__).info("Vectorizing data...")
self.data_vectorizer = CountVectorizer(analyzer='char', ngram_range=(3, 5), min_df=0.1)
self.data_vectorizer = CountVectorizer(analyzer="char", ngram_range=(3, 5), min_df=0.1)
data_vectorized = self.data_vectorizer.fit_transform(data)
self.tags_binarizer = MultiLabelBinarizer()