paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

load sklearn modules only when training data has changed

Browse Source
This commit is contained in:
jonaswinkler 2021-02-15 11:25:25 +01:00
parent 5e669534f2
commit 7e88085377
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/documents/classifier.py
View File

@ -95,9 +95,6 @@ class DocumentClassifier(object):
pickle.dump(self.document_type_classifier, f) pickle.dump(self.document_type_classifier, f)
def train(self): def train(self):
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import MultiLabelBinarizer, LabelBinarizer
data = list() data = list()
labels_tags = list() labels_tags = list()
@ -162,6 +159,10 @@ class DocumentClassifier(object):
) )
) )
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import MultiLabelBinarizer, LabelBinarizer
# Step 2: vectorize data # Step 2: vectorize data
logger.debug("Vectorizing data...") logger.debug("Vectorizing data...")
self.data_vectorizer = CountVectorizer( self.data_vectorizer = CountVectorizer(