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

removed matching model fields, automatic classifier reloading, added autmatic_classification field to matching model

Browse Source
This commit is contained in:
Jonas Winkler
2018-09-04 18:40:26 +02:00
parent 30134034e2
commit 70bd05450a
8 changed files with 126 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/documents/classifier.py
View File

@@ -1,3 +1,4 @@
import os
import pickle
from documents.models import Correspondent, DocumentType, Tag
@@ -16,6 +17,18 @@ def preprocess_content(content):
class DocumentClassifier(object):
classifier_version = None
data_vectorizer = None
tags_binarizer = None
correspondent_binarizer = None
type_binarizer = None
tags_classifier = None
correspondent_classifier = None
type_classifier = None
@staticmethod
def load_classifier():
clf = DocumentClassifier()
@@ -23,15 +36,18 @@ class DocumentClassifier(object):
return clf
def reload(self):
with open(settings.MODEL_FILE, "rb") as f:
self.data_vectorizer = pickle.load(f)
self.tags_binarizer = pickle.load(f)
self.correspondent_binarizer = pickle.load(f)
self.type_binarizer = pickle.load(f)
if self.classifier_version is None or os.path.getmtime(settings.MODEL_FILE) > self.classifier_version:
print("reloading classifier")
with open(settings.MODEL_FILE, "rb") as f:
self.data_vectorizer = pickle.load(f)
self.tags_binarizer = pickle.load(f)
self.correspondent_binarizer = pickle.load(f)
self.type_binarizer = pickle.load(f)
self.tags_classifier = pickle.load(f)
self.correspondent_classifier = pickle.load(f)
self.type_classifier = pickle.load(f)
self.tags_classifier = pickle.load(f)
self.correspondent_classifier = pickle.load(f)
self.type_classifier = pickle.load(f)
self.classifier_version = os.path.getmtime(settings.MODEL_FILE)
def save_classifier(self):
with open(settings.MODEL_FILE, "wb") as f: