paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-11-03 03:16:10 -06:00
Code Issues Packages Projects Releases Wiki Activity

changed classifier

Browse Source
This commit is contained in:
Jonas Winkler
2018-09-11 00:33:07 +02:00
parent 04bf5fc094
commit d2534a73e5
3 changed files with 9 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/documents/classifier.py
View File

@@ -2,12 +2,13 @@ import logging
import os
import pickle
from sklearn.neural_network import MLPClassifier
from documents.models import Correspondent, DocumentType, Tag, Document
from paperless import settings
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.multiclass import OneVsRestClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.preprocessing import MultiLabelBinarizer, LabelBinarizer
@@ -87,7 +88,7 @@ class DocumentClassifier(object):
# Step 2: vectorize data
logging.getLogger(__name__).info("Vectorizing data...")
self.data_vectorizer = CountVectorizer(analyzer='char', ngram_range=(2, 6), 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()
@@ -102,7 +103,7 @@ class DocumentClassifier(object):
# Step 3: train the classifiers
if len(self.tags_binarizer.classes_) > 0:
logging.getLogger(__name__).info("Training tags classifier...")
self.tags_classifier = OneVsRestClassifier(MultinomialNB())
self.tags_classifier = MLPClassifier(verbose=True)
self.tags_classifier.fit(data_vectorized, labels_tags_vectorized)
else:
self.tags_classifier = None
@@ -110,7 +111,7 @@ class DocumentClassifier(object):
if len(self.correspondent_binarizer.classes_) > 0:
logging.getLogger(__name__).info("Training correspondent classifier...")
self.correspondent_classifier = OneVsRestClassifier(MultinomialNB())
self.correspondent_classifier = MLPClassifier(verbose=True)
self.correspondent_classifier.fit(data_vectorized, labels_correspondent_vectorized)
else:
self.correspondent_classifier = None
@@ -118,7 +119,7 @@ class DocumentClassifier(object):
if len(self.type_binarizer.classes_) > 0:
logging.getLogger(__name__).info("Training document type classifier...")
self.type_classifier = OneVsRestClassifier(MultinomialNB())
self.type_classifier = MLPClassifier(verbose=True)
self.type_classifier.fit(data_vectorized, labels_type_vectorized)
else:
self.type_classifier = None

6
src/documents/management/commands/document_create_dataset.py
View File

@@ -18,7 +18,7 @@ class Command(Renderable, BaseCommand):
with open("dataset_tags.txt", "w") as f:
for doc in Document.objects.exclude(tags__is_inbox_tag=True):
labels = []
for tag in doc.tags.all():
for tag in doc.tags.filter(automatic_classification=True):
labels.append(tag.name)
f.write(",".join(labels))
f.write(";")
@@ -27,14 +27,14 @@ class Command(Renderable, BaseCommand):
with open("dataset_types.txt", "w") as f:
for doc in Document.objects.exclude(tags__is_inbox_tag=True):
f.write(doc.document_type.name if doc.document_type is not None else "None")
f.write(doc.document_type.name if doc.document_type is not None and doc.document_type.automatic_classification else "-")
f.write(";")
f.write(preprocess_content(doc.content))
f.write("\n")
with open("dataset_correspondents.txt", "w") as f:
for doc in Document.objects.exclude(tags__is_inbox_tag=True):
f.write(doc.correspondent.name if doc.correspondent is not None else "None")
f.write(doc.correspondent.name if doc.correspondent is not None and doc.correspondent.automatic_classification else "-")
f.write(";")
f.write(preprocess_content(doc.content))
f.write("\n")