Skip to main content

Addon to Django apps that allows to retrain Spacy NER with active learning.

Project description

Spacy Active learning

.. image::

Django app that uses active learning (deliberately picking the examples to annotate) to retrain the spaCy_ NER module more effectively.


For spacyal to run you need a working Celery_ installation. Something along the lines of::

from __future__ import absolute_import, unicode_literals
import os
from celery import Celery

app = Celery('tasks')

# Using a string here means the worker doesn't have to serialize
# the configuration object to child processes.
# - namespace='CELERY' means all celery-related configuration keys
# should have a `CELERY_` prefix.
app.config_from_object('django.conf:settings', namespace='CELERY')

# Load task modules from all registered Django app configs.

def debug_task(self):
print('Request: {0!r}'.format(self.request))


* Install the package
* include spacyal.urls and spacyal.api_urls in your main url definition
* ensure that you have a base template called base.html
* run python migrate
* and you should be good to go

.. _Celery:
.. _spaCy:

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

acdh-spacyal-0.3.tar.gz (14.6 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page