Skip to main content

An open-source chat bot program written in Python.

Project description

.. figure:: http://i.imgur.com/b3SCmGT.png
:alt: Chatterbot: Machine learning in Python

Chatterbot: Machine learning in Python

ChatterBot
==========

ChatterBot is a machine-learning based conversational dialog engine
build in Python which makes it possible to generate responses based on
collections of known conversations. The language independent design of
ChatterBot allows it to be trained to speak any language.

*`Read in English <readme.md>`__* *`Leia em Português <readme.pt.md>`__*
*`Leer en español <readme-es.md>`__*

|Package Version| |Requirements Status| |Build Status| |Documentation
Status| |Coverage Status| |Code Climate| |Join the chat at
https://gitter.im/chatter\_bot/Lobby|

An example of typical input would be something like this:

| **user:** Good morning! How are you doing?
| **bot:** I am doing very well, thank you for asking.
| **user:** You're welcome.
| **bot:** Do you like hats?

How it works
------------

An untrained instance of ChatterBot starts off with no knowledge of how
to communicate. Each time a user enters a statement, the library saves
the text that they entered and the text that the statement was in
response to. As ChatterBot receives more input the number of responses
that it can reply and the accuracy of each response in relation to the
input statement increase. The program selects the closest matching
response by searching for the closest matching known statement that
matches the input, it then returns the most likely response to that
statement based on how frequently each response is issued by the people
the bot communicates with.

Installation
------------

This package can be installed from
`PyPi <https://pypi.python.org/pypi/ChatterBot>`__ by running:

::

pip install chatterbot

Basic Usage
-----------

::

from chatterbot import ChatBot
from chatterbot.trainers import ChatterBotCorpusTrainer

chatbot = ChatBot("Ron Obvious")
chatbot.set_trainer(ChatterBotCorpusTrainer)

# Train based on the english corpus
chatbot.train("chatterbot.corpus.english")

# Get a response to an input statement
chatbot.get_response("Hello, how are you today?")

Training data
=============

Chatterbot comes with a data utility module that can be used to train
chat bots. At the moment there is three languages, English, Spanish and
Portuguese training data in this module. Contributions of additional
training data or training data in other languages would be greatly
appreciated. Take a look at the data files in the
`chatterbot/corpus <https://github.com/gunthercox/ChatterBot/tree/master/chatterbot/corpus>`__
directory if you are interested in contributing.

::

# Train based on the english corpus
chatbot.train("chatterbot.corpus.english")

# Train based on english greetings corpus
chatbot.train("chatterbot.corpus.english.greetings")

# Train based on the english conversations corpus
chatbot.train("chatterbot.corpus.english.conversations")

**Corpus contributions are welcome! Please make a pull request.**

`Documentation <http://chatterbot.readthedocs.io/>`__
=====================================================

View the `documentation <http://chatterbot.readthedocs.io/>`__ for
ChatterBot on Read the Docs.

Examples
========

For examples, see the
`examples <https://github.com/gunthercox/ChatterBot/tree/master/examples>`__
directory in this project's repository.

There is also an example `Django project using
ChatterBot <https://github.com/gunthercox/django_chatterbot>`__, as well
as an example `Flask project using
ChatterBot <https://github.com/chamkank/flask-chatterbot>`__.

Testing
=======

ChatterBot's built in tests can be run using nose.

::

nosetests

See the `nose documentation <https://nose.readthedocs.org/en/latest/>`__
for more information.

History
=======

See release notes for changes
https://github.com/gunthercox/ChatterBot/releases

.. |Package Version| image:: https://img.shields.io/pypi/v/chatterbot.svg
:target: https://pypi.python.org/pypi/chatterbot/
.. |Requirements Status| image:: https://requires.io/github/gunthercox/ChatterBot/requirements.svg?branch=master
:target: https://requires.io/github/gunthercox/ChatterBot/requirements/?branch=master
.. |Build Status| image:: https://travis-ci.org/gunthercox/ChatterBot.svg?branch=master
:target: https://travis-ci.org/gunthercox/ChatterBot
.. |Documentation Status| image:: https://readthedocs.org/projects/chatterbot/badge/?version=latest
:target: http://chatterbot.readthedocs.io/en/latest/?badge=latest
.. |Coverage Status| image:: https://img.shields.io/coveralls/gunthercox/ChatterBot.svg
:target: https://coveralls.io/r/gunthercox/ChatterBot
.. |Code Climate| image:: https://codeclimate.com/github/gunthercox/ChatterBot/badges/gpa.svg
:target: https://codeclimate.com/github/gunthercox/ChatterBot
.. |Join the chat at https://gitter.im/chatter\_bot/Lobby| image:: https://badges.gitter.im/chatter_bot/Lobby.svg
:target: https://gitter.im/chatter_bot/Lobby?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge

Project details


Release history Release notifications | RSS feed

Download files

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

Source Distribution

ChatterBot-0.4.7.tar.gz (56.4 kB view details)

Uploaded Source

Built Distribution

ChatterBot-0.4.7-py2.py3-none-any.whl (119.6 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file ChatterBot-0.4.7.tar.gz.

File metadata

  • Download URL: ChatterBot-0.4.7.tar.gz
  • Upload date:
  • Size: 56.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No

File hashes

Hashes for ChatterBot-0.4.7.tar.gz
Algorithm Hash digest
SHA256 ac64a62f297f9cdb14220d342668da30e3b93cf826caf25c72dc9df7164330cf
MD5 592ed270a8efb51f95ccaa966b1f61ae
BLAKE2b-256 a778c542c52977a60b7a367ad81a78db6545f76b609190d9be993da64294a8aa

See more details on using hashes here.

File details

Details for the file ChatterBot-0.4.7-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for ChatterBot-0.4.7-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 a085dbc208f06e33f354f2517ec5c3df40e8a2d34f628f87379bf2c4e7940749
MD5 33c9a00da1fa6221a4385d0e60fd0e08
BLAKE2b-256 bd3d53ea0ce2afec7ff5c77a0257cd49f56b8f45a849878eedcfdfa1bb466a58

See more details on using hashes here.

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