【自然语言处理篇】–Chatterbot聊天机器人

一、前述

ChatterBot是一个基于机器学习的聊天机器人引擎,构建在python上,主要特点是可以自可以从已有的对话中进行学(jiyi)习(pipei)。

二、具体

1、安装

是的,安装超级简单,用pip就可以啦

pip install chatterbot

2、流程

大家已经知道chatterbot的聊天逻辑和输入输出以及存储,是由各种adapter来限定的,我们先看看流程图,一会软再一起看点例子,看看怎么用。

 

 

3、每个部分都设计了不同的“适配器”(Adapter)。

机器人应答逻辑 => Logic Adapters
Closest Match Adapter  字符串模糊匹配(编辑距离)

Closest Meaning Adapter  借助nltk的WordNet,近义词评估
Time Logic Adapter 处理涉及时间的提问
Mathematical Evaluation Adapter 涉及数学运算

存储器后端 => Storage Adapters
 Read Only Mode 只读模式,当有输入数据到chatterbot的时候,数
据库并不会发生改变
 Json Database Adapter 用以存储对话数据的接口,对话数据以Json格式
进行存储。
Mongo Database Adapter  以MongoDB database方式来存储对话数据

输入形式 => Input Adapters

Variable input type adapter 允许chatter bot接收不同类型的输入的,如strings,dictionaries和Statements
Terminal adapter 使得ChatterBot可以通过终端进行对话
 HipChat Adapter 使得ChatterBot 可以从HipChat聊天室获取输入语句,通过HipChat 和 ChatterBot 进行对话
Speech recognition 语音识别输入,详见chatterbot-voice

输出形式 => Output Adapters
Output format adapter支持text,json和object格式的输出
Terminal adapter
HipChat Adapter
Mailgun adapter允许chat bot基于Mailgun API进行邮件的发送
Speech synthesisTTS(Text to speech)部分,详见chatterbot-voice

4、代码

基础版本

# -*- coding: utf-8 -*-
from chatterbot import ChatBot # 构建ChatBot并指定Adapter bot = ChatBot( 'Default Response Example Bot', storage_adapter='chatterbot.storage.JsonFileStorageAdapter',#存储的Adapter logic_adapters=[ { 'import_path': 'chatterbot.logic.BestMatch'#回话逻辑 }, { 'import_path': 'chatterbot.logic.LowConfidenceAdapter',#回话逻辑 'threshold': 0.65,#低于置信度,则默认回答 'default_response': 'I am sorry, but I do not understand.' } ], trainer='chatterbot.trainers.ListTrainer'#给定的语料是个列表 ) # 手动给定一点语料用于训练 bot.train([ 'How can I help you?', 'I want to create a chat bot', 'Have you read the documentation?', 'No, I have not', 'This should help get you started: http://chatterbot.rtfd.org/en/latest/quickstart.html' ]) # 给定问题并取回结果 question = 'How do I make an omelette?' print(question) response = bot.get_response(question) print(response) print("\n") question = 'how to make a chat bot?' print(question) response = bot.get_response(question) print(response)

 

结果:

How do I make an omelette? I am sorry, but I do not understand. how to make a chat bot? Have you read the documentation?

 

处理时间和数学计算的Adapter

# -*- coding: utf-8 -*-
from chatterbot import ChatBot bot = ChatBot( "Math & Time Bot", logic_adapters=[ "chatterbot.logic.MathematicalEvaluation", "chatterbot.logic.TimeLogicAdapter" ], input_adapter="chatterbot.input.VariableInputTypeAdapter", output_adapter="chatterbot.output.OutputAdapter" ) # 进行数学计算
question = "What is 4 + 9?"
print(question) response = bot.get_response(question) print(response) print("\n") # 回答和时间相关的问题
question = "What time is it?"
print(question) response = bot.get_response(question) print(response)

 

 结果:

What is 4 + 9? ( 4 + 9 ) = 13 What time is it? The current time is 05:08 PM

 导出语料到json文件

# -*- coding: utf-8 -*-
from chatterbot import ChatBot ''' 如果一个已经训练好的chatbot,你想取出它的语料,用于别的chatbot构建,可以这么做 ''' chatbot = ChatBot( 'Export Example Bot', trainer='chatterbot.trainers.ChatterBotCorpusTrainer' ) # 训练一下咯
chatbot.train('chatterbot.corpus.english') # 把语料导出到json文件中
chatbot.trainer.export_for_training('./my_export.json')

反馈式学习聊天机器人

# -*- coding: utf-8 -*-
from chatterbot import ChatBot import logging """ 反馈式的聊天机器人,会根据你的反馈进行学习 """

# 把下面这行前的注释去掉,可以把一些信息写入日志中 # logging.basicConfig(level=logging.INFO)

# 创建一个聊天机器人
bot = ChatBot( 'Feedback Learning Bot', storage_adapter='chatterbot.storage.JsonFileStorageAdapter', logic_adapters=[ 'chatterbot.logic.BestMatch' ], input_adapter='chatterbot.input.TerminalAdapter',#命令行端 output_adapter='chatterbot.output.TerminalAdapter' ) DEFAULT_SESSION_ID = bot.default_session.id def get_feedback(): from chatterbot.utils import input_function text = input_function() if 'Yes' in text: return True elif 'No' in text: return False else: print('Please type either "Yes" or "No"') return get_feedback() print('Type something to begin...') # 每次用户有输入内容,这个循环就会开始执行
while True: try: input_statement = bot.input.process_input_statement() statement, response = bot.generate_response(input_statement, DEFAULT_SESSION_ID) print('\n Is "{}" this a coherent response to "{}"? \n'.format(response, input_statement)) if get_feedback(): bot.learn_response(response,input_statement) bot.output.process_response(response) # 更新chatbot的历史聊天数据
 bot.conversation_sessions.update( bot.default_session.id_string, (statement, response, ) ) # 直到按ctrl-c 或者 ctrl-d 才会退出
    except (KeyboardInterrupt, EOFError, SystemExit): break

 使用Ubuntu数据集构建聊天机器人

from chatterbot import ChatBot import logging ''' 这是一个使用Ubuntu语料构建聊天机器人的例子 '''

# 允许打日志
logging.basicConfig(level=logging.INFO) chatbot = ChatBot( 'Example Bot', trainer='chatterbot.trainers.UbuntuCorpusTrainer' ) # 使用Ubuntu数据集开始训练
chatbot.train() # 我们来看看训练后的机器人的应答
response = chatbot.get_response('How are you doing today?') print(response)

借助微软的聊天机器人

 

# -*- coding: utf-8 -*-
from chatterbot import ChatBot from settings import Microsoft ''' 关于获取微软的user access token请参考以下的文档 https://docs.botframework.com/en-us/restapi/directline/ ''' chatbot = ChatBot( 'MicrosoftBot', directline_host = Microsoft['directline_host'], direct_line_token_or_secret = Microsoft['direct_line_token_or_secret'], conversation_id = Microsoft['conversation_id'], input_adapter='chatterbot.input.Microsoft', output_adapter='chatterbot.output.Microsoft', trainer='chatterbot.trainers.ChatterBotCorpusTrainer' ) chatbot.train('chatterbot.corpus.english') # 是的,会一直聊下去
while True: try: response = chatbot.get_response(None) # 直到按ctrl-c 或者 ctrl-d 才会退出
    except (KeyboardInterrupt, EOFError, SystemExit): break

HipChat聊天室Adapter

# -*- coding: utf-8 -*-
from chatterbot import ChatBot from settings import HIPCHAT ''' 炫酷一点,你可以接到一个HipChat聊天室,你需要一个user token,下面文档会告诉你怎么做 https://developer.atlassian.com/hipchat/guide/hipchat-rest-api/api-access-tokens ''' chatbot = ChatBot( 'HipChatBot', hipchat_host=HIPCHAT['HOST'], hipchat_room=HIPCHAT['ROOM'], hipchat_access_token=HIPCHAT['ACCESS_TOKEN'], input_adapter='chatterbot.input.HipChat', output_adapter='chatterbot.output.HipChat', trainer='chatterbot.trainers.ChatterBotCorpusTrainer' ) chatbot.train('chatterbot.corpus.english') # 没错,while True,会一直聊下去!
while True: try: response = chatbot.get_response(None) # 直到按ctrl-c 或者 ctrl-d 才会退出
    except (KeyboardInterrupt, EOFError, SystemExit): break

邮件回复的聊天系统

# -*- coding: utf-8 -*-
from chatterbot import ChatBot from settings import MAILGUN ''' 这个功能需要你新建一个文件settings.py,并在里面写入如下的配置: MAILGUN = { "CONSUMER_KEY": "my-mailgun-api-key", "API_ENDPOINT": "https://api.mailgun.net/v3/my-domain.com/messages" } '''

# 下面这个部分可以改成你自己的邮箱
FROM_EMAIL = "mailgun@salvius.org" RECIPIENTS = ["gunthercx@gmail.com"] bot = ChatBot( "Mailgun Example Bot", mailgun_from_address=FROM_EMAIL, mailgun_api_key=MAILGUN["CONSUMER_KEY"], mailgun_api_endpoint=MAILGUN["API_ENDPOINT"], mailgun_recipients=RECIPIENTS, input_adapter="chatterbot.input.Mailgun", output_adapter="chatterbot.output.Mailgun", storage_adapter="chatterbot.storage.JsonFileStorageAdapter", database="../database.db" ) # 简单的邮件回复
response = bot.get_response("How are you?") print("Check your inbox at ", RECIPIENTS)

一个中文的例子

注意chatterbot,中文聊天机器人的场景下一定要用python3.X,用python2.7会有编码问题。

#!/usr/bin/python # -*- coding: utf-8 -*-

#手动设置一些语料
from chatterbot import ChatBot from chatterbot.trainers import ListTrainer Chinese_bot = ChatBot("Training demo") Chinese_bot.set_trainer(ListTrainer) Chinese_bot.train([ '你好', '你好', '有什么能帮你的?', '想买数据科学的课程', '具体是数据科学哪块呢?'
    '机器学习', ]) # 测试一下
question = '你好'
print(question) response = Chinese_bot.get_response(question) print(response) print("\n") question = '请问哪里能买数据科学的课程'
print(question) response = Chinese_bot.get_response(question) print(response)

结果:

你好
你好


请问哪里能买数据科学的课程
具体是数据科学哪块呢?

利用已经提供好的小中文语料库

#!/usr/bin/python # -*- coding: utf-8 -*-
from chatterbot import ChatBot from chatterbot.trainers import ChatterBotCorpusTrainer chatbot = ChatBot("ChineseChatBot") chatbot.set_trainer(ChatterBotCorpusTrainer) # 使用中文语料库训练它
chatbot.train("chatterbot.corpus.chinese") # 开始对话
while True: print(chatbot.get_response(input(">")))

 

Categories AI