ChatterBot.ipynb

chatterbot作为聊天机器人训练一多就性能不行.

挂载google硬盘

In [0]:
```

挂载google硬盘from google.colab import drivedrive.mount(‘/content/gdrive’, force_remount=True)root_dir = “/content/gdrive/My Drive/”base_dir = root_dir + ‘fastai-v3/’app_dir = base_dir+”ChatterBot”!mkdir /content/gdrive/My\ Drive/fastai-v3/ChatterBot

```

Mounted at /content/gdrive
In [0]:  ChatterBot
==========

ChatterBot is a machine learning, conversational dialog engine for creating chat bots https://chatterbot.readthedocs.io

＃ 安装

In [0]:
!pip install chatterbot

Requirement already satisfied: chatterbot in /usr/local/lib/python3.6/dist-packages (1.0.4)Requirement already satisfied: chatterbot-corpus<1.3,>=1.2 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (1.2.0)Requirement already satisfied: pymongo<4.0,>=3.3 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (3.7.2)Requirement already satisfied: python-dateutil<2.8,>=2.7 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (2.7.5)Requirement already satisfied: sqlalchemy<1.3,>=1.2 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (1.2.18)Requirement already satisfied: pint>=0.8.1 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (0.9)Requirement already satisfied: nltk<4.0,>=3.2 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (3.2.5)Requirement already satisfied: mathparse<0.2,>=0.1 in /usr/local/lib/python3.6/dist-packages (from chatterbot) (0.1.2)Requirement already satisfied: PyYAML<4.0,>=3.12 in /usr/local/lib/python3.6/dist-packages (from chatterbot-corpus<1.3,>=1.2->chatterbot) (3.13)Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.6/dist-packages (from python-dateutil<2.8,>=2.7->chatterbot) (1.11.0)
 　测试使用

---

In [0]:
from chatterbot import ChatBotfrom chatterbot.trainers import ChatterBotCorpusTrainerchatbot = ChatBot('Ron Obvious')# Create a new trainer for the chatbottrainer = ChatterBotCorpusTrainer(chatbot)# Train the chatbot based on the english corpus or chinesetrainer.train("chatterbot.corpus.english")# Get a response to an input statementchatbot.get\_response("Hello, how are you today?")

[nltk_data] Downloading package averaged_perceptron_tagger to[nltk_data] /root/nltk_data...[nltk_data] Package averaged_perceptron_tagger is already up-to-[nltk_data] date![nltk_data] Downloading package punkt to /root/nltk_data...[nltk_data] Package punkt is already up-to-date![nltk_data] Downloading package stopwords to /root/nltk_data...[nltk_data] Package stopwords is already up-to-date!Training ai.yml: [####################] 100%Training computers.yml: [####################] 100%Training conversations.yml: [####################] 100%Training emotion.yml: [####################] 100%Training food.yml: [####################] 100%Training gossip.yml: [####################] 100%Training greetings.yml: [####################] 100%Training health.yml: [####################] 100%Training history.yml: [####################] 100%Training humor.yml: [####################] 100%Training money.yml: [####################] 100%Training movies.yml: [####################] 100%Training politics.yml: [####################] 100%Training psychology.yml: [####################] 100%Training science.yml: [####################] 100%Training sports.yml: [####################] 100%Training trivia.yml: [####################] 100%
Out[0]:
<Statement text:I'm not bragging, I'm just that awesome.>
 进阶使用

---

Training data

In [0]:
from chatterbot import ChatBotfrom chatterbot.trainers import ChatterBotCorpusTrainerfrom chatterbot.conversation import Statementimport logging# bot = ChatBot('叨叨')# 初始化数据库bot = ChatBot( '叨叨',# storage\_adapter='chatterbot.storage.MongoDatabaseAdapter', logic\_adapters=[ 'chatterbot.logic.BestMatch', 'chatterbot.logic.MathematicalEvaluation', # 'chatterbot.logic.TimeLogicAdapter' ], input\_adapter='chatterbot.input.TerminalAdapter', # 命令行端 output\_adapter='chatterbot.output.TerminalAdapter', storage\_adapter="chatterbot.storage.SQLStorageAdapter" # database\_uri='mongodb://localhost:27017/chatterbot-database')# # # Create a new trainer for the chatbot# # 载入基本训练# # Create a new trainer for the chatbot# trainer = ChatterBotCorpusTrainer(bot)# # # Train the chatbot based on the english corpus# # # trainer.train("chatterbot.corpus.chinese")# trainer.train(# # "chatterbot.corpus.chinese",# # "./data/greetings\_corpus/custom.corpus.json",# "./Dialog\_Corpus/"# )# 对话测试# The following loop will execute each time the user enters input# while True:# try:# user\_input = input()# bot\_response = bot.get\_response(user\_input)# print(bot\_response)# # Press ctrl-c or ctrl-d on the keyboard to exit# except (KeyboardInterrupt, EOFError, SystemExit):# break# while True:# message = input('You: ')# if message.strip() != 'Bye':# reply = bot.get\_response(message)# print('Bot: ', reply)# if message.strip() == 'bye':# print('Bot : Bye')# break# 对话训练def get\_feedback(): text = input() if 'y' in text.lower(): return True elif 'n' in text.lower(): return False else: print('是否训练 "Yes(y)" or "No(n)"') return get\_feedback()print('输入要开始的东西......')# The following loop will execute each time the user enters inputwhile True: try: input\_statement = Statement(text=input('>')) response = bot.generate\_response( input\_statement ) print('>>>\n 机器人返回： "{}" 是否与："{}" 相关吗? \n 是否需要训练 "Yes(y)" or "No(n)"'.format( response.text, input\_statement.text )) if get\_feedback(): print('请输入正确的') correct\_response = Statement(text=input('>')) bot.learn\_response(correct\_response, input\_statement) print('已经修正机器人') print('————————————————————————') print('———开始新的训练————————————') print('————————————————————————') # Press ctrl-c or ctrl-d on the keyboard to exit except (KeyboardInterrupt, EOFError, SystemExit): break

[nltk_data] Downloading package averaged_perceptron_tagger to[nltk_data] /root/nltk_data...[nltk_data] Package averaged_perceptron_tagger is already up-to-[nltk_data] date![nltk_data] Downloading package punkt to /root/nltk_data...[nltk_data] Package punkt is already up-to-date![nltk_data] Downloading package stopwords to /root/nltk_data...[nltk_data] Package stopwords is already up-to-date!输入要开始的东西......

No value for search_text was available on the provided input

```

机器人返回： “What is AI?” 是否与：”hah” 相关吗? 是否需要训练 “Yes(y)” or “No(n)”是否训练 “Yes(y)” or “No(n)”
```

No value for search_text was available on the provided input

```

机器人返回： “What is AI?” 是否与：”狗子” 相关吗? 是否需要训练 “Yes(y)” or “No(n)”
```
 导出训练数据

---

In [0]:
```

Now we can export the data to a filetrainer.export_for_training( app_dir+’/my_export.json’)

```