class Bot(discord.Client): async def on_ready(self): self.chatbot = ChatBot(name='Stella 2.0', read_only=False, logic_adapters=['chatterbot.logic.BestMatch']) self.trainer = ChatterBotCorpusTrainer(self.chatbot) self.trainer.train('./corpus.json') async def on_message(self, message): # don't respond to ourselves if message.author == self.user: return inpt = str(message.content.encode('utf-8')) outpt = self.chatbot.get_response(re.sub('<@[-+]?[1-9]\d*>', '', inpt)) print('> ' + inpt) print(outpt) # 25% chance of replying if random.randint(0, 100) < 10 or f'<@{self.user.id}>' in inpt: inpt.replace(f'<@{self.user.id}>', '') await asyncio.sleep(random.randint(3, 5)) async with message.channel.typing(): await asyncio.sleep(len(str(outpt)) * 0.10) await message.channel.send(f'<@{message.author.id}> ' + str(outpt)) self.trainer.export_for_training('./corpus.json')
def train(self): """ Import seed data :return: """ pub.sendMessage(Event.info, message = "Training, may take a while...") trainer = ChatterBotCorpusTrainer(self.bot) trainer.train( "chatterbot.corpus.english" ) pub.sendMessage(Event.info, message = "exporting training data") makedirs("./output") trainer.export_for_training('./output/training_export.json') pub.sendMessage(Event.info, message = "Training complete.")
from chatterbot import ChatBot from chatterbot.trainers import ChatterBotCorpusTrainer ''' This is an example showing how to create an export file from an existing chat bot that can then be used to train other bots. ''' chatbot = ChatBot('Export Example Bot') # First, lets train our bot with some data trainer = ChatterBotCorpusTrainer(chatbot) trainer.train('chatterbot.corpus.english') # Now we can export the data to a file trainer.export_for_training('./my_export.json')
from create_chatbot_instance import new_ches_cak from chatterbot.trainers import ChatterBotCorpusTrainer from chatterbot.trainers import ListTrainer # Create a new chat bot named ches cak chatbot = new_ches_cak() export = False trainer = ChatterBotCorpusTrainer(chatbot) print("Training custom datasets") trainer.train("datasets/", ) print("trained from custom datasets") print("finished training") if (export): trainer.export_for_training('./exported_train_data.json')
{ 'import_path': 'chatterbot.logic.WikipediaResponseAdapter' } ], preprocessors=[ 'chatterbot.preprocessors.clean_whitespace' ], filters=[ 'chatterbot.filters.RepetitiveResponseFilter' ], ) trainer = ChatterBotCorpusTrainer(bot) # Train the bot using training data in the file and export all training to a json file trainer.train("./Gabungan") trainer.export_for_training('./qbot_training.json') # Training the bot using responses def train(content): trainer = ListTrainer(bot) trainer.train(content) thanks = 'Thank you for training me' return thanks def get_response(content): return bot.get_response(content) async def check_for_trigger_match(query, trigger_list): for trigger in trigger_list: if query.startswith(trigger):
from chatterbot.trainers import ChatterBotCorpusTrainer, ListTrainer import playsound import speech_recognition as sr from gtts import gTTS import random app = Flask(__name__) credi_bot = ChatBot("CrediBot", storage_adapter="chatterbot.storage.SQLStorageAdapter", database_uri='sqlite:///database.sqlite3') trainer = ChatterBotCorpusTrainer(credi_bot) trainer.train("./data/creditos.yml") trainer.export_for_training('./traning.json') @app.route("/") def home(): return render_template("index.html") @app.route("/get") def get_bot_response(): userText = request.args.get('msg') return str(credi_bot.get_response(userText)) # return speak(str(daliaBot.get_response(userText))) def speak(text):
#!/usr/bin/env python from chatterbot import ChatBot from chatterbot.trainers import ChatterBotCorpusTrainer chatbot = ChatBot('Terminal', storage_adapter='chatterbot.storage.SQLStorageAdapter', trainer='chatterbot.trainers.ListTrainer', database_uri='sqlite:///database.db') trainer = ChatterBotCorpusTrainer(chatbot) trainer.export_for_training('./export.yml')
from chatterbot import ChatBot from chatterbot.trainers import ChatterBotCorpusTrainer chatbot = ChatBot( "@ti-asa", database_uri='sqlite://db/db.sqlite3', logic_adapters=["chatterbot.logic.BestMatch"], ) trainer = ChatterBotCorpusTrainer(chatbot) trainer.train('chatterbot.corpus.french.greetings') trainer.export_for_training('./salfr.json')
database_uri='sqlite:///database.sqlite3', logic_adapters=[ 'chatterbot.logic.MathematicalEvaluation', # 'chatterbot.logic.TimeLogicAdapter', 'chatterbot.logic.BestMatch' ], # ) ## First, lets train our bot with some data trainer = ChatterBotCorpusTrainer(chatbot) # trainer.train('chatterbot.corpus.english') # ## Now we can export the data to a file trainer.export_for_training('./database.sqlite3.db') trainer1=chatterbot.trainers.UbuntuCorpusTrainer(chatbot) trainer1.train() def get_feedback(): text = input() if 'yes' in text.lower(): return True elif 'no' in text.lower(): return False else: print('Please type either "Yes" or "No"') return get_feedback()