Python Chatterbot效率问题

Question

I have made a simple feedback loop program using Chatterbot. The below code takes one to two minutes to respond to itself, and a similar amount of time to load. My question is regarding efficiency - is taking one to two minutes for getting a response normal for chatterbot? If it isn't, how could I improve my efficiency?

Other details - if I don't have the silence performance warning paramater set to true in my chatterbot creation, the following error appears.

UnsuitableForProductionWarning: The JsonFileStorageAdapter is not recommended for production environments.
self.UnsuitableForProductionWarning

This is my code.

from chatterbot import ChatBot
from chatterbot.trainers import ChatterBotCorpusTrainer

chatterbot = ChatBot("Training Example",silence_performance_warning=True,storage_adapter='chatterbot.storage.JsonFileStorageAdapter')
chatterbot.set_trainer(ChatterBotCorpusTrainer)

chatterbot.train(
    "chatterbot.corpus.english.greetings",
    "chatterbot.corpus.english.conversations"
)

print("Ready")
print("1 : How are you?")
response = "How are you?"
first = False

while True:
    response = chatterbot.get_response(str(response))
    if first:
        print("1 : "+str(response))
        first = False
    else:
        print("2 : "+str(response))
        first = True

I understand that due to the nature of the bot responding to itself, it shall eventually only output one message repeatedly. This I am not worried about.

Update - the problem resides within visual studio 2015. I have discovered that running my code using the standard IDLE returns the output I expected instantaneously.

Answer 1

It's nuts to train a model for every request you process. Use a separate script to train and pickle your trained model, then load the pickled model in your interactive script (the one you show us, minus the training) and use it to handle responses.