Skip to content

AradanaD/ChatBotMLproject

Repository files navigation

ChatBotMLproject

Chatbot_main.py is the final completed version of the code

Developed using Python (chatbot code) and java (dataset)

You'll need to install ALOT of libraries - tensorflow, pickle, json, numpy .... so be careful about that

If you have issues installing it using the normal "pip install 'module' " command , then try using "python -m pip install --upgrade 'module' "

2 datasets have been uploaded - a) related to PESU academy b)related to Newolf Society, you can create your own dataset based on the type of service your chatbot is providing

Some of the links that we referred to:

 #https://www.oracle.com/in/chatbots/what-is-a-chatbot/
 #https://towardsdatascience.com/how-to-build-your-own-chatbot-using-deep-learning-bb41f970e281
 #https://towardsdatascience.com/how-to-create-a-chatbot-with-python-deep-learning-in-less-than-an-hour-56a063bdfc44
 #https://medium.com/analytics-vidhya/building-a-simple-chatbot-in-python-using-nltk-7c8c8215ac6e

You could even use java or html for the front end ,we've made it using python's gui framework

Try using lemmatisation instead of stemming , try different types of stemmers and training models to figure out which one works the best

If your chatbot's accuracy is around 0.9something it's good to go , if you get more than 1 or less than 0.8something then you'll need to try increasing the accuracy by adding more intents (this is the easiest way tho)

It may seem hard in the beginning but it's not once you understand what's actually going on :)

Also we could'nt upload the entire video of it working , so we uploaded just a small clip of it

About

Chatbot using Python

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages