#A.I Chat Bot
This project builds an automated reply A.I chatbot based on data from Cornell Movie--Dialogs Corpus dataset Link to source of dataset:
https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html
DESCRIPTION of dataset:
This corpus contains a large metadata-rich collection of fictional conversations extracted from raw movie scripts:
-
220,579 conversational exchanges between 10,292 pairs of movie characters
-
involves 9,035 characters from 617 movies
-
in total 304,713 utterances
-
movie metadata included:
-
genres
-
release year
-
IMDB rating
-
number of IMDB votes
-
IMDB rating
-
character metadata included:
-
gender (for 3,774 characters)
-
position on movie credits (3,321 characters)
-
see README.txt (included) for details
This project requires some installations of anaconda, python 3.5 version and tensorflow 1.0.0 library before running
Follow steps in the following link to install ananconda for corresponding operating systems:
https://docs.anaconda.com/anaconda/install/
Due to some issues in tensorflow library in other versions of python, python 3.5 is used to this program
For Mac/ Linux/ Windows users in terminal enter:
conda create -n chatbot python=3.5 anaconda
then press y and enter
here chatbot is the name of the environment
source activate chatbot
activate chatbot
pip install tensorflow==1.0.0
then open anaconda navigator choose chatbot as applications on Channels and run Spyder (recommended IDE for this program)
- Cuong Phan -(https://github.com/cmphan)