virtualenv env/ --python=/usr/bin/python3
source env/bin/activate
pip install -r requirements.txt
This is the code related this blog page.
In order to create the data you must first train the doc2vec model
$ python train_word2vec_model.py
$ python create_tsne_vectors.py
$ python clustering.py
Then you can generate the dialogues using
$ python3 generate_dialogues.py
This code is merely a toy dialogue generator. The dialogue generator uses lines from the Cornell movie corpus and arranges them in different order. These are lines taken from real movies. I did not modify these lines, nor looked for offensive content. I completely disassociate myself from any offensive lines that might be randomly chosen and printed out.