Deep Learning Nanodegree Foundation Project From Udacity

RNN for TV Script Generation

In this project, you can learn to generate your own Seinfeld TV scripts using RNNs. Part of the Seinfeld dataset of scripts from 9 seasons is used for this project. The Neural Network generates a new ,"fake" TV script, based on patterns it recognizes in this training data.

Libraries utilized

• NumPy - a fundamental package for scientific computing in python
• Pandas - an ease-to-use python library for manipulating data structures and performing data analysis
• Jupyter Notebook - a tool that allows the creation of documents with live code
• Matplotlib - a plotting library for the Python programming language and its numerical mathematics extension NumPy.
• PyTorch - an open source machine learning library

Download Datasets

Download the Seinfeld dataset. Place the file in this project's home directory, at the location /data.

Instruction

1. Install Anaconda.
2. Download the project
3. cd into the project folder
4. Run the code below to create and activate new environment

conda create --name tv_script_proj_env

• Mac/Linux:

source activate tv_script_proj_env 

• Windows:

activate tv_script_proj_env

Install required libraries. For example,

conda install numpy pandas matplotlib

jupyter notebook