Deep Learning Nanodegree

Deep Learning

Project: Deploying a Sentiment Analysis Model

Project for Udacity's Deep Learning Nanodegree program. In this project, I developed a deep learning model using Pytorch to analyze the sentiment of movie reviews with AWS, then proceeded to use AWS for deploying the model.

In order to complete this project, I used the GPU enabled workspaces within AWS.

Install

This project requires Python 3.x and the following Python libraries installed:

• os
• glob
• sklearn
• nltk
• re
• bs4
• pickle
• NumPy
• Counter
• Pandas
• sagemaker
• torch
• argparse
• json
• sys
• sagemaker_containers
• boto3

You will also need to have software installed to run and execute an iPython Notebook

I recommend installion Anaconda, a pre-packaged Python distribution that contains all of the necessary libraries and software for this project.

Code

Template code is provided in the SageMaker Project.ipynb file.

Run

In a terminal or command window, navigate to the top-level project directory Deploying-a-Sentiment-Analysis-Model/ (that contains this README) and run one of the following commands:

ipython notebook "SageMaker Project.ipynb"

or

jupyter notebook "SageMaker Project.ipynb"

This will open the iPython Notebook software in your browser.

Data

The movie review dataset used for this project are too large to upload to Github; thus, the dataset used for this project can be downloaded by following this link.

Certification