Skip to content
An out-of-core movie review sentiment classifier based on the IMDB ratings dataset from Stanford.
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
DATA
doc_streamer
pkl_objects
text_cleaner_2000
.gitignore
README.md
sgd_movie_classifier.py

README.md

Movie-Sentiment-Classifier

A movie review sentiment classifier based on the IMDB ratings dataset from Stanford.

See a demo of the model in an app here: http://www.jlbdatasci.com/jobs/review/

Stochastic Gradient Descent is a great option for building data science web apps, where new data is constantly coming in (IOT is a use-case too) and for processing large amounts of data on a single machine.

Requirements

Assuming you have sklearn installed:

  1. Install Pyprind (conda/pip install pyprind)

Install

  1. After cloning/uzipping file, unzip DATA\ratings_shuffled.zip into DATA\

Use

From Command line:

  1. Navigate to project folder that contains sgd_movie_classifier
  2. Run command: python sgd_movie_classifier.py

Otherwise, load in your favorite IDE.

Once the model is built, you can use the model in your own app. See link above to see this model in action.

Data from:

Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. (2011). Learning Word Vectors for Sentiment Analysis. The 49th Annual Meeting of the Association for Computational Linguistics (ACL 2011).

You can’t perform that action at this time.