/nlp-classifiers

Primary LanguageJupyter Notebook

A Comprehensive Survey of Machine Learning Methods for Text Classification

ML Models: IMDB Dataset

Carlos Santiago Bañón, Moazam Soomro

CAP 6307, Fall '21

Welcome! This folder contains all our code for this course's final project. Here, you can find the following files:

  • ml_imdb.ipynb: Contains all the classical ML algorthims and analysis plots for the IMDB dataset.
  • ml_sms.ipynb: Contains all the classical ML algorthims and analysis plots for the SMS Spam dataset.
  • lstm_imdb.py: Contains the LSTM implementation for the IMDB dataset.
  • lstm_sms.py: Contains the LSTM implementation for the SMS Spam dataset.

Further, the data folder contains both datasets. The internal data/raw folder contains the original datasets, while the main folder contains the preprocessed versions.

Thank you!