View Code? Open in Web Editor
NEW
A program to predict the language based on the n-gram character models generated.
Shell 4.48%
Python 95.52%
n-grams_language_predictor's Introduction
n-gram Language Predictor
Uni-gram, Bi-gram and Tri-gram
Charachter models for Language prediction
- Works on Linux environment only.
- Version : 1.0
- n-Grams
- SETUP
- MINIMUM SYSTEM REQUIREMENTS
- SOFTWARE/PLUG-IN DOWNLOADS
- GUIDELINES
- WARNINGS
- REPO OWNERS AND ADMINS
MINIMUM SYSTEM REQUIREMENTS
- MINIMUM 4GB RAM
- Intel core i3 or higher
SOFTWARE/PLUG-IN DOWNLOADS
- Download and install Anaconda
- NLTK and TEXTBLOB libraries
- preferred configuration: python 3.4.x with annaconda and nltk libraries
- By default, the application assumes that the test and training datasets are imported from nltk library
- How to run:
python Rachapalli_Assignment2.py
- Please note that 'python' in the command to run should include anaconda and nltk libraries.
- It is preferred to run the scripts on High Performance Clusters if the data set is huge.