Udacity - Artificial Intelligence Nanodegree Program
AI - Natural Language Processing
This project is part of Udacity´s Artificial Intelligence Nanodegree Program. Here you will find my personal solution to the challenge. The following project can be run using a Local Machine or using an external GPU (Solution provided by Amazon Web Services is recommended). Next, you can follow Udacitys instructions to install the necessary dependencies on a local machine or on AWS.
Follow the instructions to install the required environment and check the jupyter notebook files:
(pmaienv)$ jupyter notebook sentiment_analysis.ipynb
(pmaienv)$ jupyter notebook text_processing.ipynb
Coding exercises for the Natural Language Processing concentration, part of Udacity's Artificial Intelligence Nanodegree program.
You need Python 3.6+, and the packages mentioned in requirements.txt
. You can install them using:
pip install -r requirements.txt
Data files for exercises are included under data/
, but some of the NLP libraries require additional data for performing tasks like
PoS tagging, lemmatization, etc. Specifically, nltk
will throw an error if the required data is not installed. You can use the
following Python statement to open the NLTK downloader and select the desired package(s) to install:
nltk.download()
You can also download all available NLTK data packages, which includes a number of sample corpora as well, but that may take a while (10+GB).
To run any script file, use:
python <script.py>
To open a notebook, use:
jupyter notebook <notebook.ipynb>
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. Please refer to Udacity Terms of Service for further information.