This notebook takes off from Visualize Parts of Speech 1, which ended with a visualization from a single text. In this notebook, we look at how to visually compare the part of speech usage in many texts.

Do good writers use fewer adverbs than poor writers? Is it possible to improve ones writing by looking at the relative distribution of different parts of speech (POS)? I was curious about this and wanted to investigate. The first step towards determining this is to find out what a “normal” POS distribution is. To do that, we’ll explore parts of speech usage in Great Expectations by Charles Dickens.

CUDA used to be an acronym for Compute Unified Device Architecture, but now it’s no longer an acronym. It’s just CUDA. CUDA is basically C for GPUs. Just like operations in NumPy use C and go much faster, the same is true for CUDA operations in GPUs.

This tutorial aims to guide you through the process of troubleshooting issues related to your NVIDIA graphics card when working on deep learning projects.

The Natural Language ToolKit (NLTK) is the most popular library for natural language processing (NLP) in Python. The authors also created the NLTK textbook, which is a great resource for learning how to use NLTK. This notebook is a compilation of the parts of NLTK that I found most interesting.

Python offers several different methods for opening text files, but are all options equally good? What’s the best method for the generic case of opening a text file?

The Jupyter Notebook is a great tool for writing and exploring code as well as prototyping ideas. It’s one of my favorite ways to write code, in part because of all the great features it has. This post demonstrates shows some of my favorite features.