@mortrpestl
Language analysis of the 'Palanca Series', a 16-part anthology with themes of farewell and new beginnings, using NLTK, NetworkX, Seaborn, and other analysis paradigms.
This file contains:
- The Jupyter notebook for all of the code with instructions for importing important tools (e.g. the NLTK downloads)
- The corresponding image outputs of each sub-analysis, including but not limited to:
- Frequency analysis and bonus statistics of all lemmatized texts using NLTK, matplotlib, and Seaborn
- Word cloud of common words throughout the text using WordCloud
- Spring layout graph and radial network graph showing appearances of top 50 words in the documents using NetworkX
- All of the sub-analyses combined in one comprehensive report
Below is an overview of the results of the report:
All data is taken from the literature marked as 'Palanca Series' in leissezfaire.substack.com.
All rights reserved by @mortrpestl
Palanca is a 16-piece anthology of letters that I have given out to those who have had left with me great impact, in one way or another, in an important chapter of my life. I realized that it would be fun and constructive to analyze these works to find greater insight into my writing style, as well as the subconscious connections I have written between the letters.
I used this to culminate my learnings from the University of Michigan - Applied Data Science with Python Specialization course :D