fall2022-project1-Jokerxp created by GitHub Classroom
The project aims to explore a significant development of capitalism in the late 19th and early 20th century.
- Began with a word cloud to present key words of capitalism
- Explained why capitalism developed rapidly in this era based on semantic analysis with NRC Emotion lexicon
- Utilized TF-IDF to extract the most important ten words of different eras
- Calculated cosine text similarity within two schools based on a larger corpus
- Plotted a heatmap to visualize this kind of relationship
Consider that github only accepts files less than 100MB without lfs, please unizip zip files before reviewing
data/: Including original dataset, phylosophy_data.zip
doc/: ipynb files, including data prepocessing, data analysis and data story. A html version of data story is also attached to this directory
figs/: Figures
libs/: Including utils.py which contains some functions used in the project
output/: csv files, including some middle tables and output tables.