Overview
After watching Thu Vu's YouTube tutorial, I was able to use a Python script that pulls information about characters from the Witcher books and uses it to make a network diagram showing how they are connected.
Setup & context
The code scrapes character data from a webpage about the Witcher novels using the Selenium library and Chrome webdriver. The spaCy library and its named entity recognition model are then used to extract and categorize named entities from the book's text, while the displaCy library is applied to display these detected things. This information is used to generate a list of characters and their relationships in the novels. The NetworkX library is then used to build a graphical representation of these relationships, which includes the characters and their links.
The challenge & problem PROCESS
Extracting and categorising named things from the text of The Witcher novels was a significant barrier for this project due to the linguistic processing work required. It did this with the help of the spaCy library and its named entity recognition model. Problems also arose while trying to present the data in a way that was both understandable and visually appealing. In order to better understand the interplay between the characters, she utilised the NetworkX library to generate a graph that shows not only the characters themselves, but also the interactions between them. After collecting textual data from a website using Selenium and the Chrome webdriver, processing it using spaCy, and assembling a list of characters and their associations, then visualised the data with NetworkX. The layout and design components of the graph were thoughtfully considered to make it interactive and aesthetically pleasing.
results
Overall, this project was a great opportunity to apply my skills in Python programming, data analysis, and data visualization to a topic that I am passionate about. It allowed me to gain a deeper understanding of text processing and visualization techniques, as well as the complex relationships between the characters in the Witcher books. I am proud of the work I was able to accomplish and believe that it showcases my capabilities as a programmer and data analyst.