Digital Humanities Project in 48 Hours! (The Digital Alcuin Project) Day 1 (First скачать в хорошем качестве

Digital Humanities Project in 48 Hours! (The Digital Alcuin Project) Day 1 (First

For this channel's first livestream, I will be working on the Digital Alcuin Project. Over 48 hours, we will go from acquiring the data and processing it via Python and ultimately developing a front-end user interface with Streamlit. This project is intended to provide all letters of Alcuin to the public from the original MGH editions. The data will be dynamic and have features that allow researchers to identify people and places referenced, extract the relationship between those people and places, and map out how the letters survived in different collections. This is an idea I have had for over a year and I am hoping that this livestream gives the motivation to get it finished. The tentative workflow will be like this: 1) Acquire the data from the DMGH.DE website 2) OCR the PDFs with LatinOCR (a Google Tesseract Model). 3) Clean and structure the output to retain as much metadata as possible 4) Develop a spaCy pipeline for identifying specific entities (PERSON and PLACE) 5) Develop a heuristic approach to identifying relationships 6) Use the data acquired to develop a social network map of all people referenced in the letters of Alcuin 7) Develop a front-end app with Streamlit to allow users to navigate the letters dynamically. During 48 hours we will take a project from nothing to a fully-usable app. (At least that's the plan). If you enjoy this video, please subscribe. ✅Be my Patron:   / wjbmattingly   ✅PayPal: https://www.paypal.com/cgi-bin/webscr... If there's a specific video you would like to see or a tutorial series, let me know in the comments and I will try and make it. If you liked this video, check out www.PythonHumanities.com, where I have Coding Exercises, Lessons, on-site Python shells where you can experiment with code, and a text version of the material discussed here. You can follow me at:   / wjb_mattingly