This project classifies documents according to multiple labels. Dataset consists of the 6 first pages of over 18,000 documents, and the way each document has been indexed (labelled). Each document can have multiple labels. In total, there's up to 29 different labels.
Documents are from an International Organization.
The following jupyter notebooks are provided:
File 1 prepares data for both modeling and visualizations, creating 2 different files one for each purpose.
This project has been undertaken complying with a code of ethics
I provide the environment used to run this code.
This project is under Copyright © 2019 Josep Maria Niubo. It is free software, and may be redistributed under the terms specified in the LICENSE file