Fishery_Inspection_PT_2017_23

The code used for the extraction, translation, pre-processing, and protection of the vessel identification is available in a GitHub repository (https://github.com/ricardomourarpm/Fishery_Inspection_PT_2017_23). To run the provided code, it is possible to run it locally using Python in a Jupyter Notebook or even use the Anaconda Distribution, or you can use it directly online using, e.g., the Google Colaboratory (https://colab.research.google.com/). The Anaconda Distribution (https://jupyter.org/install.html) is an excellent choice for scientific computing and data science as it includes Python, Jupyter Notebook, and other commonly used packages.

One must use synthetically generated or protected data to run the codes since the original dataset cannot be shared for privacy and confidentiality reasons. Moreover, some values/variable vectors in files 4_1_k_identifiers_analysis.py and 5_Anonimization.py are not real (https://github.com/ricardomourarpm/Fishery_Inspection_PT_2017_23), as they should be withheld from the general public to ensure data protection and privacy.