## About the data This repository contains a copy of the Enhanced OCOD dataset (OCOD+), the spaCY model used to create the dataset. as well as the training data to allow researchers to create new predictive models. OCOD+ is an enhanced version of the original OCOD dataset released by the Land Registry of offshore owned property in England and Wales. OCOD+ improves upon the original version by separating out multiple properties within a single land title, parsing the addresses to make searching easier, and finally classifying the property into 5 types Airspace, Business, Car park, Residential, Land, properties that cannot be classified are labelled 'unknown'. The aim of this dataset is to reduce the barriers to researching offshore property in England and Wales. This dataset was first presented in the paper 'What's in the laundromat? Mapping and characterising offshore-owned residential property in London' The code used to create OCOD+ is found at this github repository https://github.com/JonnoB/enhance_ocod The repo contains code and instructions necessary to create OCOD+ from scratch ## Description of data files: There are several files in this repository. The sections below describe what each one of them is for ### The OCOD+ dataset This is the CSV of OCOD+ as used in the paper what's in the laundromat. It covers the whole of England and Wales - enhanced_ocod_dataset.csv (34.4 MB) ### File to create new OCOD+ The spaCy model can be used to create new OCOD+ datasets from newly released data. - spaCy model file (tar.gz) ## Files for creating new models For those that want to create and entirely new predictive model the below files can be used as training and test sets - ground_truth_dev_set_labels.csv 11.0 MB - ground_truth_test_set_labels.csv 3.1MB - parsed_ground_truth_complete.csv 186.0kB ## Supporting Code - Git hub repository of code to create dataset DOI:10.5281/zenodo.7308824 - What's in the laundromat code DOI: 10.5281/zenodo.7308832 ## License The OCOD+ dataset must be used under the terms of the original [OCOD dataset](https://use-land-property-data.service.gov.uk/datasets/ocod/licence/view). See the licence.txt file for details ## Funding The authors thank Trust for London (grant number MAIN-S2-06.10.2020-8792(6930) ) for funding this research. We would also like to thank Kingston University for providing additional research funding. Finally we would like to thank UCL for funding the publication of this paper.