The compressed package (Study_code.zip) contains the code files implemented by an under review paper ("What you see is what you get: Delineating urban jobs-housing spatial distribution at a parcel scale by using street view imagery based on deep learning technique").The compressed package (input_land_parcel_with_attributes.zip) is the sampled mixed "jobs-housing" attributes data of the study area with multiple probability attributes (Only working, Only living, working and living) at the land parcel scale.The compressed package (input_street_view_images.zip) is the surrounding street view data near sampled land parcels (input_land_parcel_with_attributes.zip) with the pixel size of 240*160 obtained from Tencent map (https://map.qq.com/).The compressed package (output_results.zip) contains the result vector files (Jobs-housing pattern distribution and error distribution) and file description (Readme.txt).This project uses some Python open source libraries (Numpy, Pandas, Selenium, Gdal, Pytorch and sklearn). This project complies with the GPL license.Numpy (https://numpy.org/) is an open source numerical calculation tool developed by Travis Oliphant. Used in this project for matrix operation. This library complies with the BSD license.Pandas (https://pandas.pydata.org/) is an open source library, providing high-performance, easy-to-use data structures and data analysis tools. This library complies with the BSD license.Selenium(https://www.selenium.dev/) is a suite of tools for automating web browsers.Used in this project for getting street view images.This library complies with the BSD license.Gdal(https://gdal.org/) is a translator library for raster and vector geospatial data formats.Used in this project for processing geospatial data.This library complies with the BSD license.Pytorch(https://pytorch.org/) is an open source machine learning framework that accelerates the path from research prototyping to production deployment.Used in this project for deep learning.This library complies with the BSD license.sklearn(https://scikit-learn.org/) is an open source machine learning tool for python.Used in this project for comparing precision metrics.This library complies with the BSD license.

Break down of social housing stock by community housing, by Local Government Area. AURIN has archived this dataset as there have been no updates since 2011.

This dataset contains Housing Affordability Supply and Demand Data broken down by very low, low and moderate income brackets.

This dataset relates to section 4, Housing Stress, of the Affordability master reports produced by the SA Housing Authority. Each master report covers one Local Government Area and is entitled Housing Affordability Demand and Supply by Local Government Area.

Explanatory Notes: Data sourced from the Australian Bureau of Statistics (ABS), Census for Population and Housing and it is updated every 5 years in line with the ABS Census.

The nature of the income imputation means that the reported proportion may significantly overstate the true proportion. Census housing stress data is best used in comparing results over Censuses (ie did it increase or decrease in an area) rather than using it to ascertain what proportion of households were in rental stress.

Income bands are based on household income.

High income households can also experience rental stress. These households are included in the total but not identified separately. Data is representative of households in very low, low and moderate income brackets.

Please note that there are small random adjustments made to all cell values to protect the confidentiality of data. These adjustments may cause the sum of rows or columns to differ by small amounts from table totals.

Field Definitions: LGA Name: 2011 Local Government Areas are an ABS approximation of officially gazetted LGAs as defined by each State and Territory Local Government Department. The boundaries produced for LGAs are constructed from allocations of whole Mesh Blocks and reviewed annually.

Tenure Type: This is a consolidation of the census tenure and landlord types. The following definitions have been used: Rented: Private and not stated, this is comprised of rented dwellings (excluding rent free) where the Landlord type is a Real Estate Agent, Person not in the same household or where the Landlord type is not stated Rented: Other, this is comprised of rented dwellings (excluding rent free) where the Landlord type is Employer (Govt or other), Housing cooperative,community,church group, or Residential park (incl caravan parks and marinas) Rented: TOTAL, this is comprised of the sum of Rented: Public, Rented: Private and not stated, and Rented: Other landlord. Please note that this field should be excluded when summing the total households Other tenure types: this is comprised of dwellings that are owned outright, occupied rent free, occupied under a life tenure scheme, other tenure types and tenure type not stated. Total Households: this is comprised of the sum of Being purchased (incl rent,buy), Rented: TOTAL and Other tenure types.

Total - Includes all South Australian households.

Source: The data was downloaded from data.sa.gov.au and spatialised by the Adelaide Data Hub using the ABS 2011 Local Government Areas dataset.

This dataset is the result of data collection and refinement within the Co-lab mapping project. The purpose of this data collection and refinement is to provide a scientifically-validated categorisation of the different collaborative housing forms in Europe and to create the basis for comparative and quantitative studies on collaborative housing. This promotes mutual learning and communication amongst users across countries and regions. It is being made public to facilitate use by other researchers and professionals in their own work.

This dataset contains quantitative data on collaborative housing forms in Sweden, Denmark, United Kingdom, and The Netherlands. Quantitative raw data was collected and refined from primary sources, namely datasets provided by umbrella organisations from the different European countries involved in the project.

Change in proportions of housing stock through Local Government Areas 2009-2010, broken down by detached/attached, townhouse/row housing and apartments.

For more information vist data.sa.gov.au. AURIN has archived this dataset as there have been no updates since the 2011-2012 release.

This dataset contains Housing Affordability Supply and Demand Data represented as tenure mix and dwelling type for each local government area.

This dataset relates to section 8 of the Affordability master reports produced by the SA Housing Authority. Each master report covers one Local Government Area and is entitled Housing Affordability Demand and Supply by Local Government Area.

Explanatory Notes: Data sourced from the Australian Bureau of Statistics (ABS), Census for Population and Housing and it is updated every 5 years in line with the ABS Census.

Source: The data was downloaded from data.sa.gov.au and spatialised by the Adelaide Data Hub using the ABS 2011 Local Government Areas dataset. AURIN has archived this dataset as there have been no updates since 2011.

Project Atlas - São Paulo

Project Atlas - São Paulo is a Data Science and Engineering initiative that aims at developing relevant and curated Geospatial features about the city of São Paulo, Brazil. It's ultimate use is varied, but it is mainly focused on Machine Learning tasks, such as Real State price prediction.

It aggregates several attributes from many public data sources at different levels of interest, which can be used to match geospatially referenced data (lat,long pairs for example).

A breakdown of the data sources currently used and their original references can be found below, but the official documentation of the project contains the full list of data sources.

Data sources

• GeoSampa: geospatial data exploration tool provided by the São Paulo's Department of Urban Development;
• IBGE: raw datasets from the 2010 Census conducted by the Brazilian Institute of Geography and Statistics;
• Infocidade: multiple sources from the city of São Paulo's local government entities;
• São Paulo Open Data Portal: multiple curated data sources from the city of São Paulo;

Relevant files:

1. tb_district.parquet: the dataset with all derived features aggregated at the District level;
2. tb_neighborhood.parquet: the dataset with all derived features aggregated at the Neighborhood level;
3. tb_zipcode.parquet: the dataset with all derived features aggregated at the Zipcode level;
4. tb_area_of_ponderation: the dataset with all derived features aggregated at the Area of Ponderation level;

Inspiration

This project had various inspirations, such as the Boston Housing Dataset. While I was studying relevant features for the real state market, I noticed that the classic Boston Housing dataset included several sociodemographic variables, which gave me the idea to do the same for São Paulo using the Brazilian Census data.

Acknowledgements

Photo by Lucas Marcomini on Unsplash

The aim of this project was to investigate the experiences of tenants moving into dwellings constructed as part of the Australian Federal Government's Nation Building Economic Stimulus Package announced in 2008 and 2009.

Approximately 600 responses were received to the survey. Subsequent to completing the survey some of the participants were interviewed as were other involved parties.

HUD Low Income Housing Tax Credit (LIHTC) projects shapefile.

This dataset in the shapefile format contains geo-located points of projects in the City of Dallas that have used the Low-Income Housing Tax Credit Program available through the Department of Housing and Urban Development. These data were used as a primary dataset to generate the Percent Subsidized factor in the MVA.

This layer shows the location of Home Ownership Scheme Courts in Hong Kong. It is a subset of the geo-referenced public facility data made available by the Hong Kong Housing Authority under the Government of Hong Kong Special Administrative Region (the “Government”) at https://DATA.GOV.HK/ (“DATA.GOV.HK”). The source data is in JSON format and has been processed and converted into Esri File Geodatabase format and then uploaded to Esri’s ArcGIS Online platform for sharing and reference purpose. The objectives are to facilitate our Hong Kong ArcGIS Online users to use the data in a spatial ready format and save their data conversion effort.For details about the data, source format and terms of conditions of usage, please refer to the website of DATA.GOV.HK at https://data.gov.hk.

A data set identifying three main categories of supported housing across Cambridgeshire, Peterborough and West Suffolk: housing schemes for older people, people with disabilities and for homeless people.
This is an initial list of over 600 schemes (not individual properties) aimed at supporting our geo-location work.

Residential property estimates by geography, property type, period of construction, property use and ownership type.

The Title and Property Assistance (TAPA) program allows residents who do not have clear title on their home to get free or discounted legal assistance to clear the title. There could me many reasons a property title is unclear such as liens or an inherited property that didn't go through probate and is still in a parent's name. Applicants must earn less than 120% AMI, have an eligible title issue with their home, and live in specific geographic areas or have applied and been denied to a city housing program.This feature layer shows the geographic areas in which properties may qualify. It includes Market Value Analysis (MVA) categories D, E, F, G, H, and I that are south of the Trinity River and I-30. This area has a concentrated amount of title issues which may cause problems for residents and neighborhoods. This feature in particular uses the MVA for Incentive Zoning layer, which expands the original MVA to the block group level.

This dataset in the shapefile format contains geo-located points of projects in the City of Dallas that have used the Low-Income Housing Tax Credit Program available through the Department of Housing and Urban Development. These data were used as a primary dataset to generate the Percent Subsidized factor in the MVA