Name: quant-hack
Owner: Bayes Hack 2016
Description: #HUD A Study of the Well Being of the Residents of San Francisco
Created: 2016-04-24 16:44:12.0
Updated: 2017-04-12 04:13:14.0
Pushed: 2016-04-24 17:00:14.0
Size: 154858
Language: Jupyter Notebook
GitHub Committers
User | Most Recent Commit | # Commits |
---|
Other Committers
User | Most Recent Commit | # Commits |
---|
This is a one-day project completed as part of the Bayes Impact hackathon.
Housing inequality is present in cities across the United States, rendering low income families unable to obtain affordable housing. Lack of fair housing opportunities is just one of the problems communities face: many people also lack access to transportation and services within the community. Both communities and residents suffer when specific populations cannot utilize all the resources communities have to offer. National and local data sets have been created by initiatives that are addressing the gaps between residents in communities.
Help cities enhance their use of data and evidence to uncover new ways to revitalize neighborhoods and improve the lives of residents. Leverage federal and local open data to identify disparities in access to resource, services, and housing that communities need to thrive. Interactive informative tools that show current trends, or tools to illustrate federal and local spending or regulatory changes, have the potential to reinvent the way communities come together and grow.
Original Brief for The Project
This project aims at characterizing the livability of San Francisco neighborhoods, and does so in 2 ways:
Visualizing features of neighborhoods using chloropleths.
Eploring the relationship between the features and the general level of satisfaction of inhabitants.
The satisfaction of inhabitants is inferred from surveys and the features are inferred from census data, notably from datasf.org.
The neighborhood features include:
The project was developed with the Python and JavaScript programming languages. The deliverable is an interactive document provided in the form of a Jupyter notebook with advanced interactive visualizations based on leafletjs, bqplot, d3.js.
bqplot
to allow the features to be adjusted visually and which displays the predicted change in well-being for the neighborhood.To be able to run the project the following software is required:
Python Scientific Stack
pandas >= 0.17.1
matplotlib >= 1.5.1
Jupyter notebook and Interactive Widget Libraries
Jupyter Notebook >= 4.2
ipywidgets >= 5.0.0
ipyleaflet >= 0.2.0b5
bqplot >= 0.6.1
GIS library
geopy >=1.10
sf_zipcodes.geojson
:
A GeoJSON file that contains San Francisco zip code level topographical data. Each feature contains an attitude id
which is the zip code associated with the Polygon
.
The main notebook of the study is Main.ipynb.