Discover dssg/tyra Open Source project

Bias Auditing & Fair ML Toolkit

986

aequitas

General Purpose Risk Modeling and Prediction Toolkit for Policy and Social Good Problems

669

triage

Statistical models and webapp for predicting when bikeshare stations will be empty or full.

182

bikeshare

Class resources for CAPP 30254 (Machine Learning for Public Policy)

115

MLforPublicPolicy

Repo for ML for Public Policy Lab course at CMU

104

mlforpublicpolicylab

Methods, tools, tips, and tricks for anyone interested in getting started doing data science for the social good.

101

data-science-101

An energy analytics tool to make commercial building more energy efficient

energywise

Hands-on tutorial on ML Fairness

fairness_tutorial

Using machine learning to predict high school dropouts

student-early-warning

MLinPractice

Repository for ML in Practice Course at CMU (10-718)

A machine learning API to analyze tweets during disasters.

tweedr

DSaPP police early intervention system: using machine learning to predict adverse incidents

police-eis

Git repo for Wiki Energy project

wikienergy

Exploratory analysis and predictive models of how Chicago's neighborhoods interact with the City's 311 service requests.

411-on-311

A simple command line interface to the datamade/dedupe library.

pgdedupe

Tracing policy ideas from think tanks and lobbyists through state legislative bills

policy_diffusion

An API tool to help understand the relationships between non-profits, for-profits, and the causes they support.

givinggraph

An API that uses machine learning to help the Ushahidi nonprofit do smarter crisis crowdsourcing.

ushine-learning

Search for potential passwords/data leaks in a folder or git repo

repo-scraper

Big data simulation of Chicago's public transportation to improve transit planning and reduce bus crowding

cta-sim

CSS

census-communities-usa

Mapping and analyzing local business data from the Census Bureau.

syracuse_public

Identifying traffic-safety issues in CCTV footage

jakarta_smart_city_traffic_safety_public

A repository of real-world data challenges faced by organizations used for project-based learning

data-challenges

usal_echo_public

Automate process for view classification of the Apical 4 chamber, Apical 2 chamber and Parasternal long axis. Segmentation of the Apical 4 chamber and Apical 2 chamber. Calculate measurements of the Ejection Fraction of the heart to classify it as normal, abnoral or grayzone.

Predictive models to identify high-achieving high school students who are likely to undermatch - attend 2-year rather than 4-year colleges, or not go to college at all.

match.edu

dsapp-reading-group

Proceedings of the Center for Data Scientists arguing (about) Public Papers

diogenes

Searching for an honest classifier

ohio

Python I/O extras

OpenTripPlanner tool and transit mobility maps for Chicago

cta-otp

Java

dirtyduck

A Guided Tour of Triage

CSS

eights

Data Science template with focus on prewritten workflows

Automatic missing value imputation using random forests

Random_Forest_Imputer

Statistical models of children's growth curves that predict which kids are at risk of obesity.

growth-curves

Thin argparse wrapper for quick, clear and easy declaration of hierarchical console command interfaces

argcmdr

What fellows are learning about data problems and tools

learning

Chicago Data Portal (data.cityofchicago.org) tree map

data-portal-treemap

This repository includes an exercise for aspiring DSaPP volunteers and research assistants to complete

DSaPP_RA_Project

dssg-training-workshop-2015

Main site for DSSG Training 2015

HTML

acs2pgsql

Download American Community Survey data and put it into a Postgres database

air_pollution_estimation

A set of tools and conventions to help data scientists share code

UPSG

Statistical models to find whether Chicago street light outages are associated with increased crime

streetlights-crime

predicting_student_enrollment_public

Statistical models and analysis of student enrollment in Chicago Public Schools

dssg-manual

This repository contains the Eric & Wendy Schmidt Data Science for Social Good Fellowship Manual

cincinnati

DSaPP project with the City of Cincinnati. Building upon the DSSG15 project

Public repository for the DSSG Memphis project

memphis-public

peeps-chili

Ethics with a side of chili. And peeps.

Analytics tool to help the Cook County Land Bank acquire vacant and abandoned properties strategically.

land-bank

johnson-county-ddj-public

Integrating HMIS and criminal-justice data

matching-tool

Text Analysis Tutorial for DSSG 2017 Conference

dssg2017-text_analysis

Randomize the order of each column to help check for leakage

randomize_your_data

generate time splits for temporal validation

timechop

Download NOAA weather for a user-specified US state

weather2pgsql

Recommending responses to law related queries - Built during DSSG in collaboration with Barefoot Law

barefoot-winnie-public

Webapp for visualizing ML'd data

hylas

Understanding city innovation hotspots using the Census CitySDK

innovation-ecosystems

CSS

healthleads-public

The public repo for the 2014 DSSG Health Leads project

A template for a sample DSSG project.

project_template

solveforgood-wri

This is the publicly available version of the babies repo, containing code used during our project with the Illinois Department of Human Services to predict and reduce adverse births in Illinois.

babies-public

Code for doing slightly atypical things with CSVs

stupid-csv-tricks

Training, testing, and evaluating machine learning classifier models

catwalk

Speaks for the trees by providing individual feature importances from random forests.

lorax

homelessness-public

Code for the Solve for Good platform run by the DSSG Foundation

marketplace

rws_accident_prediction_public

rws_accident_prediction

Predicting blight in Cincinnati

cincinnati2015-public

Public facing Mexico repository

mexico-public

audition

Choosing the best classifier models

Bash library for guided installation & bootstrapping

dssg-public-hmda

install-cli

Short tutorial on some pipeline issues

sklearn_tutorial

Automatically identify earmarks in congressional spending bills

machine_learning_legislation

OpenEdge ABL

acdhs_housing_public

Impact evaluation of the Nurse-Family Partnership nonprofit

nfp

MS2Postgres

A tool to move data from SQL Server to PostgreSQL in an environment with limited harddrive space.

Analysis of energy efficiency loan data for the Environmental Defense Fund.

EDF

check-for-secrets

Discovering Secrets analysts Possibly Pushed

Reducing Early School Dropout Rates in El Salvador

el-salvador-mined-public

hiv-retention-public

DSSG 2015 project focused on using data science methods to help partner public school districts improve their respective high school graduation rates and outcomes.

after-hours

education-highschool-public

HTML

passenv

Shell command like env to run a program in an environment modified by values read from standard input

Improving Workplace Safety through Proactive Inspections in Chile

chile-dt-public

cincinnati_ems_public

Data-Driven Planning for Sustainable Tourism in Tuscany

tuscany-tourism-public

HTML

architect

Plan, design and build train and test matrices

The command center at the DSSG office. http://en.wikipedia.org/wiki/Panopticon

panopticon

Ruby

pakistan_ihhn_public

Public Repository for the DSSG 2022 Pakistan IHHN Project

donors-choose

The sexy landing page that will make everyone want to apply for the fellowship.

data-sci-fellows

Transform text to be unreadable but still somewhat useful

obscuritext

Public Repository for DSSG 2022 Douglas and Johnson Counties, KS Mental Health Project

dojo_mh_public

Public Repository for DSSG 2022 Baltimore Roofs Project

baltimore_roofs_public

sanergy-public

Timeout library for generic interruption of main thread by an exception after a configurable duration.

signalled-timeout

A "smart" Web application for reviewing DSSG program application submissions

100

appy-reviews