Blog | Civis Analytics

Civis Blog

CivisML: Scikit-Learn at Scale

CivisML: Scikit-Learn at Scale

by Stephen Hoover

Late last year, my colleagues on the Social Science team were working on a new survey weighting scheme that would greatly improve the precision of our public opinion data. To make it work, they needed to fit dozens of models for each completed survey. Each survey asks multiple questions, each of which would need to be modeled individually, using an...

Read More 

Leading with Data: Civis and the National Technical Information Service

Leading with Data: Civis and the National Technical Information Service

by Mary Lazzeri

For the past two years and up until a few months ago I was part of a unique White House initiative that paired the country’s top technologists with its brightest civil servants, on a joint effort to improve the usability and reliability of Federal government’s critical public services. This illuminating experience gave me visibility across multiple Federal agencies into the...

Read More 

Tips and Lessons Learned from Upgrading Ruby on Rails

Tips and Lessons Learned from Upgrading Ruby on Rails

by Jonathan Cobian

In a recent post, I shared a how-to guide on upgrading Ruby on Rails based on my team’s experience in doing so for the Civis Platform. In this post, I’ll share some of the tips and lessons learned around code implementation, third-party libraries, and testing. Hopefully, they’ll help you make your next upgrade easier than your last. Code Implementation Private...

Read More 

Want to be a Better Engineer? Be a Better Researcher

by Salil Gupta

I used to think the best engineers are the ones that write the cleanest code. When I started out developing software, I thought it was all about writing the cleanest and fastest. And of course, writing robust software that can stand up to testing. But recently I came to a realization. After years of endless discussions about which design patterns...

Read More 

‘Uninsured:’ How One Word Can Bias Your Survey Results

by Kayla Benker

Words matter—especially words in survey questions. They can make the difference between getting good data, bad data, and mystery data. Exhibit A: the word “uninsured.” The Affordable Care Act (ACA) has helped millions of Americans secure health insurance. But a recent NPR poll asked about the law’s effect on the total number of Americans who have health insurance, and about...

Read More 

Who Do Consumers Really Think Should Win Best Picture at the Oscars? Data Science Has the Answer

by Geoff Bakken

With Oscar night fast approaching on Sunday, the question on the minds of movies fans is which of the nine nominated movies will walk away with the Best Picture award. As data scientists, we relish opportunities to test new ways to predict the outcomes of big events like the Academy Awards. Conventional wisdom, which is largely based on the results...

Read More