Data Day 2016

by Eric Darsow

Our digital age birthed another unusual occurrence: a tabling event devoted entirely and exclusively to the idea of data. Organizations of all sizes and girths carted in maps made in several centuries, charts of dazzling design, and slews of glimmering screens. A 3D printing robot was even spotted spewing layers of plastic into cute shapes. Amid this flurry of patterns and coefficients, the Students for Urban Data Systems (SUDSers) teamed up with nerds from CMU’s CREATE LAB to referee the pesky spar between the number crunchers and the story tellers.

The so-called “numbers and narrative” divide is turning out to be a chasm of our own making. While the process of regressing a spreadsheet full of figures obviously lacks a well-told story’s emotional pin-pricks, cryptic tabular outputs can, in fact, add dimensions of extent and intensity to an issue first illuminated by a personal narrative.

For example, how are we to make sense of, say, a sudden drop in high school test scores without talking to some teenagers about their experience bubbling in answers to mind-numbing test questions? The other direction works, too: few folks would rebuff a decision to augment an angry biker’s story about getting run off the road by a texting driver with a map showing ten years of bike crashes in Pittsburgh.

The SUDS + CREATE exhibit facilitated a safe crossing of this oft-feared number/narrative gap by displaying a few statistics about a central topic—such as transportation—and then inviting folks to write and physically connect a story or question to an otherwise lonely and contextless number.

One attendee affixed a short story about his personal experience with skyrocketing housing prices in his home city of Seoul. Pinned and ready for connections, another visitor complemented the narrative account with satellite images (pixel data) showing the Korean capital’s stunning vertical growth since the mid-1980s. Adding some sky shots of Austin, Texas’s metastasizing suburbanization over the same time period couched the sky-high rent story into a global context.

Even young people (perhaps less demoralized by hours of myopic method design meetings) sense intuitively the value of a well-told story alongside a chart or graph. One 9 year-old who visited our station looked over a bar graph depicting the average number of bicycle crashes by hour of the day. After a few minutes of thinking and talking aloud about the bars and axes, he used a marker and construction paper to ask all future board viewers: Why are there so many more bike crashes at midnight than 4:00 am? With an average bed time of 9:15 pm for children under ten in the United States, his wonder was about as genuine as it comes.

An enthusiastic transplant to Pittsburgh, Eric explores how the computerization of society impacts our geographic communities, social landscapes, and work identities. Eric is eagerly wrapping up his grad program in information systems at CMU and actively balances his screen-based life with wood carpentry and trying his hand at “installation art.” He serves as SUDS’s Assistant Director of Outreach, and interned at the CREATE Lab last summer.

Criminal Justice Work Night highlight: do police from smaller units use force more often?

At our first Work Night a few weeks ago, SUDS members dug into data on crime and criminal justice–particularly from the 2013 Law Enforcement Management and Administrative Statistics (LEMAS) survey. One student, Kee Won Song, pulled together some interesting initial insights and a sweet chart in just a few hours. He writes:
I am interested to see if we can identify factors that contribute to use of force incidents.  Specifically, I am interested to see if factors like employee demographics, education level of employees, size of department, participation in academic research (which we might also use to assign a score for ‘transparency’), budget, training methods, number of specialized units, use of data/computers in evaluating performance etc. have any affect on the frequency of use of force.  I did not get to analyze many of these factors, however, this is one figure that I produced that plots use of force incidents (expressed as incidents per employee) against total employees (full-time plus part-time):

LEMAS surveyIt’s hard to say that anything substantive can be gleaned from the visualization but it might allow us to further focus on smaller departments that have a high use of force rate (or identify outliers for further analysis).

Kee Won Song is a full-time MPM student at CMU, who is also completing Masters of Sustainability at Chatham; his interests include researching the impacts of unconventional oil and gas extraction on air quality, particularly in underprivileged communities.

Work Night: Hacking & Fracking

Environmental Sensors HackNight
We are going to be using the ESDR dataset collected by various sensors across the country. The data is collated by CMU Create Lab.
  1. Follow this link, and download the dataset (or from here and select PGH_Sensors_Data.csv if that link doesn’t work).
  1. For simplicity, we filtered it only for Pittsburgh and only the sensors that have been active. If you need more data, it can be collected through
  1. The file is a CSV file, with columns indicating the name, id , location of the sensor, and the observations it has been collecting, and at what times.
  1. Load the file into R, iPython, or wherever.
You can also check out other cool visualizations on this data here –
Discuss your ideas, cool observations here: Environmental Sensors HackNight
Sample Ideas for the ESDR data
  1. Mapping the sensors, and visualizing the pollution levels based on the neighborhood.
  1. Finding which neighborhoods are the worst in air-quality
  1. Combining with 311 data from WPRDC to figure out some cool stuff.
  1. Talk to people, and think what more can be done.
PS. If you want some tips on using Tableau to visualize data, this tutorial from a former SUDSer can get you started. The video starts with pulling data from a public API, which we’re not doing here, you’ll have to bring the data in manually, but after that follow along.
PPS. If you tweet / insta / etc… #SUDSWorkNight

Work Night: Criminal Justice + Data

We’re starting with the 2013 Law Enforcement Management and Administrative Statistics (LEMAS) survey. To access the data:
  1. Follow this link:
  2. Scroll down to “Datasets”
  3. We suggest downloading the “Excel/TSV” dataset. This is an easy format and the .zip contains the Codebook as well.
  4. Unzip the file and open what should be the only folder — “DS0001”.
  5. (Optional) If you’d like, run this R file to simplify the dataset down to fewer variables and/or to Pennsylvania only or Allegheny County only.
  6. Starting on Page 9 of the .pdf (36164-0001-Codebook.pdf) are descriptions of the variables. Starting on Page 311 is the survey that they sent to police departments in order to collect the information. Helps clarify some of the variables.
  7. Go for it! Open the file in Excel, R, Python, Tableau, Google Charts, or some other cool thing I forgot to list and start looking around. Talk with people around you. There are some questions listed below to get you started.
  8. This step is important: Share what you’re doing! Join this hackpad page to share any interesting variables, or your findings, or to add questions that can help guide others analysis.
Sample questions for the LEMAS dataset:
  • For any of these questions — are there trends between departments that do or do not utilize certain methods, or policies?
  • How many officers per jurisdiction population do different departments have?
  • Which departments allow officers to work outside the department in a law-enforcement capacity [PAY_OUT & PAY_RST_NO variables]?
  • Which departments have community-oriented policing strategies [COM_MIS variable]?
  • Which departments have cameras on officers [TECH_TYP_VPAT variable]?
  • What departments are analyzing their data [TECH_WHO_STAFF & TECH_WHO_EXTR variables], and who is analyzing it [subsequent variables]
  • Which departments are opening summary data to the public [TECH_WEB_JUR through TECH_WEB_OTHR]?
  • How many dogs per police officer, or per population, in each department [in 2007 version of survey]? 

PS. If you want some tips on using Tableau to visualize data, this tutorial from a former SUDSer can get you started. The video starts with pulling data from a public API, which we’re not doing here, you’ll have to bring the data in manually, but after that follow along.

PPS. If you tweet / insta / etc… #SUDSWorkNight

SUDS Summer Spotlight

Hard to believe there’s only one month left of summer… Curious where in the world it’s taken SUDS members? Read below to find out a few of cool things our crew has been up to:

Krista Kinnard, MS Public Policy & Management-Data Analytics, 2017
Krista Kinnard
1) Where are you working/researching/interning?
LMI, Washington D.C.

2) What does your work station look like? (e.g. Google pod, classic cubicle, etc)
Traditional cube with many “team rooms” available for collaboration and brainstorming.

3) How would you describe your main responsibilities/projects in two sentences (or one long one, with lots of commas)?
I work predominantly with insurance provider compliance with Affordable Care Act regulations. We receive data from all insurance providers on the exchanges (both federal and state) and evaluate them to ensure they are providing adequate coverage to individuals seeking health insurance through One interesting project I am working on is using Python (mostly the Pandas library) to weed through all of the individual physicians listed on the exchange through these insurance providers and identifying the languages they speak in their practices. Eventually, I will be creating a map of these languages and organizing the data in such a way that it can be included in a larger database for individuals choosing insurance plans on the exchange to be able to access physicians in their insurance network that speak their language.

4) What’s one insight about data/policy you’ve gained from your work so far?​
You can spend your entire life cleaning data

5) What’s your favorite summer after-work activity?
Exploring D.C.!

Lauren Renaud, MS Public Policy & Management-Data Analytics, 2017
Lauren Post
1) Where are you working/researching/interning?
Larimer Consensus Group in the Larimer neighborhood of Pittsburgh, just past East Liberty

2) What does your work station look like? (e.g. Google pod, classic cubicle, etc)
We’re located in the ECCO Center, a green building on Larimer Ave. The main room when you walk in has a long desk running around the edge of the room. I sit there with my laptop.

3) How would you describe your main responsibilities/projects in two sentences (or one long one, with lots of commas)?
Building maps, web tools, and analysis that will inform smart growth development and a single family housing strategy.

4) What’s one insight about data/policy you’ve gained from your work so far?
You learn so much more by having to do it every day. I’ve been jumping between ArcGIS, CartoDB, and R to clean and visualize our data. There’s not necessarily one “best” tool for the job, just use what you know and figure it out as you go.

5) What’s your favorite summer after-work activity?
Exploring Pittsburgh in the summer by bike

Justin Cole, MS Public Policy & Management-Data Analytics, 2017
1) Where are you working/researching/interning?
MetroLab Network; Washington, DC

2) What does your work station look like? (e.g. Google pod, classic cubicle, etc)
Most of the time a windowless office, but occasionally the eclectic confines of one of DC’s great coffee shops.

3) How would you describe your main responsibilities/projects in two sentences (or one long one, with lots of commas)?
I’m working with representatives from government, philanthropy, and higher education to develop strategies for long-term funding and programming of a smart cities network. The network is committed to an RD&D model to partner research and development from universities with rapid deployment in metro areas to solve some of the nation’s biggest urban challenges.

4) What’s one insight about data/policy you’ve gained from your work so far?
It’s difficult for cities to be the first to try a new data-driven approach or adopt a new policy that changes the way things have already been done; yet there’s an incredible network of public leaders out there working to share best practices and help all cities push new ideas forward.

5) What’s your favorite summer after-work activity?
Going for a run on the National Mall (even with the heat and humidity of DC’s swampy summers).


Want to share your summer experience? Answer the questions above and email us!

Update: Additions to Police Department Map

Screen Shot 2016-07-19 at 19.20.02
This article was written as part of SUDS’ partnership with the
Alliance for Police Accountability.

We have updated our post on Allegheny County’s police departments to correct a number of omissions. We’ve made the color scheme simpler so the map is easier to read. And it looks like we touched on a hot issue.

The broader conversation

In our previous post, we highlighted the overlap between departments. We didn’t mention the size of each department. However, several people are talking about the number of small police departments in the US.

In an interview for Heinz blog, CMU’s own Professor Daniel Nagin said that:

“Part of the issue with training is that, in the United States, there are over 18,000 police departments, and most of them are very small. And when you have these little police departments, the capacity to properly train the police officers and establish a culture of accountability is really limited. So I think there’s an important need to consolidate the number of police departments that exist nationwide, for a variety of reasons.”

At The Conversation, Paul Hirschfield discusses how “localism” distinguishes American from European police:

“Each of America’s 15,500 municipal and county departments is responsible for screening applicants, imposing discipline and training officers when a new weapon like Tasers are adopted. Some underresourced departments may perform some of these critical tasks poorly.

“To make matters worse, cash-strapped local governments like Ferguson, Missouri’s may see tickets, fines, impounding fees and asset forfeitures as revenue sources and push for more involuntary police encounters.”

On Meet the Press, Chuck Todd interviewed former Philadelphia Police Commissioner Charles Ramsey. When Todd asked, “…frankly, we’ve seen a lot of these negative interactions between police and African Americans have actually taken place in smaller, suburban departments. Is there a discrepancy between training [sic]?”, Ramsey replied:

“Well, I mean, you raise a great issue. There are approximately 18,000 departments in the United States. In my opinion, far too many. And we need to look at a long-term goal. More regionalization, better training, more consistency in policy and procedures.

“In your larger cities, where you have a lot of diversity, obviously you have officers that are very accustomed to dealing with a variety of people. We still have parts in our country where that’s not the case. We need to bring people together, but we need more consistency in terms of the training that’s provided, the selection and hiring of individuals. All those kinds of things need to happen. But in my opinion, we have too many police departments. I would try to cut the number in half, maybe by, in the next ten years or so. Because you are always going to have these kinds of issues as long as you have this many departments with different policies, procedures, training and the like.”

At The Daily Beast, Lauren Caroll and Jon Greenburg discuss Ramsey’s argument: Could a cut in the number of police departments reduce police killings?

So how do we cut the number of departments? In Allegheny County, we have two models for reducing municipal police departments: (i) closing a department and contracting out police work to another municipality, or (ii) merging existing departments to create joint ones.

Seventeen municipalities don’t have their own police force, like Dravosburg Borough, in which policing is “contracted out to the McKeesport Police Department”. Both joint and contractor departments have advantages over smaller departments. Information is automatically shared between the municipalities, training and hiring practices are standardized, and larger departments can provide specialized services.

Northern Regional Police Department is the only merged police department in Allegheny County. It is a collaboration between Bradford Woods Borough, Pine Township, Marshall Township and Richland Township; all four municipalities have a say in how the department is run. Joint departments some additional advantage over contractors. The people policing each municipality are more likely to be locals, and residents are likely to have more say in how the departments are run.

However, we (the authors) don’t know as much about non-municipal police departments, such as the Port Authority Police, CMU Police or UPMC police. Given the recent shooting by PAT Officer O’Malley, it seems likely that the problems of small departments and inconsistent training can also exist in transit, school and private police departments. We have a new open question: do these types of organizations ever get rid of their police, and go back to relying on civic police departments?

Updates, additions and answers to questions

Thank you to Eat That Read This for highlighting our original blog post, and to the Alliance for Police Accountability and WPRDC for tweeting it. We received helpful feedback as a result of the increased attention:

  • Thank you to Mx Daria Phoebe for pointing out that Norfolk Southern rail police are accredited, and sending us an overview of rail policing. We have added the Norfolk Southern department to the map.
  • Thank you to JI Swiderski for pointing us to a complete list of municipal police departments, and answering our question about the Northern Regional Police Department. We’ve added forty municipal police departments to the map, including Northern Regional. For the seventeen municipalities that contract out their police services, we have added who they contract out to. 

We also discovered a new department ourselves:

Future directions

We presented the map at the Alliance for Police Accountability’s last community meeting, and got several suggestions on other things that we could map out, including:

  • The demographic makeup of police departments vs. makeup of the communities they serve. The community data is available through the US Census, and the Pittsburgh Police provide annual reports with data on their demographic makeup. We will need to contact the other police departments to learn their demographic makeup.
  • Map out all incidents investigated by Pittsburgh’s Citizens’ Police Review Board, and investigate whether there is a “chilling effect”, i.e. a decrease in calls to police in nearby areas after the incident.

The list of police departments was low-hanging fruit, because all the information was already online. These questions will take longer to answer because we will have to gather more data.

If you have relevant data, or more suggestions for things we could investigate, we would like to hear from you. You can comment here or contact us at and

Lauren Renaud is a masters student in Data Analytics and Public Policy at CMU.
Lizzie Silver is a PhD student in Logic, Computation and Methodology and a masters student in Machine Learning at CMU.
In their spare time they participate in Students for Urban Data Systems at CMU, and do research for the Alliance for Police Accountability.

The Overlapping Police Departments of Allegheny County

By Lizzie Silver and Lauren Renaud


This article was written as part of SUDS’ partnership with the Alliance for Police Accountability.

“Did you know that there are over one hundred police departments in Allegheny County alone?” Prof David Harris offered this factoid at the panel discussion following the April 12 screening of Peace Officer. It sat at the back of our minds until finals were over and we started looking for a new mapping project. Spoiler alert: we were ‘only’ able to count 85 departments. [Update: we’re up to 127 departments. Details here.]

Recently, two adverse interactions between the police and the public involved officers from at least two departments: the Port Authority (PAT) Police and the City of Pittsburgh Police. The first incident involved fighting between youths and police officers at the T station downtown. In the second incident, PAT Police Officer Brian O’Malley shot and killed Bruce Kelly Jr, raising questions about PAT police policies. As Tony Norman writes, “Why the disparity in response between the officers? Why did only two of [at least eight officers] fire if Mr. Kelley was so dangerous?”

Police departments work together to solve problems when their jurisdictions overlap. Officers from different departments must coordinate with each other in high-pressure, high-stakes situations. Different departments sometimes have different training or different policies, so the way they interact with the public can vary. After the Peace Officer screening, Pittsburgh Chief of Police Cameron McLay mentioned that training on implicit bias will be available to City of Pittsburgh officers in the near future. However, that training will not be available to Port Authority officers, and officers from many other departments that have jurisdiction within the City of Pittsburgh.

Furthermore, the laws that govern Pittsburgh only apply within city limits. Recently Pittsburgh decriminalized possession of less than 30 grams of marijuana. So if you are walking down S Braddock Ave between Biddle and Whitney, smoking a blunt, the local police can only fine you $100. But walk past Overton St, and suddenly you’re committing a criminal offense that could cost you $5000, land you in prison for 30 days, and give you a criminal record, because Swissvale is outside city limits.

Even if the law is the same in different areas, the “unwritten rules” can differ. As Ryan Deto writes for the Pittsburgh City Paper:

“Mount Lebanon police cited Esquivel-Hernandez on March 26 for driving without a valid license and without insurance. He paid his fine on April 21, and according to his U.S. District Court case, he was identified as undocumented on April 25. Mount Lebanon police have not returned multiple calls requesting comment about its communication policy with ICE.
Since 2014, Pittsburgh Police have had an unwritten policy not to initiate communication with ICE about undocumented immigrants. The department will comply if ICE initiates contact. However, there is no indication that other smaller police forces in Allegheny County have adopted similar policies.”

Different police departments are also held accountable by different bodies. For example, the Citizens’ Police Review Board (CPRB) can investigate complaints against the the City of Pittsburgh police department, but the Port Authority Police do not answer to the CPRB, only to the District Attorney. DA Stephen Zappala exonerated Officers O’Malley and Rivotti for shooting Mr Bruce Kelly Jr, a questionable but unsurprising result, given how rarely police officers face charges for shooting citizens.

[Update: see also our post about the problems of small police departments.]

We thought it’d be helpful for the public to know where the different police departments’ jurisdictions are located. This may help if:

  1. You are wondering which police departments you are likely to interact with in a given area;
  2. You need to contact the police, and are wondering which department to call; or
  3. You have had an interaction with police officers, but you are not sure which department they were from.

We welcome feedback and additional information. We hope this map helps inform citizens about the different departments that serve them, and helps to start a conversation about standardizing training and policies for officers from different departments.

The Map

[Note: This updated version has more police departments included and a better color scheme. Our original, less complete version can still be accessed here.],40.2634,-79.6448,40.6323

  • Larger version of this map here
  • To see the number of overlapping jurisdictions in any given area, see this map with semi-transparent overlays here.
  • To see both, with the “spyglass” feature for more detail, see this map here.

[Old versions available here, here and here.]

The Departments

Municipal Police

There are 130 municipalities within Allegheny County, of which 70 have their own police department. We matched the county’s list of police departments to a list of municipality borders from the county’s GIS department.

One municipal police department could not be matched by name: the Northern Region Police Dept in Gibsonia, PA. It may be a joint department covering multiple municipalities.

We’ve assumed that the other municipal police departments only cover the areas they are named after. However, some municipalities have joint agreements so that a single department will patrol two municipalities. For example, North Versailles police currently patrol Wilmerding (although from 2017 onward that duty will fall to Allegheny County police). We are not aware of most of these agreements, so we can’t put them on the map. If you have more information about these agreements, please email us at our contacts below.

[Update: Thanks to feedback from JI Swiderski, we have corrected this layer of the map. Allegheny County has 130 municipalities, of which 109 have their own police department, 4 share the Northern Region joint police department, 15 contract their police services out to a nearby municipality, and 2 contract out to state police. Allegheny County’s list of police departments includes information on these contracts. We matched that list to the list of municipality borders from the county’s GIS department, so the updated map shows which PD has jurisdiction in every municipality. More details we’ve updated here.]

County Police

The Allegheny County Police Department’s jurisdiction includes ‘county-owned property’, as well as ‘Pittsburgh International Airport, the County Airport, nine County Parks and other regional parks’. We weren’t sure which ‘other regional parks’ were included, so we only mapped out the county parks. We have marked all county buildings with a spot that extends 250 feet from the center of the building. We got the building locations and the park shapefiles from from the county’s GIS website.

The Allegheny County Police might also patrol municipalities that don’t have their own police departments, but we weren’t sure which ones (if any), so we have not included any on the map.

The Allegheny County Sheriff’s Office also has jurisdiction in Allegheny County, but we weren’t sure what areas it extends to, or whether they do any patrolling, so we have not included them on the map.

Federal and State Police

The federal US Marshalls (Western District PA) has jurisdiction throughout Allegheny County, as do the Pennsylvania State Police

[Update: The PA Fish and Boat Commission polices the rivers.]

Transit Police

The Port Authority (PAT) Police have jurisdiction over PAT routes and nearby areas. We have marked the PAT routes with a line that extends 1/10 of a mile (528 feet) around the route. We think this is a conservative estimate of how far the PAT jurisdiction extends. However, if we widened the buffer much further — say, to 1000 feet — the PAT jurisdiction looked like it blanketed the entire city of Pittsburgh. We got the shapefiles from the City’s GIS website.

Amtrak police have jurisdiction over Amtrak routes and nearby areas. We have marked the Amtrak routes with a line that extends 1/10 of a mile (528 feet) around the route. We got the shapefiles from ArcGIS.

[Update: Thanks to Mx Daria Phoebe for pointing out that Norfolk Southern rail police are also accredited.]

School Police

Most of the universities in Pittsburgh have their own police. Their jurisdictions extend across the college campuses, to student dorms, and nearby areas. For example, Carnegie Mellon University Police’s “primary patrol zone… includes all campus property, Off Campus Housing & Sites, and residential areas immediately in the vicinity of the CMU Main Campus.” We do not have shapefiles for the college campuses, so instead of tracing the shape of each campus, we’ve just put big circles on the map (centered on each campus, with a radius of half a mile). There is one circle, half mile radius each for:

We left the Community College of Allegheny County (CCAC) off the map. Each of their campuses has “a Director of Safety and Security who is also a sworn police officer”, but we felt that one officer per campus was too few to count as a “department” for the purposes of this map.

Hospital Police

UPMC employs police. St Clair Hospital Police “will issue citations to those who violate parking and traffic regulations”. Neither hospital has a webpage describing their police departments; they may simply employ police officers alongside security officers. However their police have arrest powers and are employed by the hospital so we put them on the map. We assume that their jurisdictions cover the hospital complexes. We have put circles on the map for each UPMC building complex and for St Clair Hospital. We weren’t sure how large to make the circles, so we put circles with radius of both 250 feet and 500 feet around the center of the buildings; you can turn one overlay off if you prefer.

Humane Society Police

Humane Society Police Officers enforce animal cruelty laws. They are appointed per county so their jurisdiction covers the whole of Allegheny County. There are a number of Humane Society Police Officers serving Allegheny County.

Assumptions and Open Questions

We’ve tried to be conservative in our estimates of where the departments’ jurisdictions extend to, but we may have made some mistakes. We also have some open questions, such as:

  • What kind of authority, if any, do Block Watch Groups have?
  • Do some correctional facilities have their own police? Do corrections officers have arrest powers in PA?
  • Does the Allegheny County Police Department only have jurisdiction over buildings that house county departments and services, or all county-owned buildings?
  • Should the Allegheny County Sheriff’s Office count as another department? If so, what is its jurisdiction?
  • Do UPMC Police cover all UPMC hospitals, or only certain ones? What sort of authority do they have?
  • Which police department(s) have jurisdiction over the municipalities that do not have their own police force? We believe it may be the County Police or that some departments that are listed as a specific municipality may also cover their neighboring towns, but we need more clarification on this.

This map may not be complete. If you know about another police department within Allegheny County, please send us a link to the police department’s webpage, or let us know who we can contact to confirm the department’s existence. Also, if we have made a mistake, please let us know so we can correct it. You can contact us at and

Lauren Renaud is a masters student in Data Analytics and Public Policy at CMU.
Lizzie Silver is a PhD student in Logic, Computation and Methodology and a masters student in Machine Learning at CMU.
In their spare time they participate in Students for Urban Data Systems at CMU, and do research for the Alliance for Police Accountability.