Blog posts – Conor Tompkins

What region is Pittsburgh in?

Or, unsupervised demography with spatially constrained clustering

“What region is Pittsburgh in?” is a question that comes up frequently around here. Is it in Appalachia? The Midwest? Great Lakes? Mid-Atlantic? It really depends on who you…

C&S Presentation: Time Series Forecasting

This material was presented at Code & Supply on 2024-11-07

Forecasting potholes with exogenous variables

In this post I will extend the modelling approach from the previous post with exogenous variables (variables not directly about the quantity being measured in the time…

Forecasting Pittsburgh Potholes with {fable}

Potholes are the bane of Pittsburgh drivers’ existence. You can either weave around the minefield of holes in the road (some of alarming size) or risk damage to your vehicle.…

Suburbanization of Allegheny County

Allegheny County

This March, researchers at the University of Georgia and Florida State University released the HHUUD10 dataset, which contains estimates of the number of housing units for…

Making a Venn diagram in Shiny

Shiny

This blog post is about making Venn diagrams work in Shiny, and the issues I ran into with shiny::nearPoints(). I show how this impacted my initial approach, and discuss the…

Effect of Geographic Resolution on ebirdst Abundance

R

eBird

While exploring some of the citizen science bird observation data available through ebirdst, I was confused by how to understand the calculation of ebirdst’s abundance metric.

COVID-19 vaccine forecast and pastcasts

Like many other Americans, I have been following the COVID-19 vaccination campaign closely. I have found the graphs and data on the NYTimes and Bloomberg sites very useful…

Pittsburgh Riverhounds under Coach Lilley

I have been a season-ticket holder with the Pittsburgh Riverhounds for a couple seasons now. The stadium has a great fan experience, and the team has gotten a lot better…

Driving Alone vs. Public Transportation in Pittsburgh

Mapping commuter modes with bivariate discretized bins

The clash between public transportation and single passenger vehicles is a heated topic of discussion nationally and in the Pittsburgh area. Public transit ridership has…

House Price Estimator Dashboard

Click here to view the full dashboard

Bike rental access in Pittsburgh

R

Pittsburgh

Healthy Ride

WPRDC

This is an interactive Leaflet map of Healthy Ride access in Pittsburgh. It counts how many Healthy Ride stations are within a 10 minute bike ride of a given location. This…

Shifting political winds

Or, drawing arrows on maps

R

Politics

The purpose of this post is to recreate the “Shift from 2016” arrow map that the New York Times used to show which counties became more Democratic or Republican-leaning from…

Analyzing major commuter routes in Allegheny County

R

Allegheny County

Commuters

Census

Mapbox

In this post I will use the Mapbox API to calculate metrics for major commuter routes in Allegheny County. The API will provide the distance and duration of the trip, as…

Graphing volatile home values in U.S. metro areas

Housing

Zillow

Zillow publishes a variety of cool data that I haven’t explored much yet. The first dataset that caught my eye was the Zillow Home Value Index (ZHVI). Zillow describes it as…

Effect of COVID-19 on Pittsburgh parking transactions

Pittsburgh

Parking

COVID-19

The COVID-19 pandemic’s affect on commerce and mobility habits is well documented. For example, Apple publishes Mobility Trends reports about utilization of various…

Mapping BosWash commuter patterns with Flowmap.blue

Census

Commuters

This map shows the commuter patterns in the Northeast Megalopolis/Acela Corridor/BosWash metro area. I pulled the data from the Census Longitudinal Employer-Household…

Pittsburgh City Boundary Model Leaflet Map

R

Pittsburgh

Allegheny County

Last Friday I posted a classification model that attempted to identify which census tracts in Allegheny County fall within the border of the City of Pittsburgh. I used a…

Modeling the Pittsburgh City Boundary

My goal is to create a classification model that can distinguish between census tracts that are inside the city or outside the City of Pittsburgh. The border is interrupted…

Comparing Healthy Ride Usage Pre And “Post” COVID-19

Would be interested to see this @healthyridepgh data to compare pre-covid (2019) and during (2020)

Time series clustering COVID-19 case data

Interactive Tableau visualization of the clusters

Working with Paycheck Protection Program data in R

R

Politics

In this post, I walk through the process of reading in the data from the Paycheck Protection Program, and show some basic analyses that can be done.

Graphing Allegheny County COVID-19 data

R

COVID-19

In this post, I review the process I use to make daily graphs from data published by the Allegheny County Health Department. I use the data posted by Franklin Chen, who…

(re)Modeling the Office

R

The goal for this analysis is to determine which characters, directors, and writers from The Office most influence an episode’s IMDB rating. My hypothesis is that IMDB…

Cleaning Creatively Formatted US Census Bureau Migration Data

R

I recently ran across the U.S. Census Bureau page for state-to-state migration flows. There’s a lot of interesting analyses that can be done with a dataset like this.…

Clustering Bird Species with Seasonality

R

In this post, I use k-means clustering to identify clusters of bird species based on frequency of observations per month. I use bird sightings in Allegheny County from eBird.

Cumulative eBird Sightings in Allegheny County

R

This will be a quick post on cumulative bird observations in Allegheny County. Cumulative graphs show overall trends, seasonality, and quirks in how the data was recorded.…

eBirding in Allegheny County

R

In this post I will do some exploratory analysis on eBird data. I’ve picked up birdwatching as a hobby during quarantine, and eBird has a ton of cool data on bird sightings.

Roughly Calculating Allegheny County Transit Efficiency

R

WPRDC

Allegheny County

Transit

As part my work on transit lines in Allegheny County, I am interested in which transit lines are most efficient, in terms of residents and jobs served. This is possible with…

Graphing Seasonality in Ebird Bird Sightings

R

eBird

Over the winter I became interested in birding. Sitting in your back yard doing nothing but watching birds fly around is quite relaxing. Naturally I am looking for ways to…

Visualizing Transit Connections Between Pittsburgh Census Tracts

R

Pittsburgh

Allegheny County

Transit

WPRDC

In this post I will use transit line and stop data from the WPRDC to map connections between census tracts. I access the census data via {tidycensus}, which contains…

How Many Pittsburghers Cross the River to Get to Work

R

Pittsburgh

Allegheny County

Census

WPRDC

This post focuses on how many rivers Pittsburghers cross to get to work. I use the U.S. Census Bureau LEHD Origin-Destination Employment Statistics (LODES) dataset to draw…

Analyzing Commuter Patterns in Allegheny County

R

Pittsburgh

Allegheny County

Commuters

Note: high-res images of the main graphs from this post are available here, here, here, and here.

Forecasting Healthy Ride Ridership With Prophet

R

Pittsburgh

Healthy Ride

This post is about predicting demand for the Healthy Ride bike system in Pittsburgh. I wanted to try out Facebook’s prophet package and try to do some time series forecasting.

Residential Zoning in Pittsburgh

R

Pittsburgh

The New York Times recently published an article about zoning in U.S. cities, particularly single-unit detached residential housing. The article did not include Pittsburgh…

Map Census Data With R

R

Potholes

Census

This talk was presented on May 30th, 2019 at Code For Pittsburgh.

Premier League 538 SPI Ratings

R

Pittsburgh

538

Soccer

538’s Soccer Power Index (SPI) rates the quality of soccer teams from a variety of leagues around the world. In this post I’ll use gganimate to animate team SPI over the…

Animating Growth of Allegheny County

R

Allegheny County

WPRDC

Housing

In this post I will show how to create animated graphs that illustrate the increase in buildings in Allegheny County.

Modeling Pittsburgh House Sales Linear

R

Housing

Allegheny County

In this post I will be modeling house (land parcel) sales in Pittsburgh. The data is from the WPRDC’s Parcels n’at dashboard or here.

Actblue Interstate Political Campaign Donations

R

Politics

ActBlue is an online service that allows people to make donations to the political campaigns of Democractic candidates across the country. This post uses graph theory to…

Networking USL Club Similarity With Euclidean Distance

R

Soccer

538

Euclidean distance is a simple way to measure the distance between two points. It can also be used to measure how similar two sports teams are, given a set of variables. In…

Clustering Allegheny County Census Tracts With PCA and k-means

R

Census

Allegheny County

In this post I will use the census API discussed in the last post to cluster the Allegheny County census tracts using PCA and k-means.

USL in the 538 Global Club Soccer Rankings

R

USL

Riverhounds

This post was originally run with data from August 2018. 538 does not provide historical rankings, so I had to rerun the code with June 2023 data when I migrated my blog.

Exploring Allegheny County With Census Data

R

Census

Allegheny County

This post explores Allegheny County and Pennsylvania through census data. I use the tidycensus and sf packages to collect data from the census API and draw maps with the data.

Exploring 311 Data With PCA

Census

Pittsburgh

WPRDC

Principal Component Analysis is an unsupervised method that reduces the number of dimensions in a dataset and highlights where the data varies. We will use PCA to analyze…

Car Crashes in Allegheny County

WPRDC

Allegheny County

WPRDC has published a dataset on car crashes in Allegheny County from 2004-2017. I was interested to see if there were any patterns or interesting trends in the data.

R 311 Pothole Workshop Code for Pittsburgh

WPRDC

Pittsburgh

Potholes

Code for Pittsburgh

This material was presented at Code & Supply in 2018.

Comparing US Senators Casey and Toomey

As a follow-up to my post about how Pittsburgh Mayor Bill Peduto uses Twitter, I thought it would be useful to examine and compare how Pennsylvania’s U.S. senators use…

Mayor Bill Peduto Tweets

Twitter

Pittsburgh

Pittsburgh Mayor Bill Peduto uses Twitter to communicate with his constituents, express his political opinions, and comment about Pittsburgh sports. I will use various R…

Allegheny County Overdose Data

R

Allegheny County

Overdoses

Opiate addiction and overdose have become a major problem in American society. The life expectancy in the U.S. has decreased for the past 2 years, and deaths from drug…

Mapping Healthy Ride Data

Pittsburgh

Healthy Ride

This post is about mapping the Healthy Ride dataset in R.