I started using Foursquare at the end of 2012 and kept with it even after it became the pointless muck that is Swarm. Since I’ve now got 4 years of location history (ie, check-ins) data, I decided to visualize and map it with Python, matplotlib, and basemap. The code is available in this GitHub repo. It’s easy to re-purpose to visualize your own check-in history: you just need to plug in your Foursquare OAuth token then run the notebook.
First the notebook downloads all my check-ins from the Foursquare API. Then I mapped all of them, using matplotlib basemap.
The U.N. world population prospects data set depicts the U.N.’s projections for every country’s population, decade by decade through 2100. The 2015 revision was recently released, and I analyzed, visualized, and mapped the data (methodology and code described below).
The world population is expected to grow from about 7.3 billion people today to 11.2 billion in 2100. While the populations of Eastern Europe, Taiwan, and Japan are projected to decline significantly over the 21st century, the U.N. projects Africa’s population to grow by an incredible 3.2 billion people. This map depicts each country’s projected percentage change in population from 2015 to 2100:
Which U.S. cities are the most expensive for rental housing? Where are rents rising the fastest? The American Community Survey (ACS) recently released its latest batch of 1-year data and I analyzed, mapped, and visualized it. My methodology is below, and my code and data are in this GitHub repo.
This interactive map shows median rents across the U.S. for every metro/micropolitan area. Click any one for details on population, rent, and change over time. Click “switch” to re-draw the map to visualize how median rents have risen since 2010:
I like to do my data wrangling and analysis work in Python, using the pandas library. I also use Python for much of my data visualization and simple mapping. But for interactive web maps, I usually use Leaflet. There isn’t dead-simple way to dump a pandas DataFrame with geographic data to something you can load with Leaflet. You could use GeoPandas to convert your DataFrame then dump it to GeoJSON, but that isn’t a very lightweight solution.
So, I wrote a simple reusable function to export any pandas DataFrame to GeoJSON:
The fall semester begins next week at UC Berkeley. For the third year in a row, Paul Waddell and I will be teaching CP255: Urban Informatics and Visualization.
This masters-level course trains students to analyze urban data, develop indicators, conduct spatial analyses, create data visualizations, and build interactive web maps. To do this, we use the Python programming language, open source analysis and visualization tools, and public data.
This course is designed to provide future city planners with a toolkit of technical skills for quantitative problem solving. We don’t require any prior programming experience – we teach this from the ground up – but we do expect prior knowledge of basic statistics and GIS.
Our teaching materials, including IPython Notebooks, tutorials, and guides are available in this GitHub repo, updated as the semester progresses.
How big is Greenland? It’s huge, right? At 836,109 square miles in size, Greenland is the largest island and the 12th largest country on Earth. With only 56,000 people living in that enormous area (80% of which is covered by the world’s only extant ice sheet outside of Antarctica), it is also the least densely populated country on Earth.
You can get a sense of how large Greenland is when you look at a map of the world:
It’s huge! Greenland is bigger than the entire continent of Africa! Or is it? The map above uses the common Mercator projection to project the 3-D surface of the Earth onto a 2-D surface suitable for a paper map or an image on your computer screen. But it’s not easy to project the curved surface of a sphere onto a rectangular plane. Compromises must be made. In the case of the Mercator projection, the compromise is that objects’ sizes become increasingly distorted the further they are from the equator. At the poles, the scale and distortion become infinite.
Our paper on collecting and analyzing U.S. housing rental markets through Craigslist rental listings has been accepted for publication by the Journal of Planning Education and Research. Check out the article here. This map of rental listings in the contiguous U.S. is divided into quintiles by rent per square foot:
I’ve previously discussed visualizing the GPS location data from my summer travels with CartoDB, Leaflet, and Mapbox + Tilemill. I also visualized different aspects of this data set in Python, using the matplotlib plotting library. However, these spatial scatter plots used unprojected lat-long data which looked pretty distorted at European latitudes.
Today I will show how to convert this data into a projected coordinate reference system and plot it again using matplotlib. These projected maps will provide a much more accurate spatial representation of my spatial data and the geographic region. All of my code is available in this GitHub repo, particularly this notebook.
This guide was updated in June 2016 to reflect changes to the dependencies and the ability to install with Python wheels.
I recently went through the exercise of installing geopandas on Windows and getting it to run. Having learned several valuable lessons, I thought I’d share them with the world in case anyone else is trying to get this toolkit working in a Windows environment (also see this GitHub gist I put together).
It seems that pip installing geopandas works fine on Linux and Mac. However, several of its dependencies have C extensions that cause compilation failures with pip on Windows. This guide gets around that issue. For preliminaries, I have this working on Windows 7, 8, and 10. My Python environments are Anaconda, 64-bit, with both Python 2.7 and 3.5. I’m running geopandas version 0.2 with GDAL 2.0.2, Fiona 1.7.0, pyproj 126.96.36.199, and shapely 1.5.16.
This is a series of posts about visualizing spatial data. I spent a couple of months traveling in Europe this summer and collected GPS location data throughout the trip with the OpenPaths app. I explored different web mapping technologies such as CartoDB, Leaflet, Mapbox, and Tilemill to plot my travels. I also used Python and matplotlib to run some descriptive statistics and visualize other aspects of my trip.
My Python code is available in this GitHub repo. I also did some more involved work under the hood to prep the data and support these visualizations. For example, in the following posts I reverse-geocoded the spatial data set and reduced its size with clustering algorithms and the Douglas-Peucker algorithm: