Geospacial Analysis of Chicago's Neighborhoods

In the previous post we explored the concept of socioeconomic hardship in Chicago neighborhoods. To better understand this attribute city-wide, I created the below visual using a City of Chicago geospatial data file outlining each neighborhood's boundaries. For anyone in my extensive readership who did not study the previous post, the City of Chicago data portal shared a data set with socioeconomic indicators for each of the city's 77 neighborhoods. These indicators (unemployment rate, poverty rate,  per capita income, etc) are further distilled into a hardship index 1-100. The below image helps outline which areas of the city are most affected by these factors.

It warrants mentioning that these indicators were collected between 2008-2012. Communities evolve for better or for worse overtime, so much may have changed in the past seven years. Also, some neighborhoods may be missing, but the visualization should still demonstrate the city's geographic socioeconomic breakdown.

Focusing in on one specific factor for these neighborhoods, we can see how per capita income is distributed geographical throughout the city. The color scheme is intentionally centered around $39765, what reported as the Nation's average per capita personal income in 2012.

Only 9 of the 66 neighborhoods included in the analysis fall above this average figure threshold. All of which would be considered low economic hardship as well, but this correlation most likely comes at no surprise.

Another source of information from the City of Chicago data portal is a history of recorded crimes within the city from 2001 to 2019. This set assigns latitude and longitude coordinates to each crime, which can be used to geolocate into their respective specific neighborhoods. The color legend had to be truncated due to two extreme outliers- Loop, the city's most densely populated neighborhood, with 8,864 recorded crimes, and Austin with 12,325.

These crimes can also be grouped by type. For example, below we have burglary counts by neighborhood.

 Furthermore, in this dataset, there is a boolean attribute determining if an arrest was made for this crime or not. I used this field to calculate the rate of arrests per crime for each neighborhood.

The neighborhood with the lowest arrest rate is Lincoln Park at 7.57%. This is roughly one fifth the rate in North Lawndale of 38.93%. This blog is intended for analysis and data discovery, not social commentary. That being said, we will not weigh into the potential underlying causes and impacts of this discrepancy. Here is that same data in the familiar map format.

Thanks as always for reading.


Popular posts from this blog

Using a Neural Network to Predict Pneumonia From X-Ray Images

Using a Neural Network to Classify Lego Figures

Artwork Locator