Work Description

Title: Statistics and Visualization of Point-Patterns Open Access Deposited

Attribute Value
  • The data was collected on the website Tornado History Project. The data is loaded into the program and visualized using Python heatmap.
  • Many data sets come as point patterns of the form (longitude, latitude, time, magnitude). The examples of data sets in this format includes tornado events, origins/destination of internet flows, earthquakes, terrorist attacks and etc. It is difficult to visualize the data with simple plotting. This research project studies and implements non-parametric kernel smoothing in Python as a way of visualizing the intensity of point patterns in space and time. A two-dimensional grid M with size mx, my is used to store the calculation result for the kernel smoothing of each grid points. The heat-map in Python then uses the grid to plot the resulting images on a map where the resolution is determined by mx and my. The resulting images also depend on a spatial and a temporal smoothing parameters, which control the resolution (smoothness) of the figure. The Python code is applied to visualize over 56,000 tornado landings in the continental U.S. from the period 1950 - 2014. The magnitudes of the tornado are based on Fujita scale.
Contact information
Resource type
Last modified
  • 02/24/2020
  • 04/24/2016
To Cite this Work:
Stoev, S., Hu, W. (2016). Statistics and Visualization of Point-Patterns [Data set], University of Michigan - Deep Blue Data.


This work is not a member of any user collections.

Files (Count: 4; Size: 2.75 MB)

The dataset in "tornado_complete.txt" file is free for download on this website:

The data are arranged in the following format with white spaces in between:

TouchdownLong(degree) TouchdownLat(degree) Fraction_of_year(unitless) Fujita_Scale(F)

To run the program, download both the source code as well as "tornado_complete.txt" file to the same directory. Run the program and enters number of pixels you want in both x and y directions for resolution, as well as bandwidth of time.

Download All Files (To download individual files, select them in the “Files” panel above)

Best for data sets < 3 GB. Downloads all files plus metadata into a zip file.

Best for data sets > 3 GB. Globus is the platform Deep Blue Data uses to make large data sets available.   More about Globus

Remediation of Harmful Language

The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.