Choose one of David Robinson’s tidytuesday screencasts, watch the video, and summarise. https://www.youtube.com/channel/UCeiiqmVK07qhY-wvg3IZiZQ
You must follow the instructions below to get credits for this assignment.
The title of this screencast is “Analyzing Volcano Eruptions in R”.
This video was published on May 12, 2020.
Hint: What’s the source of the data; what does the row represent; how many observations?; what are the variables; and what do they mean?
The source of the data comes from data and studies from NASA, UCAR, and the Smithsonian and resides in GitHub as a TidyTuesday dataset. The row represents volcanoes and there are 238 observations. There are 130 variables. The variables place points plotted differently and cannot be found and have a context that I could not find.
Hint: For example, importing data, understanding the data, data exploration, etc.
Dave approached the analysis in a very smart and effective way. He began by importing the data from github tidytuesday forum. His next step was by going through the observations and data to make sense of it all. He then proceeded to make a histogram of the data which he then studied for a while. He began adding more variables from the data to the histogram to add more context and sense to the histogram. He then uses one of the variables that is the location of an eruption to plot on the map of the world each volcanic eruption in its respective location. He then many other variables to this map including the type of volcano it was while color coding it on the plot with a legend for this chart/map. He proceeds to make a number of other histograms for other observations and variables of the many datasets in this package. He then creates a leaflet map of the world that shows each of histories recorded volcanoes and how dangerous they are is indicated by a color scale of blue-least dangerous to red-most dangerous. Upon hovering the mouse over each colored dot on the map, a bubble pops up containing all pieces of information on the volcano including the population within a 5 km radius, name of volcano, tectonic setting, etc.
I saw a method of data representation and imagery that I learned in class. This was David’s use of the histogram. He used the histogram in several different instances throughout the course of the screencast. I really like ggplot functions such as the histogram because it helps me visualize the data. He used the histogram for many different reasons throughout the course of the video that broke down the data in a way that he customized. This made it easy to interpret the data of the volcanoes.
One major finding from the analysis was that the most dangerous volcanoes were in areas encircled by Eastern Africa, Europe, and the area just above Australia. Another major finding from the analysis is the date of the last eruption for each volcano as well as a general idea for the predictions of the next eruption.
There were many things that I really liked about this analysis. However, my favorite aspect was the leaflet map in which David created a map of the world that showed each volcano ever documented and was interactive. It was interactive in the sense that you could hover over any volcano and it would give you all the desired data on each one. This was especially cool because of the color scale of blue-least dangerous to red-most dangerous. Upon hovering the mouse over each colored dot on the map, a bubble pops up containing all pieces of information on the volcano like the population within a 5 km radius, name of volcano and tectonic setting.