Assignment Objective...
You will use the skills you have learned in R to dive into some large, weather data sets. The goal of this assignment is to create the required graphics to answer the various posed questions. Note: We'll also include some of the concepts about communicating your message from Lesson 2.
Let's get started.
Download the data...
Here is the file containing the weather data that you will need. It is a comma-delimited file containing temperature and precipitation data at O'Hare International Airport from 1 January 1976 to 31 December 2016 (40 years). Assume for the moment that the data is accurate and that no changes to the site have occurred that would affect the record. We'll learn in the next lesson how to make such determinations, but let's not complicate things at this point. WARNING! Editing this file in Excel will change the date formats (just be aware of that).
Deliverables...
Please use R to create graphics that answer the following questions regarding the data. You can build on the pieces of code that I provided in the lesson, but know that I have intentionally left a few challenges in your way that you are going to have to overcome (as does working with any new data set). You are welcome to convey the answers to the questions in any manner you wish, however, you are expected to have a clear resultant message for each problem you are asked to examine. (Correct graphics, correctly formatted, are a critical requirement.)
Each question should contain the following components:
Question and Answer Summary – Start each section of your report with the question you are trying to answer and your key message (no more than a paragraph) of what the data tell you. All of the questions here are simply asking you to present what the data say, without any deeper meteorological analysis or editorial. This, of course, is not what would happen in the real world, but visualizing the data is a key first step in any analysis procedure. If you are a statistics whiz, please refrain from providing calculation more complex than an "average" or "sum".
Graphic(s) – You may provide no more than two graphics for each question. Your client is busy and doesn't want to be bored to death with a stream of endless graphs. Please make sure that each graph is appropriate for your message and contains all of the things that good graphs should have (titles, labels, legends, etc.). You are not limited to only the look and feel of the graphs that I have presented in this lesson. Indeed, you may (and are encouraged to) experiment with different looks and ways of presenting the information as well. However, don't worry if such exploration is beyond your coding abilities. Most often, a simple approach is best to convey the proper message.
Reasoning – Provide the reasoning as to why you chose to present the data in a certain way. Why did you use a line graph instead of a bar graph? Why did you choose a histogram instead of a scatter plot? This section is key. It is meant to show me how you thought about your approach. You would never get into this much detail with a client, but you might have to argue such reasoning to members of your team.
R-Code – Finally, provide the code that produced the graphic(s) in each question. As I have stated earlier, I am not grading your code, per se. However, I would like to be able to provide feedback on your approach. Please make sure that your code is nicely formatted and has enough comments so that I can understand what you did.
Questions...
- Over the course of the year, what is the "normal" climate (normal max temperature, normal min temperature, and precipitation) like in Chicago? As a point of suggestion, check out this page from the NWS illustrating how precipitation with respect to normal is plotted. I'm not saying that you have to do it this way (if you feel there's a better way), but I wanted you to see some examples.
- The normal mean temperature for a particular day is usually based on the past 30 years of the record. But how "normal" is normal? Focus on the normal mean temperature at different months of the year. How "good" (in a qualitative sense) is the "normal" temperature at describing what you might observe? For what month(s) is the normal temperature a good measure of what to expect? What month(s) is the worst?
- The meteorological winter (Dec, Jan, Feb) of 2014-2015 seemed awfully cold... was it?
- The Chicago Heatwave of 1995 is fairly notable in its severity (Wikipedia article) and in its "estimated" death toll. My grandparents lived just outside Chicago and I know that summers there can be hot! But, just how remarkable was this string of temperatures from 12 July to 16 July 1995 compared to other hot summer periods (not necessarily those exact days, but rather a "hot" string of days)?
- They call Chicago the "Windy City". Is this true? Is it windier in Chicago than in, say, Kansas City, Kansas (yes, no, sometimes)? Note that the original data set doesn't have wind. No problem. Here are 10-year records for O'Hare International and Kansas City International. These files are straight out of the ISD Database so you might need to do some tweaking of
read.csv(...)to get them read in. Please use this library along with "openair" to discuss this question. For this question alone, I am suspending my 2-graphic limit (you may need a few here, but don't go crazy)!
The Fine Print...
- Please submit your report in either MSWord or PDF format.
- Saving images: R-Studio makes saving graphs a piece of cake. Notice that at the top of the plot window there is an "Export" pull-down where "Save as Image" is an option. When you choose "Save as image" you are given a dialog box where you can set the type (PNG is best), location, and filename of your image. I would set aside a folder for this assignment where you can save your images and then paste them into your word-processing document.
- Unlike your last assignment, please just paste all of your images in-line. I envision one page for each question with all of the required parts with the exception of the R-code perhaps.
- Proofreading is a must. It shows professionalism and care for your work. This includes not only basic spelling and grammar, but readability as well. If you struggle with proofreading, have someone give your draft a once-over and provide suggestions.
- Grading: I want to foster an environment where you can focus more on what you are learning that what "grade" you are getting. However, that said, I have to give some sort of grade and feedback for each assignment. Please see my assignment grading rubric in the Orientation section for general guidelines on assignment grades.