Name:
Andrew ID:
Collaborated with:
On this homework, you can collaborate with your classmates, but you must identify their names above, and you must submit your own homework as an knitted HTML file on Canvas, by Sunday 10pm, this week.
Important note: this assignment is to be completed using base R graphics. That means, e.g., no ggplot commands are allowed!
Below we read in a data set, as in lab, of the 2988 fastest times recorded for the 100m sprint, in men’s track, and the fastest 2137 fastest times recorded for the 100m, in women’s track. Both of these data sets were scraped from http://www.alltime-athletics.com/m_100ok.htm (this website was apparently last updated in November 2017).
sprint.dat = read.table(
file="http://www.stat.cmu.edu/~ryantibs/statcomp-S18/data/sprint.dat",
sep="\t", quote="", header=TRUE)
sprint.w.dat = read.table(
file="http://www.stat.cmu.edu/~ryantibs/statcomp-S18/data/sprint.w.dat",
sep="\t", quote="", header=TRUE)1a. Confirm that both sprint.dat and sprint.w.dat are data frames. Delete the Rank and City columns from each data frame. Then display the first and last 5 rows of each. Challenge: compute the ranks for the men’s data set and add them back as a Rank column to sprint.dat. Do the same for the women’s data set. Note: there is a clean solution that only requires one line of code per data frame. Hint: consider using rank(), or duplicated().
1b. Compute, as we did in the lab, the age of each sprinter in the data set sprint.dat when he ran the recorded time. Add a column Age to sprint.dat with these ages. Do the same for sprint.w.dat. Report the quantiles of the Age column, for each data frame, using a call to quantile().
1c. Using table(), compute for each unique country in the Country column of sprint.dat, the number of sprint times from this country that appear in the data set. Call the result sprint.counts. Do the same for the women, calling the result sprint.w.counts. What are the 5 most represented countries, for the men, and for the women? (Interesting side note: go look up the population of Jamaica, compared to that of the US. Pretty impressive sprinters, eh?) Challenge: are there any countries that are represented by women but not by men, and if so, what are they? Vice versa, represented by men and not women? Hint: for this challenge part, you will want to use %in%.
1d. Using some method for data frame subsetting, and then table(), recompute the counts of countries in sprint.dat, now only counting sprint times that are faster than or equal to 10 seconds. Call the result sprint.10.counts. Recompute counts for women too, now only counting sprint times that are faster than or equal to 11 seconds, and call the result sprint.w.11.counts. What are the 5 most represented countries now, for men, and for women?
1e. Using one of the apply functions, compute the average sprint time for each age in the sprint.dat data set, calling the result time.avg.by.age. Similarly, compute the analogous quantity for the women, calling the result time.w.avg.by.age. Are there any ages for which the men’s average time is faster than 10 seconds, and if so, which ones? Are there any ages for which the women’s average time is faster than 10.98 seconds, and if so, which ones?
1f. Plot time.avg.by.age versus the corresponding men’s ages. Set the axes labels and title appropriately. Do you notice any trend? Plot time.w.avg.by.age versus the corresponding women’s ages. Do you notice any trend, and is it the same or different as it was with the men?
2a. To solve Q1b, you should have computed a vector, call it sprint.years, that contains the years in which each time in the sprint.dat data frame was recorded. Also, define sprint.times to be the Time column of the sprint.dat data frame. Plot sprint.times versus sprint.years, using empty black circles. Label the x-axis “Year” and the y-axis “Time (seconds)”. Title the plot “Fastest men’s 100m sprint times”. Overlaid on top, plot the times versus years for Jamaican atheletes only, using small filled green circles. Use a legend to differentiate between the empty black circles (overall times) and small filled green circles (Jamaican times).
2b. Starting with your solution code from the last question, modify it so that, instead of the Jamaican times as small filled green circles, your plot shows the US times as small filled red circles. Modify the legend appropriately too. Comment on any differences you see between the resulting plot and the one from the last question.
2c. Produce plots as in Q2a and Q2b, but for the women’s times in the sprint.w.dat data frame. Describe any differences you see between the Jamaica-colored and US-colored plots.
Challenge. Revisit the men’s or women’s plots of times versus years you produced in Q2a, Q2b, Q2c. (Study the men or women for this challenge question, your choosing.) Produce a single layered plot, whose layers follow the specified order, that shows: overall times versus years as empty black circles, Jamaican times versus years as small filled green circles, US times versus years as small filled red circles, and finally, the common times versus years—these are the time-year pairs that appear in both the Jamaica and US subsets of the data set—as small filled blue circles. You may not use transparent colors here in order to somehow color the common points; you must determine the common points programmatically, and then manually color them blue. Use an legend that properly describes all the point types.
3a. The volcano object in R is a matrix of dimension 87 x 61. It is a digitized version of a topographic map of the Maungawhau volcano in Auckland, New Zealand. Plot a heatmap of the volcano, with 25 colors from the terrain color palette.
3b. Each row of volcano corresponds to a grid line running east to west. Each column of volcano corresponds to a grid line running south to north. Define a matrix volcano.rev by reversing the order of the rows, as well as the order of the columns, of volcano. Therefore, each row volcano.rev should now correspond to a grid line running west to east, and each column of volcano.rev a grid line running north to south.
3c. If we printed out the matrix volcano.rev to the console, then the elements would follow proper geographic order: left to right means west to east, and top to bottom means north to south. Now, produce a heatmap of the volcano that follows the same geographic order. Hint: recall that the image() function rotates a matrix 90 degrees counterclockwise before displaying it; and recall the function clockwise90() from the lecture, which you can copy and paste into your code here. Label the x-axis “West –> East”, and the y-axis “South –> North”. Title the plot “Heatmap of Maungawhau volcano”.
3d. Reproduce the previous plot, and now draw contour lines on top of the heatmap.
3e. The function filled.contour() provides an alternative way to create a heatmap with contour lines on top. It uses the same orientation as image() when plotting a matrix. Use filled.contour() to plot a heatmap of the volcano, with (light) contour lines automatically included. Make sure the orientation of the plot matches proper geographic orientation, as in the previous question. Use a color scale of your choosing, and label the axes and title the plot appropriately. It will help to consult the documentation for filled.contour().
table(), compute counts of the word lengths, separately, for each play you are considering. Produce a plot that displays histograms of these counts—i.e., one histogram for each play, overlaid. Make sure that probability=TRUE in the calls to hist() (so that all histograms are on the probability scale, rather than the frequency scale). Set the title and axes labels appropriately. Set the break locations appropriately. Use transparent colors, and a legend. Describe any differences/similarities that you are seeing between plays, according to Shakepeare’s word length useage.