AE 08: Durham climate + factors

Suggested answers

Getting started

Packages

We will use the tidyverse package in this application exercise.

library(tidyverse)

Data

The data come from https://www.usclimatedata.com/climate/durham/north-carolina/united-states/usnc0192 and are stored as durham-climate.csv in the data folder.

durham_climate <- read_csv("data/durham-climate.csv")

Let’s take a look at the data.

durham_climate

# A tibble: 12 × 4
   month     avg_high_f avg_low_f precipitation_in
   <chr>          <dbl>     <dbl>            <dbl>
 1 January           49        28             4.45
 2 February          53        29             3.7 
 3 March             62        37             4.69
 4 April             71        46             3.43
 5 May               79        56             4.61
 6 June              85        65             4.02
 7 July              89        70             3.94
 8 August            87        68             4.37
 9 September         81        60             4.37
10 October           71        47             3.7 
11 November          62        37             3.39
12 December          53        30             3.43

Reorder

What’s wrong with the following plot?

Months are in alphabetical, not chronological, order.

ggplot(
  durham_climate, 
  aes(x = month, y = avg_high_f, group = 1)
  ) +
  geom_line() +
  geom_point(
    shape = "circle filled", size = 2,
    color = "black", fill = "white", stroke = 1
  ) +
  labs(
    x = "Month",
    y = "Average high temperature (F)",
    title = "Durham climate"
  )

Fix the plot.

durham_climate |>
  mutate(month = fct_relevel(month, month.name)) |>
  ggplot(
    aes(x = month, y = avg_high_f, group = 1)
  ) +
  geom_line() +
  geom_point(
    shape = "circle filled", size = 2,
    color = "black", fill = "white", stroke = 1
  ) +
  labs(
    x = "Month",
    y = "Average high temperature (F)",
    title = "Durham climate"
  )

Perhaps I want the points to be plotted in order of decreasing value (i.e., decreasing avg. high temp). Add code to accomplish this in the chunk below.

durham_climate <- durham_climate |>
  arrange(desc(avg_high_f)) |>
  mutate(month = factor(month))

durham_climate |>
  mutate(month = fct_reorder(month, avg_high_f, .desc = TRUE)) |>
  ggplot(
    aes(x = month, y = avg_high_f, group = 1)
  ) +
  geom_line() +
  geom_point(
    shape = "circle filled", size = 2,
    color = "black", fill = "white", stroke = 1
  ) +
  labs(
    x = "Month",
    y = "Average high temperature (F)",
    title = "Durham climate"
  )

Recode and reorder

Update the plot above, coloring points based on season. Additionally:

• Make sure the legend is on top of the plot and the seasons appear in the legend in the order they appear in the plot (Winter, Spring, Summer, Fall).

• Use "circle filled" as the shape for points, set their size to 3 points, outline (stroke) to 1 point, and fill them in with the following colors:

  • Winter: lightskyblue1
  • Spring: chartreuse3
  • Summer: gold2
  • Fall: lightsalmon4

durham_climate <- durham_climate |>
  mutate(month = fct_relevel(month, month.name)) |>
  mutate(season = case_when(
    month %in% c("December", "January", "February") ~ "Winter",
    month %in% c("March", "April", "May") ~ "Spring",
    month %in% c("June", "July", "August") ~ "Summer",
    month %in% c("September", "October", "November") ~ "Fall"),
    season = fct_relevel(season, c("Winter", "Spring", "Summer", "Fall"))
)

ggplot(durham_climate,
  aes(x = month, y = avg_high_f, group = 1)
) +
geom_line() +
geom_point(
  aes(fill = season),
  shape = "circle filled", size = 2, stroke = 1
) +
scale_fill_manual(
  values = c(
    "Winter" = "lightskyblue1",
    "Spring" = "chartreuse3",
    "Summer" = "gold2",
    "Fall" = "lightsalmon4"
  )
) +
labs(
  x = "Month",
  y = "Average high temperature (F)",
  title = "Durham climate"
) +
theme_minimal() +
theme(legend.position = "top")

Pivot

Overlay lines for both high and low temperatures on the same plot. Additionally, use different colors for the two lines – a darker color for high and a lighter color for low temperatures.

durham_climate_longer <- durham_climate |>
  pivot_longer(
    cols = 2:3,
    names_to = "temp_type",
    ## removes the prefix "avg_" from the pivoted column names
    names_prefix = "avg_",
    values_to = "avg_temp_f"
  ) |>
  ## remove the suffix "_f" from the values in the `temp_type` vector
  mutate(temp_type = str_remove(temp_type, "_f"))
  
  ggplot(durham_climate_longer, aes(x = month, y = avg_temp_f, 
                                    group = temp_type, color = temp_type)) +
  geom_line() +
  geom_point(
    aes(fill = season),
    shape = "circle filled",
    size = 3,
    stroke = 1
  ) +
  scale_fill_manual(
    values = c(
      "Winter" = "lightskyblue1",
      "Spring" = "chartreuse3",
      "Summer" = "gold2",
      "Fall" = "lightsalmon4"
    )
  ) +
  scale_color_manual(
    values = c(
      "high" = "gray20",
      "low" = "gray70"
    )
  ) +
  labs(
    x = "Month",
    y = "Average temperature (F)",
    title = "Durham climate",
    fill = "Season",
    color = "Type"
  ) +
  theme_minimal() +
  theme(legend.position = "top")