Exploratory analysis II

Data visualization, part 2. Code for Quiz 8.

  1. Load the R package we will use.
  1. Quiz questions
  1. Pick one of your plots to save as your preview plot. Use the ggsave command at the end of the chunk of the plot that you want to preview.

Question: modify slide 51

ggplot(data = mpg) +
  geom_point(aes(x = displ, y = hwy)) +
  facet_wrap(facets = vars(manufacturer))


Question: modify facet-ex-2

ggplot(mpg) +
  geom_bar(aes(y = manufacturer)) +
  facet_grid(vars(class), scales = "free_y", space = "free_y")


Question: spend_time

To help you complete this question use:

read it into spend_time

read_csv("https://estanny.com/static/week8/spend_time.csv")
# A tibble: 50 x 3
   activity        year avg_hours
   <chr>          <dbl>     <dbl>
 1 leisure/sports  2019      5.19
 2 leisure/sports  2018      5.27
 3 leisure/sports  2017      5.24
 4 leisure/sports  2016      5.13
 5 leisure/sports  2015      5.21
 6 leisure/sports  2014      5.3 
 7 leisure/sports  2013      5.26
 8 leisure/sports  2012      5.37
 9 leisure/sports  2011      5.21
10 leisure/sports  2010      5.18
# ... with 40 more rows
spend_time  <- read_csv("https://estanny.com/static/week8/spend_time.csv")

Start with spend_time

p1 <- spend_time %>% filter(year == "2015") %>% 
ggplot() +
  geom_col(aes(x = activity, y = avg_hours, fill = activity)) +
  scale_y_continuous(breaks = seq(0, 6, by = 1)) +
  labs(subtitle = "Avg hours per day: 2015", x = NULL, y = NULL)

p1


Start with spend_time

p2 <- spend_time %>% 
ggplot() +
  geom_col(aes(x = year, y = avg_hours, fill = activity)) +
  labs(subtitle = "Avg hours per day: 2010-2019", x = NULL, y = NULL)

p2


Use patchwork to display p1 on top of p2

p_all <- p1 / p2

p_all


Start will p_all

p_all_no_legend <- p_all & theme(legend.position = 'none')
p_all_no_legend


Start with p_all_no_legend

p_all_no_legend +
  plot_annotation(title = "How much time Americans spent on selected activities",
                  caption = "Source: American Time of Use Survey, https://data.bls.gov/cgi-bin/surveymost?tu")


Question: Patchwork 2

use spend_time from last question patchwork slides

start with spend_time

p4 <- 
spend_time %>% filter(activity == "food prep") %>% 
ggplot() +
  geom_point(aes(x = year, y = avg_hours)) +
  geom_smooth(aes(x = year, y = avg_hours)) +
  scale_x_continuous(breaks = seq(2010, 2019, by = 1)) +
  labs(subtitle = "Avg hours per day: food prep", x = NULL, y = NULL)

p4


Start with p4

p5 <- p4 + coord_cartesian(ylim = c(0,6))
p5


Start with spend_time

p6 <- 
  spend_time %>% 
ggplot() +
  geom_point(aes(x = year, y = avg_hours, color = activity, group = activity)) +
  geom_smooth(aes(x = year, y = avg_hours, color = activity, group = activity)) +
  scale_x_continuous(breaks = seq(2010, 2019, by=1)) +
  coord_cartesian(ylim = c(0, 6)) +
  labs(x = NULL, y = NULL)

p6


Use patchwork to display p4 and p5 on top of p6

( p4 / p5 ) / p6

ggsave(filename = "preview.png",
       path = here::here("_posts", "2022-03-28-exploratory-analysis-ii"))