R visualization note - Air quality

Load the data

library(datasets)
library(ggplot2)

data("airquality")
#View("airquality")

airquality$Month <- factor(airquality$Month,
                           labels = c('May', 'Jun', 'Jul', 'Aug', 'Sep'))

Box plot

ggplot(airquality, aes(x = Month, y = Ozone)) + 
  geom_boxplot()

## Warning: Removed 37 rows containing non-finite values (stat_boxplot).

fill = "#4271AE"
line = "#1F3552"

ggplot(airquality, aes(x = Month, y = Ozone)) + 
  geom_boxplot(fill = fill, color = line, alpha = .7,
               outlier.colour = line, outlier.shape = 8)

## Warning: Removed 37 rows containing non-finite values (stat_boxplot).

# notch : draws more attention to mean
# geom_jitter(): show data points
# outlier.shape = NA: avoid duplicated points caused by geom_jitter()
ggplot(airquality, aes(x = Month, y = Ozone)) + 
  geom_boxplot(fill = fill, color = line, alpha = .7,
               notch = TRUE,
               outlier.shape = NA) + 
  geom_jitter(shape = 20, alpha = .5) + 
  # alternative: geom_point(alpha = .4) all points will be on a vertical line
  scale_y_continuous(name = "Mean ozone in\nparts per billion",
                     breaks = seq(0, 175, 25),
                     limits = c(0,175)) + 
  scale_x_discrete(name = "Month") + 
  ggtitle("Boxplot of mean ozone by month") +
  theme_bw()

## Warning: Removed 37 rows containing non-finite values (stat_boxplot).

## notch went outside hinges. Try setting notch=FALSE.

## Warning: Removed 37 rows containing missing values (geom_point).

Plot 2: temperature high/low

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ tibble  3.1.3     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   2.0.1     ✓ forcats 0.5.1
## ✓ purrr   0.3.4

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

months = c("Jul", "Aug", "Sep")

airquality_trimmed = filter(airquality, Month %in% months)
# A new binomial variable - 1: temp > mean; 0: otherwise
airquality_trimmed$Temp.f = factor(ifelse(airquality_trimmed$Temp > mean(airquality_trimmed$Temp), 1, 0),
                                   labels = c("Low Temp", "High Temp"))

library(RColorBrewer)

# scale_fill_brewer() depends on package "RColorBrewer" for coloring
ggplot(airquality_trimmed, aes(x = Month, y = Ozone, fill = Temp.f)) + 
  geom_boxplot(alpha = .7, outlier.shape = NA) + 
  geom_jitter(aes(color = Temp.f), shape = 20, alpha = .5) + 
  scale_fill_brewer(palette = "Accent") +
  scale_color_brewer(palette = "Accent") + 
  theme_bw()

## Warning: Removed 11 rows containing non-finite values (stat_boxplot).

## Warning: Removed 11 rows containing missing values (geom_point).