GEOG 5680 Module 7: Better Plotting with ggplot2

Introduction

Use ggplot2 to explore temperature and salinity data.

library(ggplot2)
temp = read.csv("Temperature.csv")

Histograms of Salinity

Overall Salinity

myplot = ggplot(temp, aes(x = Salinity))
myplot +
  geom_histogram()

`stat_bin()` using `bins = 30`. Pick better value `binwidth`.

Warning: Removed 798 rows containing non-finite outside the scale range
(`stat_bin()`).

Salinity by Year

myplot = ggplot(temp, aes(x = Salinity))
myplot + geom_histogram(binwidth = 0.5,
    color = "lightblue",
    fill = "white") +
  facet_wrap(~ Year)

Warning: Removed 798 rows containing non-finite outside the scale range
(`stat_bin()`).

Salinity by Month

temp$Month = factor(temp$Month,
  levels = 1:12,
  labels = c("Jan", "Feb", "Mar", "Apr",
    "May", "Jun", "Jul", "Aug",
    "Sep", "Oct", "Nov", "Dec"))

myplot = ggplot(temp, aes(x = Salinity))
myplot +
  geom_histogram(binwidth = 0.5,
    color = "lightpink",
    fill = "white") +
  facet_wrap(~ Month)

Warning: Removed 798 rows containing non-finite outside the scale range
(`stat_bin()`).

Temperature by Station

Temperature Boxplots

myplot = ggplot(temp,
  aes(x = Station,
    y = Temperature))
myplot +
  geom_boxplot() +
  xlab("Station") +
  ylab("Temperature (deg C)") +
  ggtitle("Temperature by Station")

Warning: Removed 927 rows containing non-finite outside the scale range
(`stat_boxplot()`).

Stations Ordered by Median Temperature

myplot = ggplot(
  temp,
  aes( x = reorder(Station, Temperature, median),
    y = Temperature))

myplot +
  geom_boxplot(fill = "lightblue")

Warning: Removed 927 rows containing non-finite outside the scale range
(`stat_boxplot()`).

Time Series Analysis

Create a Decimal Date Variable

temp$decdate = temp$Year + temp$dDay3 / 365

Salinity Through Time

myplot = ggplot(temp,
  aes(x = decdate,
    y = Salinity))

myplot +
  geom_point(alpha = 0.4,size = 1) +
  xlab("Year") +
  ylab("Salinity (psu)") +
  ggtitle("Salinity Through Time")

Warning: Removed 798 rows containing missing values or values outside the scale range
(`geom_point()`).

Salinity Through Time by Area

myplot = ggplot(temp,
  aes(x = decdate,
    y = Salinity))

myplot +
  geom_point(alpha = 0.4,
    size = 1) +
  facet_wrap(~ Area) +
  xlab("Year") +
  ylab("Salinity (psu)") +
  ggtitle("Salinity Through Time by Area")

Warning: Removed 798 rows containing missing values or values outside the scale range
(`geom_point()`).

Salinity Time Series by Station and Area

myplot = ggplot(temp,
  aes(x = decdate,
    y = Salinity))
myplot +
  geom_line(aes(group = Station)) +
  facet_wrap(~ Area) +
  xlab("Year") +
  ylab("Salinity (psu)") +
  ggtitle("Salinity Time Series by Station and Area")

Warning: Removed 4 rows containing missing values or values outside the scale range
(`geom_line()`).