Lecture 8

library(tidyverse)
library(lubridate)

# Import the downloaded data (set your own working directory)
hydro <- read_csv("data/1111473b.csv")
names(hydro) <- c("cruise", "station", "type", "date_time", 
  "lat", "long", "depth", "pres", "temp", "psal", "doxy")
hydro$month <- month(hydro$date_time)
hydro$day <- day(hydro$date_time)
hydro$yday <- yday(hydro$date_time)

# Since month is not really a continuous variable
# (double format in the tibble) convert it
# to a factor (necessary for some of the plots!)
hydro$month <- as.factor(hydro$month)


# ONE VARIABLE -----------------

# discrete --
d <- ggplot(hydro, aes(x = month)) 

d + geom_bar() # x, alpha, color, fill, linetype, size, weight

# continuous --
c <- ggplot(hydro, aes(x = temp)) 

c + geom_histogram(binwidth = 3) # x, y, alpha, color, fill, linetype, 
# size, weight
c + geom_area(stat = "bin") # x, y, alpha, color, fill, linetype, size


# TWO VARIABLES -----------------

# discrete x , discrete y --
g <- ggplot(hydro, aes(x = month, y = day))
g + geom_count() # x, y, alpha, color, fill, shape, size, stroke

# discrete x , continuous y --
f <- ggplot(hydro, aes(x = month, y = temp))

f + geom_col() # x, y, alpha, color, fill, group, linetype, size
f + geom_boxplot()  # x, y, lower, middle, upper, ymax, ymin, alpha, 
# color, fill, group, linetype, shape, size, weight

# continuous x , continuous y --
e <- ggplot(hydro, aes(x = yday, y = temp))

e + geom_point() # x, y, alpha, color, fill, shape, size, stroke
e + geom_smooth() # x, y, alpha, color, fill, group, linetype, size, weight
e + geom_text(aes(label = month), nudge_x = 1, nudge_y = 1, check_overlap = TRUE)
# x, y, label, alpha, angle, color, family, fontface, hjust, lineheight, size, vjust
e + geom_quantile() # x, y, alpha, color, group, linetype, size, weight

# continuous bivariate distribution --
h <- ggplot(hydro, aes(x = psal, y = temp))

h + geom_bin2d()
h + geom_density2d()
h + geom_hex()