ggplot2: qplot()

library(ggplot2)
head(diamonds)

##   carat       cut color clarity depth table price   x   y   z
## 1  0.23     Ideal     E     SI2    62    55   326 4.0 4.0 2.4
## 2  0.21   Premium     E     SI1    60    61   326 3.9 3.8 2.3
## 3  0.23      Good     E     VS1    57    65   327 4.0 4.1 2.3
## 4  0.29   Premium     I     VS2    62    58   334 4.2 4.2 2.6
## 5  0.31      Good     J     SI2    63    58   335 4.3 4.3 2.8
## 6  0.24 Very Good     J    VVS2    63    57   336 3.9 4.0 2.5

set.seed(1410)
dsmall <- diamonds[sample(nrow(diamonds), 100), ]

# Basic use
qplot(carat, price, data = diamonds)

qplot(log(carat), log(price), data = diamonds)

qplot(carat, x * y * z, data = diamonds)

# Color and shape
qplot(carat, price, data = dsmall, colour = color)

qplot(carat, price, data = dsmall, shape = cut)

# Alpha aesthetic
qplot(carat, price, data = diamonds, alpha = I(1/10))

qplot(carat, price, data = diamonds, alpha = I(1/100))

qplot(carat, price, data = diamonds, alpha = I(1/200))

# Add smoother
qplot(carat, price, data = dsmall, geom = c("point", "smooth"))

## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.

qplot(carat, price, data = diamonds, geom = c("point", "smooth"))

## geom_smooth: method="auto" and size of largest group is >=1000, so using gam with formula: y ~ s(x, bs = "cs"). Use 'method = x' to change the smoothing method.

# method = "loess", default for n < 1000
qplot(carat, price, data = dsmall, geom = c("point", "smooth"), 
  span = 0.2)

## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.

qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
  span = 1)

## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.

# method = "gam", default for n > 1000
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
  method = "gam", formula = y ~ s(x))

qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
  method = "gam", formula = y ~ s(x, bs = "cs"))

# method = "lm"
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
  method = "lm")

library(splines)
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
  method = "lm", formula = y ~ ns(x,5))

# method = "rlm"
library(MASS)
qplot(carat, price, data = dsmall, geom = c("point", "smooth"),
  method = "rlm")

# Basic command
qplot(color, price / carat, data = diamonds, geom = "jitter")

qplot(color, price / carat, data = diamonds, geom = "boxplot")

# More colorful?
qplot(color, price / carat, data = diamonds, geom = "jitter",
  color = color)

qplot(color, price / carat, data = diamonds, geom = "boxplot",
  fill = color)

# Add semi-transparent
qplot(color, price / carat, data = diamonds, geom = "jitter", 
  alpha = I(1 / 5))

qplot(color, price / carat, data = diamonds, geom = "jitter", 
  alpha = I(1 / 50))

qplot(color, price / carat, data = diamonds, geom = "jitter", 
  alpha = I(1 / 200))

# basic
qplot(carat, data = diamonds, geom = "histogram")

## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust this.

qplot(carat, data = diamonds, geom = "density")

# add binwidth & xlim
qplot(carat, data = diamonds, geom = "histogram", binwidth = 1,
  xlim = c(0,3))

qplot(carat, data = diamonds, geom = "histogram", binwidth = 0.1,
  xlim = c(0,3))

qplot(carat, data = diamonds, geom = "histogram", binwidth = 0.01,
  xlim = c(0,3))

## Warning: position_stack requires constant width: output may be incorrect

# more colorful?
qplot(carat, data = diamonds, geom = "density", colour = color)

qplot(carat, data = diamonds, geom = "histogram", fill = color)

## stat_bin: binwidth defaulted to range/30. Use 'binwidth = x' to adjust this.

# simple version
qplot(color, data = diamonds, geom = "bar")

# weighted version (by carat)
qplot(color, data = diamonds, geom = "bar", weight = carat) +
  scale_y_continuous("carat")

# more colorful?
qplot(color, data = diamonds, geom = "bar", fill = color)

# with line
qplot(date, unemploy / pop, data = economics, geom = "line")

qplot(date, uempmed, data = economics, geom = "line")

# with path
year <- function(x) as.POSIXlt(x)$year + 1900
qplot(unemploy / pop, uempmed, data = economics,
  geom = c("point", "path"))

qplot(unemploy / pop, uempmed, data = economics,
  geom = "path", color = year(date)) + scale_size_area()

# facets
qplot(carat, data = diamonds, facets = color ~ .,
  geom = "histogram", binwidth = 0.1, xlim = c(0, 3))

# with ..density..
qplot(carat, ..density.., data = diamonds, facets = color ~ .,
  geom = "histogram", binwidth = 0.1, xlim = c(0, 3))

qplot(
  carat, price, data = dsmall,
  xlab = "Price ($)", ylab = "Weight (carats)",
  main = "Price-weight relationship"
)

qplot(
  carat, price/carat, data = dsmall,
  ylab = expression(frac(price,carat)),
  xlab = "Weight (carats)",
  main="Small diamonds",
  xlim = c(.2,1)
)

## Warning: Removed 35 rows containing missing values (geom_point).

qplot(carat, price, data = dsmall, log = "xy")