ggplot2 part 1

library(ggplot2)
diamonds <- na.omit(diamonds)  # remove rows with NA
dim(diamonds)

set.seed(9999)  # Make the sample reproducible
dsmall <- diamonds[sample(nrow(diamonds), 1000), ]

# the first two arguments give the x- and y-coordinates
qplot(carat, price, data = diamonds)

# The relationship looks exponential, we’d like to do is to transform the
# variables
qplot(log(carat), log(price), data = diamonds)

# Arguments can also be combinations of existing variables
qplot(carat, x * y * z, data = diamonds)

# Mapping point colour to diamond colour
qplot(carat, price, data = dsmall, colour = color)

# Mapping point shape to cut quality (right).
qplot(carat, price, data = dsmall, shape = cut)

# Reducing the alpha value to 1/10 to makes it possible to see where the
# bulk of the points lie.  the denominator specifies the number of points
# that must overplot to get a completely opaque colour.
qplot(carat, price, data = diamonds, alpha = I(1/10))

# Reducing the alpha value to 1/100,
qplot(carat, price, data = diamonds, alpha = I(1/100))

library(splines)
library(mgcv)
# Smooth curves add to scatterplots The geoms will be overlaid in the order
# in which they appear.
qplot(carat, price, data = dsmall, geom = c("point", "smooth"), method = "gam",
formula = y ~ s(x, bs = "cs"))

# The effect of the span parameter. The wiggliness of the line is controlled
# by the span parameter, which ranges from 0 (exceedingly wiggly) to 1 (not
# so wiggly)
qplot(carat, price, data = dsmall, geom = c("point", "smooth"), span = 0.2)

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

# more method available: loess, gam, lm, rlm

# The effect of the formula parameter, using a generalised additive model as
# a smoother.
qplot(carat, price, data = dsmall, geom = c("point", "smooth"), method = "gam",
formula = y ~ s(x))

# default when there are more than 1,000 points
qplot(carat, price, data = dsmall, geom = c("point", "smooth"), method = "gam",
formula = y ~ s(x, bs = "cs"))

# The effect of the formula parameter using a linear model as a smoother.
qplot(carat, price, data = dsmall, geom = c("point", "smooth"), method = "lm")

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

# Using jittering and boxplots to investigate the distribution of price per
# carat, conditional on colour.  As the colour improves (from left to right)
# the spread of values decreases, but there is little change in the centre
# of the distribution.
qplot(color, price/carat, data = diamonds, geom = "jitter")

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

# Varying the alpha level.  From left to right: $1/5$, $1/50$, $1/200$.  As
# the opacity decreases we begin to see where the bulk of the data lies.
# However, the boxplot still does much better.
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))

# Displaying the distribution of diamonds.
qplot(carat, data = diamonds, geom = "histogram")

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

# For the density plot, the **adjust** argument controls the degree of
# smoothness (high values of adjust produce smoother plots). For the
# histogram, the **binwidth** argument controls the amount of smoothing by
# setting the bin size.

# Varying the bin width on a histogram of carat reveals interesting
# patterns.  Binwidths from left to right: 1, 0.1 and 0.01 carats.  Only
# diamonds between 0 and 3 carats shown.
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))

# Mapping a categorical variable to an aesthetic will automatically split up
# the geom by that variable.  Density plots are overlaid
qplot(carat, data = diamonds, geom = "density", colour = color)

# histograms are stacked.
qplot(carat, data = diamonds, geom = "histogram", fill = color)

# Bar charts of diamond colour.  The first plot is a simple bar chart of
# diamond colour, and the second is a bar chart of diamond colour weighted
# by carat.
qplot(color, data = diamonds, geom = "bar")

qplot(color, data = diamonds, geom = "bar", weight = carat) + scale_y_continuous("carat")

# Line plots join the points from left to right, while path plots join them
# in the order that they appear in the dataset

# Two time series measuring amount of unemployment.

# Percent of population that is unemployed
qplot(date, unemploy/pop, data = economics, geom = "line")

# median number of weeks unemployed.
qplot(date, uempmed, data = economics, geom = "line")

# Path plots illustrating the relationship between percent of people
# unemployed and median length of unemployment.
year <- function(x) as.POSIXlt(x)$year + 1900

# Scatterplot with overlaid path.
qplot(unemploy/pop, uempmed, data = economics, geom = c("point", "path"))

# Pure path plot coloured by year.
qplot(unemploy/pop, uempmed, data = economics, geom = "path", colour = year(date)) +
scale_size_area()

# It creates tables of graphics by splitting the data into subsets and
# displaying the same graph for each subset in an arrangement that
# facilitates comparison

# The density plot makes it easier to compare distributions ignoring the
# relative abundance of diamonds within each colour. High-quality diamonds
# (colour D) are skewed towards small sizes, and as quality declines the
# distribution becomes more flat.

# Histograms showing the distribution of carat conditional on colour.  Bars
# show counts
qplot(carat, data = diamonds, facets = color ~ ., geom = "histogram", binwidth = 0.1,
xlim = c(0, 3))

# bars show densities (proportions of the whole).
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(0.2, 1))

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