# R para principiantes
# PUCE, Quito, 5-8 enero 2010
# Simon Queenborough

# MIERCOLES: clase 6

# GRAFICOS BASICOS

########################## plot #################################

# To quantify biodiversity, species richness was calculated. In a statistical
# analysis, we may want to model richness as a function of BARESOIL (or any of
# the other soil and climate variables). Suppose we want to make a plot of species
# richness versus the substrate variable ‘‘exposed soil,’’ denoted by BARESOIL.
# The R commands to create such a graph is

setwd("c:/R_Quito/data/")
Veg <- read.table(file = "Vegetation2.txt", header = TRUE)
plot(Veg$BARESOIL, Veg$R)

# To import a graph from R into Microsoft Word, right-click on the graph in R to copy
# and paste it into Word, or save it as a metafile (recommended, as it produces a good quality
# graph), bitmap, or postscript file. This will also work with non-Windows operating systems.
# Importing the latter two formats into Word is more complicated. 

# The first argument of the
# plot command is displayed on the horizontal axis with the second argument
# along the vertical axis. Richness, in this case, is the response, or dependent,
# variable, and BARESOIL is the explanatory, or independent, variable. It is
# conventional to plot the response variable along the vertical axis and the
# explanatory variable along the horizontal axis. Be aware that for some
# statistical functions in R, you must specify the response variable first, fol-
# lowed by the explanatory variables. You would not be the first to accidentally type

plot(Veg$R, Veg$BARESOIL)

# and discover that the order should have been reversed. Alternatively, you can use

plot(x = Veg$BARESOIL, y = Veg$R)

# to avoid confusion over which variables will be plotted on the x-axis (horizontal) 
# and which on the y-axis (vertical).
# The plot function does have a data argument, but we cannot use

plot(BARESOIL, R, data = Veg)

plot(R ~ BARESOIL, data = Veg) # does work


# The most common modifications to any graph are adding a title and x- and
# y-labels and setting the x- and y-limits. This is
# accomplished by extending the plot command:

plot(x = Veg$BARESOIL, y = Veg$R,
    xlab = "Exposed soil",
    ylab = "Species richness", main = "Scatter plot",
    xlim = c(0, 45), ylim = c(4, 19))

# The order in which xlab, ylab , main, xlim,and ylim are entered is
# irrelevant, but they must be in lowercase letters. The xlab and ylab options
# are used for labels and the main option for the title. The xlim and ylim options
# are used to specify the lower and upper limits on the axes. You can also use

xlim = c(min(Veg$BARESOIL), max(Veg$BARESOIL))

# within the plot command, but, if there aremissing values in the plotted variable,
# you should extend the min and max functions with the na.rm=TRUE option.
# This produces

xlim = c(min(Veg$BARESOIL, na.rm = TRUE), max(Veg$BARESOIL, na.rm = TRUE))




####################### simbolos, colores y tamanos ##########################################

### simbolos

# By default, the plot function uses open circles (open dots) as plotting char-
# acters, but characters can be selected from about 20 additional symbols. The
# plotting character is specified with the pch option in the plot function; its
# default value is 1 (which is the open dot or circle). 

plot(x = Veg$BARESOIL, y = Veg$R,
    xlab = "Exposed soil",
    ylab = "Species richness", main = "Scatter plot",
    xlim = c(0, 45), ylim = c(4, 19), pch = 16)




# Make an empty chart
plot(1, 1, xlim=c(1,5.5), ylim=c(0,7), type="n", ann=FALSE)

# Plot digits 0-4 with increasing size and color
text(1:5, rep(6,5), labels=c(0:4), cex=1:5, col=1:5)

# Plot symbols 0-4 with increasing size and color
points(1:5, rep(5,5), cex=1:5, col=1:5, pch=0:4)
text((1:5)+0.4, rep(5,5), cex=0.6, (0:4))

# Plot symbols 5-9 with labels
points(1:5, rep(4,5), cex=2, pch=(5:9))
text((1:5)+0.4, rep(4,5), cex=0.6, (5:9))

# Plot symbols 10-14 with labels
points(1:5, rep(3,5), cex=2, pch=(10:14))
text((1:5)+0.4, rep(3,5), cex=0.6, (10:14))

# Plot symbols 15-19 with labels
points(1:5, rep(2,5), cex=2, pch=(15:19))
text((1:5)+0.4, rep(2,5), cex=0.6, (15:19))

# Plot symbols 20-25 with labels
points((1:6)*0.8+0.2, rep(1,6), cex=2, pch=(20:25))
text((1:6)*0.8+0.5, rep(1,6), cex=0.6, (20:25))


### colores

# The plotting option for changing colours is useful for graphics presented on a
# screen or in a report, but is less so for scientific publications, as these are most
# often printed in black and white. We recommend that you read Section 5.2.1
# before reading this section, as the procedure for colour is the same as that for symbols.
# To replace the black dots in Fig. 5.2 with red, use

plot(x = Veg$BARESOIL, y = Veg$R,
    xlab = "Exposed soil",
    ylab = "Species richness", main = "Scatter plot",
    xlim = c(0, 45), ylim = c(4, 19),
    col = 2)

# For green, use col =3. Run the following code to see the other available colours.

x <- 1:8
plot(x, col = x)

# una lista de colores:
# como hacer un palette de colores:


# un vector de colores

# You can also use a vector for the col option in the plot function. Suppose you
# want to plot the observations from 1958 to 1974 as black filled squares and the
# observations from1981 to 2002 as red filled circles (shown here as light grey). In
# the previous section, you learned how to create filled squares and circles using
# the variable Time2 with values 15 (square) and 16 (circle). Using two colours is
# based on similar R code. First, create a new variable of the same length as
# BARESOIL and richness R, which can be called Col2 . For those observations
# from1958 to 1974, Col2 takes the value 1 (= black) and, for the following
# years, 2 (= red). The R code is


Veg$Time2 <- Veg$Time
Veg$Time2 [Veg$Time <= 1974] <- 15
Veg$Time2 [Veg$Time > 1974] <- 16
Veg$Col2 <- Veg$Time
Veg$Col2 [Veg$Time <= 1974] <- 1
Veg$Col2 [Veg$Time > 1974] <- 2
plot(x = Veg$BARESOIL, y = Veg$R,
    xlab = "Exposed soil",
    ylab = "Species richness", main = "Scatter plot",
    xlim = c(0, 45), ylim = c(4, 19),
    pch = Veg$Time2, col = Veg$Col2)



#### tamano de simbolos


# The size of the plotting symbols can be changed with the cex option, and again,
# this can be added as an argument to the plot command. The default value for
# cex is 1. Adding cex=1.5 to the plot command produces a graph in which all
# points are 1.5 times the default size:

plot(x = Veg$BARESOIL, y = Veg$R,
    xlab = "Exposed soil", ylab = "Species richness",
    main = "Scatter plot",
    xlim = c(0, 45), ylim = c(4, 19),
    pch = 16, cex = 1.5)




### usando un vector con 'cex'

# As with the pch and col options, we demonstrate the use of a vector as the
# argument of the cex option. Suppose you want to plot BARESOIL against species
# richness using a large filled dot for observations made in 2002 and a smaller filled
# dot for all other observations. Begin by creatinganewvectorwithvaluesof2for
# observations made in 2002 and 1 for those from all other years. The values 1 and 2
# are good starting points for finding, through trial and error, the optimal size
# difference. Try 3 and 1, 1.5 and 1, or 2 and 0.5, and so on, and decide which
# looks best.

Veg$Cex2 <- Veg$Time
Veg$Cex2[Veg$Time == 2002] <- 2
Veg$Cex2[Veg$Time != 2002] <- 1


plot(x = Veg$BARESOIL, y = Veg$R,
    xlab = "Exposed soil", ylab = "Species richness",
    main = "Scatter plot",
    xlim = c(0, 45), ylim = c(4, 19),
    pch = 16, cex = Veg$Cex2)


# Altering the symbol size can also be accomplished by using cex =1.5 * Veg$Cex2 
# or cex =Veg$Cex2 /2.