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

# MIERCOLES: clase 5

# FUNCIONES SIMPLES


####################### tapply #######################

# datos de vegatacion: species richness en transectos diferentes

setwd("C:/R_Quito/")
Veg <- read.table(file="Vegetation2.txt", header= TRUE)

# verificar como es:
names(Veg)

str(Veg)


# species richness overall & per transect - the long way!
m <- mean(Veg$R)
m1<- mean(Veg$R[Veg$Transect == 1])
m2<- mean(Veg$R[Veg$Transect == 2])
m3<- mean(Veg$R[Veg$Transect == 3])
m4<- mean(Veg$R[Veg$Transect == 4])
m5<- mean(Veg$R[Veg$Transect == 5])
m6<- mean(Veg$R[Veg$Transect == 6])
m7<- mean(Veg$R[Veg$Transect == 7])
m8<- mean(Veg$R[Veg$Transect == 8])
c(m, m1, m2, m3, m4, m5, m6, m7, m8)

# The variable m contains the mean richness of all 8 transects, and m1 through
# m8 show the mean richness values per transect. Note that the mean command is
# applied to Veg $R, which is a vector of data. It is not amatrix; hence there is no
# need for a comma between the square brackets.



# mean species richness per transect - a better way!

# The R function tapply performs the same operation as the code
# above (for m1 through m8 ), but with a single line of code

tapply(Veg$R, Veg$Transect, mean)

# or

tapply(X = Veg$R, INDEX = Veg$Transect, FUN = mean)

# The tapply function splits the data of the first variable (R),based on the levels
# of the second variable (Transect). To each subgroup of data, it applies a function,
# in this case the mean, but we can also use the standard deviation (function sd),
# variance (function var), length (function length),and so on. The following
# lines of code calculate some of these functions for the vegetation data.


Me <- tapply(Veg$R, Veg$Transect, mean)
Sd <- tapply(Veg$R, Veg$Transect, sd)
Le <- tapply(Veg$R, Veg$Transect, length)
cbind(Me, Sd, Le)

# Each row in the output gives the mean richness, standard deviation, and
# number of observations per transect. 



#################### sapply & lapply ##########################

# To calculate the mean, minimum, maximum, standard deviation, and length of
# the full series, we still need to use mean (Veg$R), min (Veg$R), max (Veg$R),
# sd (Veg$R), and length (Veg$R). This is laborious if we wish to calculate the
# mean of a large number of variables such as all the numerical variables of
# the vegetation data. We specifically say ‘‘numerical’’ as one cannot calculate
# the mean of a factor. There are 20 numerical variables in the vegetation dataset,
# columns 5–25 of the data frame Veg. However, we do not need to type in the
# mean command 20 times. R provides other functions similar to the tapply to
# address this situation: the lapply and the sapply. 

sapply(Veg[, 5:9], FUN= mean)


# It is important to realise that tapply calculates the mean (or any other function)
# for subsets of observations of a variable, whereas lapply and sapply calcu-
# late the mean (or any other function) of one or more variables, using all
# observations.
# The word FUN stands for function, and must be written in capitals. Instead
# of the mean, you can use any other function as an argument for FUN, and you
# can write your own functions. So what is the difference between sapply and
# lapply? The major differences lie in the presentation of output, as can be seen
# in the following example.

lapply(Veg[, 5:9], FUN= mean)

# The output of lapply is presented as a list, whereas sapply gives it as a
# vector. The choice depends on the format in which you would like the output.
# The variable that contains the data in lapply and sapply needs to be a
# data frame. This will not work: 

sapply(cbind(Veg$R, Veg$ROCK, Veg$LITTER, Veg$ML, Veg$BARESOIL), FUN = mean)

# It will produce one long vector of data, because the output of the cbind
# command is not a data frame. It can easily be changed to a data frame:

sapply(data.frame(cbind(Veg$R, Veg$ROCK, Veg$LITTER, Veg$ML, Veg$BARESOIL)), FUN = mean)

# Note that we have lost the variable labels. To avoid this, make a proper data
# frame before running the sapply function. Alternatively, use the
# colnames function after combining the data with the cbind function.



################################### summary ##############################

# Another function that gives basic information on variables is the summary
# command. The argument can be a variable, the output from a cbind command, 
# or a data frame. It is run by the following commands.

Z <-cbind(Veg$R, Veg$ROCK, Veg$LITTER)

colnames(Z) <- c("R", "ROCK", "LITTER")

summary(Z)

# The summary command gives the minimum, first quartile, median, mean,
# third quartile, and maximum value of the variable. An alternative R code gives
# the same result:

summary(Veg[ , c("R","ROCK","LITTER")])

# or

summary(Veg[ , c(5, 6, 7)])




################################### table ##################################


# The table function can be
# used to learn how many animals per farm were sampled, as well as the number
# of observations per sex and year. The following code imports the data, and
# shows the results.

setwd("c:/R_Quito/")
Deer <- read.table(file="Deer.txt", header= TRUE)
names (Deer)
str(Deer)

# Farm has been coded as AL, AU, and so on, and is automatically imported
# as a factor. The other variables are all vectors of numerical or integer values.
# The number of observations per farm is obtained by

table(Deer$Farm)

table(Deer$Sex, Deer$Year)


##### HACEN LOS EJERCICIOS !! #######