吴裕雄--天生自然 R语言开发学习：高级数据管理（续一）

#-----------------------------------#
# R in Action (2nd ed): Chapter 5   #
# Advanced data management          #
# requires that the reshape2        #
# package has been installed        #
# install.packages("reshape2")      #
#-----------------------------------#

# Class Roster Dataset
Student "John Davis","Angela Williams","Bullwinkle Moose",
             "David Jones","Janice Markhammer",
             "Cheryl Cushing","Reuven Ytzrhak",
             "Greg Knox","Joel England","Mary Rayburn")
math )
science )
english )
roster  data.frame(Student, math, science, english, 
                     stringsAsFactors=FALSE)


# Listing 5.1 - Calculating the mean and standard deviation
x )
mean(x)
sd(x)
n  length(x)
meanx n
css )            
sdx ))
meanx
sdx


# Listing 5.2 - Generating pseudo-random numbers from 
# a uniform distribution
runif(5)
runif(5)
set.seed(1234)                                                     
runif(5)
set.seed(1234)                                                      
runif(5)


# Listing 5.3 - Generating data from a multivariate
# normal distribution
library(MASS)
mean )                                           
sigma ,                              
                   6721.2, 4700.9, -16.5,
                   -47.1,  -16.5,   0.3), nrow=3, ncol=3)
set.seed(1234)
mydata , mean, sigma)                                     
mydata  as.data.frame(mydata)                                         
names(mydata) "y", "x1", "x2")                                       
dim(mydata)                                                             
head(mydata, n=10)   


# Listing 5.4 - Applying functions to data objects
a 
sqrt(a)
b )
round(b)
c )
c
log(c)
mean(c)


#  Listing 5.5 - Applying a function to the rows (columns) of a matrix
mydata )
mydata
apply(mydata, 1, mean)     
apply(mydata, 2, mean) 
apply(mydata, 2, mean, trim=.4)   


# Listing 5.6 - A solution to the learning example
options(digits=2)
Student "John Davis", "Angela Williams", "Bullwinkle Moose",
             "David Jones", "Janice Markhammer", "Cheryl Cushing",
             "Reuven Ytzrhak", "Greg Knox", "Joel England",
             "Mary Rayburn")
Math )
Science )
English )

roster  data.frame(Student, Math, Science, English,
                     stringsAsFactors=FALSE)

z ])
score , mean)
roster  cbind(roster, score)

y ))
roster$grade[score >= y[1]] "A"
roster$grade[score = y[2]] "B"
roster$grade[score = y[3]] "C"
roster$grade[score = y[4]] "D"
roster$grade[score "F"

name " ")
Lastname "[", 2)
Firstname "[", 1)
roster ])
roster  roster[order(Lastname,Firstname),]

roster


# Listing 5.4 - A switch example
feelings "sad", "afraid")
for (i in feelings)
  print(
    switch(i,
           happy  = "I am glad you are happy",
           afraid = "There is nothing to fear",
           sad    = "Cheer up",
           angry  = "Calm down now"
    )
  )


# Listing 5.5 - mystats(): a user-written function for 
# summary statistics
mystats print=FALSE) {
  if (parametric) {
    center  sd(x)
  } else {
    center  mad(x)
  }
  if (print & parametric) {
    cat("Mean=", center, "\n", "SD=", spread, "\n")
  } else if (print & !parametric) {
    cat("Median=", center, "\n", "MAD=", spread, "\n")
  }
  result spread)
  return(result)
}


# trying it out
set.seed(1234)
x ) 
y  mystats(x)
y print=TRUE)


# mydate: a user-written function using switch
mydate "long") {
  switch(type,
         long =  format(Sys.time(), "%A %B %d %Y"), 
         short = format(Sys.time(), "%m-%d-%y"),
         cat(type, "is not a recognized type\n"))
}
mydate("long")
mydate("short")
mydate()
mydate("medium")


# Listing 5.9 - Transposing a dataset
cars ]      
cars
t(cars)


# Listing 5.10 - Aggregating data
options(digits=3)
attach(mtcars)
aggdata list(cyl,gear), 
                    FUN=mean, na.rm=TRUE)
aggdata


# Using the reshape2 package
library(reshape2)

# input data
mydata " ", text="
ID Time X1 X2
1 1 5 6
1 2 3 5
2 1 6 1
2 2 2 4
")

# melt data
md "ID", "Time"))

# reshaping with aggregation
dcast(md, ID~variable, mean)
dcast(md, Time~variable, mean)
dcast(md, ID~Time, mean)

# reshaping without aggregation
dcast(md, ID+Time~variable)
dcast(md, ID+variable~Time)
dcast(md, ID~variable+Time)