# R in Action (2nd ed): Chapter 4
# Basic data management
# requires that the reshape package has been installed
# install.packages("reshape")
#-----------------------------------------------------

# leadership dataset
manager <- c(1,2,3,4,5)
date <- c("10/24/08","10/28/08","10/1/08","10/12/08","5/1/09")
gender <- c("M","F","F","M","F")
age <- c(32,45,25,39,99)
q1 <- c(5,3,3,3,2)
q2 <- c(4,5,5,3,2)
q3 <- c(5,2,5,4,1)
q4 <- c(5,5,5,NA,2)
q5 <- c(5,5,2,NA,1)
leadership <- data.frame(manager,date,gender,age,q1,q2,q3,q4,q5, stringsAsFactors=FALSE)
attach(leadership)


# Recoding variables
leadership$agecat[age > 75] <- "Elder"
leadership$agecat[age > 45 & age <= 75] <- "Middle Aged"
leadership$agecat[age <= 45] <- "Young"


# Renaming variables with the reshape package
library(reshape)
rename(leadership, 
       c( manager="managerID", date="testDate" ))

# Applying the is.na() function
is.na(leadership[, 6:10])

# recode 99 to missing for the variable age
leadership[age == 99, "age"] <- NA
leadership

# Using na.omit() to delete incomplete observations
na.omit(leadership)


# Converting character values to dates
strDates <- c("01/05/1965", "08/16/1975")
dates <- as.Date(strDates, "%m/%d/%Y") 
mydates <- as.Date(c("2007-06-22", "2004-02-13"))
mydates

# Calculations with with dates
startdate <- as.Date("2004-02-13")
enddate   <- as.Date("2009-06-22")
enddate - startdate


# Date functions and formatted printing
today <- Sys.Date()
format(today, format="%B %d %Y")           
dob <- as.Date("1956-10-10")
format(dob, format="%A") 

# Converting from one data type to another
a <- c(1,2,3)
a
is.numeric(a)
is.vector(a)
a <- as.character(a)
a
is.numeric(a)
is.vector(a)
is.character(a)

# Sorting a dataset
leadership[order(age),] 
leadership[order(gender, age),] 
leadership[order(gender, -age),]


# Selecting variables
leadership[, c(6:10)] 
myvars <- c("q1", "q2", "q3", "q4", "q5")
leadership[myvars]
myvars <- paste("q", 1:5, sep="")  
leadership[myvars]

# Dropping variables
myvars <- names(leadership) %in% c("q3", "q4") 
leadership[!myvars]
leadership[c(-7,-8)] 


# Selecting observations
leadership[1:5,] 
leadership[which(leadership$gender=="M" & leadership$age > 30),]
leadership[which(gender == 'M' & age > 30),] 



# Selecting observations based on dates
leadership$date <- as.Date(leadership$date, "%m/%d/%y")   
startdate <- as.Date("2009-01-01")                               
enddate   <- as.Date("2009-10-31")
leadership[leadership$date >= startdate & leadership$date <= enddate,]


# Using the subset() function
subset(leadership, age >= 35 | age < 24,    
  select=c(q1, q2, q3, q4)) 
subset(leadership, gender=="M" & age > 25,    
  select=gender:q4)