RinAction - R Data Manipulation - Subsetting data

gistfile1.r

#################################################
##              Subsetting Dataset             ##
#################################################


####################
# Keeping variables
####################

# method 1
newdata <- leadership[, c(6:9)]

# method 2
myvars <- c("q1", "q2", "q3", "q4", "q5")
newdata <- leadership[myvars]

# method 3
myvars <- paste("q", 1:5, sep = "")
newdata <- leadership[myvars]

# method 4 -- using the subset(function)
newdata <- subset(leadership, select=c(6:9))
newdata <- subset(leadership, select=c(q1:q5))

####################
# Dropping variables
####################

# method 1
myvars <- names(leadership) %in% c("q3", "q4")
myvars
newdata <- leadership[!myvars]

# method 2 (if you know the position of the variables to exclude)
newdata <- leadership[c(-7, -8)]

# You could use the following to delete q3 and q4
# from the leadership dataset (commented out so 
# the rest of the code in this file will work)
#
# leadership$q3 <- leadership$q4 <- NULL

########################
# Filtering Observations
########################

# method 1
newdata <- leadership[1:3, ]

# method 2
newdata <- leadership[which(leadership$gender == "M" & 
  leadership$age > 30), ]
newdata

# method 3
attach(leadership)
newdata <- leadership[which(leadership$gender == "M" & 
  leadership$age > 30), ]
detach(leadership)

# method 4 -- using subset() function
newdata <- subset(leadership, age >= 35 | age < 24)

# 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")
newdata <- leadership[leadership$date >= startdate & 
  leadership$date <= enddate, ]


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

#######################################
# Using SQL to manipulate data frames
#######################################
library(sqldf)
newdf <- sqldf("select * from mtcars where carb=1 order by mpg", 
               row.names = TRUE)
newdf <- sqldf("select avg(mpg) as avg_mpg, avg(disp) as avg_disp,
    gear from mtcars where cyl in (4, 6) group by gear")