# Chapter 1: Introduction

## Section 1.2: How to Use this Book

## install.packages("swirl") # install the package
install_course_github("kosukeimai", "qss-swirl") # install the course
swirl()

## Section 1.3: Introduction to R

### Section 1.3.1: Arithmetic Operations

5 + 3
## [1] 8
5 - 3
## [1] 2
5 / 3
## [1] 1.666667
5 ^ 3
## [1] 125
5 * (10 - 3)
## [1] 35
sqrt(4)
## [1] 2

### Section 1.3.2: Objects

result <- 5 + 3
result
## [1] 8
print(result)
## [1] 8
result <- 5 - 3
result
## [1] 2
kosuke <- "instructor"
kosuke
## [1] "instructor"
kosuke <- "instructor and author"
kosuke
## [1] "instructor and author"
Result <- "5"
Result
## [1] "5"
result
## [1] 2
class(result)
## [1] "numeric"
Result
## [1] "5"
class(Result)
## [1] "character"
class(sqrt)
## [1] "function"

### Section 1.3.3: Vectors

world.pop <- c(2525779, 3026003, 3691173, 4449049, 5320817, 6127700, 6916183)
world.pop
## [1] 2525779 3026003 3691173 4449049 5320817 6127700 6916183
pop.first <- c(2525779, 3026003, 3691173)
pop.second <- c(4449049, 5320817, 6127700, 6916183)
pop.all <- c(pop.first, pop.second)
pop.all
## [1] 2525779 3026003 3691173 4449049 5320817 6127700 6916183
world.pop[2]
## [1] 3026003
world.pop[c(2, 4)]
## [1] 3026003 4449049
world.pop[c(4, 2)]
## [1] 4449049 3026003
world.pop[-3]
## [1] 2525779 3026003 4449049 5320817 6127700 6916183
pop.million <- world.pop / 1000
pop.million
## [1] 2525.779 3026.003 3691.173 4449.049 5320.817 6127.700 6916.183
pop.rate <- world.pop / world.pop[1]
pop.rate
## [1] 1.000000 1.198047 1.461400 1.761456 2.106604 2.426063 2.738238
pop.increase <- world.pop[-1] - world.pop[-7]
percent.increase <- (pop.increase / world.pop[-7]) * 100
percent.increase
## [1] 19.80474 21.98180 20.53212 19.59448 15.16464 12.86752
percent.increase[c(1, 2)] <- c(20, 22)
percent.increase
## [1] 20.00000 22.00000 20.53212 19.59448 15.16464 12.86752

### Section 1.3.4: Functions

length(world.pop)
## [1] 7
min(world.pop)
## [1] 2525779
max(world.pop)
## [1] 6916183
range(world.pop)
## [1] 2525779 6916183
mean(world.pop)
## [1] 4579529
sum(world.pop) / length(world.pop)
## [1] 4579529
year <- seq(from = 1950, to = 2010, by = 10)
year
## [1] 1950 1960 1970 1980 1990 2000 2010
seq(to = 2010, by = 10, from = 1950)
## [1] 1950 1960 1970 1980 1990 2000 2010
seq(from = 2010, to = 1950, by = -10)
## [1] 2010 2000 1990 1980 1970 1960 1950
2008:2012
## [1] 2008 2009 2010 2011 2012
2012:2008
## [1] 2012 2011 2010 2009 2008
names(world.pop)
## NULL
names(world.pop) <- year
names(world.pop)
## [1] "1950" "1960" "1970" "1980" "1990" "2000" "2010"
world.pop
##    1950    1960    1970    1980    1990    2000    2010
## 2525779 3026003 3691173 4449049 5320817 6127700 6916183
## myfunction <- function(input1, input2, ..., inputN) {
##
##     DEFINE output' USING INPUTS
##
##     return(output)
## }

my.summary <- function(x){ # function takes one input
s.out <- sum(x)
l.out <- length(x)
m.out <- s.out / l.out
out <- c(s.out, l.out, m.out) # define the output
names(out) <- c("sum", "length", "mean") # add labels
return(out) # end function by calling output
}
z <- 1:10
my.summary(z)
##    sum length   mean
##   55.0   10.0    5.5
my.summary(world.pop)
##      sum   length     mean
## 32056704        7  4579529

### Section 1.3.5: Data Files

## setwd("qss/INTRO")
## getwd()

data("UNpop", package = "qss")
class(UNpop)
## [1] "data.frame"
## load("UNpop.RData")

names(UNpop)
## [1] "year"      "world.pop"
nrow(UNpop)
## [1] 7
ncol(UNpop)
## [1] 2
dim(UNpop)
## [1] 7 2
summary(UNpop)
##       year        world.pop
##  Min.   :1950   Min.   :2525779
##  1st Qu.:1965   1st Qu.:3358588
##  Median :1980   Median :4449049
##  Mean   :1980   Mean   :4579529
##  3rd Qu.:1995   3rd Qu.:5724258
##  Max.   :2010   Max.   :6916183
UNpop$world.pop ## [1] 2525779 3026003 3691173 4449049 5320817 6127700 6916183 UNpop[, "world.pop"] # extract the column called "world.pop" ## [1] 2525779 3026003 3691173 4449049 5320817 6127700 6916183 UNpop[c(1, 2, 3),] # extract the first three rows (and all columns) ## year world.pop ## 1 1950 2525779 ## 2 1960 3026003 ## 3 1970 3691173 UNpop[1:3, "year"] # extract the first three rows of the "year" column ## [1] 1950 1960 1970 ## take elements 1, 3, 5, ... of the "world.pop" variable UNpop$world.pop[seq(from = 1, to = nrow(UNpop), by = 2)]
## [1] 2525779 3691173 5320817 6916183
world.pop <- c(UNpop$world.pop, NA) world.pop ## [1] 2525779 3026003 3691173 4449049 5320817 6127700 6916183 NA mean(world.pop) ## [1] NA mean(world.pop, na.rm = TRUE) ## [1] 4579529 ### Section 1.3.6: Saving Objects save.image("qss/INTRO/Chapter1.RData") save(UNpop, file = "Chapter1.RData") save(world.pop, year, file = "qss/INTRO/Chapter1.RData") write.csv(UNpop, file = "UNpop.csv") load("Chapter1.RData") ### Section 1.3.7: Packages ## install.packages("foreign") # install package library("foreign") # load package read.dta(system.file("extdata/data_files/UNpop.dta", package = "qss")) ## year world_pop ## 1 1950 2525.779 ## 2 1960 3026.003 ## 3 1970 3691.173 ## 4 1980 4449.049 ## 5 1990 5320.817 ## 6 2000 6127.700 ## 7 2010 6916.183 ## read.spss("UNpop.sav") write.dta(UNpop, file = "UNpop.dta") ### Section 1.3.8: Programming and Learning Tips ## source("UNpop.R") ## ## File: UNpop.R ## Author: Kosuke Imai ## The code loads the UN population data and saves it as a STATA file ## data("UNpop", package = "qss") UNpop$world.pop <- UNpop\$world.pop / 1000  # population in millions
library(foreign)
write.dta(UNpop, file = "UNpop.dta")
library(lintr)
#lint("demo/UNpop.R")`