1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
#-*- R -*-
## Script from Fourth Edition of `Modern Applied Statistics with S'
# Chapter 2 Data Manipulation
library(MASS)
options(echo = T, width=65, digits=5, height=9999)
-2:2
powers.of.pi <- pi^(-2:2)
powers.of.pi
class(powers.of.pi)
print(powers.of.pi)
summary(powers.of.pi)
# rm(powers.of.pi)
powers.of.pi[5]
names(powers.of.pi) <- -2:2
powers.of.pi
powers.of.pi["2"]
class(powers.of.pi)
as.vector(powers.of.pi)
names(powers.of.pi) <- NULL
powers.of.pi
citizen <- factor(c("uk", "us", "no", "au", "uk", "us", "us"))
citizen
unclass(citizen)
citizen[5:7]
citizen <- factor(c("uk", "us", "no", "au", "uk", "us", "us"),
levels = c("us", "fr", "no", "au", "uk"))
citizen
income <- ordered(c("Mid", "Hi", "Lo", "Mid", "Lo", "Hi", "Lo"))
income
as.numeric(income)
inc <- ordered(c("Mid", "Hi", "Lo", "Mid", "Lo", "Hi", "Lo"),
levels = c("Lo", "Mid", "Hi"))
inc
erupt <- cut(geyser$duration, breaks = 0:6)
erupt <- ordered(erupt, labels=levels(erupt))
erupt
painters
row.names(painters)
summary(painters) # try it!
attach(painters)
School
detach("painters")
mymat <- matrix(1:30, 3, 10)
mymat
myarr <- mymat
dim(myarr) <- c(3, 5, 2)
class(myarr)
myarr
dim(myarr)
dimnames(myarr) <- list(letters[1:3], NULL, c("(i)", "(ii)"))
myarr
newvar <- NA
class(NA)
newvar > 3
x <- c(pi, 4, 5)
x[2] <- NA
x
class(x)
is.na(x)
1/0
x <- c(-1, 0, 1)/0
x
is.na(x)
x > Inf
x <- c(2.9, 3.1, 3.4, 3.4, 3.7, 3.7, 2.8, 2.5)
letters[1:3]
letters[c(1:3,3:1)]
longitude <- state.center$x
names(longitude) <- state.name
longitude[c("Hawaii", "Alaska")]
myarr[1, 2:4, ]
myarr[1, 2:4, , drop = F]
attach(painters)
painters[Colour >= 17, ]
painters[Colour >= 15 & Composition > 10, ]
painters[Colour >= 15 & School != "D", ]
painters[is.element(School, c("A", "B", "D")), ]
painters[School %in% c("A", "B", "D"), ] ## R only
painters[cbind(1:nrow(painters), ifelse(Colour > Expression, 3, 4))]
painters[grep("io$", row.names(painters)), ]
detach("painters")
m <- 30
fglsub1 <- fgl[sort(sample(1:nrow(fgl), m)), ]
fglsub2 <- fgl[rbinom(nrow(fgl), 1, 0.1) == 1, ]
fglsub3 <- fgl[seq(1, nrow(fgl), by = 10), ]
painters[sort.list(row.names(painters)), ]
lcrabs <- crabs # make a copy
lcrabs[, 4:8] <- log(crabs[, 4:8])
scrabs <- crabs # make a copy
scrabs[, 4:8] <- lapply(scrabs[, 4:8], scale)
## or to just centre the variables
scrabs[, 4:8] <- lapply(scrabs[, 4:8], scale, scale = F)
scrabs <- crabs # make a copy
scrabs[ ] <- lapply(scrabs,
function(x) {if(is.numeric(x)) scale(x) else x})
sapply(crabs, is.numeric)
by(crabs[, 4:8], list(crabs$sp, crabs$sex), summary)
aggregate(crabs[, 4:8], by = list(sp=crabs$sp, sex=crabs$sex),
median)
authors <- data.frame(
surname = c("Tukey", "Venables", "Tierney", "Ripley", "McNeil"),
nationality = c("US", "Australia", "US", "UK", "Australia"),
deceased = c("yes", rep("no", 4)))
books <- data.frame(
name = c("Tukey", "Venables", "Tierney",
"Ripley", "Ripley", "McNeil", "R Core"),
title = c("Exploratory Data Analysis",
"Modern Applied Statistics ...",
"LISP-STAT",
"Spatial Statistics", "Stochastic Simulation",
"Interactive Data Analysis",
"An Introduction to R"))
authors
books
merge(authors, books, by.x = "surname", by.y = "name")
attach(quine)
table(Age)
table(Sex, Age)
tab <- xtabs(~ Sex + Age, quine)
unclass(tab)
tapply(Days, Age, mean)
tapply(Days, Age, mean, trim = 0.1)
tapply(Days, list(Sex, Age), mean)
tapply(Days, list(Sex, Age),
function(x) sqrt(var(x)/length(x)))
quineFO <- quine[sapply(quine, is.factor)]
#tab <- do.call("table", quineFO)
tab <- table(quineFO)
QuineF <- expand.grid(lapply(quineFO, levels))
QuineF$Freq <- as.vector(tab)
QuineF
# End of ch02
|
