5.1 Comparing Groups: Tables and Visualization
# Names of the variables we will define for each segment
segVars <- c("age", "gender", "income", "kids", "ownHome", "subscribe")
# the data type for each segment
segVarType <- c("norm", "binom", "norm", "pois", "binom", "binom")
# names of the segments
segNames <- c("Suburb mix", "Urban hip", "Travelers", "Moving up")
# the size of each segment (N)
segSize <- c(100, 50, 80, 70)
# the means for each variable for each segment
segMeans <- matrix( c(
40, .5, 55000, 2, .5, .1,
24, .7, 21000, 1, .2, .2,
58, .5, 64000, 0, .7, .05,
36, .3, 52000, 2, .3, .2 ), ncol=length(segVars), byrow=TRUE)
colnames(segMeans) = segVars
segMeans
## age gender income kids ownHome subscribe
## [1,] 40 0.5 55000 2 0.5 0.10
## [2,] 24 0.7 21000 1 0.2 0.20
## [3,] 58 0.5 64000 0 0.7 0.05
## [4,] 36 0.3 52000 2 0.3 0.20
# the standard deviations for each segment (NA = not applicable for the variable)
segSDs <- matrix( c(
5, NA, 12000, NA, NA, NA,
2, NA, 5000, NA, NA, NA,
8, NA, 21000, NA, NA, NA,
4, NA, 10000, NA, NA, NA ), ncol=length(segVars), byrow=TRUE)
colnames(segSDs) = segVars
segSDs
## age gender income kids ownHome subscribe
## [1,] 5 NA 12000 NA NA NA
## [2,] 2 NA 5000 NA NA NA
## [3,] 8 NA 21000 NA NA NA
## [4,] 4 NA 10000 NA NA NA
### 5.1.2 Language Brief: for() Loops
(i.seq <- rep(sqrt(seq(from=2.1, to=6.2, by=1.7)), 3))
## [1] 1.449138 1.949359 2.345208 1.449138 1.949359 2.345208 1.449138 1.949359
## [9] 2.345208
for (i in i.seq ) { print(i) }
## [1] 1.449138
## [1] 1.949359
## [1] 2.345208
## [1] 1.449138
## [1] 1.949359
## [1] 2.345208
## [1] 1.449138
## [1] 1.949359
## [1] 2.345208
for (i in c("Hello ","world, ","welcome to R!")) { cat(i) }
## Hello world, welcome to R!
for (i in 1:length(i.seq)) { cat("Entry", i, "=", i.seq[i], "\n") }
## Entry 1 = 1.449138
## Entry 2 = 1.949359
## Entry 3 = 2.345208
## Entry 4 = 1.449138
## Entry 5 = 1.949359
## Entry 6 = 2.345208
## Entry 7 = 1.449138
## Entry 8 = 1.949359
## Entry 9 = 2.345208
for (i in seq_along(i.seq)) { cat("Entry", i, "=", i.seq[i], "\n") }
## Entry 1 = 1.449138
## Entry 2 = 1.949359
## Entry 3 = 2.345208
## Entry 4 = 1.449138
## Entry 5 = 1.949359
## Entry 6 = 2.345208
## Entry 7 = 1.449138
## Entry 8 = 1.949359
## Entry 9 = 2.345208
#for loopの注意点
#naとNULLのlengthを見る
c(na = length(NA),null = length(NULL))
## na null
## 1 0
#for loopで実行される、1:length(x)は何回回す？
c(1:length(NA))
## [1] 1
#!!!!!!1:0
c(1:length(NULL))
## [1] 1 0
# lengthがNULLの場合は
i.seq <- NULL
for (i in 1:length(i.seq)) { print (i) } # bad
## [1] 1
## [1] 0
# lengthがNAの場合
i.seq <- NA
for (i in 1:length(i.seq)) { print (i) } # bad
## [1] 1
# NA,NULL除く: use seq_along()
for (i in seq_along(NULL)) { print (i) } # better
# NA含め, NULL除く: use seq()
for (i in seq(NA)) { print (i) } # better
## [1] 1
for (i in seq(NULL)) { print (i) } # better
#it tests whether x[1] > 1 and then x[2] > 1 and so forth
#x is vector, not scalar.
x <- 1:5
if (x > 1) { # bad code -- will produce warning!
print ("hi")
} else {
print ("bye")
}
## Warning in if (x > 1) {: the condition has length > 1 and only the first
## element will be used
## [1] "bye"
ifelse(x > 1, "hi", "bye") # better
## [1] "bye" "hi" "hi" "hi" "hi"
#functionを使う時
fn.hi <- function(x) { paste(x,"dan") }
fn.bye <- function(x) { paste(x,"dan") }
ifelse(x > 2, fn.hi("hi"), fn.bye("bye") )
## [1] "bye dan" "bye dan" "hi dan" "hi dan" "hi dan"
###5.1.4 Final Segment Data Generation
# make sure we're starting our dataset from a known state
seg.df <- NULL
set.seed(02554)
# iterate over all the segments and create data for each
for (i in seq_along(segNames)) {
cat(i, segNames[i], "\n")
cat(i, segSize[i], "\n")
cat(i, segVars[i], "\n")
# create an empty matrix to hold this particular segment's data
this.seg <- data.frame(matrix(NA, nrow=segSize[i], ncol=length(segVars)))
# within a segment, iterate over the variables and draw appropriate random data
for (j in seq_along(segVars)) { # and iterate over each variable
if (segVarType[j] == "norm") { # draw random normals
this.seg[, j] <- rnorm(segSize[i], mean=segMeans[i, j], sd=segSDs[i, j])
} else if (segVarType[j] == "pois") { # draw counts
this.seg[, j] <- rpois(segSize[i], lambda=segMeans[i, j])
} else if (segVarType[j] == "binom") { # draw binomials
this.seg[, j] <- rbinom(segSize[i], size=1, prob=segMeans[i, j])
} else {
stop("Bad segment data type: ", segVarType[j])
}
}
# add this segment to the total dataset
seg.df <- rbind(seg.df, this.seg)
}
## 1 Suburb mix
## 1 100
## 1 age
## 2 Urban hip
## 2 50
## 2 gender
## 3 Travelers
## 3 80
## 3 income
## 4 Moving up
## 4 70
## 4 kids
# make the data frame names match what we defined
names(seg.df) <- segVars
# add segment membership for each row
seg.df$Segment <- factor(rep(segNames, times=segSize))
# convert the binomial variables to nicely labeled factors
seg.df$ownHome <- factor(seg.df$ownHome, labels=c("ownNo", "ownYes"))
seg.df$gender <- factor(seg.df$gender, labels=c("Female", "Male"))
seg.df$subscribe <- factor(seg.df$subscribe, labels=c("subNo", "subYes"))
# check the data and confirm it
summary(seg.df)
## age gender income kids ownHome
## Min. :19.26 Female:157 Min. : -5183 Min. :0.00 ownNo :159
## 1st Qu.:33.01 Male :143 1st Qu.: 39656 1st Qu.:0.00 ownYes:141
## Median :39.49 Median : 52014 Median :1.00
## Mean :41.20 Mean : 50937 Mean :1.27
## 3rd Qu.:47.90 3rd Qu.: 61403 3rd Qu.:2.00
## Max. :80.49 Max. :114278 Max. :7.00
## subscribe Segment
## subNo :260 Moving up : 70
## subYes: 40 Suburb mix:100
## Travelers : 80
## Urban hip : 50
##
##
5.2 Finding Descriptives by Group
mean(seg.df$income[seg.df$Segment == "Moving up"])
## [1] 53090.97
mean(seg.df$income[seg.df$Segment == "Moving up" &
seg.df$subscribe=="subNo"])
## [1] 53633.73
by(seg.df$income, seg.df$Segment, mean)
## seg.df$Segment: Moving up
## [1] 53090.97
## --------------------------------------------------------
## seg.df$Segment: Suburb mix
## [1] 55033.82
## --------------------------------------------------------
## seg.df$Segment: Travelers
## [1] 62213.94
## --------------------------------------------------------
## seg.df$Segment: Urban hip
## [1] 21681.93
by(seg.df$income, list(seg.df$Segment, seg.df$subscribe), mean)
## : Moving up
## : subNo
## [1] 53633.73
## --------------------------------------------------------
## : Suburb mix
## : subNo
## [1] 54942.69
## --------------------------------------------------------
## : Travelers
## : subNo
## [1] 62746.11
## --------------------------------------------------------
## : Urban hip
## : subNo
## [1] 22082.11
## --------------------------------------------------------
## : Moving up
## : subYes
## [1] 50919.89
## --------------------------------------------------------
## : Suburb mix
## : subYes
## [1] 56461.41
## --------------------------------------------------------
## : Travelers
## : subYes
## [1] 58488.77
## --------------------------------------------------------
## : Urban hip
## : subYes
## [1] 20081.19
aggregate(seg.df$income, list(seg.df$Segment), mean)
## Group.1 x
## 1 Moving up 53090.97
## 2 Suburb mix 55033.82
## 3 Travelers 62213.94
## 4 Urban hip 21681.93
seg.income.mean <- aggregate(seg.df$income, list(seg.df$Segment), mean)
seg.df$segIncome <- seg.income.mean[seg.df$Segment, 2]
car::some(seg.df)
## age gender income kids ownHome subscribe Segment segIncome
## 58 34.46528 Male 60971.76 2 ownNo subNo Suburb mix 55033.82
## 79 42.31337 Male 49674.79 0 ownYes subNo Suburb mix 55033.82
## 124 22.30333 Female 24541.24 1 ownNo subNo Urban hip 21681.93
## 136 23.08861 Male 33909.50 3 ownNo subNo Urban hip 21681.93
## 158 43.35230 Male 51787.88 0 ownNo subNo Travelers 62213.94
## 186 48.84991 Female 59075.12 0 ownNo subNo Travelers 62213.94
## 232 37.85733 Male 50980.48 5 ownYes subNo Moving up 53090.97
## 243 36.97339 Female 53792.40 0 ownNo subNo Moving up 53090.97
## 257 43.30929 Female 69549.93 3 ownNo subYes Moving up 53090.97
## 288 35.82586 Female 41766.29 2 ownNo subYes Moving up 53090.97
seg.df$Segment
## [1] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [7] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [13] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [19] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [25] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [31] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [37] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [43] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [49] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [55] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [61] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [67] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [73] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [79] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [85] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [91] Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix Suburb mix
## [97] Suburb mix Suburb mix Suburb mix Suburb mix Urban hip Urban hip
## [103] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [109] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [115] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [121] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [127] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [133] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [139] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [145] Urban hip Urban hip Urban hip Urban hip Urban hip Urban hip
## [151] Travelers Travelers Travelers Travelers Travelers Travelers
## [157] Travelers Travelers Travelers Travelers Travelers Travelers
## [163] Travelers Travelers Travelers Travelers Travelers Travelers
## [169] Travelers Travelers Travelers Travelers Travelers Travelers
## [175] Travelers Travelers Travelers Travelers Travelers Travelers
## [181] Travelers Travelers Travelers Travelers Travelers Travelers
## [187] Travelers Travelers Travelers Travelers Travelers Travelers
## [193] Travelers Travelers Travelers Travelers Travelers Travelers
## [199] Travelers Travelers Travelers Travelers Travelers Travelers
## [205] Travelers Travelers Travelers Travelers Travelers Travelers
## [211] Travelers Travelers Travelers Travelers Travelers Travelers
## [217] Travelers Travelers Travelers Travelers Travelers Travelers
## [223] Travelers Travelers Travelers Travelers Travelers Travelers
## [229] Travelers Travelers Moving up Moving up Moving up Moving up
## [235] Moving up Moving up Moving up Moving up Moving up Moving up
## [241] Moving up Moving up Moving up Moving up Moving up Moving up
## [247] Moving up Moving up Moving up Moving up Moving up Moving up
## [253] Moving up Moving up Moving up Moving up Moving up Moving up
## [259] Moving up Moving up Moving up Moving up Moving up Moving up
## [265] Moving up Moving up Moving up Moving up Moving up Moving up
## [271] Moving up Moving up Moving up Moving up Moving up Moving up
## [277] Moving up Moving up Moving up Moving up Moving up Moving up
## [283] Moving up Moving up Moving up Moving up Moving up Moving up
## [289] Moving up Moving up Moving up Moving up Moving up Moving up
## [295] Moving up Moving up Moving up Moving up Moving up Moving up
## Levels: Moving up Suburb mix Travelers Urban hip
#!!!!!! how it works?
car::some(seg.income.mean[seg.df$Segment, ],20)
## Group.1 x
## 2.20 Suburb mix 55033.82
## 2.47 Suburb mix 55033.82
## 2.52 Suburb mix 55033.82
## 2.65 Suburb mix 55033.82
## 2.70 Suburb mix 55033.82
## 2.83 Suburb mix 55033.82
## 2.85 Suburb mix 55033.82
## 2.90 Suburb mix 55033.82
## 4.41 Urban hip 21681.93
## 3.6 Travelers 62213.94
## 3.20 Travelers 62213.94
## 3.22 Travelers 62213.94
## 3.33 Travelers 62213.94
## 3.34 Travelers 62213.94
## 3.51 Travelers 62213.94
## 3.57 Travelers 62213.94
## 3.72 Travelers 62213.94
## 1.32 Moving up 53090.97
## 1.37 Moving up 53090.97
## 1.59 Moving up 53090.97
#The result is a data frame in which each row of seg.income.mean occurs many times in the order requested.
car::some(seg.income.mean[seg.df$Segment, 2],20)
## [1] 55033.82 55033.82 55033.82 55033.82 55033.82 21681.93 21681.93
## [8] 62213.94 62213.94 62213.94 62213.94 62213.94 53090.97 53090.97
## [15] 53090.97 53090.97 53090.97 53090.97 53090.97 53090.97
#one more time with another sample data,
(test = data.frame(group = c("A","B"), value= c(1:10)))
## group value
## 1 A 1
## 2 B 2
## 3 A 3
## 4 B 4
## 5 A 5
## 6 B 6
## 7 A 7
## 8 B 8
## 9 A 9
## 10 B 10
#factor works
#一番上に一致するfactorのレコードを返す(valueが1,2のみ)
test[factor(rep(c("A","B"),5)),]
## group value
## 1 A 1
## 2 B 2
## 1.1 A 1
## 2.1 B 2
## 1.2 A 1
## 2.2 B 2
## 1.3 A 1
## 2.3 B 2
## 1.4 A 1
## 2.4 B 2
#integer also works
test[as.integer(factor(rep(c("A","B"),5))),]
## group value
## 1 A 1
## 2 B 2
## 1.1 A 1
## 2.1 B 2
## 1.2 A 1
## 2.2 B 2
## 1.3 A 1
## 2.3 B 2
## 1.4 A 1
## 2.4 B 2
#character dosn't work
test[c("A","B"),]
## group value
## NA <NA> NA
## NA.1 <NA> NA
#結論:ちゃんとわかって使わないと、変な結果が出るので気をつけるように
# clear that variable
seg.df$segIncome <- NULL
#### formula version
#response variables on the left from explanatory variables on the right.
#take income by Segment within the data set seg.df, and apply mean to each group
aggregate(income ~ Segment, data=seg.df, mean)
## Segment income
## 1 Moving up 53090.97
## 2 Suburb mix 55033.82
## 3 Travelers 62213.94
## 4 Urban hip 21681.93
##########
# two-way data aggregation
#by list
aggregate(seg.df$income, list(seg.df$Segment, seg.df$ownHome), mean)
## Group.1 Group.2 x
## 1 Moving up ownNo 54497.68
## 2 Suburb mix ownNo 54932.83
## 3 Travelers ownNo 63188.42
## 4 Urban hip ownNo 21337.59
## 5 Moving up ownYes 50216.37
## 6 Suburb mix ownYes 55143.21
## 7 Travelers ownYes 61889.12
## 8 Urban hip ownYes 23059.27
#by formula
aggregate(income ~ Segment + ownHome, data=seg.df, mean)
## Segment ownHome income
## 1 Moving up ownNo 54497.68
## 2 Suburb mix ownNo 54932.83
## 3 Travelers ownNo 63188.42
## 4 Urban hip ownNo 21337.59
## 5 Moving up ownYes 50216.37
## 6 Suburb mix ownYes 55143.21
## 7 Travelers ownYes 61889.12
## 8 Urban hip ownYes 23059.27
#Multiple variable formula
aggregate(income ~ Segment + ownHome + subscribe, data=seg.df, mean)
## Segment ownHome subscribe income
## 1 Moving up ownNo subNo 55402.89
## 2 Suburb mix ownNo subNo 54579.99
## 3 Travelers ownNo subNo 65852.54
## 4 Urban hip ownNo subNo 21604.16
## 5 Moving up ownYes subNo 49898.85
## 6 Suburb mix ownYes subNo 55354.86
## 7 Travelers ownYes subNo 61749.71
## 8 Urban hip ownYes subNo 23993.93
## 9 Moving up ownNo subYes 50675.70
## 10 Suburb mix ownNo subYes 63753.97
## 11 Travelers ownNo subYes 48091.75
## 12 Urban hip ownNo subYes 20271.33
## 13 Moving up ownYes subYes 51359.44
## 14 Suburb mix ownYes subYes 52815.13
## 15 Travelers ownYes subYes 62944.64
## 16 Urban hip ownYes subYes 19320.64
agg.data <- aggregate(income ~ Segment + ownHome, data=seg.df, mean)
agg.data[2, ]
## Segment ownHome income
## 2 Suburb mix ownNo 54932.83
agg.data[2, 3]
## [1] 54932.83
# Count of factor level occurence by factor
#not bad
table(seg.df$Segment, ownHome = seg.df$ownHome)
## ownHome
## ownNo ownYes
## Moving up 47 23
## Suburb mix 52 48
## Travelers 20 60
## Urban hip 40 10
#better
with(seg.df, table(Segment, ownHome))
## ownHome
## Segment ownNo ownYes
## Moving up 47 23
## Suburb mix 52 48
## Travelers 20 60
## Urban hip 40 10
#multi dimentional array
temp = with(seg.df, table(Segment, ownHome, subscribe))
temp
## , , subscribe = subNo
##
## ownHome
## Segment ownNo ownYes
## Moving up 38 18
## Suburb mix 50 44
## Travelers 17 53
## Urban hip 32 8
##
## , , subscribe = subYes
##
## ownHome
## Segment ownNo ownYes
## Moving up 9 5
## Suburb mix 2 4
## Travelers 3 7
## Urban hip 8 2
temp[,,1]
## ownHome
## Segment ownNo ownYes
## Moving up 38 18
## Suburb mix 50 44
## Travelers 17 53
## Urban hip 32 8
temp[,,2]
## ownHome
## Segment ownNo ownYes
## Moving up 9 5
## Suburb mix 2 4
## Travelers 3 7
## Urban hip 8 2
with(seg.df, table(kids, Segment))
## Segment
## kids Moving up Suburb mix Travelers Urban hip
## 0 13 11 80 17
## 1 17 36 0 17
## 2 18 22 0 11
## 3 13 19 0 4
## 4 5 7 0 1
## 5 3 3 0 0
## 6 0 2 0 0
## 7 1 0 0 0
# total of variables by factor, total kids by Segment
xtabs(kids ~ Segment, data=seg.df)
## Segment
## Moving up Suburb mix Travelers Urban hip
## 134 192 0 55
table(seg.df$kids, seg.df$Segment)
##
## Moving up Suburb mix Travelers Urban hip
## 0 13 11 80 17
## 1 17 36 0 17
## 2 18 22 0 11
## 3 13 19 0 4
## 4 5 7 0 1
## 5 3 3 0 0
## 6 0 2 0 0
## 7 1 0 0 0
aggregate(kids ~ Segment, data=seg.df, sum)
## Segment kids
## 1 Moving up 134
## 2 Suburb mix 192
## 3 Travelers 0
## 4 Urban hip 55
#Another option is to multiply the frequency table by marginal number of kids and add it up:
seg.tab <- with(seg.df, table(kids, Segment))
apply(seg.tab*0:7, 2, sum)
## Moving up Suburb mix Travelers Urban hip
## 134 192 0 55
colSums(seg.tab*0:7)
## Moving up Suburb mix Travelers Urban hip
## 134 192 0 55
#### visualize counts by group
# histogram by 1 factor
lattice::histogram(~subscribe | Segment, data=seg.df)
with(seg.df, table(Segment, subscribe)/as.integer(table(Segment)))
## subscribe
## Segment subNo subYes
## Moving up 0.800 0.200
## Suburb mix 0.940 0.060
## Travelers 0.875 0.125
## Urban hip 0.800 0.200
#prop.table can do this easier
# counts instead of proportions, and some visual options
lattice::histogram(~subscribe | Segment, data=seg.df, type="count",
layout=c(4,1), col=c("burlywood", "darkolivegreen"))
with(seg.df, table(Segment, subscribe))
## subscribe
## Segment subNo subYes
## Moving up 56 14
## Suburb mix 94 6
## Travelers 70 10
## Urban hip 40 10
# histogram by 2 factors
lattice::histogram(~subscribe | Segment + ownHome, data=seg.df)
#?how to make this data
# use prop.table to get just positive proportion
prop.table(table(seg.df$subscribe, seg.df$Segment), margin=2)
##
## Moving up Suburb mix Travelers Urban hip
## subNo 0.800 0.940 0.875 0.800
## subYes 0.200 0.060 0.125 0.200
prop.table(with(seg.df, table(subscribe, Segment)), margin=2)
## Segment
## subscribe Moving up Suburb mix Travelers Urban hip
## subNo 0.800 0.940 0.875 0.800
## subYes 0.200 0.060 0.125 0.200
lattice::barchart(prop.table(table(seg.df$subscribe, seg.df$Segment), margin=2)[2, ],
xlab="Subscriber proportion by Segment", col="darkolivegreen")
#with generic function
par(mfrow=c(1,1), mar=c(3, 7, 3, 3))
barplot(prop.table(table(seg.df$subscribe, seg.df$Segment), margin=2)[2, ],
horiz=TRUE,
col="darkolivegreen",
las=2
)
par(old.par)
#### visualize continuous data by group
## bar chart for continuous variable, the "spreadsheet" way to graph it
# aggregate our data
seg.mean <- aggregate(income ~ Segment, data=seg.df, mean)
lattice::barchart(income~Segment, data=seg.mean, col="grey")
seg.income.agg <- aggregate(income ~ Segment + ownHome, data=seg.df, mean)
# then plot it
lattice::barchart(income ~ Segment, data=seg.income.agg,
groups=ownHome, auto.key=TRUE,
par.settings = lattice::simpleTheme(col=c("gray95", "gray50"))
)
## better = boxplot for continuous variable
# base graphics way to do this
temp <- boxplot(income ~ Segment, data=seg.df, yaxt="n", ylab="Income ($k)")
ax.seq <- seq(from=0, to=120000, by=20000)
axis(side=2, at=ax.seq, labels=paste(ax.seq/1000, "k", sep=""), las=1)
#四分位数
iqr_stats <- temp$stats
colnames(iqr_stats) <- temp$names
rownames(iqr_stats) <- c("not min??", "第1四分位数","中央値","第3四分位数", "not max??")
print(iqr_stats)
## Moving up Suburb mix Travelers Urban hip
## not min?? 29771.91 28270.15 15346.68 11985.25
## 第1四分位数 46540.88 48057.69 48549.67 17784.57
## 中央値 52564.55 54819.01 61014.30 22141.01
## 第3四分位数 58933.34 61339.16 77359.70 24533.93
## not max?? 73797.50 81041.99 114278.26 33909.50
# lattice gives more options, especially for multiway breakouts ("conditioning")
lattice::bwplot(Segment ~ income, data=seg.df, horizontal=TRUE, xlab = "Income")
# add conditioning variable
lattice::bwplot(Segment ~ income | ownHome, data=seg.df, horizontal=TRUE, xlab="Income")
