Data
setwd("~/Dropbox/Works/Class/Case_studies_in_stat/R.WD/sejong")
load("reading.rda")
options(width=132)
reading.rate
## year size all m f 20s 30s 40s 50s 60.over under.middle high.school college metro medium small
## 1 1995 1200 79.0 81.7 76.3 94.9 84.6 77.6 53.4 NA 44.8 85.5 95.8 84.3 84.1 61.8
## 2 1996 1200 77.2 79.6 74.8 93.9 87.1 71.6 53.7 NA 43.8 82.0 95.0 80.2 82.5 62.9
## 3 1999 1500 77.8 77.1 78.5 91.2 86.4 74.3 49.5 NA 36.4 79.9 93.4 82.0 80.1 64.9
## 4 2002 1200 72.0 70.0 74.0 85.9 79.8 74.1 39.1 NA 25.2 69.3 88.5 76.6 72.7 60.2
## 5 2004 1000 76.3 74.0 78.6 92.2 82.9 78.1 43.0 NA 30.2 75.2 90.5 80.1 76.7 66.7
## 6 2006 1000 75.9 78.6 73.1 88.6 87.0 74.7 53.0 NA 31.0 67.0 93.7 75.1 78.9 66.3
## 7 2007 1000 76.7 76.8 76.6 86.3 84.2 79.0 57.5 NA 27.0 71.9 88.1 76.7 77.2 74.2
## 8 2008 1000 72.2 67.8 76.7 81.1 76.6 77.5 56.0 NA 34.8 62.3 87.4 71.0 74.0 70.5
## 9 2009 1000 71.7 73.2 70.2 85.7 82.0 74.2 55.9 36.4 26.8 64.7 89.4 71.0 74.0 64.8
## 10 2010 1000 65.4 63.0 67.9 82.9 72.3 64.6 55.4 34.8 29.1 51.0 86.0 67.8 67.5 41.2
str(reading.rate)
## 'data.frame': 10 obs. of 16 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010
## $ size : int 1200 1200 1500 1200 1000 1000 1000 1000 1000 1000
## $ all : num 79 77.2 77.8 72 76.3 75.9 76.7 72.2 71.7 65.4
## $ m : num 81.7 79.6 77.1 70 74 78.6 76.8 67.8 73.2 63
## $ f : num 76.3 74.8 78.5 74 78.6 73.1 76.6 76.7 70.2 67.9
## $ 20s : num 94.9 93.9 91.2 85.9 92.2 88.6 86.3 81.1 85.7 82.9
## $ 30s : num 84.6 87.1 86.4 79.8 82.9 87 84.2 76.6 82 72.3
## $ 40s : num 77.6 71.6 74.3 74.1 78.1 74.7 79 77.5 74.2 64.6
## $ 50s : num 53.4 53.7 49.5 39.1 43 53 57.5 56 55.9 55.4
## $ 60.over : num NA NA NA NA NA NA NA NA 36.4 34.8
## $ under.middle: num 44.8 43.8 36.4 25.2 30.2 31 27 34.8 26.8 29.1
## $ high.school : num 85.5 82 79.9 69.3 75.2 67 71.9 62.3 64.7 51
## $ college : num 95.8 95 93.4 88.5 90.5 93.7 88.1 87.4 89.4 86
## $ metro : num 84.3 80.2 82 76.6 80.1 75.1 76.7 71 71 67.8
## $ medium : num 84.1 82.5 80.1 72.7 76.7 78.9 77.2 74 74 67.5
## $ small : num 61.8 62.9 64.9 60.2 66.7 66.3 74.2 70.5 64.8 41.2
reading.quantity
## year size all m f 20s 30s 40s 50s 60.over under.middle high.school college metro medium small
## 1 1995 1200 9.6 9.9 9.3 13.1 11.2 7.7 4.7 NA 3.3 8.9 15.7 10.3 13.9 10.6
## 2 1996 1200 9.1 10.2 8.1 14.5 9.8 7.3 4.2 NA 2.3 9.2 14.5 10.7 10.0 4.4
## 3 1999 1500 9.3 9.6 8.9 13.0 10.5 7.6 3.5 NA 1.6 7.6 15.0 10.5 9.7 5.9
## 4 2002 1200 10.0 10.2 9.8 14.1 10.1 10.4 3.4 NA 1.3 8.2 14.5 9.9 11.8 7.9
## 5 2004 1000 11.0 10.4 11.7 16.9 10.2 10.3 3.8 NA 4.2 8.0 15.7 12.0 10.7 9.0
## 6 2006 1000 11.9 12.3 11.5 14.6 13.3 10.4 9.0 NA 2.4 7.9 17.3 10.3 13.9 10.6
## 7 2007 1000 12.1 12.8 11.4 14.4 14.4 12.3 7.4 NA 2.5 9.5 15.5 11.5 12.6 13.5
## 8 2008 1000 11.9 11.4 12.4 13.4 13.1 13.4 8.1 NA 4.8 8.0 16.5 11.4 12.9 9.1
## 9 2009 1000 10.9 12.6 9.3 19.4 11.1 9.0 5.5 4.6 2.9 8.2 15.3 10.7 12.0 6.9
## 10 2010 1000 10.8 10.3 11.4 16.1 12.0 11.0 6.2 5.4 2.5 6.4 16.5 12.0 10.6 5.7
str(reading.quantity)
## 'data.frame': 10 obs. of 16 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010
## $ size : int 1200 1200 1500 1200 1000 1000 1000 1000 1000 1000
## $ all : num 9.6 9.1 9.3 10 11 11.9 12.1 11.9 10.9 10.8
## $ m : num 9.9 10.2 9.6 10.2 10.4 12.3 12.8 11.4 12.6 10.3
## $ f : num 9.3 8.1 8.9 9.8 11.7 11.5 11.4 12.4 9.3 11.4
## $ 20s : num 13.1 14.5 13 14.1 16.9 14.6 14.4 13.4 19.4 16.1
## $ 30s : num 11.2 9.8 10.5 10.1 10.2 13.3 14.4 13.1 11.1 12
## $ 40s : num 7.7 7.3 7.6 10.4 10.3 10.4 12.3 13.4 9 11
## $ 50s : num 4.7 4.2 3.5 3.4 3.8 9 7.4 8.1 5.5 6.2
## $ 60.over : num NA NA NA NA NA NA NA NA 4.6 5.4
## $ under.middle: num 3.3 2.3 1.6 1.3 4.2 2.4 2.5 4.8 2.9 2.5
## $ high.school : num 8.9 9.2 7.6 8.2 8 7.9 9.5 8 8.2 6.4
## $ college : num 15.7 14.5 15 14.5 15.7 17.3 15.5 16.5 15.3 16.5
## $ metro : num 10.3 10.7 10.5 9.9 12 10.3 11.5 11.4 10.7 12
## $ medium : num 13.9 10 9.7 11.8 10.7 13.9 12.6 12.9 12 10.6
## $ small : num 10.6 4.4 5.9 7.9 9 10.6 13.5 9.1 6.9 5.7
독서율
reshape for ggplot
library(reshape2)
(reading.r.sex <- melt(reading.rate[c("year", "all", "m", "f")], idvars = "year", measure.vars=c("all", "m", "f"), variable.name = "gender", value.name = "rate"))
## year gender rate
## 1 1995 all 79.0
## 2 1996 all 77.2
## 3 1999 all 77.8
## 4 2002 all 72.0
## 5 2004 all 76.3
## 6 2006 all 75.9
## 7 2007 all 76.7
## 8 2008 all 72.2
## 9 2009 all 71.7
## 10 2010 all 65.4
## 11 1995 m 81.7
## 12 1996 m 79.6
## 13 1999 m 77.1
## 14 2002 m 70.0
## 15 2004 m 74.0
## 16 2006 m 78.6
## 17 2007 m 76.8
## 18 2008 m 67.8
## 19 2009 m 73.2
## 20 2010 m 63.0
## 21 1995 f 76.3
## 22 1996 f 74.8
## 23 1999 f 78.5
## 24 2002 f 74.0
## 25 2004 f 78.6
## 26 2006 f 73.1
## 27 2007 f 76.6
## 28 2008 f 76.7
## 29 2009 f 70.2
## 30 2010 f 67.9
str(reading.r.sex)
## 'data.frame': 30 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ gender: Factor w/ 3 levels "all","m","f": 1 1 1 1 1 1 1 1 1 1 ...
## $ rate : num 79 77.2 77.8 72 76.3 75.9 76.7 72.2 71.7 65.4 ...
(reading.r.age <- melt(reading.rate[c("year", "20s", "30s", "40s", "50s", "60.over")], idvars = "year", measure.vars=c("20s", "30s", "40s", "50s", "60.over"), variable.name = "age", value.name = "rate"))
## year age rate
## 1 1995 20s 94.9
## 2 1996 20s 93.9
## 3 1999 20s 91.2
## 4 2002 20s 85.9
## 5 2004 20s 92.2
## 6 2006 20s 88.6
## 7 2007 20s 86.3
## 8 2008 20s 81.1
## 9 2009 20s 85.7
## 10 2010 20s 82.9
## 11 1995 30s 84.6
## 12 1996 30s 87.1
## 13 1999 30s 86.4
## 14 2002 30s 79.8
## 15 2004 30s 82.9
## 16 2006 30s 87.0
## 17 2007 30s 84.2
## 18 2008 30s 76.6
## 19 2009 30s 82.0
## 20 2010 30s 72.3
## 21 1995 40s 77.6
## 22 1996 40s 71.6
## 23 1999 40s 74.3
## 24 2002 40s 74.1
## 25 2004 40s 78.1
## 26 2006 40s 74.7
## 27 2007 40s 79.0
## 28 2008 40s 77.5
## 29 2009 40s 74.2
## 30 2010 40s 64.6
## 31 1995 50s 53.4
## 32 1996 50s 53.7
## 33 1999 50s 49.5
## 34 2002 50s 39.1
## 35 2004 50s 43.0
## 36 2006 50s 53.0
## 37 2007 50s 57.5
## 38 2008 50s 56.0
## 39 2009 50s 55.9
## 40 2010 50s 55.4
## 41 1995 60.over NA
## 42 1996 60.over NA
## 43 1999 60.over NA
## 44 2002 60.over NA
## 45 2004 60.over NA
## 46 2006 60.over NA
## 47 2007 60.over NA
## 48 2008 60.over NA
## 49 2009 60.over 36.4
## 50 2010 60.over 34.8
str(reading.r.age)
## 'data.frame': 50 obs. of 3 variables:
## $ year: int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ age : Factor w/ 5 levels "20s","30s","40s",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ rate: num 94.9 93.9 91.2 85.9 92.2 88.6 86.3 81.1 85.7 82.9 ...
(reading.r.edu <- melt(reading.rate[c("year", "under.middle", "high.school", "college")], idvars = "year", measure.vars=c("under.middle", "high.school", "college"), variable.name = "education", value.name = "rate"))
## year education rate
## 1 1995 under.middle 44.8
## 2 1996 under.middle 43.8
## 3 1999 under.middle 36.4
## 4 2002 under.middle 25.2
## 5 2004 under.middle 30.2
## 6 2006 under.middle 31.0
## 7 2007 under.middle 27.0
## 8 2008 under.middle 34.8
## 9 2009 under.middle 26.8
## 10 2010 under.middle 29.1
## 11 1995 high.school 85.5
## 12 1996 high.school 82.0
## 13 1999 high.school 79.9
## 14 2002 high.school 69.3
## 15 2004 high.school 75.2
## 16 2006 high.school 67.0
## 17 2007 high.school 71.9
## 18 2008 high.school 62.3
## 19 2009 high.school 64.7
## 20 2010 high.school 51.0
## 21 1995 college 95.8
## 22 1996 college 95.0
## 23 1999 college 93.4
## 24 2002 college 88.5
## 25 2004 college 90.5
## 26 2006 college 93.7
## 27 2007 college 88.1
## 28 2008 college 87.4
## 29 2009 college 89.4
## 30 2010 college 86.0
str(reading.r.edu)
## 'data.frame': 30 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ education: Factor w/ 3 levels "under.middle",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ rate : num 44.8 43.8 36.4 25.2 30.2 31 27 34.8 26.8 29.1 ...
(reading.r.res <- melt(reading.rate[c("year", "metro", "medium", "small")], idvars = "year", measure.vars=c("metro", "medium", "small"), variable.name = "residence", value.name = "rate"))
## year residence rate
## 1 1995 metro 84.3
## 2 1996 metro 80.2
## 3 1999 metro 82.0
## 4 2002 metro 76.6
## 5 2004 metro 80.1
## 6 2006 metro 75.1
## 7 2007 metro 76.7
## 8 2008 metro 71.0
## 9 2009 metro 71.0
## 10 2010 metro 67.8
## 11 1995 medium 84.1
## 12 1996 medium 82.5
## 13 1999 medium 80.1
## 14 2002 medium 72.7
## 15 2004 medium 76.7
## 16 2006 medium 78.9
## 17 2007 medium 77.2
## 18 2008 medium 74.0
## 19 2009 medium 74.0
## 20 2010 medium 67.5
## 21 1995 small 61.8
## 22 1996 small 62.9
## 23 1999 small 64.9
## 24 2002 small 60.2
## 25 2004 small 66.7
## 26 2006 small 66.3
## 27 2007 small 74.2
## 28 2008 small 70.5
## 29 2009 small 64.8
## 30 2010 small 41.2
str(reading.r.res)
## 'data.frame': 30 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ residence: Factor w/ 3 levels "metro","medium",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ rate : num 84.3 80.2 82 76.6 80.1 75.1 76.7 71 71 67.8 ...
성별
library(ggplot2)
source("../../R.WD/lifetable/theme_kr.R")
(r.sex1 <- ggplot(reading.r.sex, aes(x=year, y=rate, colour=gender)) + geom_point())
(r.sex2 <- r.sex1 + geom_line())
(r.sex3 <- r.sex2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서율(%)") + ggtitle("성별 독서율의 변화"))
(r.sex4 <- r.sex3 + labs(colour="성별") + scale_colour_discrete(labels=c("전체", "남자", "여자")))
(r.sex5 <- r.sex4 + scale_y_continuous(limits=c(60, 90)))
연령별
(r.age1 <- ggplot(reading.r.age, aes(x=year, y=rate, colour=age)) + geom_point())
## Warning: Removed 8 rows containing missing values (geom_point).
(r.age2 <- r.age1 + geom_line())
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
(r.age3 <- r.age2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서율(%)") + ggtitle("연령별 독서율의 변화"))
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
(r.age4 <- r.age3 + labs(colour="연령별") + scale_colour_discrete(labels=c("20대", "30대", "40대", "50대", "60이상")))
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
(r.age5 <- r.age4 + scale_y_continuous(limits=c(25, 100)))
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
교육수준별
(r.edu1 <- ggplot(reading.r.edu, aes(x=year, y=rate, colour=education)) + geom_point())
(r.edu2 <- r.edu1 + geom_line())
(r.edu3 <- r.edu2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서율(%)") + ggtitle("교육수준별 독서율의 변화"))
(r.edu4 <- r.edu3 + labs(colour="교육수준") + scale_colour_discrete(labels=c("중졸 이하", "고졸", "대학 이상")))
(r.edu5 <- r.edu4 + scale_y_continuous(limits=c(0, 100)))
거주지역별
(r.res1 <- ggplot(reading.r.res, aes(x=year, y=rate, colour=residence)) + geom_point())
(r.res2 <- r.res1 + geom_line())
(r.res3 <- r.res2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서율(%)") + ggtitle("거주지역별 독서율의 변화"))
(r.res4 <- r.res3 + labs(colour="거주지역") + scale_colour_discrete(labels=c("대도시", "중소도시", "읍면")))
(r.res5 <- r.res4 + scale_y_continuous(limits=c(0, 100)))
독서량
reshape for ggplot
(reading.q.sex <- melt(reading.quantity[c("year", "all", "m", "f")], idvars = "year", measure.vars=c("all", "m", "f"), variable.name = "gender", value.name = "quantity"))
## year gender quantity
## 1 1995 all 9.6
## 2 1996 all 9.1
## 3 1999 all 9.3
## 4 2002 all 10.0
## 5 2004 all 11.0
## 6 2006 all 11.9
## 7 2007 all 12.1
## 8 2008 all 11.9
## 9 2009 all 10.9
## 10 2010 all 10.8
## 11 1995 m 9.9
## 12 1996 m 10.2
## 13 1999 m 9.6
## 14 2002 m 10.2
## 15 2004 m 10.4
## 16 2006 m 12.3
## 17 2007 m 12.8
## 18 2008 m 11.4
## 19 2009 m 12.6
## 20 2010 m 10.3
## 21 1995 f 9.3
## 22 1996 f 8.1
## 23 1999 f 8.9
## 24 2002 f 9.8
## 25 2004 f 11.7
## 26 2006 f 11.5
## 27 2007 f 11.4
## 28 2008 f 12.4
## 29 2009 f 9.3
## 30 2010 f 11.4
str(reading.q.sex)
## 'data.frame': 30 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ gender : Factor w/ 3 levels "all","m","f": 1 1 1 1 1 1 1 1 1 1 ...
## $ quantity: num 9.6 9.1 9.3 10 11 11.9 12.1 11.9 10.9 10.8 ...
(reading.q.age <- melt(reading.quantity[c("year", "20s", "30s", "40s", "50s", "60.over")], idvars = "year", measure.vars=c("20s", "30s", "40s", "50s", "60.over"), variable.name = "age", value.name = "quantity"))
## year age quantity
## 1 1995 20s 13.1
## 2 1996 20s 14.5
## 3 1999 20s 13.0
## 4 2002 20s 14.1
## 5 2004 20s 16.9
## 6 2006 20s 14.6
## 7 2007 20s 14.4
## 8 2008 20s 13.4
## 9 2009 20s 19.4
## 10 2010 20s 16.1
## 11 1995 30s 11.2
## 12 1996 30s 9.8
## 13 1999 30s 10.5
## 14 2002 30s 10.1
## 15 2004 30s 10.2
## 16 2006 30s 13.3
## 17 2007 30s 14.4
## 18 2008 30s 13.1
## 19 2009 30s 11.1
## 20 2010 30s 12.0
## 21 1995 40s 7.7
## 22 1996 40s 7.3
## 23 1999 40s 7.6
## 24 2002 40s 10.4
## 25 2004 40s 10.3
## 26 2006 40s 10.4
## 27 2007 40s 12.3
## 28 2008 40s 13.4
## 29 2009 40s 9.0
## 30 2010 40s 11.0
## 31 1995 50s 4.7
## 32 1996 50s 4.2
## 33 1999 50s 3.5
## 34 2002 50s 3.4
## 35 2004 50s 3.8
## 36 2006 50s 9.0
## 37 2007 50s 7.4
## 38 2008 50s 8.1
## 39 2009 50s 5.5
## 40 2010 50s 6.2
## 41 1995 60.over NA
## 42 1996 60.over NA
## 43 1999 60.over NA
## 44 2002 60.over NA
## 45 2004 60.over NA
## 46 2006 60.over NA
## 47 2007 60.over NA
## 48 2008 60.over NA
## 49 2009 60.over 4.6
## 50 2010 60.over 5.4
str(reading.q.age)
## 'data.frame': 50 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ age : Factor w/ 5 levels "20s","30s","40s",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ quantity: num 13.1 14.5 13 14.1 16.9 14.6 14.4 13.4 19.4 16.1 ...
(reading.q.edu <- melt(reading.quantity[c("year", "under.middle", "high.school", "college")], idvars = "year", measure.vars=c("under.middle", "high.school", "college"), variable.name = "education", value.name = "quantity"))
## year education quantity
## 1 1995 under.middle 3.3
## 2 1996 under.middle 2.3
## 3 1999 under.middle 1.6
## 4 2002 under.middle 1.3
## 5 2004 under.middle 4.2
## 6 2006 under.middle 2.4
## 7 2007 under.middle 2.5
## 8 2008 under.middle 4.8
## 9 2009 under.middle 2.9
## 10 2010 under.middle 2.5
## 11 1995 high.school 8.9
## 12 1996 high.school 9.2
## 13 1999 high.school 7.6
## 14 2002 high.school 8.2
## 15 2004 high.school 8.0
## 16 2006 high.school 7.9
## 17 2007 high.school 9.5
## 18 2008 high.school 8.0
## 19 2009 high.school 8.2
## 20 2010 high.school 6.4
## 21 1995 college 15.7
## 22 1996 college 14.5
## 23 1999 college 15.0
## 24 2002 college 14.5
## 25 2004 college 15.7
## 26 2006 college 17.3
## 27 2007 college 15.5
## 28 2008 college 16.5
## 29 2009 college 15.3
## 30 2010 college 16.5
str(reading.q.edu)
## 'data.frame': 30 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ education: Factor w/ 3 levels "under.middle",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ quantity : num 3.3 2.3 1.6 1.3 4.2 2.4 2.5 4.8 2.9 2.5 ...
(reading.q.res <- melt(reading.quantity[c("year", "metro", "medium", "small")], idvars = "year", measure.vars=c("metro", "medium", "small"), variable.name = "residence", value.name = "quantity"))
## year residence quantity
## 1 1995 metro 10.3
## 2 1996 metro 10.7
## 3 1999 metro 10.5
## 4 2002 metro 9.9
## 5 2004 metro 12.0
## 6 2006 metro 10.3
## 7 2007 metro 11.5
## 8 2008 metro 11.4
## 9 2009 metro 10.7
## 10 2010 metro 12.0
## 11 1995 medium 13.9
## 12 1996 medium 10.0
## 13 1999 medium 9.7
## 14 2002 medium 11.8
## 15 2004 medium 10.7
## 16 2006 medium 13.9
## 17 2007 medium 12.6
## 18 2008 medium 12.9
## 19 2009 medium 12.0
## 20 2010 medium 10.6
## 21 1995 small 10.6
## 22 1996 small 4.4
## 23 1999 small 5.9
## 24 2002 small 7.9
## 25 2004 small 9.0
## 26 2006 small 10.6
## 27 2007 small 13.5
## 28 2008 small 9.1
## 29 2009 small 6.9
## 30 2010 small 5.7
str(reading.q.res)
## 'data.frame': 30 obs. of 3 variables:
## $ year : int 1995 1996 1999 2002 2004 2006 2007 2008 2009 2010 ...
## $ residence: Factor w/ 3 levels "metro","medium",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ quantity : num 10.3 10.7 10.5 9.9 12 10.3 11.5 11.4 10.7 12 ...
성별
(q.sex1 <- ggplot(reading.q.sex, aes(x=year, y=quantity, colour=gender)) + geom_point())
(q.sex2 <- q.sex1 + geom_line())
(q.sex3 <- q.sex2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서량(권)") + ggtitle("성별 독서량의 변화"))
(q.sex4 <- q.sex3 + labs(colour="성별") + scale_colour_discrete(labels=c("전체", "남자", "여자")))
(q.sex5 <- q.sex4 + scale_y_continuous(limits=c(0, 20)))
연령별
(q.age1 <- ggplot(reading.q.age, aes(x=year, y=quantity, colour=age)) + geom_point())
## Warning: Removed 8 rows containing missing values (geom_point).
(q.age2 <- q.age1 + geom_line())
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
(q.age3 <- q.age2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서량(권)") + ggtitle("연령별 독서량의 변화"))
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
(q.age4 <- q.age3 + labs(colour="연령별") + scale_colour_discrete(labels=c("20대", "30대", "40대", "50대", "60이상")))
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
(q.age5 <- q.age4 + scale_y_continuous(limits=c(0, 20)))
## Warning: Removed 8 rows containing missing values (geom_point).
## Warning: Removed 8 rows containing missing values (geom_path).
교육수준별
(q.edu1 <- ggplot(reading.q.edu, aes(x=year, y=quantity, colour=education)) + geom_point())
(q.edu2 <- q.edu1 + geom_line())
(q.edu3 <- q.edu2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서량(권)") + ggtitle("교육수준별 독서량의 변화"))
(q.edu4 <- q.edu3 + labs(colour="교육수준") + scale_colour_discrete(labels=c("중졸 이하", "고졸", "대학 이상")))
(q.edu5 <- q.edu4 + scale_y_continuous(limits=c(0, 20)))
거주지역별
(q.res1 <- ggplot(reading.q.res, aes(x=year, y=quantity, colour=residence)) + geom_point())
(q.res2 <- q.res1 + geom_line())
(q.res3 <- q.res2 + theme_bw() + theme.kr + xlab("연도") + ylab("독서량(권)") + ggtitle("거주지역별 독서량의 변화"))
(q.res4 <- q.res3 + labs(colour="거주지역") + scale_colour_discrete(labels=c("대도시", "중소도시", "읍면")))
(q.res5 <- q.res4 + scale_y_continuous(limits=c(0, 20)))
