绘制按变量对分组的数据

Question

我有一大堆这样的数据，包括以下变量。

Field    Country    AgeRange    Score    Test

我想绘制按Field和AgeRange分组的所有人口中每组人口的平均得分。也就是说，我喜欢这样的事情。

请注意，变量AgeRange会获取这3个值中的一个，而不是每个参与者的确切年龄。

根据需要对数据进行分组没有问题。例如，通过执行

aggr_data = aggregate(data, by=list(data$Field, data$AgeRange), FUN=mean)

我按照我需要的方式对数据进行分组，每个Field-AgeRange对都有一个得分平均值。问题是我无法找到一种直接的方法来从那些y轴对应于获得的分数的值和每对的x轴获得条形图。

我想我可以抓住我感兴趣的每个子集，就像这样

young_cs = subset(data, Field=="CompSci" & AgeRange=="18-35")
m_young_cs = mean(young_cs[,"Score"])
mid_cs = subset(data, Field=="CompSci" & AgeRange=="36-53")
m_mid_cs = mean(mid_cs[,"Score"])

然后绘制所有获得的手段，但这显然非常耗时。有更简单，更快捷的方法吗？

这是一个随机的小数据样本。

Field        Country    AgeRange    Score    Test
Psychology   US         18-35       4.2      A
Psychology   US         18-35       3.1      C
Psychology   US         18-35       5.2      B
Psychology   US         36-53       4.7      A
Psychology   US         36-53       3.5      A
Psychology   US         54+         3.1      B
Psychology   US         54+         2.2      B
Psychology   US         54+         6.7      C
Psychology   US         54+         5.1      C
CompSci      US         18-35       5.2      B
CompSci      US         18-35       7.4      C
CompSci      US         18-35       6.1      A
CompSci      US         36-53       7.7      A
CompSci      US         36-53       8.1      A
CompSci      US         54+         8.2      B
CompSci      US         54+         7.7      B
CompSci      US         54+         6.9      A
CompSci      US         54+         9.0      C
Mathematics  US         18-35       6.2      B
Mathematics  US         18-35       6.4      A
Mathematics  US         18-35       7.1      A
Mathematics  US         36-53       8.7      A
Mathematics  US         36-53       9.4      A
Mathematics  US         54+         7.2      C
Mathematics  US         54+         6.1      B
Mathematics  US         54+         6.5      C
Mathematics  US         54+         7.0      C

Answer 1

试试这个

#dummay data
field=c("P","C","M")
agerange=c(18,36,54)
score=rnorm(27, 7)
test=c("A","B","C")

df<-data.frame(field=rep(field, each=9),agerange= as.factor(rep(agerange,each=3, times=9)), score=score,test=rep(test, 9))

p<-ggplot(df, aes(x=field,y=score, fill=agerange))
p+geom_bar(stat="identity", position="dodge")

#or
p+stat_summary(fun.y = "mean",geom = "bar", position="dodge") 

Answer 2

library(ggplot2)
library(plyr)

# a faceting approach
df2 <- ddply(df, .(Field, AgeRange), summarise, mscore = mean(Score))
ggplot(df2, aes(x=AgeRange, y = mscore, fill = AgeRange)) + geom_bar( stat = "identity" ) +
       facet_wrap(~Field)

# good enough?

    df <- structure(list(field = structure(c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), class = "factor", .Label = c("C", 
"M", "P")), agerange = structure(c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 
3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 
2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 
2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 
1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 
3L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L), .Label = c("18", "36", 
"54"), class = "factor"), score = c(7.30127138725929, 7.37770686922096, 
7.41317998674043, 6.64841878521039, 7.86711279540953, 7.17048025193224, 
8.44148594576163, 8.13949581473566, 6.30312423530373, 6.78529906805563, 
8.60960304217661, 7.08300936020387, 7.33518750196135, 7.29903060579703, 
7.81598828814603, 6.51481883845345, 6.85779851460457, 8.5001156704776, 
7.90225168492658, 6.57536590278191, 6.01020914251986, 7.28458327350041, 
7.07419918080273, 8.93252585403122, 6.54527682832174, 6.35152240141314, 
6.75924970388344, 7.30127138725929, 7.37770686922096, 7.41317998674043, 
6.64841878521039, 7.86711279540953, 7.17048025193224, 8.44148594576163, 
8.13949581473566, 6.30312423530373, 6.78529906805563, 8.60960304217661, 
7.08300936020387, 7.33518750196135, 7.29903060579703, 7.81598828814603, 
6.51481883845345, 6.85779851460457, 8.5001156704776, 7.90225168492658, 
6.57536590278191, 6.01020914251986, 7.28458327350041, 7.07419918080273, 
8.93252585403122, 6.54527682832174, 6.35152240141314, 6.75924970388344, 
7.30127138725929, 7.37770686922096, 7.41317998674043, 6.64841878521039, 
7.86711279540953, 7.17048025193224, 8.44148594576163, 8.13949581473566, 
6.30312423530373, 6.78529906805563, 8.60960304217661, 7.08300936020387, 
7.33518750196135, 7.29903060579703, 7.81598828814603, 6.51481883845345, 
6.85779851460457, 8.5001156704776, 7.90225168492658, 6.57536590278191, 
6.01020914251986, 7.28458327350041, 7.07419918080273, 8.93252585403122, 
6.54527682832174, 6.35152240141314, 6.75924970388344), test = structure(c(1L, 
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L
), class = "factor", .Label = c("A", "B", "C"))), .Names = c("field", 
"agerange", "score", "test"), row.names = c(NA, -81L), class = "data.frame")