I have a dataframe with 5 dimensions of data that looks like this:
> dim(alldata)
[1] 162 6
> head(alldata)
value layer Kmultiplier Resolution Season Variable
1: 0.01308008 b .01K 1km Baseflow Evapotranspiration
2: 0.03974779 b .01K 1km Peak Flow Evapotranspiration
3: 0.02396524 b .01K 1km Summer Flow Evapotranspiration
4: -0.15670996 b .01K 1km Baseflow Discharge
5: 0.06774948 b .01K 1km Peak Flow Discharge
6: -0.04138313 b .01K 1km Summer Flow Discharge
What I'd like to do is get the mean of the value column for certain 'characteristics' of the data based on the other columns. So I use which to subset the data to only the variables I'm interested in, for example:
> subset=alldata[which(alldata$Variable=="Discharge" & alldata$Resolution=="1km" & alldata$Season=="Peak Flow"),]
> subset
value layer Kmultiplier Resolution Season Variable
1: 0.067749478 b .01K 1km Peak Flow Discharge
2: 0.058260448 b .1K 1km Peak Flow Discharge
3: -0.223953725 b 10K 1km Peak Flow Discharge
4: 0.272916114 g .01K 1km Peak Flow Discharge
5: 0.240135025 g .1K 1km Peak Flow Discharge
6: -0.216730348 g 10K 1km Peak Flow Discharge
7: 0.088966500 s .01K 1km Peak Flow Discharge
8: -0.018943754 s .1K 1km Peak Flow Discharge
9: -0.008339365 s 10K 1km Peak Flow Discharge
Here's where I'm stuck. Let's say I want a vector or list of the mean value for each value in the "layer" column... so I would end up with 3 numbers, one for 'b' one for 'g' and one for 's'. I need to make a bunch of subsets like this and I think the apply functions can help, but after multiple tutorials and stack questions I cannot get this to work. A simpler example is fine too, like this:
> A=data.frame(seq(1,9),rep(c("a","b","c"),3),c(rep("type1",3),rep("type2",3),rep("type3",3)),c(rep("place1",2),rep("place2",2),rep("place3",2),rep("place1",2),rep("place2",1)))
> names(A)=c("value","Letter","Type","Place")
> A
value Letter Type Place
1 1 a type1 place1
2 2 b type1 place1
3 3 c type1 place2
4 4 a type2 place2
5 5 b type2 place3
6 6 c type2 place3
7 7 a type3 place1
8 8 b type3 place1
9 9 c type3 place2
From this simple example, I need the mean of column "value", listed by Letter, for "place1", which should return a something like: "a=mean value, b=mean value, c=mean value" in whatever format works.
Is this a job for the apply functions? If so, how? If not, let me know a better alternative for subsetting my data.
Thank you!
Alternative Solutions implemented on the example dataset given by you and not using any apply family functions here.
Using dplyr package
library(dplyr)
A %>%
group_by_(.dots = c("Place","Letter")) %>%
summarise(MEAN = mean(value))
# Source: local data frame [6 x 3]
# Groups: Place [?]
# Place Letter MEAN
# <fctr> <fctr> <dbl>
# 1 place1 a 4
# 2 place1 b 5
# 3 place2 a 4
# 4 place2 c 6
# 5 place3 b 5
# 6 place3 c 6
OR
Using by() function
> by(A$value, A[,c(2,4)], FUN = mean)
# Letter: a
# Place: place1
# [1] 4
# ------------------------------------------------------------
# Letter: b
# Place: place1
# [1] 5
# ------------------------------------------------------------
# Letter: c
# Place: place1
# [1] NA
# ------------------------------------------------------------
# Letter: a
# Place: place2
# [1] 4
# ------------------------------------------------------------
# Letter: b
# Place: place2
# [1] NA
# ------------------------------------------------------------
# Letter: c
# Place: place2
# [1] 6
# ------------------------------------------------------------
# Letter: a
# Place: place3
# [1] NA
# ------------------------------------------------------------
# Letter: b
# Place: place3
# [1] 5
# ------------------------------------------------------------
# Letter: c
# Place: place3
# [1] 6
Consider by the object-oriented wrapper of tapply that can subset a dataframe across one or more factors such as, Place and Time. From the list of dataframes you can row bind to one final df.
df_List <- by(A, A[,c("Place", "Letter")],
FUN = function(i) transform(i, mean = mean(i$value)))
finaldf <- do.call(rbind, dfList)
finaldf
# value Letter Type Place mean
# 1 1 a type1 place1 4
# 7 7 a type3 place1 4
# 4 4 a type2 place2 4
# 2 2 b type1 place1 5
# 8 8 b type3 place1 5
# 5 5 b type2 place3 5
# 3 3 c type1 place2 6
# 9 9 c type3 place2 6
# 6 6 c type2 place3 6
Thanks for the advice. I ended up going with ddply in order to get my data into a more usable format, following general advice from this post.
Here's the simple example:
> A=data.frame(seq(1,9),rep(c("a","b","c"),3),c(rep("type1",3),rep("type2",3),rep("type3",3)),c(rep("place1",2),rep("place2",2),rep("place3",2),rep("place1",2),rep("place2",1)))
> names(A)=c("value","Letter","Type","Place")
> A
value Letter Type Place
1 1 a type1 place1
2 2 b type1 place1
3 3 c type1 place2
4 4 a type2 place2
5 5 b type2 place3
6 6 c type2 place3
7 7 a type3 place1
8 8 b type3 place1
9 9 c type3 place2
Then here is my code to find the mean of 'value' for every value that is both place1 and type1:
> sub=ddply(A[which(A$Place=="place1" & A$Type=="type1"),],"value",summarize,mean=mean(value,na.rm=T))
> sub
value mean
1 1 1
2 2 2
Since 'sub' is already a dataframe, it's easy to add columns with other characteristics and then plot these results.
---------------------------------------------------------------------------------
If you are interested, here is the more complex dataset I was actually trying to subset:
> head(alldata)
value layer Kmultiplier Resolution Season Variable
1: 0.00000000 b 1 1km Baseflow Evapotranspiration
2: 0.01308008 b .01 1km Baseflow Evapotranspiration
3: 0.00000000 b 1 1km Peak Flow Evapotranspiration
4: 0.03974779 b .01 1km Peak Flow Evapotranspiration
5: 0.00000000 b 1 1km Summer Flow Evapotranspiration
6: 0.02396524 b .01 1km Summer Flow Evapotranspiration
And the lines of code I wrote to subset it into plottable pieces:
for(j in Season){
for(i in res){
ET=ddply(alldata[which(alldata$Variable=="Evapotranspiration" & alldata$Resolution==sprintf("%s",i) & alldata$Season==sprintf("%s",j)),],"Kmultiplier", summarize, mean = mean(value,na.rm=T))
ET$Variable="Evapotranspiration";ET$Resolution=sprintf("%s",i);ET$Season=sprintf("%s",j)
S=ddply(alldata[which(alldata$Variable=="Change in Storage" & alldata$Resolution==sprintf("%s",i) & alldata$Season==sprintf("%s",j)),],"Kmultiplier", summarize, mean = mean(value,na.rm=T))
S$Variable="Change in Storage";S$Resolution=sprintf("%s",i);S$Season=sprintf("%s",j)
Q=ddply(alldata[which(alldata$Variable=="Discharge" & alldata$Resolution==sprintf("%s",i) & alldata$Season==sprintf("%s",j)),],"Kmultiplier", summarize, mean = mean(value,na.rm=T))
Q$Variable="Discharge";Q$Resolution=sprintf("%s",i);Q$Season=sprintf("%s",j)
if(i=="1km"){resbind=rbind(Q,S,ET)}else{resbind2=rbind(resbind,Q,S,ET)}
}
if(j=="Baseflow"){sbind=rbind(resbind2,Q,S,ET)}else if(j=="Peak Flow"){sbind2=rbind(resbind2,sbind,Q,S,ET)}else{ETSQ=rbind(resbind2,sbind2,Q,S,ET)}
}
ETSQ$Variable=factor(ETSQ$Variable,levels=c("Change in Storage","Evapotranspiration","Discharge"))
print(ggplot(data=ETSQ,aes(x=Kmultiplier,y=mean, color=Variable,group=Variable))
+geom_point()
+geom_line()
+labs(x="K scaled by",y="Percent change from Baseline case")
+scale_y_continuous(labels=percent)
+facet_grid(Season~Resolution)
+theme_bw()
)
ggsave(sprintf("%s/Plots/SimpleLines/Variable_by_K.png",path),device = NULL,scale=1)
And finally the resulting plot:
{var%20f='http://v.t.sina.com.cn/share/share.php?appkey=1515056452',u=z||d.location,p=['&url=',e(u),'&title=',e(t||d.title),'&source=',e(r),'&sourceUrl=',e(l),'&content=',c||'gb2312','&pic=',e(p||'')].join('');function%20a(){if(!window.open([f,p].join(''),'mb',['toolbar=0,status=0,resizable=1,width=440,height=430,left=',(s.width-440)/2,',top=',(s.height-430)/2].join('')))u.href=[f,p].join('');};if(/Firefox/.test(navigator.userAgent))setTimeout(a,0);else%20a();})(screen,document,encodeURIComponent,'','','https://i.stack.imgur.com/uUs5V.png', '推荐 爷的心禁止访问 的文章《Using lapply and which to subset dataframe by both》','https://www.manongdao.com/article-863804.html','页面编码gb2312|utf-8默认gb2312'));){kind=link}