I have a tall data frame as such:
data = data.frame("id"=c(1,2,3,4,5,6,7,8,9,10),
"group"=c(1,1,2,1,2,2,2,2,1,2),
"type"=c(1,1,2,3,2,2,3,3,3,1),
"score1"=c(sample(1:4,10,r=T)),
"score2"=c(sample(1:4,10,r=T)),
"score3"=c(sample(1:4,10,r=T)),
"score4"=c(sample(1:4,10,r=T)),
"score5"=c(sample(1:4,10,r=T)),
"weight1"=c(173,109,136,189,186,146,173,102,178,174),
"weight2"=c(147,187,125,126,120,165,142,129,144,197),
"weight3"=c(103,192,102,159,128,179,195,193,135,145),
"weight4"=c(114,182,199,101,111,116,198,123,119,181),
"weight5"=c(159,125,104,171,166,154,197,124,180,154))
library(reshape2)
library(plyr)
data1 <- reshape(data, direction = "long",
varying = list(c(paste0("score",1:5)),c(paste0("weight",1:5))),
v.names = c("score","weight"),
idvar = "id", timevar = "count", times = c(1:5))
data1 <- data1[order(data1$id), ]
And what I want to create is a new data frame like so:
want = data.frame("score"=rep(1:4,6),
"group"=rep(1:2,12),
"type"=rep(1:3,8),
"weightedCOUNT"=NA) # how to calculate this? count(data1, score, wt = weight)
I am just not sure how to calculate weightedCOUNT which should apply the weights to the score variable so then it gives in column 'weightedCOUNT' a weighted count that is aggregated by score and group and type.
An option would be to melt (from data.table - which can take multiple measure patterns, and then grouped by 'group', 'type' get the count
library(data.table)
library(dplyr)
melt(setDT(data), measure = patterns('^score', "^weight"),
value.name = c("score", "weight")) %>%
group_by(group, type) %>%
count(score, wt = weight)
If we need to have a complete set of combinations
library(tidyr)
melt(setDT(data), measure = patterns('^score', "^weight"),
value.name = c("score", "weight")) %>%
group_by(group, type) %>%
ungroup %>%
complete(group, type, score, fill = list(n = 0))