Sum a variable in a grouped dataframe only once for each unique combination of two other variables with dplyr
Question
I have a long table with repeating combinations of area and cluster .
counts <- tibble::tribble(
~age, ~area, ~cluster, ~norm.to.area,
"gw_25", "cingulate", "cluster_1", 0.03,
"gw_20", "cingulate", "cluster_1", 0.03,
"gw_18", "hippocampus", "cluster_1", 0.02,
"gw_25", "insula", "cluster_1", 0.01,
"gw_20", "motor", "cluster_1", 0.01,
"gw_22", "motor", "cluster_1", 0.01,
"gw_25", "motor", "cluster_1", 0.01,
"gw_14", "motor", "cluster_1", 0.01,
"gw_18", "motor", "cluster_1", 0.01,
"gw_19", "motor", "cluster_1", 0.01,
"gw_17", "motor", "cluster_1", 0.01,
"gw_20", "occipital", "cluster_1", 0.01,
"gw_17", "occipital", "cluster_1", 0.01,
"gw_18", "occipital", "cluster_1", 0.01,
"gw_19", "occipital", "cluster_1", 0.01,
"gw_22", "occipital", "cluster_1", 0.01,
"gw_14", "occipital", "cluster_1", 0.01,
"gw_22", "parietal", "cluster_1", 0,
"gw_25", "parietal", "cluster_1", 0,
"gw_17", "parietal", "cluster_1", 0,
"gw_19", "parietal", "cluster_1", 0,
"gw_20", "parietal", "cluster_1", 0,
"gw_20", "PFC", "cluster_1", 0.01,
"gw_22", "PFC", "cluster_1", 0.01,
"gw_25", "PFC", "cluster_1", 0.01
)
I want to create a new variable, sum.norm.to.area , which is the sum of norm.to.area for each cluster , using the value of norm.to.area only ONCE for each combination of area / subcluster.merge .
I've tried to group_by cluster , but this sums the values as many times as a given combination appears.
counts %>% group_by(cluster) %>% mutate(sum.norm.to.area = sum(norm.to.area)
Thanks for your advice.
UPDATE 1:
Tried using summarize as suggested below, but the same thing occurs (except, of course, without adding as a new column):
> counts %>% group_by(subcluster.merge, area) %>% summarize(sum(norm.to.area))
tibble::tribble(
~cluster . , ~area, ~sum.norm.to.area.,
"cluster_1", "PFC", 0.06,
"cluster_1", "somatosensory", 0.05,
"cluster_1", "motor", 0.07,
"cluster_1", "parietal", 0,
"cluster_1", "temporal", 0.03,
"cluster_1", "occipital", 0.06,
"cluster_1", "hippocampus", 0.02,
"cluster_1", "insula", 0.01,
"cluster_1", "cingulate", 0.06,
"cluster_10-34", "PFC", 0.42,
"cluster_10-34", "somatosensory", 0.35,
"cluster_10-34", "motor", 0.48,
"cluster_10-34", "parietal", 0.36,
"cluster_10-34", "temporal", 0.28,
"cluster_10-34", "occipital", 0.4,
"cluster_10-34", "hippocampus", 0.12,
"cluster_10-34", "insula", 0,
"cluster_10-34", "cingulate", 0,
"cluster_11", "PFC", 0.18,
"cluster_11", "somatosensory", 0.15,
"cluster_11", "motor", 0.14,
"cluster_11", "parietal", 0.12,
"cluster_11", "temporal", 0.04,
"cluster_11", "occipital", 0.18,
"cluster_11", "hippocampus", 0.02
)
UPDATE 2
This is the output that I want, but the way I'm arriving at it is too convoluted. I'd like to find an easier way using mutate and not having to use join .
> tmp <- counts %>% distinct(area, cluster, .keep_all = TRUE) %>%
add_count(cluster, wt = norm.to.area, name = "sum.norm.to.area")
counts %>% left_join(tmp, by = c("cluster", "area"))
Desired output: sum.norm.to.area is the result of adding norm.to.area (only once) for all unique combinations of area and cluster :
tibble::tribble(
~age, ~area, ~cluster, ~norm.to.area, ~sum.norm.to.area,
"gw_25", "cingulate", "cluster_1", 0.03, 0.11,
"gw_20", "cingulate", "cluster_1", 0.03, 0.11,
"gw_18", "hippocampus", "cluster_1", 0.02, 0.11,
"gw_25", "insula", "cluster_1", 0.01, 0.11,
"gw_20", "motor", "cluster_1", 0.01, 0.11,
"gw_22", "motor", "cluster_1", 0.01, 0.11,
"gw_25", "motor", "cluster_1", 0.01, 0.11,
"gw_14", "motor", "cluster_1", 0.01, 0.11,
"gw_18", "motor", "cluster_1", 0.01, 0.11,
"gw_19", "motor", "cluster_1", 0.01, 0.11,
"gw_17", "motor", "cluster_1", 0.01, 0.11,
"gw_20", "occipital", "cluster_1", 0.01, 0.11,
"gw_17", "occipital", "cluster_1", 0.01, 0.11,
"gw_18", "occipital", "cluster_1", 0.01, 0.11,
"gw_19", "occipital", "cluster_1", 0.01, 0.11,
"gw_22", "occipital", "cluster_1", 0.01, 0.11,
"gw_14", "occipital", "cluster_1", 0.01, 0.11,
"gw_22", "parietal", "cluster_1", 0, 0.11,
"gw_25", "parietal", "cluster_1", 0, 0.11,
"gw_17", "parietal", "cluster_1", 0, 0.11,
"gw_19", "parietal", "cluster_1", 0, 0.11,
"gw_20", "parietal", "cluster_1", 0, 0.11,
"gw_20", "PFC", "cluster_1", 0.01, 0.11,
"gw_22", "PFC", "cluster_1", 0.01, 0.11,
"gw_25", "PFC", "cluster_1", 0.01, 0.11,
"gw_18", "PFC", "cluster_1", 0.01, 0.11,
"gw_19", "PFC", "cluster_1", 0.01, 0.11,
"gw_17", "PFC", "cluster_1", 0.01, 0.11,
"gw_22", "somatosensory", "cluster_1", 0.01, 0.11,
"gw_20", "somatosensory", "cluster_1", 0.01, 0.11,
"gw_25", "somatosensory", "cluster_1", 0.01, 0.11,
"gw_18", "somatosensory", "cluster_1", 0.01, 0.11,
"gw_19", "somatosensory", "cluster_1", 0.01, 0.11,
"gw_25", "temporal", "cluster_1", 0.01, 0.11,
"gw_19", "temporal", "cluster_1", 0.01, 0.11,
"gw_20", "temporal", "cluster_1", 0.01, 0.11
)
2 answers
solution1
1 ACCPTED 2019-04-20 00:43:44
Using dplyr we can group_by cluster and sum only the unique value in each area .
library(dplyr)
counts %>%
group_by(cluster) %>%
mutate(sum.norm = sum(norm.to.area[!duplicated(area)]))
# age area cluster norm.to.area sum.norm
# <chr> <chr> <chr> <dbl> <dbl>
# 1 gw_25 cingulate cluster_1 0.03 0.09
# 2 gw_20 cingulate cluster_1 0.03 0.09
# 3 gw_18 hippocampus cluster_1 0.02 0.09
# 4 gw_25 insula cluster_1 0.01 0.09
# 5 gw_20 motor cluster_1 0.01 0.09
# 6 gw_22 motor cluster_1 0.01 0.09
# 7 gw_25 motor cluster_1 0.01 0.09
# 8 gw_14 motor cluster_1 0.01 0.09
# 9 gw_18 motor cluster_1 0.01 0.09
#10 gw_19 motor cluster_1 0.01 0.09
# … with 15 more rows
solution2
0 2019-04-20 00:06:21
我认为您不是在寻找mutate（）
counts %>% group_by(cluster, area) %>% summarize(sum.norm.to.area = sum(norm.to.area))
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.