[英]Sum a variable in a grouped dataframe only once for each unique combination of two other variables with dplyr
我有一張長桌子，上面重復着area和cluster組合。
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
)
我想創建一個新變量sum.norm.to.area ，它是每個cluster的norm.to.area的總和， norm.to.area每個area / subcluster.merge norm.to.area組合使用norm.to.area的值。
我嘗試對group_by cluster ，但這會根據給定組合的出現將這些值相加多次。
counts %>% group_by(cluster) %>% mutate(sum.norm.to.area = sum(norm.to.area)
謝謝你的建議。
更新1：
嘗試使用匯總，如下所示，但是發生了相同的事情（當然，除了沒有添加為新列）：
> 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
)
更新2
這是我想要的輸出，但是我到達它的方式太復雜了。 我想找到一種使用mutate而不需要使用join的簡便方法。
> 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"))
所需的輸出： sum.norm.to.area是為area和cluster所有唯一組合添加norm.to.area的結果（僅一次）：
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
)
使用dplyr我們可以對每個area的唯一值進行group_by cluster和sum 。
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
我認為您不是在尋找mutate（）
counts %>% group_by(cluster, area) %>% summarize(sum.norm.to.area = sum(norm.to.area))
為數據集中兩個變量的每個組合保存變量的唯一值
[英]Save unique values of variable for each combination of two variables in a dataset
在 R 中，如果其他兩列中的值組合是唯一的，則取多個變量的總和
[英]In R, take sum of multiple variables if combination of values in two other columns are unique
Map dplyr function to each combination of variable pairs in an R dataframe
[英]Map dplyr function to each combination of variable pairs in an R dataframe
對於分組數據幀（dplyr）R中的每個元素，值的總和大於或等於
[英]Sum of values greater than or equal too for each element in grouped dataframe (dplyr) R
如何在 R dataframe 中將數據從第 i 行第 2 列更新到第 j 行第 1 列但由兩個變量 (dplyr) 分組？
[英]How to update data from column i row 2 to column j row 1 but grouped by two variables (dplyr) in a R dataframe?
計算由r中的兩個其他列的唯一組合分組的列中的成對值的出現
[英]Count occurrence of pair wise values in a column grouped by a unique combination of two other columns in r
循環遍歷數據框：計算每個唯一變量的值的每個成對組合。
[英]Loop through a dataframe: counting each pairwise combination of a value for each unique variable.
聲明:本站的技術帖子網頁，遵循CC BY-SA 4.0協議，如果您需要轉載，請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.