r - 根据多列减去行

Question

我有这个数据框

数据

df <- data.frame(id=c(rep("site1", 3), rep("site2", 8), rep("site3", 9), rep("site4", 15)),
                 major_rock = c("greywacke",    "mudstone", "gravel",   "greywacke",    "gravel",   "mudstone", "gravel", "mudstone", "mudstone",   
                                "conglomerate", "gravel", "mudstone",   "greywacke","conglomerate", "gravel",   "gravel",   "greywacke","gravel",   
                                "greywacke",    "gravel",   "mudstone", "greywacke",    "gravel", "gravel", "gravel",   "conglomerate", "greywacke",
                                "coquina",  "gravel",   "gravel",   "greywacke",    "gravel",   "mudstone","mudstone",  "gravel"),
                 minor_rock = c("sandstone mudstone basalt chert limestone",  "limestone",   "sand silt clay", "sandstone mudstone basalt chert limestone",
                                "sand silt clay", "sandstone conglomerate coquina tephra", NA, "limestone",  "mudstone sandstone coquina limestone",
                                "sandstone mudstone limestone",  "sand loess silt",  "sandstone conglomerate coquina tephra", "sandstone mudstone basalt chert limestone",
                                "sandstone mudstone limestone", "sand loess silt", "loess silt sand", "sandstone mudstone conglomerate chert limestone basalt",
                                "sand silt clay",  "sandstone mudstone conglomerate", "loess sand silt", "sandstone conglomerate coquina tephra", "sandstone mudstone basalt chert limestone",
                                "sand loess silt", "sand silt clay", "loess silt sand",  "sandstone mudstone limestone", "sandstone mudstone conglomerate chert limestone basalt",
                                "limestone", "loess sand silt",  NA, "sandstone mudstone conglomerate", "sandstone siltstone mudstone limestone silt lignite", "limestone",
                                "mudstone sandstone coquina limestone", "mudstone tephra loess"),
                 area_ha = c(1066.68,   7.59,   3.41,   4434.76,    393.16, 361.69, 306.75, 124.93, 95.84,  9.3,    8.45,   4565.89,    2600.44,    2198.52,    
                             2131.71,   2050.09,    1640.47,    657.09, 296.73, 178.12, 10403.53,   8389.2,  8304.08,   3853.36,    2476.36,    2451.25,    
                             1640.47,   1023.02,    532.94, 385.68, 296.73, 132.45, 124.93, 109.12, 4.87))

其中有 4 个站点，其中 2 个是独立(site1 和 site3 ；它们不包括任何上游站点)和 2 个依赖(site2 和 site4；它们包括上游站点( s))

我想创建一个新的 data.frame，我们称它为 df_indep。其中，我希望所有站点都是独立，这意味着从依赖站点中减去任何上游站点，如下所示

site1 and site3 will remain the same as they are independent

site2 (independent) = site2 - site1

site4 (independent) = site4 -(site2+site3)

下面的 df 仅适用于 area_percent 大于 15% 的 major_rock 和 minor_rock 组合(减去之前上游站点；site2 和 site3)

library(dplyr)
head(df %>% group_by(id) %>% 
       mutate(area_percent = area_ha/sum(area_ha)*100) %>% 
       filter(area_percent>5),15)


#       id   major_rock                                             minor_rock  area_ha area_percent
#   <fctr>       <fctr>                                                 <fctr>    <dbl>        <dbl>
#1   site1    greywacke              sandstone mudstone basalt chert limestone  1066.68    98.979289
#2   site2    greywacke              sandstone mudstone basalt chert limestone  4434.76    77.329604
#3   site2       gravel                                         sand silt clay   393.16     6.855592
#4   site2     mudstone                  sandstone conglomerate coquina tephra   361.69     6.306845
#5   site2       gravel                                                     NA   306.75     5.348848
#6   site3     mudstone                  sandstone conglomerate coquina tephra  4565.89    27.978879
#7   site3    greywacke              sandstone mudstone basalt chert limestone  2600.44    15.934986
#8   site3 conglomerate                           sandstone mudstone limestone  2198.52    13.472099
#9   site3       gravel                                        sand loess silt  2131.71    13.062701
#10  site3       gravel                                        loess silt sand  2050.09    12.562550
#11  site3    greywacke sandstone mudstone conglomerate chert limestone basalt  1640.47    10.052479
#12  site4     mudstone                  sandstone conglomerate coquina tephra 10403.53    25.925869
#13  site4    greywacke              sandstone mudstone basalt chert limestone  8389.20    20.906106
#14  site4       gravel                                        sand loess silt  8304.08    20.693984
#15  site4       gravel                                         sand silt clay  3853.36     9.602674

这是

最终结果

我要减去上游站点之后

#       id   major_rock                                             minor_rock area_ha area_percent
#1   site1    greywacke              sandstone mudstone basalt chert limestone 1066.68    98.979289
#2   site2    greywacke              sandstone mudstone basalt chert limestone 3368.08    72.319849
#3   site2       gravel                                         sand silt clay  389.75     8.368762
#4   site2     mudstone                  sandstone conglomerate coquina tephra  361.69     7.766254
#5   site2       gravel                                                     NA  306.75     6.586576
#6   site3     mudstone                  sandstone conglomerate coquina tephra 4565.89    27.978879
#7   site3    greywacke              sandstone mudstone basalt chert limestone 2600.44    15.934986
#8   site3 conglomerate                           sandstone mudstone limestone 2198.52    13.472099
#9   site3       gravel                                        sand loess silt 2131.71    13.062701
#10  site3       gravel                                        loess silt sand 2050.09    12.562550
#11  site3    greywacke sandstone mudstone conglomerate chert limestone basalt 1640.47    10.052479
#12  site4     mudstone                  sandstone conglomerate coquina tephra 5475.95    30.297305
#13  site4    greywacke              sandstone mudstone basalt chert limestone 1354.00     7.491403
#14  site4       gravel                                        sand loess silt 6163.92    34.103701
#15  site4       gravel                                         sand silt clay 2803.11    15.509031

对于如何在 R 中执行此操作的任何建议，我将不胜感激。

更新

这是一张显示所有 4 个站点的 map

下图在减去 site2 和 site3

下图显示site2(累积)和独立的相同

关于@rbierman 的网站依赖项如何编码的问题，请查看下方。

#      id dependent dep_site1 dep_site2 dep_site3
#1  site1        no        no        no        no
#2  site1        no        no        no        no
#3  site1        no        no        no        no
#4  site2       yes       yes        no        no
#5  site2       yes       yes        no        no
#6  site2       yes       yes        no        no
#7  site2       yes       yes        no        no
#8  site2       yes       yes        no        no
#9  site2       yes       yes        no        no
#10 site2       yes       yes        no        no
#11 site2       yes       yes        no        no
#12 site3        no        no        no        no
#13 site3        no        no        no        no
#14 site3        no        no        no        no
#15 site3        no        no        no        no
#16 site3        no        no        no        no
#17 site3        no        no        no        no
#18 site3        no        no        no        no
#19 site3        no        no        no        no
#20 site3        no        no        no        no
#21 site4       yes       yes       yes       yes
#22 site4       yes       yes       yes       yes
#23 site4       yes       yes       yes       yes
#24 site4       yes       yes       yes       yes
#25 site4       yes       yes       yes       yes
#26 site4       yes       yes       yes       yes
#27 site4       yes       yes       yes       yes
#28 site4       yes       yes       yes       yes
#29 site4       yes       yes       yes       yes
#30 site4       yes       yes       yes       yes
#31 site4       yes       yes       yes       yes
#32 site4       yes       yes       yes       yes
#33 site4       yes       yes       yes       yes
#34 site4       yes       yes       yes       yes
#35 site4       yes       yes       yes       yes

Answer 1

这还不错，只是稍微重命名和加入。

首先，我们需要一个漂亮的两列格式的依赖项。您可以在发布的宽依赖项上使用 reshape2::melt 或 tidyr::gather 以使其变长:

deps = data.frame(
    id = c("site2", "site4", "site4"),
    dependency = c("site1", "site2", "site3"),
    stringsAsFactors = FALSE
)
#      id dependency
# 1 site2      site1
# 2 site4      site2
# 3 site4      site3

使用 dplyr 进行连接，我们还需要 character 而不是 factor 列，以防级别不完全相同。

    library(dplyr)    
df = mutate_at(df, .cols = c("id", "major_rock", "minor_rock"), .funs = funs(as.character))

首先，我们创建一个“依赖与度量”数据框，该数据框具有明确的依赖区域名称和 ID(编辑)，然后我们将其聚合到 id水平，总结依赖领域:

dep_w_measure = df %>%
    select(dependency = id, major_rock, minor_rock, dep_area = area_ha) %>%
    inner_join(deps) %>%
    group_by(id, major_rock, minor_rock) %>%
    summarize(dep_area = sum(dep_area))

然后我们将其加入原始数据，并减去相关区域(如果存在):

result = left_join(df, dep_w_measure, by = c("major_rock", "minor_rock", "id")) %>%
    mutate(area_ind = area_ha - coalesce(dep_area, 0))
head(result)
#      id major_rock                                minor_rock area_ha dep_area area_ind
# 1 site1  greywacke sandstone mudstone basalt chert limestone 1066.68       NA  1066.68
# 2 site1   mudstone                                 limestone    7.59       NA     7.59
# 3 site1     gravel                            sand silt clay    3.41       NA     3.41
# 4 site2  greywacke sandstone mudstone basalt chert limestone 4434.76  1066.68  3368.08
# 5 site2     gravel                            sand silt clay  393.16     3.41   389.75
# 6 site2   mudstone     sandstone conglomerate coquina tephra  361.69       NA   361.69

我将 dep_area 和 area_ha 列留在“展示我的作品”中，您可以根据需要清理它。独立区域 area_ind 列与所需输出中的 area_ha 匹配。