Question

从示例数据开始：

> dput(data)
structure(list(Country = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L), .Label = c("France", "Spain"), class = "factor"), 
    Car = structure(c(6L, 17L, 7L, 18L, 4L, 13L, 20L, 5L, 14L, 
    21L, 8L, 11L, 15L, 9L, 12L, 16L, 8L, 11L, 15L, 9L, 12L, 19L, 
    3L, 10L, 1L, 2L), .Label = c("Audi_1_EON", "Audi_2_EON", 
    "Ferrari_1_EOD", "Fiat_1_EOD", "Fiat_1_EON", "Mazda_1_EOD", 
    "Mazda_1_EON", "Mercedes_1_EOD", "Mercedes_1_EON", "Mercedes_2_EOD", 
    "Nexia_1_EOD", "Nexia_1_EON", "Opel_1_EOD", "Opel_1_EON", 
    "Peugeot_1_EOD", "Peugeot_1_EON", "Porsche_2_EOD", "Porsche_2_EON", 
    "Tico_1_EON", "VW_1_EOD", "VW_1_EON"), class = "factor"), 
    ValueOfComp = c(13L, 13L, 13L, 13L, 14L, 14L, 14L, 14L, 14L, 
    14L, 15L, 15L, 15L, 15L, 15L, 15L, 16L, 16L, 16L, 16L, 16L, 
    16L, 12L, 12L, 12L, 12L)), .Names = c("Country", "Car", "ValueOfComp"
), class = "data.frame", row.names = c(NA, -26L))

在提交的data中，我们在第一列中有两个不同的国家/地区。在下一栏中，我们可以找到分配给每个国家/地区的汽车，最后一列是汽车的编号。

我想在每个国家/地区只保留一个群集。它必须是每个国家最大的集群。我们以法国为例。两个群集（13和14）已分配到此国家/地区。很明显，集群14包含更多元素/汽车。在这种情况下，我想保留集群14并从数据中删除集群13。

提供的数据只是一个例子。我的真实数据是一个庞大的表格，因此我相信在某些情况下，集群可能会包含相同数量的元素，因此哪个元素与数据保持一致并不重要。

Answer 1

library(data.table)

data[ValueOfComp %in% setDT(data)[,rle(ValueOfComp), Country][
                                  ,values[which.max(lengths)], Country]$V1,]

    Country            Car ValueOfComp
 1:  France     Fiat_1_EOD          14
 2:  France     Opel_1_EOD          14
 3:  France       VW_1_EOD          14
 4:  France     Fiat_1_EON          14
 5:  France     Opel_1_EON          14
 6:  France       VW_1_EON          14
 7:   Spain Mercedes_1_EOD          15
 8:   Spain    Nexia_1_EOD          15
 9:   Spain  Peugeot_1_EOD          15
10:   Spain Mercedes_1_EON          15
11:   Spain    Nexia_1_EON          15
12:   Spain  Peugeot_1_EON          15

Answer 2

使用dplyr，您可以：

data %>% 
  group_by(Country, ValueOfComp) %>%
  mutate(size = n()) %>%
  group_by(Country) %>%
  filter(size == max(size), ValueOfComp == max(ValueOfComp))

Source: local data frame [12 x 4]
Groups: Country [2]

   Country            Car ValueOfComp  size
    (fctr)         (fctr)       (int) (int)
1   France     Fiat_1_EOD          14     6
2   France     Opel_1_EOD          14     6
3   France       VW_1_EOD          14     6
4   France     Fiat_1_EON          14     6
5   France     Opel_1_EON          14     6
6   France       VW_1_EON          14     6
7    Spain Mercedes_1_EOD          16     6
8    Spain    Nexia_1_EOD          16     6
9    Spain  Peugeot_1_EOD          16     6
10   Spain Mercedes_1_EON          16     6
11   Spain    Nexia_1_EON          16     6
12   Spain     Tico_1_EON          16     6

Answer 3

我们可以使用plyr包和subset来获取

ddply(dat, "Country", subset, ValueOfComp == count(ValueOfComp)$x[which.max(count(ValueOfComp)$freq)])
#   Country            Car ValueOfComp
#1   France     Fiat_1_EOD          14
#2   France     Opel_1_EOD          14
#3   France       VW_1_EOD          14
#4   France     Fiat_1_EON          14
#5   France     Opel_1_EON          14
#6   France       VW_1_EON          14
#7    Spain Mercedes_1_EOD          15
#8    Spain    Nexia_1_EOD          15
#9    Spain  Peugeot_1_EOD          15
#10   Spain Mercedes_1_EON          15
#11   Spain    Nexia_1_EON          15
#12   Spain  Peugeot_1_EON          15

只保留＆＃34; cluster＆＃34;元素数量最多的

3 个答案: