R数据表唯一记录计数基于两列给定值列表的所有组合

我有一个

数据。R中的表如下

Col1          Col2         
Col1Value1    Col2Value1   
Col1Value1    Col2Value2
Col1Value1    Col2Value3
Col1Value2    Col2Value1   
Col1Value2    Col2Value3
Col1Value3    Col2Value1
Col1Value3    Col2Value2
Col1Value3    Col2Value3

我想获得
Col1-（Col1Value1，Col1Value2）
中给定值与
Col2-Col1（Col2Value1，Col2Value2）
中的值之间的每个组合的记录计数，如果没有组合的记录，则返回0

计数您可以尝试以下代码：

a<-c("Col1Value1", "Col1Value2")
b<-c("Col2Value1", "Col2Value2")

df2<-df %>% select(Col1, Col2) %>% filter(Col1 %in% a) %>% filter(Col2 %in% b)  %>% group_by(Col1, Col2) %>% summarise(count = n()) %>% as.data.frame()

expand.grid(a,b) %>% left_join(df2, by = c("Var1"="Col1", "Var2"="Col2")) %>% mutate(count2 = ifelse(is.na(count), 0, count)) %>% select(-count)

资料

在base R中，您可以执行以下操作：

data.frame(table(dt))

        Var1       Var2 Freq
1 Col1Value1 Col2Value1    1
2 Col1Value2 Col2Value1    1
3 Col1Value3 Col2Value1    1
4 Col1Value1 Col2Value2    1
5 Col1Value2 Col2Value2    0
6 Col1Value3 Col2Value2    1
7 Col1Value1 Col2Value3    1
8 Col1Value2 Col2Value3    1
9 Col1Value3 Col2Value3    1

您可以像这样使用
表格
：

data.table(with(dt, table(Col1, Col2)))

         Col1       Col2 N
1: Col1Value1 Col2Value1 1
2: Col1Value2 Col2Value1 1
3: Col1Value3 Col2Value1 1
4: Col1Value1 Col2Value2 1
5: Col1Value2 Col2Value2 0
6: Col1Value3 Col2Value2 1
7: Col1Value1 Col2Value3 1
8: Col1Value2 Col2Value3 1
9: Col1Value3 Col2Value3 1

数据

dt <- setDT(read.table(text="Col1          Col2         
                 Col1Value1    Col2Value1   
                 Col1Value1    Col2Value2
                 Col1Value1    Col2Value3
                 Col1Value2    Col2Value1   
                 Col1Value2    Col2Value3
                 Col1Value3    Col2Value1
                 Col1Value3    Col2Value2
                 Col1Value3    Col2Value3", header=TRUE,stringsAsFactors=FALSE) )

dt对于具有0条记录的组合，您可能必须首先创建所有具有零值的行，然后覆盖那些具有0条以上记录的行。这让我想知道您是否真的需要将这两列分开，或者您是否可以从创建一个新列中获益，该列通过添加Col1和Col2作为逗号分隔的字符（例如“2，3”）而产生。这样你就可以先清点所有可能的组合，然后统计出现的次数。谢谢。我认为要求是所有组合集合中的有限组合，所以采用这种方法。
DT[CJ(Col1, Col2, unique = TRUE), on = .(Col1, Col2), .(count = .N), by = .EACHI]

#          Col1       Col2 count
# 1: Col1Value1 Col2Value1     1
# 2: Col1Value1 Col2Value2     1
# 3: Col1Value1 Col2Value3     1
# 4: Col1Value2 Col2Value1     1
# 5: Col1Value2 Col2Value2     0
# 6: Col1Value2 Col2Value3     1
# 7: Col1Value3 Col2Value1     1
# 8: Col1Value3 Col2Value2     1
# 9: Col1Value3 Col2Value3     1

DT <- fread(
  "Col1          Col2         
  Col1Value1    Col2Value1   
  Col1Value1    Col2Value2
  Col1Value1    Col2Value3
  Col1Value2    Col2Value1   
  Col1Value2    Col2Value3
  Col1Value3    Col2Value1
  Col1Value3    Col2Value2
  Col1Value3    Col2Value3"
)

a <- c("Col1Value1", "Col1Value2")
b <- c("Col2Value1", "Col2Value2")
DT[Col1 %in% a & Col2 %in% b
   ][CJ(Col1, Col2, unique = TRUE), on = .(Col1, Col2), .(count = .N), by = .EACHI]

data.frame(table(dt))

        Var1       Var2 Freq
1 Col1Value1 Col2Value1    1
2 Col1Value2 Col2Value1    1
3 Col1Value3 Col2Value1    1
4 Col1Value1 Col2Value2    1
5 Col1Value2 Col2Value2    0
6 Col1Value3 Col2Value2    1
7 Col1Value1 Col2Value3    1
8 Col1Value2 Col2Value3    1
9 Col1Value3 Col2Value3    1

data.table(with(dt, table(Col1, Col2)))

         Col1       Col2 N
1: Col1Value1 Col2Value1 1
2: Col1Value2 Col2Value1 1
3: Col1Value3 Col2Value1 1
4: Col1Value1 Col2Value2 1
5: Col1Value2 Col2Value2 0
6: Col1Value3 Col2Value2 1
7: Col1Value1 Col2Value3 1
8: Col1Value2 Col2Value3 1
9: Col1Value3 Col2Value3 1

dt <- setDT(read.table(text="Col1          Col2         
                 Col1Value1    Col2Value1   
                 Col1Value1    Col2Value2
                 Col1Value1    Col2Value3
                 Col1Value2    Col2Value1   
                 Col1Value2    Col2Value3
                 Col1Value3    Col2Value1
                 Col1Value3    Col2Value2
                 Col1Value3    Col2Value3", header=TRUE,stringsAsFactors=FALSE) )