Question

这是我的问题：

df1 <- data.frame(x = 1:5, y = 2:6, z = 3:7)
rownames(df1) <- LETTERS[1:5]
df1
  x y z
A 1 2 3
B 2 3 4
C 3 4 5
D 4 5 6
E 5 6 7

df2 <- data.frame(x = 1:5, y = 2:6, z = 3:7)
rownames(df2) <- LETTERS[3:7]
df2
  x y z
C 1 2 3
D 2 3 4
E 3 4 5
F 4 5 6
G 5 6 7

我想要的是：

其中重复的行由同一个变量加起来。

Answer 1

使用：

# create a new variable from the rownames
df1$rn <- rownames(df1)
df2$rn <- rownames(df2)

# bind the two dataframes together by row and aggregate
res <- aggregate(cbind(x,y,z) ~ rn, rbind(df1,df2), sum)
# or (thx to @alistaire for reminding me):
res <- aggregate(. ~ rn, rbind(df1,df2), sum)

# assign the rownames again
rownames(res) <- res$rn

# get rid of the 'rn' column
res <- res[, -1]

你得到：

Answer 2

使用dplyr，

library(dplyr)

# add rownames as a column in each data.frame and bind rows
bind_rows(df1 %>% add_rownames(), 
          df2 %>% add_rownames()) %>% 
    # evaluate following calls for each value in the rowname column
    group_by(rowname) %>% 
    # add all non-grouping variables
    summarise_all(sum)

## # A tibble: 7 x 4
##   rowname     x     y     z
##     <chr> <int> <int> <int>
## 1       A     1     2     3
## 2       B     2     3     4
## 3       C     4     6     8
## 4       D     6     8    10
## 5       E     8    10    12
## 6       F     4     5     6
## 7       G     5     6     7

Answer 3

这可能需要一些诀窍来让rownames逻辑工作在一个更长的例子上：

function DisplayOE(){
$link = mysqli_connect('local','kw','pass'); //Creates a connection
if(!$link){die(' Could not connect: '.mysql_error());}
mysqli_select_db($link,'kvw') or die(mysqli_error());
$rows = mysqli_query($link, "SELECT * FROM CreateOE");
$oe = mysqli_fetch_array($rows);
//$OEquestions = 

    return $oe;
    mysqli_close($link);
}

如果rownames都可以假定为字母字符，则dfr <-rbind(df1,df2) do.call(rbind, lapply( split(dfr, sapply(rownames(dfr),substr,1,1)), colSums)) x y z A 1 2 3 B 2 3 4 C 4 6 8 D 6 8 10 E 8 10 12 F 4 5 6 G 5 6 7解决方案应该很容易。

Answer 4

另一种方法是融化数据并进行投射。首先，我们将行名称设置为两个数据帧的最后一列，这要归功于@Procrastinatus Maximus

df1$rn <- rownames(df1)
df2$rn <- rownames(df2)

然后我们根据名称

来融化数据

melt(list(df1, df2), id.vars = "rn")

然后我们使用带有mget函数的dcast，它用于一次检索多个变量。

mydf<- dcast(melt(mget(ls(pattern = "df\\d+")), id.vars = "rn"), 
      rn ~ variable, value.var = "value", fun.aggregate = sum)

rownames(mydf) <- mydf$rn

# get rid of the 'rn' column
mydf <- mydf[, -1]

> mydf
#  x  y  z
#A 1  2  3
#B 2  3  4
#C 4  6  8
#D 6  8 10
#E 8 10 12
#F 4  5  6
#G 5  6  7

Answer 5

还可以向量化将dfs转换为矩阵的操作：

result_df <- as.data.frame(as.matrix(df1) + as.matrix(df2))

如何合并和求和两个数据帧

5 个答案: