1

我需要加入几个基于不精确匹配的数据帧，这可以使用fuzzyjoin和IRanges包来实现：

数据：

df1 <- data.frame(
  line = 1:4,
  start = c(75,100,170,240),
  end = c(100,150,190,300)
)
df2 <- data.frame(
  v2 = c("A","B","C","D","E","F","G","H","I","J","K","F"),
  start = c(0,10,30,90,120,130,154,161,175,199,205,300),
  end = c(10,20,50,110,130,140,160,165,180,250,300,305)
)

df3 <- data.frame(
  v3 = c("a","b","c","d","e","f"),
  start = c(5,90,200,333,1000,1500),
  end = c(75,171,210,400,1001,1600)
)

在这里，我想根据和之间的间隔df2加入和。我能做的就是分步进行，即通过加入加入：df3df1startend

library(fuzzyjoin)

# install package "IRanges":
if (!requireNamespace("BiocManager", quietly = TRUE))
   install.packages("BiocManager")
 
BiocManager::install("IRanges")
library(BiocManager)

# First join:
df12 <- interval_left_join(x = df1,
                            y = df2,
                            by = c("start", "end")) %>%
  select(-c(start.y, end.y)) %>%
  rename(start = start.x, end = end.x)

# Second join:
df123 <- interval_left_join(x = df12,
                             y = df3,
                             by = c("start", "end")) %>%
  select(-c(start.y, end.y)) %>%
  rename(start = start.x, end = end.x)

结果：

df123  
  line start end v2   v3
1    1    75 100  D    a
2    1    75 100  D    b
3    2   100 150  D    b
4    2   100 150  E    b
5    2   100 150  F    b
6    3   170 190  I    b
7    4   240 300  J <NA>
8    4   240 300  K <NA>
9    4   240 300  F <NA>

这一切都很好，但在我的实际数据中，我有多个数据框要加入，然后，逐个加入是不切实际且容易出错的。如何一次性对所有数据帧执行连接？

4

1 回答 1

3

将数据框放入列表中，并将数据框与Reduce.

library(fuzzyjoin)
library(dplyr)

join_two_dataframes <- function(df1, df2) {
  interval_left_join(x = df1,
                     y = df2,
                     by = c("start", "end")) %>%
    select(-c(start.y, end.y)) %>%
    rename(start = start.x, end = end.x)
}

list_df <- list(df1, df2, df3)
Reduce(join_two_dataframes, list_df)

#  line start end v2   v3
#1    1    75 100  D    a
#2    1    75 100  D    b
#3    2   100 150  D    b
#4    2   100 150  E    b
#5    2   100 150  F    b
#6    3   170 190  I    b
#7    4   240 300  J <NA>
#8    4   240 300  K <NA>
#9    4   240 300  F <NA>
于 2021-02-28T13:45:20.657 回答