R 筛选变量以连接不同维度上的两个数据帧

我想连接两个数据帧

因为我有两个维度从第二个表的列中过滤一个值，它满足第一个表的一些条件。 第一个数据帧如下所示：

 letter   year  value
    A        2001   
    B        2002
    C        2003
    D        2004

第二个：

       letter  2001  2002 2003 2004
        A         4     9    9   9
        B         6      7   6    6  
        C         2      3   5    8 
        D         1       1  1    1

这给了我类似的东西

letter year    value
A       2001    4
B       2002    7
C       2003    5
D       2004    1

thank all of you

---

一个选项是

行/列

索引。这里，行索引可以是行的序列，而我们从

获得的列索引将第一个数据的“年”列与第二个数据的列名进行匹配，
cbind
索引创建一个
矩阵
（'m1'），并使用它从第二个数据集中提取值，并将这些值分配给第一个数据中的“值”列

i1 <- seq_len(nrow(df1))
j1 <- match(df1$year, names(df2)[-1])
m1 <- cbind(i1, j1)
df1$value <- df2[-1][m1]
df1
#   letter year value
#1      A 2001     4
#2      B 2002     7
#3      C 2003     5
#4      D 2004     1

数据
df1一个选项是
行/列
索引。这里，行索引可以是行的序列，而我们从
获得的列索引将第一个数据的“年”列与第二个数据的列名进行匹配，
cbind
索引创建一个
矩阵
（'m1'），并使用它从第二个数据集中提取值，并将这些值分配给第一个数据中的“值”列

i1 <- seq_len(nrow(df1))
j1 <- match(df1$year, names(df2)[-1])
m1 <- cbind(i1, j1)
df1$value <- df2[-1][m1]
df1
#   letter year value
#1      A 2001     4
#2      B 2002     7
#3      C 2003     5
#4      D 2004     1

数据
df1tidyverse中的另一个选项是首先将您的价值数据转向更长的数据帧（来自@akrun答案的数据）：

tidyverse中的另一个选项是首先将您的价值数据透视到更长的数据帧（来自@akrun答案的数据）：

基本R解决方案：

# Reshape your dataframe from wide to long: 

df3 <- reshape(df2,
               direction = "long",
               idvar = "letter",
               varying = c(names(df2)[names(df2) != "letter"]),
               v.names = "Value",
               timevar = "Year",
               times = names(df2)[names(df2) != "letter"],
               new.row.names = 1:(nrow(df2) * length(names(df2)[names(df2) != "letter"]))
              )

# Inner join the long_df with the first dataframe: 

df_final <- merge(df1[,c(names(df1) != "Value")], df3, by = intersect(colnames(df1), colnames(df3)))

#将数据帧从宽改为长：
df3基本R解决方案：

# Reshape your dataframe from wide to long: 

df3 <- reshape(df2,
               direction = "long",
               idvar = "letter",
               varying = c(names(df2)[names(df2) != "letter"]),
               v.names = "Value",
               timevar = "Year",
               times = names(df2)[names(df2) != "letter"],
               new.row.names = 1:(nrow(df2) * length(names(df2)[names(df2) != "letter"]))
              )

# Inner join the long_df with the first dataframe: 

df_final <- merge(df1[,c(names(df1) != "Value")], df3, by = intersect(colnames(df1), colnames(df3)))

#将数据帧从宽改为长：
df3
df.final <- df2.long %>% 
  mutate(year = as.numeric(year)) %>% 
  inner_join(df1)

  letter  year value
  <chr>  <dbl> <int>
1 A       2001     4
2 B       2002     7
3 C       2003     5
4 D       2004     1

# Reshape your dataframe from wide to long: 

df3 <- reshape(df2,
               direction = "long",
               idvar = "letter",
               varying = c(names(df2)[names(df2) != "letter"]),
               v.names = "Value",
               timevar = "Year",
               times = names(df2)[names(df2) != "letter"],
               new.row.names = 1:(nrow(df2) * length(names(df2)[names(df2) != "letter"]))
              )

# Inner join the long_df with the first dataframe: 

df_final <- merge(df1[,c(names(df1) != "Value")], df3, by = intersect(colnames(df1), colnames(df3)))

lapply(c("dplyr", "tidyr"), require, character.only = TRUE)

df3_long <- 

  df2 %>% 

  pivot_longer(`2001`:`2004`, names_to = 'year', values_to = 'value') %>% 

  mutate(year = as.numeric(year)) %>% 

  inner_join(., df1, by = intersect(colnames(df1, df2)))

df1 <-
  structure(list(letter = c("A", "B", "C", "D"), year = 2001:2004),
            class = "data.frame",
            row.names = c(NA,-4L))

df2 <-
  structure(
    list(
      letter = c("A", "B", "C", "D"),
      `2001` = c(4L,
                 6L, 2L, 1L),
      `2002` = c(9L, 7L, 3L, 1L),
      `2003` = c(9L, 6L, 5L,
                 1L),
      `2004` = c(9L, 6L, 8L, 1L)
    ),
    class = "data.frame",
    row.names = c(NA,-4L)
  )