根据另一个数据框中的值有条件地替换数据框中的列名

Conditionally replace column names in a dataframe based on values in another dataframe

我下载了一个table的导流数据("df_download")。此 table 的列名主要取自测量站的 ID 号。

我想有条件地将用于列名的 ID 号替换为站名文本,这将有助于在我共享时提高数据的可读性结果。我用 ID 号和站名创建了一个 table ("stationIDs"),用作更改 "df_download".

的列名的参考

我可以单独替换列名,但我想编写某种循环来处理 "df_download" 的所有列并更改数据框中引用的列的名称 "stationIDs".

下面是我尝试做的一个例子。

已下载数据("df_download")

部分下载数据类似这样:

df_downloaded <- data.frame(Var1 = seq(as.Date("2012-01-01"),as.Date("2012-12-01"), by="month"),
                            Var2 = sample(50:150,12, replace =TRUE),
                            Var3 = sample(10:100,12, replace =TRUE),
                            Var4 = sample(15:45,12, replace =TRUE),
                            Var5 = sample(50:200,12, replace =TRUE),
                            Var6 = sample(15:100,12, replace =TRUE),
                            Var7 = c(rep(0,3),rep(13,6),rep(0,3)),
                            Var8 = rep(5,12))
colnames(df_downloaded) <- c("Diversion.Date","360410059","360410060",
                             "360410209","361000655","361000656","Irrigation","Seep") 

df_download # not run
# 
#    Diversion.Date 360410059 360410060 360410209 361000655 361000656 Irrigation Seep
# 1      2012-01-01        93        57        28       101        16          0    5
# 2      2012-02-01       102        68        19       124        98          0    5
# 3      2012-03-01       124        93        36       109        56          0    5
# 4      2012-04-01        94        96        23        54        87         13    5
# 5      2012-05-01        83        70        43       119        15         13    5
# 6      2012-06-01        78        63        45       195        15         13    5
# 7      2012-07-01        86        77        20       130        63         13    5
# 8      2012-08-01       118        29        27       118        57         13    5
# 9      2012-09-01       142        18        45       116        27         13    5
# 10     2012-10-01        74        68        34       182        79          0    5
# 11     2012-11-01       106        48        27        95        74          0    5
# 12     2012-12-01        91        41        20       179        55          0    5

参考Table ("stationIDs")

stationIDs <- data.frame(ID = c("360410059", "360410060", "360410209", "361000655", "361000656"),
                         Names = c("RimView", "IPCO", "WMA.Ditch", "RV.Bypass", "LowerFalls"))
stationIDs # not run
#
#          ID      Names
# 1 360410059    RimView
# 2 360410060       IPCO
# 3 360410209  WMA.Ditch
# 4 361000655  RV.Bypass
# 5 361000656 LowerFalls

我可以使用单独的语句替换 "df_downloaded" 中的列名。我在下面展示了前三个迭代。
经过三次迭代 "RimValley"、"IPCO" 和 "WMA.Ditch" 已替换了各自的仪表 ID 号。

names(df_downloaded) <- gsub(stationIDs$ID[1],stationIDs$Name[1],names(df_downloaded))

# head(df_downloaded)
#   Diversion.Date RimView 360410060 360410209 361000655 361000656 Irrigation Seep
# 1     2012-01-01      93        57        28       101        16          0    5
# 2     2012-02-01     102        68        19       124        98          0    5
# 3     2012-03-01     124        93        36       109        56          0    5
# 4     2012-04-01      94        96        23        54        87         13    5
# 5     2012-05-01      83        70        43       119        15         13    5
# 6     2012-06-01      78        63        45       195        15         13    5

names(df_downloaded) <- gsub(stationIDs$ID[2],stationIDs$Name[2],names(df_downloaded))

# head(df_downloaded)
#   Diversion.Date RimView IPCO 360410209 361000655 361000656 Irrigation Seep
# 1     2012-01-01      93   57        28       101        16          0    5
# 2     2012-02-01     102   68        19       124        98          0    5
# 3     2012-03-01     124   93        36       109        56          0    5
# 4     2012-04-01      94   96        23        54        87         13    5
# 5     2012-05-01      83   70        43       119        15         13    5
# 6     2012-06-01      78   63        45       195        15         13    5

names(df_downloaded) <- gsub(stationIDs$ID[3],stationIDs$Name[3],names(df_downloaded))

# head(df_downloaded)
#   Diversion.Date RimView IPCO WMA.Ditch 361000655 361000656 Irrigation Seep
# 1     2012-01-01      93   57        28       101        16          0    5
# 2     2012-02-01     102   68        19       124        98          0    5
# 3     2012-03-01     124   93        36       109        56          0    5
# 4     2012-04-01      94   96        23        54        87         13    5
# 5     2012-05-01      83   70        43       119        15         13    5
# 6     2012-06-01      78   63        45       195        15         13    5

如果我尝试使用 for 循环进行重命名,我最终会使用 NA 作为列名。

for(i in seq_along(names(df_downloaded))){
    names(df_downloaded) <- gsub(stationIDs$ID[i],stationIDs$Name[i],names(df_downloaded))
}

# head(df_downloaded)
#           NA  NA NA NA  NA NA NA NA
# 1 2012-01-01  93 57 28 101 16  0  5
# 2 2012-02-01 102 68 19 124 98  0  5
# 3 2012-03-01 124 93 36 109 56  0  5
# 4 2012-04-01  94 96 23  54 87 13  5
# 5 2012-05-01  83 70 43 119 15 13  5
# 6 2012-06-01  78 63 45 195 15 13  5

我真的希望能够使用 for 循环或类似的东西来更改名称,因为我从中下载数据的站点数量会根据我分析的年份而变化。

感谢您花时间看我的问题。

你可以做到这一点 dplyr 和 tidyr。您基本上想让数据变长,以便 ID 位于一列中,这样您就可以通过对名称的 ID 引用对其进行连接。然后你可以让你的数据再次变宽。

df_downloaded %>%
   gather(ID, value, -Diversion.Date, -Irrigation, -Seep) %>% 
   left_join(., stationIDs) %>%
   dplyr::select(-ID) %>% 
   spread(Names, value)

我们可以使用match

#Convert factor columns to character
stationIDs[] <- lapply(stationIDs, as.character)
#Match names of df_downloaded with stationIDs$ID
inds <- match(names(df_downloaded), stationIDs$ID)
#Replace the matched name with corresponding Names from stationIDs
names(df_downloaded)[which(!is.na(inds))] <- stationIDs$Names[inds[!is.na(inds)]]

df_downloaded
#   Diversion.Date RimView IPCO WMA.Ditch RV.Bypass LowerFalls Irrigation Seep
#1      2012-01-01     142   14        41       200         79          0    5
#2      2012-02-01      97  100        35       176         22          0    5
#3      2012-03-01      85   59        26        88         71          0    5
#4      2012-04-01      68   49        34        63         15         13    5
#5      2012-05-01      62   58        44        87         16         13    5
#6      2012-06-01      70   59        33       145         87         13    5
#7      2012-07-01     112   65        25        52         64         13    5
#8      2012-08-01      75   12        27       103         19         13    5
#9      2012-09-01      73   65        36       172         68         13    5
#10     2012-10-01      87   35        27       146         42          0    5
#11     2012-11-01     122   17        33       183         32          0    5
#12     2012-12-01     108   65        15       120         99          0    5