Question

我有一个包含多个行和列的数据集。下面是一些行和列的快照。

  ID  Date        Gender Age  Col1    Col2    Col3    Col4    Col5    Col6    Col7    Col8 
  10  2015-10-14  F      68   345.50  884.2   008.69  202.18  189.8   435.2   084.7   757
  93  2002-07-22  F      87   242.80  710.9   345.50  884.2   008.69  202.18  189.8   435.2  
  14  2004-07-28  M      92   084.7   757     242.80  710.9   427.2   530.10  567.89  227.9
  41  2011-02-24  M      39   714.0   084.7   757     242.80  710.9   427.2   530.10  567.89
  64  2002-03-14  F      39   227.9   714.0   V58.49  906.7   800.35  V88.0   349.31  289.84 
  22  2015-11-21  F      68   324.0   V65.44  411.8   200.41  187.7   E869.3  041.04  170.4
  36  2003-09-17  F      75   389.1   176.3   788.37  E936.3  277.82  812.12  E816.7  663.90
  11  2000-10-07  M      74   716.90  396.3   482.1   E816.7  663.90  716.90  396.3   482.1 
  45  2001-07-14  F      31   614.2   945.44  799.4   864.05  371.31  268     626.2   780.72
  60  1999-02-23  M      45   674     645.2   006.5   V68.2   V67.00  665.24  434.00  914.3

我有另一个数据集是一个查找表，其中包含Col1, Col2, Col3, Col4, Col5, Col6, Col7和Col8中代码的简短说明，如下所示

 Code       Short_Description
 345.50     interStellar
 884.2      indispensable
 008.69     hallucination
 202.18     flow
 189.8      categorizing
 435.2      choppiness
 084.7      chieftain
 757        substantiating
 V58.49     unbridled
 V88.0      polish
 324.0      stumble
 V65.44     hoopster
 411.8      overtrimmed
 E869.3     overbrutalizing
 041.04     choric
 E936.3     busera
 277.82     subdelegating
 E816.7     baton   
 663.90     Space

我的问题是如何将第一个数据集中的代码与第二个查找数据集中的代码进行匹配，并将匹配的代码替换为相应的简短描述？

下面的预期输出显示代码345.50匹配并替换为interStellar，V58.49匹配并替换为unbridled我希望输出全部代码匹配并替换为相应的说明。我知道如何使用 if-then-else 进行此操作，但效率非常低，我认为应该有一些简单的方法来执行此操作。任何帮助深表感谢。提前谢谢。

  ID  Date        Gender Age  Col1    Col2    Col3    Col4    Col5    Col6    Col7    Col8 
  10  2015-10-14  F      68   interStellar  884.2   008.69  202.18  189.8   435.2   084.7   757
  93  2002-07-22  F      87   242.80  710.9   interStellar  884.2   008.69  202.18  189.8   435.2  
  14  2004-07-28  M      92   084.7   757     242.80  710.9   427.2   530.10  567.89  227.9
  41  2011-02-24  M      39   714.0   084.7   757     242.80  710.9   427.2   530.10  567.89
  64  2002-03-14  F      39   227.9   714.0   unbridled  906.7   800.35  V88.0   349.31  289.84 
  22  2015-11-21  F      68   324.0  hoopster  411.8   200.41  187.7   E869.3  041.04  170.4
  36  2003-09-17  F      75   389.1   176.3   788.37  E936.3  277.82  812.12  baton  663.90
  11  2000-10-07  M      74   716.90  396.3   482.1   baton  663.90  716.90  396.3   482.1 
  45  2001-07-14  F      31   614.2   945.44  799.4   864.05  371.31  268     626.2   780.72
  60  1999-02-23  M      45   674     645.2   006.5   V68.2   V67.00  665.24  434.00  914.3

==================== 本例中使用的可重复数据集========================

df1 = structure(list(ID = c(10L, 93L, 14L, 41L, 64L, 22L, 36L, 11L, 
45L, 60L), Date = c("10/14/2015", "7/22/2002", "7/28/2004", "2/24/2011", 
"3/14/2002", "11/21/2015", "9/17/2003", "10/7/2000", "7/14/2001", 
"2/23/1999"), Gender = c("F", "F", "M", "M", "F", "F", "F", "M", 
"F", "M"), Age = c(68L, 87L, 92L, 39L, 39L, 68L, 75L, 74L, 31L, 
45L), Col1 = c(345.5, 242.8, 84.7, 714, 227.9, 324, 389.1, 716.9, 
614.2, 674), Col2 = c("884.2", "710.9", "757", "84.7", "714", 
"V65.44", "176.3", "396.3", "945.44", "645.2"), Col3 = c("8.69", 
"345.5", "242.8", "757", "V58.49", "411.8", "788.37", "482.1", 
"799.4", "6.5"), Col4 = c("202.18", "884.2", "710.9", "242.8", 
"906.7", "200.41", "E936.3", "E816.7", "864.05", "V68.2"), Col5 = c("189.8", 
"8.69", "427.2", "710.9", "800.35", "187.7", "277.82", "663.9", 
"371.31", "V67.00"), Col6 = c("435.2", "202.18", "530.1", "427.2", 
"V88.0", "E869.3", "812.12", "716.9", "268", "665.24"), Col7 = c("84.7", 
"189.8", "567.89", "530.1", "349.31", "41.04", "E816.7", "396.3", 
"626.2", "434"), Col8 = c(757, 435.2, 227.9, 567.89, 289.84, 
170.4, 663.9, 482.1, 780.72, 914.3)), class = c("tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -10L), .Names = c("ID", "Date", 
"Gender", "Age", "Col1", "Col2", "Col3", "Col4", "Col5", "Col6", 
"Col7", "Col8"), spec = structure(list(cols = structure(list(
    ID = structure(list(), class = c("collector_integer", "collector"
    )), Date = structure(list(), class = c("collector_character", 
    "collector")), Gender = structure(list(), class = c("collector_character", 
    "collector")), Age = structure(list(), class = c("collector_integer", 
    "collector")), Col1 = structure(list(), class = c("collector_double", 
    "collector")), Col2 = structure(list(), class = c("collector_character", 
    "collector")), Col3 = structure(list(), class = c("collector_character", 
    "collector")), Col4 = structure(list(), class = c("collector_character", 
    "collector")), Col5 = structure(list(), class = c("collector_character", 
    "collector")), Col6 = structure(list(), class = c("collector_character", 
    "collector")), Col7 = structure(list(), class = c("collector_character", 
    "collector")), Col8 = structure(list(), class = c("collector_double", 
    "collector"))), .Names = c("ID", "Date", "Gender", "Age", 
"Col1", "Col2", "Col3", "Col4", "Col5", "Col6", "Col7", "Col8"
)), default = structure(list(), class = c("collector_guess", 
"collector"))), .Names = c("cols", "default"), class = "col_spec"))


lookup_table = structure(list(Code = c("345.5", "884.2", "8.69", "202.18", "189.8", 
"435.2", "84.7", "757", "V58.49", "V88.0", "324", "V65.44", "411.8", 
"E869.3", "41.04", "E936.3", "277.82", "E816.7", "63.9"), Short_Description = c("interStellar", 
"indispensable", "hallucination", "flow", "\tcategorizing", "choppiness", 
"chieftain", "\tsubstantiating", "unbridled", "polish", "stumble", 
"hoopster", "overtrimmed", "overbrutalizing", "choric", "busera", 
"subdelegating", "baton\t", "Space")), class = c("tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -19L), .Names = c("Code", "Short_Description"
), spec = structure(list(cols = structure(list(Code = structure(list(), class = c("collector_character", 
"collector")), Short_Description = structure(list(), class = c("collector_character", 
"collector"))), .Names = c("Code", "Short_Description")), default = structure(list(), class = c("collector_guess", 
"collector"))), .Names = c("cols", "default"), class = "col_spec"))

Answer 1

我们可以通过重塑“广泛”来gather/spread来实现这一目标。数据集到＆＃39; long＆＃39;格式最初使用gather，使用＆＃39; lookup_table＆＃39;，left_join＆＃39;代码＆＃39;进行mutate。通过替换＆＃39; Code＆＃39;中的元素使用＆＃39; Short_Description＆＃39; （它不是缺失的值）和spread到＆＃39;宽＆＃39; select所需列后的格式（删除＆＃39; Short_Description＆＃39;）。

library(dplyr)
library(tidyr)
gather(df1, Var, Code, matches("Col")) %>% 
      left_join(., lookup_table) %>% 
      mutate(Code = if_else(!is.na(Short_Description), Short_Description, Code)) %>% 
      select(-Short_Description) %>%
      spread(Var, Code)

对于大型数据集，另一个选项是来自set的{{1}}。创建一个包含＆＃39; Col＆＃39;的列名的数字索引。 as substring（＆＃39; nm1＆＃39;）。转换＆＃39; data.frame＆＃39;到＆＃39; data.table＆＃39; （data.table），循环通过＆＃39; nm1＆＃39;指定setDT(df1)后的列并将其转换为.SDcols（因为预期的输出将包含来自＆＃39; Short_Description＆＃39;列的character字符串。使用{{1} }循环并使用character更改＆＃39; i＆＃39;中指定的列和行的＆＃39;值（使用for）。

set

Answer 2

您可以使用<style> .image { width: 510px; float: right; } p::after { content: " "; visibility: hidden; display: block; height: 0; clear: both; } </style> <div class="image"> <img src="Foo.jpg"> <p class="caption">Caption</p> </div> <p>Text about Foo. Text text text text text text text text text text text text text text text text text text text text text text text text</p> <div class="image"> <img src="Bar.jpg"> <p class="caption">Caption</p> </div> <p>Text about Bar. Text text text text text text text text text text text text text text text text text text text text text text text text</p>包

中的lookup为其执行循环

qdap

r匹配并替换

2 个答案: