R 使用循环在数据帧中的列上迭代操作

我有一个带有列名的数据框，其中包括W1_2019格式的周和年标识符以及其他文本。完整的数据框架包含52周的数据，每个数据框架包含5列。我的目标是使用下面的代码，它完全符合我在第1周和第2周的要求，并将其放入x=1到52的循环中，这样我就不必使用52次相同的半打行

eidsr <- dget(file="test1.txt")

mode_xmt <- data.frame(District=eidsr$district) #Initializes dataframe mode_xmt with only 1 column containing District names

wtmp <- select(eidsr, contains("W1_2019"))
wtmp$mode <- "NoRep"
wtmp$mode[wtmp$W1_2019_EIDSR_Total_Malaria_cases>0] <- "Report"
wtmp$mode[wtmp$`W1_2019_EIDSR-Mobile_SMS`==1] <- "Mobile_SMS"
wtmp$mode[wtmp$`W1_2019_EIDSR-Mobile_Internet`==1] <- "Mobile_Internet"

#At this point the dataframe wtmp looks like the example below.

mode_xmt$`2019_W1` <- wtmp$mode #Appends ONLY the W1_2019 column to mode_xmt
rm(wtmp)

wtmp <- select(eidsr, contains("W2_2019"))
wtmp$mode <- "NoRep"
wtmp$mode[wtmp$W2_2019_EIDSR_Total_Malaria_cases>0] <- "Report"
wtmp$mode[wtmp$`W2_2019_EIDSR-Mobile_SMS`==1] <- "Mobile_SMS"
wtmp$mode[wtmp$`W2_2019_EIDSR-Mobile_Internet`==1] <- "Mobile_Internet"

mode_xmt$`2019_W2` <- wtmp$mode
rm(wtmp)

一旦我完成了W2的第二次迭代，mode_xmt如下所示：

   `W1_2019_EIDSR-Timely_~ W1_2019_EIDSR_Total_Mala~ W1_2019_EIDSR_Date_R~ `W1_2019_EIDSR-Mobile_~ `W1_2019_EIDSR-Mobi~ mode 
                     <dbl>                     <dbl> <chr>                                   <dbl>                <dbl> <chr>
 1                      NA                         0 NA                                         NA                   NA NoRep
 2                      NA                        NA NA                                         NA                   NA NoRep
 3                      NA                        51 NA                                         NA                   NA Repo~
 4                      NA                        NA NA                                         NA                   NA NoRep
 5                      NA                        64 NA                                         NA                   NA Repo~
 6                      NA                        86 NA                                         NA                   NA Repo~
 7                      NA                        92 NA                                         NA                   NA Repo~
 8                      NA                        47 NA                                         NA                   NA Repo~
 9                      NA                        46 NA                                         NA                   NA Repo~
10                      NA                        35 NA                                         NA                   NA Repo~

   District 2019_W01
1        Bo    NoRep
2        Bo    NoRep
3        Bo   Report
4        Bo    NoRep
5        Bo   Report
6        Bo   Report
7        Bo   Report
8        Bo   Report
9        Bo   Report
10       Bo   Report

   District 2019_W01 2019_W02
1        Bo    NoRep   Report
2        Bo    NoRep    NoRep
3        Bo   Report   Report
4        Bo    NoRep    NoRep
5        Bo   Report   Report
6        Bo   Report   Report
7        Bo   Report   Report
8        Bo   Report   Report
9        Bo   Report   Report
10       Bo   Report   Report

起泡，冲洗，重复。时报52。正如@DS_UNI所观察到的，虽然将周和年分开列会很好，但它们会破坏最终目的，即一个超过一年的时间序列。。。但是为了不让自己完全发疯，如果我能重复一年中的52周，我会很高兴

正如我所说，上面的代码是有效的。我只是在寻找一种循环的方法，而不是像往常一样重复它

以下是工作目录中另存为test1.txt的截断数据的dput文本：

structure(list(`W1_2019_EIDSR-Timely_Report` = c(NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_), W1_2019_EIDSR_Total_Malaria_cases = c(0,  NA, 51, NA, 64, 86, 92, 47, 46, 35, 33, NA, NA, 77, 35, 7, 24,  27, 14, 72), W1_2019_EIDSR_Date_Received = c(NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_, NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_, NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_, NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_), `W1_2019_EIDSR-Mobile_Internet` = c(NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), `W1_2019_EIDSR-Mobile_SMS` = c(NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), `W2_2019_EIDSR-Timely_Report`
= c(NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), W2_2019_EIDSR_Total_Malaria_cases = c(55,  NA, 44, NA, 38, 26, 29, 40, 59, 18, 48, NA, NA, 37, 34, 51, 34,  38, 13, 56), W2_2019_EIDSR_Date_Received = c(NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_, NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_, NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_, NA_character_, NA_character_,  NA_character_, NA_character_, NA_character_), `W2_2019_EIDSR-Mobile_Internet` = c(NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), `W2_2019_EIDSR-Mobile_SMS` = c(NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_,  NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), district = c("Bo",  "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo",  "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo", "Bo")), .Names = c("W1_2019_EIDSR-Timely_Report",  "W1_2019_EIDSR_Total_Malaria_cases", "W1_2019_EIDSR_Date_Received",  "W1_2019_EIDSR-Mobile_Internet", "W1_2019_EIDSR-Mobile_SMS",  "W2_2019_EIDSR-Timely_Report", "W2_2019_EIDSR_Total_Malaria_cases",  "W2_2019_EIDSR_Date_Received", "W2_2019_EIDSR-Mobile_Internet",  "W2_2019_EIDSR-Mobile_SMS", "district"), row.names = c(NA, -20L ), class = c("tbl_df", "tbl", "data.frame"))

---

你的数据应该是这样的，我也希望每周有一列，每年有一列。最有可能的是，有一种方法可以操纵你得到你想要的东西

library(dplyr)
library(reshape2)

eidsr %>% 
  # values should be in a column (not in headers) 
  melt(id.var = 'district') %>% 
  # extract the new variables
  mutate(week_year = substr(variable, 1, 7),
         variable = sub(".*EIDSR[- _]", "", variable)) %>% 
  # assuming missing values don't have a specific meaning you can just remove them
  na.omit()

#     district            variable value week_year
# 21        Bo Total_Malaria_cases     0   W1_2019
# 23        Bo Total_Malaria_cases    51   W1_2019
# 25        Bo Total_Malaria_cases    64   W1_2019
# 26        Bo Total_Malaria_cases    86   W1_2019
# 27        Bo Total_Malaria_cases    92   W1_2019
# 28        Bo Total_Malaria_cases    47   W1_2019
# 29        Bo Total_Malaria_cases    46   W1_2019
# 30        Bo Total_Malaria_cases    35   W1_2019

我可以看出您正在失去耐心，因此如果必须使用循环，则应使用其中一个应用函数，对于那些需要在向量或列表上重复应用函数的函数：

wacky_fun <- function(x_chr){
  malaria_col <- paste0(x_chr, '_EIDSR_Total_Malaria_cases')
  sms_col <- paste0(x_chr, '_EIDSR-Mobile_SMS')
  internet_col <- paste0(x_chr, '_EIDSR-Mobile_Internet')

  mode_col <- rep("NoRep", nrow(eidsr))
  mode_col[eidsr[malaria_col]>0] <- "Report"
  mode_col[eidsr[sms_col]==1] <- "Mobile_SMS"
  mode_col[eidsr[internet_col]==1] <- "Mobile_Internet"

  return(mode_col)
}

我们将对数据中的所有周应用该函数

# get the unique weeks in the headers 
weeks <- names(eidsr)[grepl('W[[:digit:]]_[[:digit:]]{4}', names(eidsr))] %>% 
  substr(1, 7) %>% 
  unique()
# apply the function on all the weeks, bind them with the district, and convert to data.frame
cbind('district' = eidsr$district, sapply(weeks, wacky_fun)) %>% 
  as.data.frame()

---

我建议您看看什么是，以及如何重塑数据以优化分析，处理类似数据，tbh我不建议使用循环来解决这个问题，也就是说，如果没有可复制的示例，帮助解决这个问题非常具有挑战性，这可能会给您一些关于如何提供样本数据的想法，可重复的例子，一个预期的结果我担心你会说。。。这些数据太乱了，我要花很长时间才能创建虚拟数据进行复制。我试试……：对不起！但你也可以看看我在第一条评论中添加的问题，看看答案可能会有所帮助。我知道这是大量的新手材料，但我经常遇到这样的问题，因为我不知道如何创建与我正在处理的导入数据类似的示例数据。你有没有任何创建虚拟数据的链接，你可以告诉我吗？不，这不是我的目标。看起来我无法格式化评论，因此将在上面的问题中重新编辑。谢谢你的耐心。再加上我迟来的感谢@DS_UNI。你的古怪乐趣完美地工作了，代码行比我的克鲁格少得多。我有很多分析要做，所以代码的进一步学习将不得不推迟到以后，但我感谢您的帮助，并完全打算回来分析您的代码，直到我理解它！