我有一个数据列，其列名包括格式为“ W1_2019”的星期和年份指示符以及其他文本。完整的数据框包含52个星期，每个星期有5列。我的目标是采用以下代码，该代码完全按照我希望在第1周和第2周的时间进行操作，并将其放入x = 1到52的循环中，因此我不必使用相同的一半的52倍十二行。
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)
在每次操作结束时，我的工作数据如下。数据框wtmp看起来像这样：
`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~
mode_xmt，附加新列，如下所示：
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
完成W2的第二次迭代后，mode_xmt如下所示：
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所观察到的那样，尽管每周和每年使用单独的列会很不错，但它们将无法达到最终目的，因为它是一个长达一年以上的时间序列...但是要阻止我自己继续前进疯了，如果我可以迭代一年的52周，我会很高兴。
正如我所说，以上代码有效。我只是在寻找一种循环播放的方式，而不是在重复恶心的情况下重复播放。
以下是被截断的数据的dput文本（在工作目录中另存为test1.txt）：
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"))
答案 0 :(得分：1)
您的数据应如下所示（我也希望有一个列用于星期，而一列则用于年）。而且很可能有一种方法来操纵您想要的东西。
select * from student a
inner join student_groups b on a.student_studgroup=b.studgroups_number
inner join study on study_studgroup_id=stud_Group_id
where (your condition --)
我可以看到您正在失去耐心，因此，如果必须使用循环，则应使用apply函数之一，而对于那些循环，则需要一个函数反复应用于向量或列表：
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
我们将在数据的所有星期中应用该功能
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)
}