我是R的新手，目前正在尝试根据预定义的分析排除标准对数据进行子集化。我目前正在尝试删除所有由ICD-10编码的痴呆病例。问题是有多个变量包含有关每个人疾病状态的信息(~70个变量(，尽管由于它们以相同的方式编码，因此可以将相同的条件应用于所有这些变量。
一些模拟数据：
#Create dataframe containing simulated data
df = data.frame(ID = c(1001, 1002, 1003, 1004, 1005,1006,1007,1008,1009,1010,1011),
disease_code_1 = c('I802','H356','G560','D235','B178','F011','F023','C761','H653','A049','J679'),
disease_code_2 = c('A071','NA','G20','NA','NA','A049','NA','NA','G300','G308','A045'),
disease_code_3 = c('H250','NA','NA','I802','NA','A481','NA','NA','NA','NA','D352'))
#data is structured as below:
ID disease_code_1 disease_code_2 disease_code_3
1 1001 I802 A071 H250
2 1002 H356 NA NA
3 1003 G560 G20 NA
4 1004 D235 NA I802
5 1005 B178 NA NA
6 1006 F011 A049 A481
7 1007 F023 NA NA
8 1008 C761 NA NA
9 1009 H653 G300 NA
10 1010 A049 G308 NA
11 1011 J679 A045 D352
在这里，我正在尝试删除任何在任何"disease_code"变量中具有"痴呆代码"的情况。
#Remove cases with dementia from dataframe (e.g. F023, G20)
Newdata_df <- subset(df, (2:4 != "F023"|"G20"|"F009"|"F002"|"F001"|"F000"|"F00"|
"G309"| "G308"|"G301"|"G300"|"G30"| "F01"|"F018"|"F013"|
"F012"| "F011"| "F010"|"F01"))
我收到的错误是：
Error in 2:4 != "F023" | "G20" :
operations are possible only for numeric, logical or complex types
理想情况下，子集数据帧如下所示：
ID disease_code_1 disease_code_2 disease_code_3
1 1001 I802 A071 H250
2 1002 H356 NA NA
4 1004 D235 NA I802
5 1005 B178 NA NA
8 1008 C761 NA NA
11 1011 J679 A045 D352
我知道我的代码中存在错误，尽管我不确定如何准确修复它。我已经尝试了其他几种方法(使用 dplyr(，尽管到目前为止没有任何运气。
任何帮助将不胜感激！
我们可以创建一个包含要删除的代码的向量并使用rowSums进行删除，即
codes_to_remove <- c("F023", "G20", "F009", "F002", "F001", "F000", "F00", "G309", "G308",
"G301", "G300", "G30", "F01", "F018", "F013", "F012", "F011", "F010", "F01")
df[rowSums(sapply(df[-1], `%in%`, codes_to_remove)) == 0,]
这给了，
ID disease_code_1 disease_code_2 disease_code_3 1 1001 I802 A071 H250 2 1002 H356 NA NA 4 1004 D235 NA I802 5 1005 B178 NA NA 8 1008 C761 NA NA 11 1011 J679 A045 D352
一种dplyr可能性是：
df %>%
filter_at(vars(2:4), all_vars(! . %in% c("F023","G20","F009","F002","F001","F000","F00",
"G309", "G308","G301","G300","G30", "F01","F018","F013",
"F012", "F011", "F010","F01")))
ID disease_code_1 disease_code_2 disease_code_3
1 1001 I802 A071 H250
2 1002 H356 NA NA
3 1004 D235 NA I802
4 1005 B178 NA NA
5 1008 C761 NA NA
6 1011 J679 A045 D352
在这种情况下，它会检查任何列 2：4 是否包含任何给定的代码。
或：
df %>%
filter_at(vars(contains("disease_code")), all_vars(! . %in% c("F023","G20","F009","F002","F001","F000","F00",
"G309", "G308","G301","G300","G30", "F01","F018","F013",
"F012", "F011", "F010","F01")))
在这种情况下，它会检查任何具有名称disease_code的列是否包含任何给定的代码。
正如 @docendo discimus 的评论中所述，我们可以使用 gather 将数据帧转换为长格式，group_by ID并仅选择那些没有dementia_code的ID，然后将它们spread回宽格式。
library(tidyverse)
df %>%
gather(key, value, -ID) %>%
group_by(ID) %>%
filter(!any(value %in% dementia_code)) %>%
spread(key, value)
# ID disease_code_1 disease_code_2 disease_code_3
# <dbl> <chr> <chr> <chr>
#1 1001 I802 A071 H250
#2 1002 H356 NA NA
#3 1004 D235 NA I802
#4 1005 B178 NA NA
#5 1008 C761 NA NA
#6 1011 J679 A045 D352
数据
dementia_code <- c("F023", "G20", "F009", "F002", "F001", "F000", "F00", "G309",
"G308","G301", "G300", "G30", "F01", "F018", "F013", "F012", "F011", "F010", "F01")
这个怎么样：
> dementia <- c("F023", "G20", "F009", "F002", "F001", "F000", "F00", "G309", "G308",
+ "G301", "G300", "G30", "F01", "F018", "F013", "F012", "F011", "F010", "F01")
>
> dementia <- apply(sapply(df[, -1], function(x) {x %in% dementia}), 1, any)
>
> df[!dementia,]
ID disease_code_1 disease_code_2 disease_code_3
1 1001 I802 A071 H250
2 1002 H356 NA NA
4 1004 D235 NA I802
5 1005 B178 NA NA
8 1008 C761 NA NA
11 1011 J679 A045 D352
>
编辑：
一个更优雅的解决方案，感谢@Ronan Shah：
> df[apply(df[-1], 1, function(x) {!any(x %in% dementia)}),]
ID disease_code_1 disease_code_2 disease_code_3
1 1001 I802 A071 H250
2 1002 H356 NA NA
4 1004 D235 NA I802
5 1005 B178 NA NA
8 1008 C761 NA NA
11 1011 J679 A045 D352
希望对您有所帮助。
我们可以使用data.table中的melt/dcast
library(data.table)
dcast(melt(setDT(df), id.var = 'ID')[,
if(!any(value %in% dementia_codes)) .SD, .(ID)], ID ~ variable)
# ID disease_code_1 disease_code_2 disease_code_3
#1: 1001 I802 A071 H250
#2: 1002 H356 NA NA
#3: 1004 D235 NA I802
#4: 1005 B178 NA NA
#5: 1008 C761 NA NA
#6: 1011 J679 A045 D352
或者这可以在base R更紧凑地完成，无需重塑
df[!Reduce(`|`, lapply(df[-1], `%in%` , dementia_codes)),]
# ID disease_code_1 disease_code_2 disease_code_3
#1 1001 I802 A071 H250
#2 1002 H356 NA NA
#4 1004 D235 NA I802
#5 1005 B178 NA NA
#8 1008 C761 NA NA
#11 1011 J679 A045 D352
数据
dementia_codes <- c("F023", "G20", "F009", "F002", "F001", "F000",
"F00", "G309", "G308", "G301", "G300", "G30", "F01", "F018", "F013",
"F012", "F011", "F010", "F01")
带有
base R 的for循环版本，以防您喜欢的话。
df <- data.frame(ID = c(1001, 1002, 1003, 1004, 1005,1006,1007,1008,1009,1010,1011),
disease_code_1 = c('I802','H356','G560','D235','B178','F011','F023','C761','H653','A049','J679'),
disease_code_2 = c('A071','NA','G20','NA','NA','A049','NA','NA','G300','G308','A045'),
disease_code_3 = c('H250','NA','NA','I802','NA','A481','NA','NA','NA','NA','D352'), stringsAsFactors = FALSE)
dementia_codes <- c("F023", "G20", "F009", "F002", "F001", "F000", "F00", "G309", "G308", "G301", "G300", "G30", "F01", "F018", "F013", "F012", "F011", "F010", "F01")
new_df <- df[0,]
for(i in 1:nrow(df)){
currRow <- df[i,]
if(any(dementia_codes %in% as.character(currRow)) == FALSE){
new_df <- rbind(new_df, currRow)
}
}
new_df
# ID disease_code_1 disease_code_2 disease_code_3
# 1 1001 I802 A071 H250
# 2 1002 H356 NA NA
# 4 1004 D235 NA I802
# 5 1005 B178 NA NA
# 8 1008 C761 NA NA
# 11 1011 J679 A045 D352