filter(！is.na(column)) 没有从 R 中的列中删除 NA

Question

我正在重做一项研究作业，看看我是否可以改进它并重新投入其中；状态"；以及"；结果"；返回给定结果/疾病死亡率最低的州的医院名称。由于某种原因，我的filter(！is.na(((行似乎不起作用。我有一种感觉，这与我使用粘贴来选择列名有关，但在我的炖菜中，这似乎无关紧要。

这是代码：

library(dplyr)
data <- read.csv("outcome-of-care-measures.csv", colClasses = "character")
dataSelected <- data %>%
select("Hospital.Name", "State", "Hospital.30.Day.Death..Mortality..Rates.from.Heart.Attack", "Hospital.30.Day.Death..Mortality..Rates.from.Heart.Failure", "Hospital.30.Day.Death..Mortality..Rates.from.Pneumonia")
colnames(dataSelected) <- c("HostpitalName","State","DeathRateHeartAttack","DeathRateHeartFailure","DeathRatePneumonia")
dataSelected[,3] <- as.numeric(dataSelected[,3])
dataSelected[,4] <- as.numeric(dataSelected[,4])
dataSelected[,5] <- as.numeric(dataSelected[,5])

best <- function(state,outcome){
column <- paste('DeathRate',outcome, sep = "")
if (state %in% dataSelected$State < 1){
return('Invalid state')
} else if (column %in% colnames(dataSelected) < 1){
return('Invalid outcome')
} else{
BestHospitals <- dataSelected %>%
select(HostpitalName,State,column) %>%
filter(!is.na(column)) %>%
filter(State == state) %>%
arrange(column,HostpitalName)
return(BestHospitals[1,1])
}
}

我的函数调用

best("AL","HeartAttack")

版本信息

平台x86_64-apple-darwin15.6.0
arch x86_64
os darwin15.6.0
系统x86_64，darwin15.6.0
状态
主要3
次要6.1
2019年
月07日
第05天
svn修订版76782
语言R
版本。字符串R版本3.6.1(2019-07-05(昵称脚趾动作

dput的输出(磁头(dataSelected((：

structure(list(HostpitalName = c("SOUTHEAST ALABAMA MEDICAL CENTER", 
"MARSHALL MEDICAL CENTER SOUTH", "ELIZA COFFEE MEMORIAL HOSPITAL", 
"MIZELL MEMORIAL HOSPITAL", "CRENSHAW COMMUNITY HOSPITAL", "MARSHALL MEDICAL CENTER NORTH"
), State = c("AL", "AL", "AL", "AL", "AL", "AL"), DeathRateHeartAttack = c(14.3, 
18.5, 18.1, NA, NA, NA), DeathRateHeartFailure = c(11.4, 15.2, 
11.3, 13.6, 13.8, 12.5), DeathRatePneumonia = c(10.9, 13.9, 13.4, 
14.9, 15.8, 8.7)), row.names = c(NA, 6L), class = "data.frame")

Answer 1

按列号而不是名称进行筛选怎么样？

best <- function(state,outcome){
column <- paste('DeathRate',outcome, sep = "")
if (state %in% dataSelected$State < 1){
return('Invalid state')
} else if (column %in% colnames(dataSelected) < 1){
return('Invalid outcome')
} else{
BestHospitals <- dataSelected %>%
select(HostpitalName,State,column) %>%
filter(!is.na(.[,3])) %>%
filter(State == state) %>%
arrange(desc(.[3])))
return(BestHospitals[1,1])
}
}

Answer 2

我随意重写了您的函数。

# it is usually a bad idea to insert a global variable (like your data frame) inside a function. 
best <- function(dat=NULL,state=NULL,outcome=NULL){ 

column <- paste('DeathRate',outcome, sep = "")

if (!state %in% dat$State | !column %in% colnames(dat)){
stop('Invalid input')
} # negating and using or "|" makes it easier to read
else{
BestHospitals <- dat %>%
select(HostpitalName,State,column) %>%
na.omit() %>% # for your purpose the much more concise na.omit() is a better option
filter(State == state) %>%
arrange(column,HostpitalName) %>% 
filter(row_number()==1) #dplyr way to choose the first row

return(BestHospitals)
}
}
best(dat = dataSelected, state = "AL", outcome = "HeartAttack")
HostpitalName State DeathRateHeartAttack
1 ELIZA COFFEE MEMORIAL HOSPITAL    AL                 18.1

Answer 3

这里有一个类似tidyverse的函数版本。

正如D.J.所评论的，在函数中包含对全局对象(dataSelected(的引用不是一种好的做法。将其作为参数传递要好得多。这还有一个有益的副作用，即允许您在管道中使用该函数。

此外，HostpitalName可能是一个拼写错误。你是说HospitalName吗？由于你不止一次使用这个奇怪的拼写，我保留了下来

虽然我理解为什么允许用户通过将"DeathRate"的公共前缀粘贴到outcome中传递的值来缩短所需结果的名称，但这可能不是最佳实践，因为需要用户了解此约定，并将函数的使用限制为遵循此约定的数据帧和列。它也不太适合tidyverse语法。

best <- function(d, state, outcome){
# By adding d as the first parameter, you make it easy to use the function in
# a pipe.  And on data frames other than dataSelected.
qOutcome <- enquo(outcome)
# calling stop is better than returning an error message as 
# it stops processing immediately.
if (!(state %in% (d %>% distinct(State) %>% pull(State) ))) {
stop('Invalid state')
}
if (!(as_label(qOutcome) %in% colnames(d)) ){
stop('Invalid outcome')
}
# Converting original code to equivalent tidyverse idioms.
# HostpitalName should perhaps be HospitalName in the source data frame
d %>%
select(HostpitalName, State, !! qOutcome) %>%
filter(!is.na(!! qOutcome)) %>%
filter(State == state) %>%
arrange(!! qOutcome, HostpitalName) %>% 
pull(HostpitalName) %>% 
head(1)
}

这样我们就可以写了

dataSelected %>% best("AL", DeathRateHeartFailure)
[1] "ELIZA COFFEE MEMORIAL HOSPITAL"

或者说

dataSelected %>% best("AL", DeathRatePneumonia)
[1] "MARSHALL MEDICAL CENTER NORTH"