R 使用未对齐的数据和间隙重新格式化数据帧

我有一个数据集，它有一个奇怪的报告格式，我需要把它放到一个可行的数据框架中。我处理的数据如下所示：

ids<-(c("A101","","","","B101","","","C101","","",""))
dx<-c("Lung","","","","Kidney","","","Prostate","","","")
alt<-c("","A766","G283","F933","","B293","T432","","U920","D289","S203")
val<-c(NA,3.2,4.3,7.2,NA,2.1,3.8,NA,8.1,5.3,7.1)
df.in<-data.frame(ids,dx,alt,val)

ids<-(c("A101","A101","A101","B101","B101","C101","C101","C101"))
dx<-c("Lung","Lung","Lung","Kidney","Kidney","Prostate","Prostate","Prostate")
alt<-c("A766","G283","F933","B293","T432","U920","D289","S203")
val<-c(3.2,4.3,7.2,2.1,3.8,8.1,5.3,7.1)
df.out<-data.frame(ids,dx,alt,val)

ids
细分：

> first<-which(is.na(df.in$val))# The positions for every new group ie 1,5 and 8
> groups=cumsum(is.na(df.in$val))#The groups you have
> groupsize=rle(groups)$length#The size of the groups
> newdf=transform(df.in[rep(first,groupsize),],val=df.in$val)#Create the new df
> newdf=na.omit(newdf)#Remove the NA rows
> row.names(newdf)=NULL# REMOVE THE ROWNAMES GIVEN
> newdf
   ids       dx alt val
1 A101     Lung     3.2
2 A101     Lung     4.3
3 A101     Lung     7.2
4 B101   Kidney     2.1
5 B101   Kidney     3.8
6 C101 Prostate     8.1
7 C101 Prostate     5.3
8 C101 Prostate     7.1

>first groups=cumsum（is.na（df.in$val））#您拥有的组
>groupsize=rle（组）$length#组的大小
>newdf=transform（df.in[rep（first，groupsize），]，val=df.in$val）#创建新的df
>newdf=na.省略（newdf）#删除na行
>row.names（newdf）=NULL#删除给定的行名
>新发展基金
ids dx alt val
1 A101肺3.2
2 A101肺4.3
3 A101肺7.2
4 B101肾脏2.1
5 B101肾脏3.8
6 C101前列腺癌8.1
7 C101前列腺癌5.3
8 C101前列腺癌7.1
单程与
tidyr
和
dplyr
：

library(dplyr)
library(tidyr)

# Replace blank cells "" with NA
df.in[df.in == ""] <- NA

# Fill NA values with value of row above it
df.in %>% 
  fill(c(ids, dx), .direction = "down") %>% 
  drop_na() %>% 
  mutate_if(is.factor, as.character) # optional

# A tibble: 8 x 4
  ids   dx       alt     val
  <chr> <chr>    <chr> <dbl>
1 A101  Lung     A766   3.20
2 A101  Lung     G283   4.30
3 A101  Lung     F933   7.20
4 B101  Kidney   B293   2.10
5 B101  Kidney   T432   3.80
6 C101  Prostate U920   8.10
7 C101  Prostate D289   5.30
8 C101  Prostate S203   7.10

库（dplyr）
图书馆（tidyr）
#将空白单元格“”替换为NA
df.in[df.in==“”]%
填充（c（ID，dx），.direction=“down”）%>%
下拉菜单（）%>%
如果（is.factor，as.character）发生变异#可选
#一个tibble:8x4
ids dx alt val
1 A101肺A766 3.20
2 A101 Lung G283 4.30
3 A101肺F933 7.20
4 B101肾脏B293 2.10
5 B101肾脏T432 3.80
6 C101前列腺U920 8.10
7 C101前列腺D289 5.30
8 C101前列腺S203 7.10

链中的最后一行，
mutate\u if（is.factor，as.character）
是可选的，它将因子转换为字符。我们可以在创建数据集时使用
stringsAsFactors=FALSE
来避免此步骤。
这非常有效。谢谢我确实收到了一个关于mutate_if函数的错误，因为它似乎在我的安装中不可用（R版本3.4，tidyr_0.8.0）
library(dplyr)
library(tidyr)

# Replace blank cells "" with NA
df.in[df.in == ""] <- NA

# Fill NA values with value of row above it
df.in %>% 
  fill(c(ids, dx), .direction = "down") %>% 
  drop_na() %>% 
  mutate_if(is.factor, as.character) # optional

# A tibble: 8 x 4
  ids   dx       alt     val
  <chr> <chr>    <chr> <dbl>
1 A101  Lung     A766   3.20
2 A101  Lung     G283   4.30
3 A101  Lung     F933   7.20
4 B101  Kidney   B293   2.10
5 B101  Kidney   T432   3.80
6 C101  Prostate U920   8.10
7 C101  Prostate D289   5.30
8 C101  Prostate S203   7.10