r - R:将因子列转换为多个 boolean 列

Question

我正在尝试将一个因素列转换为多个 bool(boolean) 列，如下图所示。数据来自使用精细weatherData包检索的气象站。我想转换为多个 bool(boolean) 列的factor列包含11个因子。其中一些是单个“事件”，而另一些则是“事件”的组合。

这是显示我想要实现的图像:

这是R代码，它将生成具有要转换为多个 bool(boolean) 列的组合因子的数据帧:

df <- read.table(text="
date    Events
1/8/2013    Rain
1/9/2013    Fog
1/10/2013   ''
1/11/2013   Fog-Rain
1/12/2013   Snow
1/13/2013   Rain-Snow
1/14/2013   Rain-Thunderstorm
1/15/2013   Thunderstorm
1/16/2013   Fog-Rain-Thunderstorm
1/17/2013   Fog-Thunderstorm
1/18/2013   Fog-Rain-Thunderstorm-Snow",
                 header=T)
df$date <- as.character(as.Date(df$date, "%m/%d/%Y"))

提前致谢。

Answer 1

您可以尝试:

 lst <- strsplit(as.character(df$Events),"-")
 lvl <- unique(unlist(lst))      
 res <- data.frame(date=df$date,
            do.call(rbind,lapply(lst, function(x) table(factor(x, levels=lvl)))), 
                                       stringsAsFactors=FALSE)

  res
 #         date Rain Fog Snow Thunderstorm
 #1  2013-01-08    1   0    0            0
 #2  2013-01-09    0   1    0            0
 #3  2013-01-10    0   0    0            0
 #4  2013-01-11    1   1    0            0
 #5  2013-01-12    0   0    1            0
 #6  2013-01-13    1   0    1            0
 #7  2013-01-14    1   0    0            1
 #8  2013-01-15    0   0    0            1
 #9  2013-01-16    1   1    0            1
 #10 2013-01-17    0   1    0            1
# 11 2013-01-18    1   1    1            1

或者，可能比上述方法更快(由@alexis_laz提供)

  setNames(data.frame(df$date, do.call(rbind,lapply(lst, function(x) as.integer(lvl %in% x)) )), c("date", lvl))  

要么

 library(devtools)
 library(data.table)
 source_gist("11380733")
 library(reshape2) #In case it is needed 

 res1 <- dcast.data.table(cSplit(df, "Events", "-", "long"), date~Events)
 res2 <- merge(subset(df, select=1), res1, by="date", all=TRUE)
 res2 <- as.data.frame(res2)
 res2[,-1]  <- (!is.na(res2[,-1]))+0
 res2[,c(1,3,2,4,5)]
 #          date Rain Fog Snow Thunderstorm
  #1  2013-01-08    1   0    0            0
  #2  2013-01-09    0   1    0            0
  #3  2013-01-10    0   0    0            0
  #4  2013-01-11    1   1    0            0
  #5  2013-01-12    0   0    1            0
  #6  2013-01-13    1   0    1            0
  #7  2013-01-14    1   0    0            1
  #8  2013-01-15    0   0    0            1
  #9  2013-01-16    1   1    0            1
  #10 2013-01-17    0   1    0            1
  #11 2013-01-18    1   1    1            1

要么

 library(qdap)
 with(df, termco(Events, date, c("Rain", "Fog", "Snow", "Thunderstorm")))[[1]][,-2]
 #         date Rain Fog Snow Thunderstorm
 #1  2013-01-08    1   0    0            0
 #2  2013-01-09    0   1    0            0
 #3  2013-01-10    0   0    0            0
 #4  2013-01-11    1   1    0            0
 #5  2013-01-12    0   0    1            0
 #6  2013-01-13    1   0    1            0
 #7  2013-01-14    1   0    0            1
 #8  2013-01-15    0   0    0            1
 #9  2013-01-16    1   1    0            1
 #10 2013-01-17    0   1    0            1
 #11 2013-01-18    1   1    1            1