转换列类/类型时维护date/POSIXct列

Question

我有一个包含多个日期列的400列数据格式。在下面的有代表性的例子中，我想实现以下目标：

1. 将因素转换为数字或字符或POSIXct
2. 将字符转换为数字/整数，在其中有意义
3. 将包含日期的任何列转换为POSIXct，而不管它是因子、字符还是日期。 set.seed(123) df1 <- data.frame( A= as.numeric(1:10)，B=样本(as.POSIXct(‘2000/01/01’)，as.POSIXct('2018/01/01')，by=“日”)，C=as.numeric(样本(20:90，大小= 10))，D=样本(“是”，“否”，size=10，替换为真)，E=as.factor(样本(1000:2000，大小= 10))，F=as.character(c(“测试”、"test2“、"test3”、"test4“、"test5”、"test6“、"test7”、"test8“、"test9”、“test10”)、G=as.factor(“测试”、"test2“、"test3”、"test4“、"test5”、"test6“、"test7”、"test8“、”“)，H= as.character(sample(seq(as.POSIXct('2000/01/01')，as.POSIXct('2018/01/01')，by=“day”，size=10)( stringsAsFactors=FALSE ) df1 A、C、D、E、G、H 1、2005-03-06 00:00:00 87无1963年测试测试2002-07-27 23:00:00 2 2 2014-03-00:00 51无1902 test2 test2 2007-06 23:00:00 3 3 2007-05-11 23:00:00 66 no 1690 test3 test3 2007-06-11 : 00:00:00004 2015-11-22 00: 00 :00 58不1793 test4 test4 2006-20 23:00:00 5 2016-12-02 :00:00 26无1024 test5 test5 2002-09-27 :00:00 6 6 2000-10-26 00:00 79无1475 test6 test6 2002-06-30 23:00:00 7 2009-06-30 :00:00 35 no 1754 test7 test7 2004-11 00:00:00 8 2016-0119 :00:00 22 no 1215 test8 test8 2008-05-17 23:00 9 9 2009-11-30 00:00 40 yes 1315 test9 test9 2004- 10 -12 00:00 10 10 2008-03-17 00:00:00 85 yes 1229 test10 test10 2015-06-03 23:00( B1 B2 C、D、E、F、G、H、“数字”、"POSIXct“、"POSIXt”、“数字”、“因素”、“字符”、“因素”、“字符”)

到目前为止，我尝试了以下方法(但它没有保留POSIXct列B)或将字符日期列(H列)转换为POSIXct：

df1_clean <- df1 %>% mutate_all(funs(type.convert(as.character(.), as.is = TRUE)))
unlist(lapply(df1_clean, class))
      A           B           C           D           E           F            G           H 
      "integer" "character"   "integer" "character"   "integer" "character" "character" "character" 

对于这个小数据集，我只需调用列，并使用lubridate将B和H转换为POSIXct，但我希望它能够自动跨越数据帧。

任何帮助都将不胜感激！谢谢莫伊

Answer 1

这可能不是最优雅的方式--但它似乎适合我。

#install.packages("tidyverse")
#install.packages("dataCompareR")
library("tidyverse")
library("dataCompareR")



# create reproducible df
set.seed(123)
df1 <- data.frame(
  A = as.numeric(1:10),
  B = sample(seq(as.POSIXct('2000/01/01', tz = "UTC"), as.POSIXct('2018/01/01', tz = "UTC"), by="day"), size=10),
  C = as.numeric(sample(20:90, size = 10)),
  D = sample(c("yes", "no"), size=10, replace = TRUE),
  E = as.factor(sample(1000:2000, size = 10)),
  F = as.character(c("test","test2","test3","test4","test5","test6","test7","test8","test9","test10")),
  G = as.factor(c("test","test2","test3","test4","test5","test6","test7","test8","test9","test10")),
  H = as.character(sample(seq(as.POSIXct('2000/01/01', tz = "UTC"), as.POSIXct('2018/01/01', tz = "UTC"), by="day"), size=10)),stringsAsFactors=FALSE
)
df1 #look at df

unlist(lapply(df1, class)) #look at df classes


df1_clean <- df1 %>% mutate_all(funs(type.convert(as.character(.), as.is = TRUE))) #reassign classes by running type.convert (input are all variables from the df but as.character)
unlist(lapply(df1_clean, class)) #look at df classes now

#check if a column is a Date - https://stackoverflow.com/questions/18178451/is-there-a-way-to-check-if-a-column-is-a-date-in-r
tmp=sapply(df1_clean, function(x) !all(is.na(as.Date(as.character(x),format="%Y-%m-%d", tz = "UTC")))) 

# if tmp is True, change according column to as.POSIXct 
for (i in 1:ncol(df1_clean)){
  if (tmp[i] == T){
    df1_clean[,i]<- as.POSIXct(df1_clean[,i], tz = "UTC")
  }
}

df1_clean #look at df
unlist(lapply(df1_clean, class)) #look at df classes


comp <- rCompare(df1, df1_clean) #compare your dfs before and after using the dataCompareR package
summary(comp) # check summary