Question

为什么openair timeAverage会从数据框中删除某些列？

例如，我有这个数据框：

> dput(Df)
structure(list(key_date = c("2017-04-30", "2017-05-01", "2017-05-01", 
"2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", 
"2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", 
"2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", 
"2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", "2017-05-01", 
"2017-05-01"), date = structure(c(1493593200, 1493596800, 1493600400, 
1493604000, 1493607600, 1493611200, 1493614800, 1493618400, 1493622000, 
1493625600, 1493629200, 1493632800, 1493636400, 1493640000, 1493643600, 
1493647200, 1493650800, 1493654400, 1493658000, 1493661600, 1493665200, 
1493668800, 1493672400, 1493676000), class = c("POSIXct", "POSIXt"
), tzone = ""), PM = c(5.1, 4.8, 4.4, 7.4, 6.9, 9.3, 7.3, 10.3, 
6.4, 4, 8.2, 5.6, 6.7, 4.4, 8.1, 6.1, 3.4, NA, 10.2, 11.3, 7.3, 
8.6, 6, 10.5), site = c("LW2", "LW2", "LW2", "LW2", "LW2", "LW2", 
"LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", 
"LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2"
), code = c("LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", 
"LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", 
"LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2", "LW2"), airport = structure(c(NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_), .Label = character(0), class = "factor"), 
    ws = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_), wd = c(NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_), tempi = c(NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_), humidity = c(NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, NA_real_, 
    NA_real_, NA_real_, NA_real_, NA_real_)), .Names = c("key_date", 
"date", "PM", "site", "code", "airport", "ws", "wd", "tempi", 
"humidity"), row.names = c(NA, -24L), class = "data.frame")

应用timeAverage：

Df <- timeAverage(Df, avg.time = "1 hour")
Warning message:
In checkPrep(mydata, vars, type = "default", remove.calm = FALSE,  :
  Detected data with Daylight Saving Time, converting to UTC/GMT
> 
> dput(Df)
structure(list(date = structure(c(1493596800, 1493600400, 1493604000, 
1493607600, 1493611200, 1493614800, 1493618400, 1493622000, 1493625600, 
1493629200, 1493632800, 1493636400, 1493640000, 1493643600, 1493647200, 
1493650800, 1493654400, 1493658000, 1493661600, 1493665200, 1493668800, 
1493672400, 1493676000, 1493679600), class = c("POSIXct", "POSIXt"
), tzone = "GMT"), PM = c(5.1, 4.8, 4.4, 7.4, 6.9, 9.3, 7.3, 
10.3, 6.4, 4, 8.2, 5.6, 6.7, 4.4, 8.1, 6.1, 3.4, NaN, 10.2, 11.3, 
7.3, 8.6, 6, 10.5), ws = c(NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN), wd = c(NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN), tempi = c(NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN), humidity = c(NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 
NaN, NaN, NaN, NaN, NaN, NaN)), .Names = c("date", "PM", "ws", 
"wd", "tempi", "humidity"), row.names = c(NA, -24L), class = c("tbl_df", 
"tbl", "data.frame"))

列：key_date，代码，网站被删除。为什么？我怎么能保留它们？

此外，它将我的NA数据更改为NaN - 我如何保持 NA数据？

修改

我设法保留了这些列：

Df <- timeAverage(Df, avg.time = "1 hour", type = c("site", "code"))

但我如何保留NA值？

timeAverage从数据框中移除某些列

0 个答案: