如何从输入数据中获取输出文件中的 15 行平均日期和时间列？

问题描述 投票：0回答：1

我使用下面在 R 中给出的代码计算了我的数据（.txt 文件）每 15 行的平均值。

x <- df %>% separate(`Date/Time`, into = c("Date", "Time"), sep = "T")
mn <- x %>%
 group_by(group = as.integer(gl(n(), 15, n()))) %>%
 summarise_all(funs(mean))
write.csv(min, 'C:/Users/Alexia/Desktop/Test/15row.csv')

我成功获得了输出，但在日期和时间列输出中，我收到了 NA。但是，所需的输出应如下所示：

Date   Time   Col1   Col2   Col3....
2021-01-01   00:00:00  12  36  56
2021-01-01   00:15:00  34  54  43
2021-01-01   00:30:00  24  23  21
2021-01-01   00:45:00  12  36  56
2021-01-01   01:00:00  34  54  43
2021-01-01   01:15:00  24  23  21
2021-01-01   01:30:00  12  36  43
2021-01-01   01:45:00  12  36  34
2021-01-01   02:00:00  12  36  34
.
.
.

我的输入数据（.txt）是每分钟的，并且具有以下方式的日期和时间：

Date/Time   Col1   Col2   Col3....
2021-01-01T00:00:00  20  12  34...
2021-01-01T00:01:00  .....
2021-01-01T00:02:00  .....
2021-01-01T00:03:00  .....
2021-01-01T01:04:00  .....
2021-01-01T01:05:00  .....
2021-01-01T01:05:00  .....
2021-01-01T01:07:00  .....
2021-01-01T02:08:00  .....

dput(df)的输出如下：

structure(list(`Date/Time` = c("2021-03-01T00:01:00", "2021-03- 
01T00:02:00", "2021-03-01T00:03:00", "2021-03-01T00:04:00", "2021-03- 
01T00:05:00", "2021-03-01T00:06:00", "2021-03-01T00:07:00", "2021-03- 
01T00:08:00", "2021-03-01T00:09:00", "2021-03-01T00:10:00", "2021-03- 
01T00:11:00", "2021-03-01T00:12:00", "2021-03-01T00:13:00", "2021-03- 
01T00:14:00", "2021-03-01T00:15:00", "2021-03-01T00:16:00", "2021-03- 
01T00:17:00", "2021-03-01T00:18:00", "2021-03-01T00:19:00", "2021-03- 
01T00:20:00", "2021-03-01T00:21:00", "2021-03-01T00:22:00", "2021-03- 
01T00:23:00", "2021-03-01T00:24:00", "2021-03-01T00:25:00", "2021-03- 
01T00:26:00", "2021-03-01T00:27:00", "2021-03-01T00:28:00", "2021-03- 
01T00:29:00", "2021-03-01T00:30:00"), `XY [XY]` = c(0.990641, 0.990641, 
0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 
0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 
0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 
0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641, 0.990641), 
`C1 [CC]` = c(257L, 257L, 257L, 257L, 257L, 257L, 257L, 
257L, 257L, 257L, 257L, 257L, 257L, 257L, 257L, 257L, 257L, 
257L, 257L, 257L, 257L, 257L, 257L, 257L, 257L, 257L, 257L, 
257L, 257L, 257L), Cc = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `C2 [C2]` = c(285L, 
285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 
285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 
285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L, 285L), Dc = c(0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), 
`C3 [C2]` = c(255L, 255L, 255L, 255L, 255L, 255L, 255L, 
255L, 255L, 255L, 255L, 255L, 255L, 255L, 255L, 255L, 255L, 
255L, 255L, 255L, 255L, 255L, 255L, 255L, 255L, 255L, 255L, 
255L, 255L, 255L), Ac = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), C4 = c(0.463735, 0.463735, 
0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 
0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 
0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 
0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 0.463735, 
0.463735, 0.463735, 0.463735, 0.463735), `C5 [h]` = c(1013L, 
1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 
1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 
1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 1013L, 
1013L, 1013L), `C6 [%]` = c(43L, 43L, 43L, 43L, 43L, 43L, 
43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 
43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L, 43L
), `C7 [E2]` = c(390L, 390L, 390L, 390L, 390L, 390L, 
390L, 390L, 390L, 390L, 390L, 390L, 390L, 390L, 390L, 390L, 
390L, 390L, 390L, 390L, 390L, 390L, 390L, 390L, 390L, 390L, 
390L, 390L, 390L, 390L), Jc = c(0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `D [S]` = c(62.3716, 
62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 
62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 
62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 
62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 62.3716, 
62.3716), `Sw [S2]` = c(1392.95, 1392.95, 1392.95, 1392.95, 
1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 
1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 
1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 1392.95, 
1392.95, 1392.95, 1392.95, 1392.95, 1392.95), `SW [Q2]` = 
c(389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 
389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 
389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 
389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 389.164, 
389.164), `OA [H2]` = c(646.61, 646.61, 646.61, 646.61, 
646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 
646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 
646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 646.61, 
646.61, 646.61), `T2 [C]` = c(3.7, 3.7, 3.7, 3.7, 3.7, 
3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 
3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 3.7, 
3.7), Lc = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L)), class = "data.frame", row.names = c(NA, 
-30L))
r date datetime mean
1个回答
0
投票

问题在于您的数据类型 - 您需要告诉 

R
您正在使用日期和时间，否则它会假设您正在使用字符向量。如果你取字符向量的平均值，它会产生
NA
.

尝试：

library(lubridate)
x <- df %>% separate(`Date/Time`, into = c("Date", "Time"), sep = "T")

min <- x %>% 
  as_tibble() %>%
  mutate(
    # Convert Date column into the Date datatype
    Date = lubridate::ymd(Date), 
    # Convert Time column into the Period datatype (HMS). Then, 
    # change this to number of seconds
    Time = period_to_seconds(hms(Time))
  ) %>%
  summarise(across(everything(), mean)) %>% 
  # Convert Time column from number of seconds 
  # back into the Period datatype (HMS). Omit this line
  # if you'd prefer to have the average in seconds
  mutate(Time = seconds_to_period(Time))

write.csv(min, 'C:/Users/Alexia/Desktop/Test/15row.csv')
最新问题
© www.soinside.com 2019 - 2024. All rights reserved.