r - 如何操作我的数据以计算具有多个 NA 实例的 R 中的平均值？
问题描述
我正在使用 R Studio，并且有一个非常大的数据集，其中包含 4 个变量。我正在尝试计算 O2 柱每天 06:30:00 到 19:00:00 之间的时间平均值。数据集的示例如下所示：
RBWQ <- read.csv(".../R/WY06 to WY19.csv", skip = 2, header = TRUE, sep = ",", na.strings=c("","NA"))
RBWQ <- setNames(RBWQ, c("datetime","NDCQ","O2","SpCond","PaseoQ"))
View(RBWQ)
datetime NDCQ O2 SpCond PaseoQ
1 2005-10-01 00:00:00 NA NA NA 827
2 2005-10-01 00:15:00 NA NA NA 857
3 2005-10-01 00:30:00 NA NA NA 857
4 2005-10-01 00:45:00 NA NA NA 807
5 2005-10-01 01:00:00 NA 10 300 797
6 2005-10-01 01:15:00 NA 10.3 319 817
7 2005-10-01 01:30:00 NA 10 401 797
8 2005-10-01 01:45:00 NA 10.2 398 788
9 2005-10-01 02:00:00 NA NA NA 788
10 2005-10-01 02:15:00 NA NA NA 807
每小时有 15 分钟的间隔，如您所见，此数据集中有很多 NA。如何操作此数据集确定每天特定时间段内的平均值，并让它在 R 中生成包含日期和平均值的表中的报告？
dput(head(RBWQ))
structure(list(datetime = structure(list(sec = c(0, 0, 0, 0,
0, 0), min = c(0L, 15L, 30L, 45L, 0L, 15L), hour = c(0L, 0L,
0L, 0L, 1L, 1L), mday = c(1L, 1L, 1L, 1L, 1L, 1L), mon = c(9L,
9L, 9L, 9L, 9L, 9L), year = c(105L, 105L, 105L, 105L, 105L, 105L
), wday = c(6L, 6L, 6L, 6L, 6L, 6L), yday = c(273L, 273L, 273L,
273L, 273L, 273L), isdst = c(1L, 1L, 1L, 1L, 1L, 1L), zone = c("MDT",
"MDT", "MDT", "MDT", "MDT", "MDT"), gmtoff = c(NA_integer_, NA_integer_,
NA_integer_, NA_integer_, NA_integer_, NA_integer_)), class = c("POSIXlt",
"POSIXt")), NDCQ = c(NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), O2 = c(NA_real_, NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_), SpCond = c(NA_real_, NA_real_, NA_real_,
NA_real_, NA_real_, NA_real_), PaseoQ = c(827L, 857L, 857L, 807L,
797L, 817L)), row.names = c(NA, 6L), class = "data.frame")
某些日子可能会因为各种原因（例如被埋没）而导致仪器读数不正确，可能会出现一整天的 NA。
dput(head(RBWQ, 96))
structure(list(datetime = structure(list(sec = c(0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0), min = c(0L, 15L, 30L, 45L, 0L, 15L,
30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L,
45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L,
0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L,
15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L,
30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L,
45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L,
0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L, 0L, 15L, 30L, 45L), hour = c(0L,
0L, 0L, 0L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L,
8L, 8L, 8L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 11L, 11L, 11L,
11L, 12L, 12L, 12L, 12L, 13L, 13L, 13L, 13L, 14L, 14L, 14L, 14L,
15L, 15L, 15L, 15L, 16L, 16L, 16L, 16L, 17L, 17L, 17L, 17L, 18L,
18L, 18L, 18L, 19L, 19L, 19L, 19L, 20L, 20L, 20L, 20L, 21L, 21L,
21L, 21L, 22L, 22L, 22L, 22L, 23L, 23L, 23L, 23L), mday = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L),
mon = c(9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L), year = c(105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L, 105L,
105L, 105L, 105L), wday = c(6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L), yday = c(273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L, 273L,
273L, 273L, 273L, 273L, 273L), isdst = c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), zone = c("MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT",
"MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT", "MDT"
), gmtoff = 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_,
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_, 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_, 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_)), class = c("POSIXlt", "POSIXt"
)), NDCQ = 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_, 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_, 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_, 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_
), O2 = 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_, 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_,
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_, 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_),
SpCond = 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_, 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_, 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_, 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_), PaseoQ = c(827L, 857L, 857L, 807L, 797L, 817L,
797L, 788L, 788L, 807L, 788L, 797L, 807L, 797L, 778L, 797L,
807L, 797L, 750L, 741L, 750L, 714L, 714L, 696L, 696L, 687L,
687L, 678L, 678L, 661L, 669L, 661L, 678L, 678L, 696L, 661L,
644L, 635L, 661L, 644L, 644L, 635L, 635L, 627L, 635L, 652L,
652L, 652L, 644L, 635L, 644L, 652L, 661L, 652L, 661L, 635L,
661L, 644L, 652L, 635L, 644L, 619L, 619L, 619L, 635L, 635L,
635L, 652L, 635L, 652L, 652L, 661L, 652L, 652L, 652L, 652L,
661L, 652L, 644L, 627L, 619L, 635L, 619L, 619L, 603L, 611L,
603L, 603L, 619L, 635L, 635L, 635L, 627L, 619L, 635L, 619L
)), row.names = c(NA, 96L), class = "data.frame")
解决方案
对于时间序列数据，请考虑xts包。根据您的数据创建一个时间序列（第一列中包含您的日期时间）。然后根据时间范围进行子集化，并用于colMeans计算每日均值（去除NA）。如果这是您的想法，请告诉我。
library(xts)
RBWQ_xts <- xts(RBWQ[, -1], RBWQ[, 1])
apply.daily(RBWQ_xts["T06:30:00/T19:00:00"], colMeans, na.rm = TRUE)
推荐阅读
- tooltip - 为什么我的 AmChart XYChart 只显示多个系列的单个工具提示？
- android - 尽管我确定是，但未找到默认活动？
- php - 使用 Docker 使用 dblib 将 php 5.5 连接到 MSSQL
- c - 为什么我的 TIMER0 不使用 Atmega644 控制器上 XTAL1 和 XTAL2 之间的振荡器？
- reactjs - 当我在前端使用 ReactJS 库时，如何在 www.mywebsite.com/robot.txt 拥有 robots.txt 文件？
- javascript - jQuery 带参数的淡入淡出功能
- vba - 需要循环代码以从文档中获取文本并将其粘贴到另一个文档中
- swift - 如何快速从结构中过滤
- java - 更新关系时更新@LastModifiedDate
- encryption - 为什么我不能使用密码作为加密密钥来安全地加密密码？