In R aggregating by hour changes date and time - r

I regularly use the aggregate function to find means and sums of POSIXlt data per hour and per day. I am trying to use the same function on a new dataset to get hourly averages, but when I apply it, it changes the timestamp.
The data is a data.frame (called "moT") like this:
TS T
1 2016-06-26 10:10:34 19.662
2 2016-06-26 10:40:34 21.091
3 2016-06-26 11:10:34 23.388
4 2016-06-26 11:40:34 24.448
5 2016-06-26 12:10:34 25.513
6 2016-06-26 12:40:34 26.390
7 2016-06-26 01:10:34 27.468
8 2016-06-26 01:40:34 27.567
9 2016-06-26 02:10:34 26.977
10 2016-06-26 02:40:34 25.222
11 2016-06-26 03:10:34 23.100
12 2016-06-26 03:40:34 24.158
13 2016-06-26 04:10:34 21.951
14 2016-06-26 04:40:34 21.473
15 2016-06-26 05:10:34 19.948
16 2016-06-26 05:40:34 19.472
17 2016-06-26 06:10:34 18.806
18 2016-06-26 06:40:34 16.808
19 2016-06-26 07:10:34 15.282
20 2016-06-26 07:40:34 14.517
or as per suggested format:
structure(list(TS = structure(list(sec = c(34, 34, 34, 34, 34,
34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34, 34),
min = c(10L, 40L, 10L, 40L, 10L, 40L, 10L, 40L, 10L, 40L,
10L, 40L, 10L, 40L, 10L, 40L, 10L, 40L, 10L, 40L), hour = c(10L,
10L, 11L, 11L, 12L, 12L, 1L, 1L, 2L, 2L, 3L, 3L, 4L, 4L,
5L, 5L, 6L, 6L, 7L, 7L), mday = c(26L, 26L, 26L, 26L, 26L,
26L, 26L, 26L, 26L, 26L, 26L, 26L, 26L, 26L, 26L, 26L, 26L,
26L, 26L, 26L), mon = c(5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), year = c(116L,
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L,
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L), wday = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L), yday = c(177L, 177L, 177L, 177L, 177L, 177L,
177L, 177L, 177L, 177L, 177L, 177L, 177L, 177L, 177L, 177L,
177L, 177L, 177L, 177L), isdst = c(0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L),
zone = c("GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5",
"GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5",
"GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5", "GMT+5"
), 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_)), .Names = c("sec", "min", "hour", "mday", "mon",
"year", "wday", "yday", "isdst", "zone", "gmtoff"), class = c("POSIXlt",
"POSIXt"), tzone = "Etc/GMT+5"), T = c(19.662, 21.091, 23.388,
24.448, 25.513, 26.39, 27.468, 27.567, 26.977, 25.222, 23.1,
24.158, 21.951, 21.473, 19.948, 19.472, 18.806, 16.808, 15.282,
14.517)), .Names = c("TS", "T"), row.names = c(NA, 20L), class = "data.frame")
I apply this code to "moT":
dat <- aggregate(moT["T"], format(moT["TS"], "%Y-%m-%d %H"), mean)
I expect this output (for the first five rows):
TS meanT
1 "2016-06-26 10" 20.3765
2 "2016-06-26 11" 23.918
3 "2016-06-26 12" 25.9515
4 "2016-06-26 13" 27.5175
5 "2016-06-26 14" 26.0995
that is what has happened when I have used the same function on other datasets.
but instead it is this:
TS meanT
1 "2016-01-07 00" 14.5650
2 "2016-01-07 01" 14.0380
3 "2016-01-07 02" 13.6540
4 "2016-01-07 03" 13.6540
5 "2016-01-07 04" 13.7500
Why is the date and time changing???
I have tried using POSIXct instead of POSIXlt, have tried reformatting the datetime objects in my csv files, have tried removing the time zone from the POSIXlt object.
I've seen this post
How to calculate average of a variable by hour in R
that would give me the result I want, but requires separating date and time into two columns. I'm happy to do that but I'd like to know why this is happening so I can avoid it in future and know which method to use for which data.
Thanks very much.

Related

Formatting x_scale in ggplot with weekly data

In my ggplot, I've managed to create a x_scale based on time (I have weekly data) but am not sure how to create year-month labels using scale_x_date
The following is my code - I have tried using (...breaks = "1 month") and (...minor_breaks = "1 month") but this does not produce the desired result. I am aiming for the labels to simply be Dec-16, Jan-17, Feb-17 and so on. What is the proper formatting to make the x_scale to show Month-Year in an abbreviated way?
ggplot(data=test, aes(x=as.Date(test$weekly), y=test$dist, group=1)) +
geom_path(col = "blue") +
scale_x_date(labels = date_format("%b-%Y"))
Here is a sample of the data
> dput(test)
structure(list(weekly = 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), min = 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, 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
), hour = 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, 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), mday = c(18L, 25L, 1L,
8L, 15L, 22L, 29L, 5L, 12L, 19L, 26L, 3L, 10L, 17L, 24L, 31L,
7L, 14L, 21L, 28L, 5L, 12L, 19L, 26L, 2L, 9L, 16L, 23L, 30L,
6L, 13L, 20L, 27L, 6L, 13L, 20L, 27L, 3L, 10L, 17L, 24L, 1L,
8L, 15L, 22L, 29L, 5L, 12L, 19L, 26L, 3L, 10L, 17L, 24L, 31L),
mon = c(6L, 6L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 9L, 9L,
9L, 9L, 9L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 0L, 0L,
0L, 0L, 0L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L),
year = c(116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L,
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L,
116L, 116L, 116L, 116L, 116L, 116L, 117L, 117L, 117L, 117L,
117L, 117L, 117L, 117L, 117L, 117L, 117L, 117L, 117L, 117L,
117L, 117L, 117L, 117L, 117L, 117L, 117L, 117L, 117L, 117L,
117L, 117L, 117L, 117L, 117L, 117L, 117L), wday = 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), yday = c(199L, 206L, 213L,
220L, 227L, 234L, 241L, 248L, 255L, 262L, 269L, 276L, 283L,
290L, 297L, 304L, 311L, 318L, 325L, 332L, 339L, 346L, 353L,
360L, 1L, 8L, 15L, 22L, 29L, 36L, 43L, 50L, 57L, 64L, 71L,
78L, 85L, 92L, 99L, 106L, 113L, 120L, 127L, 134L, 141L, 148L,
155L, 162L, 169L, 176L, 183L, 190L, 197L, 204L, 211L), isdst = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), zone = c("CEST", "CEST",
"CEST", "CEST", "CEST", "CEST", "CEST", "CEST", "CEST", "CEST",
"CEST", "CEST", "CEST", "CEST", "CEST", "CET", "CET", "CET",
"CET", "CET", "CET", "CET", "CET", "CET", "CET", "CET", "CET",
"CET", "CET", "CET", "CET", "CET", "CET", "CET", "CET", "CET",
"CEST", "CEST", "CEST", "CEST", "CEST", "CEST", "CEST", "CEST",
"CEST", "CEST", "CEST", "CEST", "CEST", "CEST", "CEST", "CEST",
"CEST", "CEST", "CEST"), 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_)), .Names = c("sec",
"min", "hour", "mday", "mon", "year", "wday", "yday", "isdst",
"zone", "gmtoff"), class = c("POSIXlt", "POSIXt")), dist = c(23621.19,
30400.01, 27458.66, 24511.07, 24908.37, 24413.81, 21096.52, 24557.51,
14833.71, 15513.72, 13516.23, 8102.02, 5881.44, 8370.01, 7339.34,
7703.79, 9297.52, 4542, 3555.56, 4438.33, 1968.65, 2259.06, 2729.89,
2876.66, 1767.86, 784.17, 2004.55, 4446.98, 2203.16, 3956.35,
4095.28, 3999.88, 3288.59, 4593.19, 6164.63, 6111.46, 8462.84,
7404.8, 9725.91, 9652.72, 9357.52, 15535.51, 11810.82, 17890.89,
23518.06, 18754.44, 16377.46, 15023.27, 23354.14, 23328.12, 27024.1,
23414.38, 28273.08, 24213.3, 19068.03)), .Names = c("weekly",
"dist"), row.names = c(NA, -55L), class = "data.frame")

R shows NA although a value is present

I have two columns of PosixLT times with no NA values , yet NA values show up upon check
> sum(is.na(check$start))
[1] 19
> sum(is.na(check$end))
[1] 23
The data is present in the cells, so why does this happen? I have heard that this can happen with PosixLT but even when I convert this to posixCT, there is very strange behavior. How does one go about solving this?
> as.POSIXct(check$start, format = "%Y-%m-%d %H:%M:%S", tz = "CST6CDT")
[1] NA "2014-03-09 01:35:01 CST" NA "2014-03-09 01:53:30 CST" NA
[6] NA NA NA NA "2014-03-09 04:17:11 CDT"
[11] NA NA "2015-03-08 01:54:43 CST" NA NA
[16] NA NA NA NA NA
[21] NA NA NA
> dput(check)
structure(list(start = structure(list(sec = c(24, 1, 27, 30,
8, 21, 40, 9, 43, 11, 31, 43, 43, 55, 39, 54, 41, 19, 2, 35,
6, 54, 40), min = c(45L, 35L, 14L, 53L, 36L, 37L, 47L, 48L, 54L,
17L, 57L, 53L, 54L, 3L, 52L, 22L, 34L, 28L, 41L, 42L, 52L, 52L,
53L), hour = c(2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 4L, 2L, 2L,
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), mday = c(9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L, 8L, 8L), mon = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L),
year = c(114L, 114L, 114L, 114L, 114L, 114L, 114L, 114L,
114L, 114L, 114L, 115L, 115L, 115L, 115L, 115L, 115L, 115L,
115L, 115L, 115L, 115L, 115L), wday = c(0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L), yday = c(67L, 67L, 67L, 67L, 67L, 67L, 67L,
67L, 67L, 67L, 67L, 66L, 66L, 66L, 66L, 66L, 66L, 66L, 66L,
66L, 66L, 66L, 66L), isdst = c(-1L, 0L, -1L, 0L, -1L, -1L,
-1L, -1L, -1L, 1L, -1L, -1L, 0L, -1L, -1L, -1L, -1L, -1L,
-1L, -1L, -1L, -1L, -1L), zone = c("", "CST", "", "CST",
"", "", "", "", "", "CDT", "", "", "CST", "", "", "", "",
"", "", "", "", "", ""), 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_)), .Names = c("sec", "min", "hour", "mday", "mon",
"year", "wday", "yday", "isdst", "zone", "gmtoff"), class = c("POSIXlt",
"POSIXt"), tzone = c("CST6CDT", "CST", "CDT")), end = structure(list(
sec = c(7, 59, 38, 45, 29, 46, 39, 14, 52, 29, 37, 5, 23,
41, 10, 43, 46, 46, 53, 24, 57, 13, 51), min = c(55L, 47L,
30L, 2L, 43L, 51L, 53L, 56L, 54L, 54L, 57L, 56L, 6L, 3L,
13L, 29L, 37L, 32L, 48L, 47L, 55L, 55L, 55L), hour = c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L), mday = c(9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L,
8L, 8L, 8L), mon = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L),
year = c(114L, 114L, 114L, 114L, 114L, 114L, 114L, 114L,
114L, 114L, 114L, 115L, 115L, 115L, 115L, 115L, 115L, 115L,
115L, 115L, 115L, 115L, 115L), wday = c(0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L), yday = c(67L, 67L, 67L, 67L, 67L, 67L, 67L,
67L, 67L, 67L, 67L, 66L, 66L, 66L, 66L, 66L, 66L, 66L, 66L,
66L, 66L, 66L, 66L), 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), zone = c("", "", "", "", "", "",
"", "", "", "", "", "", "", "", "", "", "", "", "", "", "",
"", ""), 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_
)), .Names = c("sec", "min", "hour", "mday", "mon", "year",
"wday", "yday", "isdst", "zone", "gmtoff"), class = c("POSIXlt",
"POSIXt"), tzone = c("CST6CDT", "CST", "CDT"))), .Names = c("start",
"end"), row.names = c(1559963L, 1560092L, 1560157L, 1560220L,
1560240L, 1560247L, 1560252L, 1560253L, 1560255L, 1560258L, 1560260L,
2004432L, 2004583L, 2004591L, 2004594L, 2004596L, 2004598L, 2004599L,
2004600L, 2004603L, 2004609L, 2004610L, 2004611L), class = "data.frame")

How works is.na in this context ?
> is.na.POSIXlt
function (x)
is.na(as.POSIXct(x))
<bytecode: 0x0000000014232980>
How does as.POSIXct behave here ?
> as.POSIXct(check$start)
[1] NA "2014-03-09 01:35:01 CST" NA "2014-03-09 01:53:30 CST"
[5] NA NA NA NA
[9] NA "2014-03-09 04:17:11 CDT" NA NA
[13] "2015-03-08 01:54:43 CST" NA NA NA
[17] NA NA NA NA
[21] NA NA NA
Ok, but WHY ????
Let's check the doc of as.POSIXct:
Any conversion that needs to go between the two date-time classes
requires a time zone: conversion from "POSIXlt" to "POSIXct" will
validate times in the selected time zone. One issue is what happens at
transitions to and from DST, for example in the UK
Let's see:
> check$start$zone
[1] "" "CST" "" "CST" "" "" "" "" "" "CDT" "" "" "CST" "" "" "" "" "" "" ""
[21] "" "" ""
An here's the dragons, there's no timezone except for 4 entries, so as.POSIXct can't tell if the dates are valid (within DST change or not ?) as you can see with:
> check$start$isdst
[1] -1 0 -1 0 -1 -1 -1 -1 -1 1 -1 -1 0 -1 -1 -1 -1 -1 -1 -1 -1 -1 -1
So the converstion between POSIXlt (your dataframe) and POSIXct can't guess if the date is valid, and return NA.
One fixing method could be to enforce a timezone on all records:
> check$start <- as.POSIXlt(strftime(check$start,tz="CST"),tz="CST6CDT")
> is.na(check$start)
[1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE

ggplot + boxplot with time series value by group

A variation of this question -- I can't quite get the dimensions right in the data structure to make a boxplot with the right values.
what I'm looking to do: hours would be on the x-axis, region would be on the y-axis, and for every region there will be a boxplot showing the distribution of income by hour.
The closest I can get is the following, but it's not right. How do I create the boxplot with two factors (one a time series) as axes, populated by the value distribution?
data:
regions <- structure(list(location = structure(c(2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("east",
"north", "west"), class = "factor"), hour = 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), min = 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, 0L, 0L, 0L), hour = c(0L,
1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 0L, 1L, 2L, 3L, 4L,
5L, 6L, 7L, 8L, 9L, 10L, 0L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L,
9L, 10L), mday = c(13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L,
13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L,
13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L), mon = c(7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L
), year = c(115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L,
115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L,
115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L, 115L,
115L, 115L), wday = c(4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L), yday = c(224L, 224L, 224L, 224L,
224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L,
224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L, 224L,
224L, 224L, 224L, 224L, 224L, 224L, 224L), 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),
zone = c("CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT",
"CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT",
"CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT",
"CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT", "CDT"),
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_)), .Names = c("sec",
"min", "hour", "mday", "mon", "year", "wday", "yday", "isdst",
"zone", "gmtoff"), class = c("POSIXlt", "POSIXt")), hour_income = c(67L,
98L, 89L, 75L, 75L, 89L, 70L, 97L, 52L, 94L, 80L, 84L, 52L, 82L,
81L, 93L, 85L, 94L, 64L, 90L, 54L, 60L, 97L, 100L, 57L, 63L,
90L, 58L, 86L, 68L, 52L, 78L, 61L)), .Names = c("location", "hour",
"hour_income"), row.names = c(NA, -33L), class = "data.frame")
And the boxplot
ggplot(regions) +
geom_boxplot(aes(x=hour, y=hour_income, group=location))

First we convert datetimes to character format, then create the boxplots.
regions$hour <- strftime(regions$hour, format="%H:%M:%S")
ggplot(data = regions, aes(x = hour, y = hour_income)) + geom_boxplot()
But because you only have an observation for each region and hour when you try to create a boxplot to visualise the regions you can only obtain lines instead of boxplots, which are not very meaningful:
ggplot(data = regions, aes(x = hour, y = hour_income)) + geom_boxplot(aes(fill= location))

plotting x-axes with custom label in R

I've to plot these data:
day temperature
02/01/2012 13:30:00 10
10/01/2012 20:30:00 8
15/01/2012 13:30:00 12
25/01/2012 20:30:00 6
02/02/2012 13:30:00 5
10/02/2012 20:30:00 3
15/02/2012 13:30:00 6
25/02/2012 20:30:00 -1
02/03/2012 13:30:00 4
10/03/2012 20:30:00 -2
15/03/2012 13:30:00 7
25/03/2012 20:30:00 1
in the x-axis I want to label only the month and the day (e.g. Jan 02 ). How can I do this using the command plot() and axis()?

First, you will need to put your date text into a dtae class (e.g. as.POSIXct):
df <- structure(list(day = structure(list(sec = c(0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0), min = c(30L, 30L, 30L, 30L, 30L, 30L, 30L,
30L, 30L, 30L, 30L, 30L), hour = c(13L, 20L, 13L, 20L, 13L, 20L,
13L, 20L, 13L, 20L, 13L, 20L), mday = c(2L, 10L, 15L, 25L, 2L,
10L, 15L, 25L, 2L, 10L, 15L, 25L), mon = c(0L, 0L, 0L, 0L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L), year = c(112L, 112L, 112L, 112L,
112L, 112L, 112L, 112L, 112L, 112L, 112L, 112L), wday = c(1L,
2L, 0L, 3L, 4L, 5L, 3L, 6L, 5L, 6L, 4L, 0L), yday = c(1L, 9L,
14L, 24L, 32L, 40L, 45L, 55L, 61L, 69L, 74L, 84L), isdst = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L)), .Names = c("sec",
"min", "hour", "mday", "mon", "year", "wday", "yday", "isdst"
), class = c("POSIXlt", "POSIXt")), temperature = c(10L, 8L,
12L, 6L, 5L, 3L, 6L, -1L, 4L, -2L, 7L, 1L)), .Names = c("day",
"temperature"), row.names = c(NA, -12L), class = "data.frame")
df
df$day <- as.POSIXct(df$day, format="%d/%m/%Y %H:%M:%S")
Your dates should now plot correctly. Don't apply the x-axis, by using the argument xaxt="n". Afterwards, you can create a sequence of dates where you would like your axis labeled, and apply this with axis.POSIXct:
plot(df$day, df$temperature, t="l", ylab="Temperature", xlab="Date", xaxt="n")
SEQ <- seq(min(df$day), max(df$day), by="months")
axis.POSIXct(SEQ, at=SEQ, side=1, format="%b %Y")
Similarly, to get a daily axis, simply modify the SEQ and axis.POSIXct code accordingly. For example, you may try:
plot(df$day, df$temperature, t="l", ylab="Temperature", xlab="Date", xaxt="n")
SEQ <- seq(min(df$day), max(df$day), by="days")
axis.POSIXct(SEQ, at=SEQ, side=1, format="%b %d")

draw a vertical line based on hour minute on y-axis

x
structure(list(Date = structure(c(15358, 15359, 15362, 15363,
15364, 15365), class = "Date"), EndTime1 = structure(list(sec = c(0,
0, 0, 0, 0, 0), min = c(45L, 25L, 7L, 19L, 5L, 23L), hour = c(5L,
8L, 3L, 4L, 4L, 3L), mday = c(18L, 18L, 18L, 18L, 18L, 18L),
mon = c(0L, 0L, 0L, 0L, 0L, 0L), year = c(113L, 113L, 113L,
113L, 113L, 113L), wday = c(5L, 5L, 5L, 5L, 5L, 5L), yday = c(17L,
17L, 17L, 17L, 17L, 17L), isdst = c(0L, 0L, 0L, 0L, 0L, 0L
)), .Names = c("sec", "min", "hour", "mday", "mon", "year",
"wday", "yday", "isdst"), class = c("POSIXlt", "POSIXt")), EndTime2 = structure(list(
sec = c(0, 0, 0, 0, 0, 0), min = c(45L, 41L, 11L, 27L, 19L,
34L), hour = c(7L, 15L, 5L, 7L, 8L, 5L), mday = c(18L, 18L,
18L, 18L, 18L, 18L), mon = c(0L, 0L, 0L, 0L, 0L, 0L), year = c(113L,
113L, 113L, 113L, 113L, 113L), wday = c(5L, 5L, 5L, 5L, 5L,
5L), yday = c(17L, 17L, 17L, 17L, 17L, 17L), isdst = c(0L,
0L, 0L, 0L, 0L, 0L)), .Names = c("sec", "min", "hour", "mday",
"mon", "year", "wday", "yday", "isdst"), class = c("POSIXlt",
"POSIXt")), EndTime3 = structure(list(sec = c(0, 0, 0, 0, 0,
0), min = c(7L, 59L, 30L, 48L, 46L, 58L), hour = c(8L, 15L, 5L,
7L, 8L, 5L), mday = c(18L, 18L, 18L, 18L, 18L, 18L), mon = c(0L,
0L, 0L, 0L, 0L, 0L), year = c(113L, 113L, 113L, 113L, 113L, 113L
), wday = c(5L, 5L, 5L, 5L, 5L, 5L), yday = c(17L, 17L, 17L,
17L, 17L, 17L), isdst = c(0L, 0L, 0L, 0L, 0L, 0L)), .Names = c("sec",
"min", "hour", "mday", "mon", "year", "wday", "yday", "isdst"
), class = c("POSIXlt", "POSIXt"))), .Names = c("Date", "EndTime1",
"EndTime2", "EndTime3"), row.names = c(NA, 6L), class = "data.frame")
\n
y_limits = as.POSIXct(c(strptime("00:00", "%H:%M"), strptime("23:29", "%H:%M")))
y_breaks = seq(from=strptime("00:00", "%H:%M"),
to=strptime("23:29", "%H:%M"), by="2 hours")
y_labels = format(y_breaks, "%H:%M")
s<-as.POSIXlt("09:00", format="%H:%M")
ggplot(x, aes(Date, EndTime1, group=1, colour="Team1")) + geom_line() + scale_y_datetime(limits=y_limits, breaks=y_breaks, labels=y_labels) + geom_line(aes(Date, EndTime2, colour="Team2")) + geom_line(aes(Date, EndTime3, colour="Team3")) + geom_hline(yintercept=s, colour="red")
I like to draw a geom_line at s but not working. Getting error as:
Error : Invalid intercept type: should be a numeric vector, a function, or a name of a function
Error in if (nrow(layer_data) == 0) return() : argument is of length zero
Any ideas How I can draw a vertical line at a given s?

s<-as.POSIXct(c("09:00"), format="%H:%M")
s<-as.numeric(s)

Resources