I have to make groups by months and years and sort data in chronological order. I am using following data and code:
mydf = structure(list(vnum1 = c(0.213462416929903, 0.988030047419118,
-1.18652469981587, -0.869178623205718, 0.912875335795115, -1.98798388768447,
-0.304573289627417, 0.559868758619623, -0.663557878516269, -0.558487562052716,
0.437910610434683, 0.294626820421212, 1.22382550331396, 1.33307181022467,
-0.111632843418732, 0.012593612409791, 0.202491597986104, -0.0926340952847484,
0.838878748813974, 0.397235027161488, -0.24188970321148, 0.941276507145062,
0.209022985751647, 1.12583170538807, 1.32872138538229, 0.490518883526501,
-1.5848233402832, 0.21465692222817, 0.32862179851896, 1.25692197516853,
-0.101168594652985, 0.151940891762939, -1.56082855559097, 0.81784767965823,
0.400190430382005, -1.53216256468244, -1.28940381159733, -0.795006205948021,
1.06739871977495, 0.529556847460609, 0.39886466332703, 0.392956914201864,
-1.87574207207718, 0.394469467803633, 1.78815629799651, 1.64468036754424,
-1.5042078341332, 0.963769152123962, -0.22245472921696, 0.0439610905616637
), vmonthnum = c(12L, 7L, 3L, 9L, 3L, 9L, 9L, 5L, 7L, 12L, 5L,
8L, 12L, 6L, 3L, 1L, 3L, 8L, 7L, 3L, 6L, 8L, 7L, 4L, 4L, 8L,
10L, 1L, 11L, 9L, 7L, 6L, 10L, 8L, 9L, 8L, 3L, 9L, 1L, 6L, 12L,
6L, 2L, 2L, 7L, 1L, 6L, 8L, 3L, 12L), vmonth = c("Dec", "Jul",
"Mar", "Sep", "Mar", "Sep", "Sep", "May", "Jul", "Dec", "May",
"Aug", "Dec", "Jun", "Mar", "Jan", "Mar", "Aug", "Jul", "Mar",
"Jun", "Aug", "Jul", "Apr", "Apr", "Aug", "Oct", "Jan", "Nov",
"Sep", "Jul", "Jun", "Oct", "Aug", "Sep", "Aug", "Mar", "Sep",
"Jan", "Jun", "Dec", "Jun", "Feb", "Feb", "Jul", "Jan", "Jun",
"Aug", "Mar", "Dec"), vyear = c(2013L, 2014L, 2014L, 2010L, 2011L,
2012L, 2012L, 2011L, 2014L, 2011L, 2011L, 2010L, 2011L, 2014L,
2010L, 2009L, 2010L, 2012L, 2010L, 2009L, 2010L, 2011L, 2013L,
2013L, 2011L, 2013L, 2012L, 2011L, 2010L, 2010L, 2011L, 2014L,
2010L, 2014L, 2013L, 2009L, 2012L, 2011L, 2014L, 2013L, 2013L,
2009L, 2009L, 2010L, 2014L, 2011L, 2014L, 2010L, 2012L, 2014L
)), .Names = c("vnum1", "vmonthnum", "vmonth", "vyear"), row.names = c(NA,
-50L), class = "data.frame")
>
head(mydf)
vnum1 vmonthnum vmonth vyear
1 0.2134624 12 Dec 2013
2 0.9880300 7 Jul 2014
3 -1.1865247 3 Mar 2014
4 -0.8691786 9 Sep 2010
5 0.9128753 3 Mar 2011
6 -1.9879839 9 Sep 2012
outdf = with(mydf, aggregate(vnum1~paste(vmonthnum,vyear,sep="_"),FUN=mean))
names(outdf)=c("grp", "grp_mean")
head(outdf)
grp grp_mean
1 10_2010 -1.56082856
2 10_2012 -1.58482334
3 11_2010 0.32862180
4 1_2009 0.01259361
5 1_2011 0.92966864
6 1_2014 1.06739872
>
outdf
grp grp_mean
1 10_2010 -1.560828556
2 10_2012 -1.584823340
3 11_2010 0.328621799
4 1_2009 0.012593612
5 1_2011 0.929668645
6 1_2014 1.067398720
7 12_2011 0.332668971
8 12_2013 0.306163540
9 12_2014 0.043961091
10 2_2009 -1.875742072
11 2_2010 0.394469468
12 3_2009 0.397235027
13 3_2010 0.045429377
14 3_2011 0.912875336
15 3_2012 -0.755929270
16 3_2014 -1.186524700
17 4_2011 1.328721385
18 4_2013 1.125831705
19 5_2011 0.498889685
20 6_2009 0.392956914
21 6_2010 -0.241889703
22 6_2013 0.529556847
23 6_2014 -0.006398377
24 7_2010 0.838878749
25 7_2011 -0.101168595
26 7_2013 0.209022986
27 7_2014 0.704209489
28 8_2009 -1.532162565
29 8_2010 0.629197986
30 8_2011 0.941276507
31 8_2012 -0.092634095
32 8_2013 0.490518884
33 8_2014 0.817847680
34 9_2010 0.193871676
35 9_2011 -0.795006206
36 9_2012 -1.146278589
37 9_2013 0.400190430
>
How can I sort outdf on grp column so that it comes in chronological order? I can use 'Jan', 'Feb' etc (vmonth) for this. This is needed for plotting means (on y-axis) with time on x-axis. I tried to see solutions on this page but there the exact date was available: Sorting an data frame based on month-year time format
Thanks for your help.
You could also use zoo package as.yearmon
library(zoo)
mydf$grp <- with(mydf, as.yearmon(paste(vmonth, vyear)))
outdf <- with(mydf, aggregate(vnum1 ~ grp, FUN = mean))
head(outdf)
# grp vnum1
# 1 Jan 2009 0.01259361
# 2 Feb 2009 -1.87574207
# 3 Mar 2009 0.39723503
# 4 Jun 2009 0.39295691
# 5 Aug 2009 -1.53216256
# 6 Feb 2010 0.39446947
If you want to scale the solution, use data.table:
data.table is an evolved version of data.frame, and works much faster for grouping.
library(data.table) # Load package
mydt <- data.table(mydf) # Convert to data.table
setkey(mydt,vyear,vmonthnum) # Set the key, order is important
mydt[,mean(vnum1), by=key(mydt)] # Do the computation
Hope this helps.
A sortable year_month key could be obtained from these data using:
> sprintf("%4d_%02d",mydf$vyear,mydf$vmonthnum)
[1] "2013_12" "2014_07" "2014_03" "2010_09" "2011_03" "2012_09" "2012_09"
[8] "2011_05" "2014_07" "2011_12" "2011_05" "2010_08" "2011_12" "2014_06"
[15] "2010_03" "2009_01" "2010_03" "2012_08" "2010_07" "2009_03" "2010_06"
[22] "2011_08" "2013_07" "2013_04" "2011_04" "2013_08" "2012_10" "2011_01"
[29] "2010_11" "2010_09" "2011_07" "2014_06" "2010_10" "2014_08" "2013_09"
[36] "2009_08" "2012_03" "2011_09" "2014_01" "2013_06" "2013_12" "2009_06"
[43] "2009_02" "2010_02" "2014_07" "2011_01" "2014_06" "2010_08" "2012_03"
[50] "2014_12"
>
... or:
> yrVal <- mydf$vyear + mydf$vmonthnum/12
> yrVal
[1] 2014.000 2014.583 2014.250 2010.750 2011.250 2012.750 2012.750 2011.417
[9] 2014.583 2012.000 2011.417 2010.667 2012.000 2014.500 2010.250 2009.083
[17] 2010.250 2012.667 2010.583 2009.250 2010.500 2011.667 2013.583 2013.333
[25] 2011.333 2013.667 2012.833 2011.083 2010.917 2010.750 2011.583 2014.500
[33] 2010.833 2014.667 2013.750 2009.667 2012.250 2011.750 2014.083 2013.500
[41] 2014.000 2009.500 2009.167 2010.167 2014.583 2011.083 2014.500 2010.667
[49] 2012.250 2015.000
The second version has the advantage that it can be used as the value on the x axis of a graph without even sorting the data first.
Related
I have a dataset with multiple rows per ID like this
ID From To State
1 2004 2005 MD
1 2005 2005 MD
1 2005 2012 DC
1 2012 2015 DC
1 2015 2020 DC
1 2012 2013 MD
1 2013 2016 MD
1 2016 2019 MD
1 2019 2020 MD
2 2003 2004 OR
2 2004 2008 OR
2 2008 2013 AZ
2 2013 2015 AZ
My goal is to collapse the multiple From and To columns to create a smooth timeline like
ID From To State
1 2004 2005 MD
1 2005 2020 DC
1 2012 2020 MD
2 2003 2008 OR
2 2008 2015 AZ
Not sure how to accomplish this. An help is much appreciated. Thanks.
Group by 'ID', 'State' and the run-length-id of 'State', get the first of 'From' and last of 'To'
library(dplyr)
library(data.table)
df1 %>%
group_by(ID, State, grp = rleid(State)) %>%
summarise(From = first(From), To = last(To), .groups = 'drop') %>%
select(-grp)
-output
# A tibble: 5 × 4
ID State From To
<int> <chr> <int> <int>
1 1 DC 2005 2020
2 1 MD 2004 2005
3 1 MD 2012 2020
4 2 AZ 2008 2015
5 2 OR 2003 2008
data
df1 <- structure(list(ID = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L), From = c(2004L, 2005L, 2005L, 2012L, 2015L, 2012L,
2013L, 2016L, 2019L, 2003L, 2004L, 2008L, 2013L), To = c(2005L,
2005L, 2012L, 2015L, 2020L, 2013L, 2016L, 2019L, 2020L, 2004L,
2008L, 2013L, 2015L), State = c("MD", "MD", "DC", "DC", "DC",
"MD", "MD", "MD", "MD", "OR", "OR", "AZ", "AZ")),
class = "data.frame", row.names = c(NA,
-13L))
I am running analysis in Bike Sharing (kaggle) dataset. Heres is a sample:
Head
yr mnth Ano cnt
<int> <int> <chr> <int>
1 0 1 2011 985
2 0 1 2011 801
3 0 1 2011 1349
4 0 1 2011 1562
5 0 1 2011 1600
Tail
yr mnth Ano cnt
<int> <int> <chr> <int>
1 1 12 2012 2114
2 1 12 2012 3095
3 1 12 2012 1341
4 1 12 2012 1796
5 1 12 2012 2729
Where "cnt" means the number of bikes for each day. Every line is a day from 01/01/2011 to 12/12/2012
My goal was to analyse the cnt for each month from both 2011 and 2012; However, I keep getting this weird output:
my code:
k<- bike_new %>%
ggplot(aes(x=mnth,y=cnt))+ geom_line();k
What am I doing wrong here?
As mentioned by the sage advice from #AllanCameron add the group element as a factor, and as you have two years, you would need a color. Here the code using simulated data:
library(ggplot2)
library(dplyr)
#Code
bike_new %>%
ggplot(aes(x=factor(mnth),y=cnt,group=factor(Ano),color=factor(Ano)))+
geom_line()+
xlab('month')+
labs(color='Ano')
Output:
Some data used:
#Data
bike_new <- structure(list(yr = c(0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L, 1L,
0L, 0L, 0L, 0L, 0L), mnth = c(1, 1, 1, 1, 1, 12, 12, 12, 12,
12, 2, 2, 2, 2, 2), Ano = c(2011L, 2011L, 2011L, 2011L, 2011L,
2012L, 2012L, 2012L, 2012L, 2012L, 2011L, 2011L, 2011L, 2011L,
2011L), cnt = c(985, 801, 1349, 1562, 1600, 2114, 3095, 1341,
1796, 2729, 1085, 901, 1449, 1662, 1700)), row.names = c(NA,
-15L), class = "data.frame")
If you want to see only one line per year, a strategy could be that explained by #Phil using other variable as day. Or you can aggregate values in next form:
#Code 2
bike_new %>%
group_by(Ano,mnth) %>%
summarise(cnt=sum(cnt,na.rm=T)) %>%
ggplot(aes(x=factor(mnth),y=cnt,group=factor(Ano),color=factor(Ano)))+
geom_line()+
geom_point()+
xlab('month')+
labs(color='Ano')
Output:
As you are analyzing number of bikes.
I have a sequence that happens over a very long period of time. I tried 8 different algorithms to classify my sequences (OM, CHi2,...). Time goes from 1 to 123. I have 110 individual and 8 events.
My results are not as expected. First, it's very difficult to read. Second, a category contains too many representatives sequence (group3). Third, the number of sequence per group is really unbalanced.
It may comes from the fact that my time variable has a range of 123. I searched for articles that had an issue with a too long time range. I read in Sabherwal and Robey (1993) and in Shi and Prescott (2011) that you can standardize "each sequence by dividing the number of transformations required by the length of the longer sequence". How can I do that in R?
Please find underneath a description of my data:
library(TraMineRextras)
head(seq.tse.data)
seq.tse.data <- structure(list(
ID = c(1L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L),
Year = c(2008L, 2010L, 2012L, 2007L, 2009L, 2010L, 2012L,
2013L, 1996L, 1997L, 1999L, 2003L, 2006L, 2008L,
2012L, 2007L, 2007L, 2008L, 2003L, 2007L, 2007L,
2009L, 2009L, 2011L, 2014L, 2016L, 2006L, 2009L,
2011L, 2013L, 2013L, 2015L, 2015L, 2016L),
Event = c(5L, 4L, 5L, 3L, 1L, 5L, 5L, 5L, 3L,3L,3L,3L,3L,5L, 1L, 5L,
5L,5L,4L,5L, 5L, 5L, 5L, 5L, 5L,5L,5L,5L, 4L, 4L, 1L, 4L, 1L,5L)),
class = "data.frame", row.names = c(NA, -34L)
)
seq.sts <- TSE_to_STS(seq.tse.data,
id = 1, timestamp = 2, event = 3,
stm =NULL, tmin = 1935, tmax = 2018,
firstState = "None")
seq.SPS <- seqformat(seq.sts, 1:84, from = "STS", to = "SPS")
seq.obj <- seqdef(seq.SPS)
> head(seq.tse.data)
ID Year Event
1 1 2008 5
2 2 2010 4
3 2 2012 5
4 3 2007 3
5 3 2009 1
6 3 2010 5
> head(seq.obj)
Sequence
[1] (None,74)-(5,10)-1
[2] (None,76)-(4,2)-(5.4,6)-2
[3] (None,73)-(3,2)-(3.1,1)-(5.3.1,8)-3
[4] (None,62)-(3,12)-(5.3,4)-(5.3.1,6)-3
[5] (None,73)-(5,11)-1
[6] (None,69)-(4,4)-(5.4,11)-2
> head(alphabet(seq.obj),10)
[1] "(1,1)" "(1,10)" "(1,11)" "(1,12)" "(1,14)" "(1,19)" "(1,2)" "(1,21)" "(1,25)" "(1,3)"
...
[145] "(5.4.3.1,5)" "(5.4.3.1,6)" "(5.4.3.1,7)" "(5.4.3.1,8)" "(5.4.3.1.2,9)" "(None,1)" "(None,11)" "(None,20)"
[153] "(None,26)" "(None,30)" "(None,38)" "(None,41)" "(None,42)" "(None,44)" "(None,45)" "(None,49)"
[161] "(None,51)" "(None,53)" "(None,55)" "(None,57)" "(None,58)" "(None,59)" "(None,60)" "(None,61)"
[169] "(None,62)" "(None,64)" "(None,65)" "(None,66)" "(None,67)" "(None,68)" "(None,69)" "(None,7)"
[177] "(None,70)" "(None,71)" "(None,72)" "(None,73)" "(None,74)" "(None,75)" "(None,76)" "(None,77)"
[185] "(None,78)" "(None,79)"
Thanks in advance,
Antonin
I guess that your question is about normalizing the dissimilarities between sequences. E.g., Sabherwal and Robey (1993, p 557) refer to the distance standardization proposed by Abbott & Hyrcac (1990) and do not consider at all the standardization of a sequence. Anyway, I cannot figure out what the standardization of a sequence could be.
The seqdist function of TraMineR has a norm argument that can be used to normalize some of the distance measures proposed. Here is an excerpt from the seqdist help page:
Distances can optionally be normalized by means of the norm argument.
If set to "auto", Elzinga's normalization (similarity divided by
geometrical mean of the two sequence lengths) is applied to "LCS",
"LCP" and "RLCP" distances, while Abbott's normalization (distance
divided by length of the longer sequence) is used for "OM", "HAM" and
"DHD". Elzinga's method can be forced with "gmean" and Abbott's rule
with "maxlength". With "maxdist" the distance is normalized by its
maximal possible value. For more details, see Gabadinho et al. (2009,
2011). Finally, "YujianBo" is the normalization proposed by Yujian and
Bo (2007) that preserves the triangle inequality.
Let me warn you that while normalization makes distances between two short sequences (say of length 10) more comparable with distances between two long sequences (say of length 100), it does not solve the issue of comparing sequences of different lengths.
You find a detailed discussion on the normalization of distance and similarity in sequence analysis in Elzinga & Studer (2016).
First, a reproducible example. I am using data.table because I am dealing with around 20 million rows -
> require(data.table)
> x <- structure(list(DoM = c(2011241L, 2015359L, 2016352L, 2015360L,
2015287L, 2014038L, 2017066L, 2012227L, 2015041L, 2015295L),
Year = c(2011L, 2015L, 2016L, 2015L, 2015L, 2014L, 2017L,
2012L, 2015L, 2015L), Month = c(8L, 12L, 12L, 12L, 10L, 2L,
3L, 8L, 2L, 10L)), .Names = c("DoM", "Year", "Month"), row.names = c(NA,
-10L), class = c("data.table", "data.frame"))
> x
DoM Year Month
1: 2011241 2011 8
2: 2015359 2015 12
3: 2016352 2016 12
4: 2015360 2015 12
5: 2015287 2015 10
6: 2014038 2014 2
7: 2017066 2017 3
8: 2012227 2012 8
9: 2015041 2015 2
10: 2015295 2015 10
I need to extract the date from the DoM column, which contains the day in a Julian like format. Each element of the DoM column is of the form yyyyddd, where ddd is the day of the year yyyy (and hence 1 <= ddd <= 366).
E.g. The first date would be 2011-08-29 because it corresponds to the 241st day of 2011
I currently am not satisfied with what I have, which is -
x[, Date:=as.Date((DoM-1000*Year)-1, origin=paste(Year,1,1,sep='-'))]
I suspect the paste is inefficient and was looking for any alternatives that might be better.
This is possible with basic formatting. See ?strptime:
as.Date(as.character(x$DoM), format="%Y%j")
# or as #Frank suggests, for integer dates in data.table:
as.IDate(as.character(x$DoM), format="%Y%j")
# [1] "2011-08-29" "2015-12-25" "2016-12-17" "2015-12-26" "2015-10-14"
# [6] "2014-02-07" "2017-03-07" "2012-08-14" "2015-02-10" "2015-10-22"
This is the next step from a question I asked earlier. I've got two data frames: one focused on birth data, and one focused on winter weather events. The aim of my project is to discover whether there exists a simple correlation between extreme winter weather events (i.e. winter storms) and a spike in births nine months later (due to people getting stuck in doors during the storms).
There are several areas with which I'm struggling:
I need to factor out less extreme winter weather events from combined.weather.birth$EVENT_TYPE. The factors currently included are "Frost/Freeze", "Hail", "Heavy Snow", "Ice Storm", "Winter Storm", "Winter Weather", and "Blizzard". Of these, I wish to exclude frost/freeze and hail.
I'm having difficulty running the cff() function on this data. As described above, I want to discover and analyze potential correlations between these data sets. I'm only comparing data in Massachusetts from years 2007-2011.
Here is what I've tried so far:
correlation1 <- ccf(birth.data$DATE, combined.weather.birth$DATE, lag.max = NULL,
type="correlation", plot=TRUE)
correlation2 <- ccf(birth.data$DATE, combined.weather.birth$DATE + combined.weather$EVENT_TYPE,
lag.max = NULL, type="correlation", plot=TRUE)
I need to offset this data by nine months, to account for pregnancy after the winter weather events.
Here is some information on the data I'm working with:
str(combined.weather.birth) <-
'data.frame': 966 obs. of 8 variables:
$ EVENT_ID : int 9620 9619 9623 5391 13835 13845 13844 13847 13846 13836 ...
$ STATE : Factor w/ 1 level "MASSACHUSETTS": 1 1 1 1 1 1 1 1 1 1 ...
$ YEAR : int 2007 2007 2007 2007 2007 2007 2007 2007 2007 2007 ...
$ MONTH_NAME : Factor w/ 12 levels "April","August",..: 5 5 5 5 4 4 4 4 4 4 ...
$ EVENT_TYPE : Factor w/ 7 levels "Frost/Freeze",..: 6 6 4 4 5 5 5 5 5 5 ...
$ INJURIES_DIRECT: int 0 0 0 1 0 0 0 0 0 0 ...
$ DEATHS_DIRECT : int 0 0 0 0 0 0 0 0 0 0 ...
$ DATE : POSIXct, format: "2007-01-01" "2007-01-01" "2007-01-01" "2007-01-01" ...
str(birth.data) <-
'data.frame': 60 obs. of 4 variables:
$ YEAR : int 2007 2007 2007 2007 2007 2007 2007 2007 2007 2007 ...
$ MONTH : Factor w/ 12 levels "April","August",..: 5 4 8 1 9 7 6 2 12 11 ...
$ BIRTH_TOTAL: num 6250 5833 6570 6227 6858 ...
$ DATE : POSIXct, format: "2007-01-01" "2007-02-01" "2007-03-01" "2007-04-01" ..
EDIT: I should add that I'm not married to using cff() here. If there is a better function for finding the specified correlation, I am open to learning about it. I've read a bit about cor(), but that doesn't seem appropriate here since it's designed to only work with matrices.
EDIT 2: adding dput() data.
dput(birth.data)
structure(list(YEAR = c(2007L, 2007L, 2007L, 2007L, 2007L, 2007L,
2007L, 2007L, 2007L, 2007L, 2007L, 2007L, 2008L, 2008L, 2008L,
2008L, 2008L, 2008L, 2008L, 2008L, 2008L, 2008L, 2008L, 2008L,
2009L, 2009L, 2009L, 2009L, 2009L, 2009L, 2009L, 2009L, 2009L,
2009L, 2009L, 2009L, 2010L, 2010L, 2010L, 2010L, 2010L, 2010L,
2010L, 2010L, 2010L, 2010L, 2010L, 2010L, 2011L, 2011L, 2011L,
2011L, 2011L, 2011L, 2011L, 2011L, 2011L, 2011L, 2011L, 2011L
), MONTH = structure(c(5L, 4L, 8L, 1L, 9L, 7L, 6L, 2L, 12L, 11L,
10L, 3L, 5L, 4L, 8L, 1L, 9L, 7L, 6L, 2L, 12L, 11L, 10L, 3L, 5L,
4L, 8L, 1L, 9L, 7L, 6L, 2L, 12L, 11L, 10L, 3L, 5L, 4L, 8L, 1L,
9L, 7L, 6L, 2L, 12L, 11L, 10L, 3L, 5L, 4L, 8L, 1L, 9L, 7L, 6L,
2L, 12L, 11L, 10L, 3L), .Label = c("April", "August", "December",
"February", "January", "July", "June", "March", "May", "November",
"October", "September"), class = "factor"), BIRTH_TOTAL = c(6250,
5833, 6570, 6227, 6858, 6735, 6933, 7291, 6385, 6466, 6198, 6221,
6341, 6051, 6444, 6396, 6781, 6583, 6820, 6803, 6531, 6510, 5627,
6135, 5976, 5515, 6208, 6261, 6520, 6509, 6834, 6616, 6489, 6318,
5730, 6040, 5667, 5459, 6162, 6212, 6221, 6194, 6469, 6380, 6342,
5981, 5853, 5925, 5979, 5414, 6070, 6085, 6242, 6438, 6506, 6459,
6260, 6158, 5754, 5801), DATE = structure(c(1167609600, 1170288000,
1172707200, 1175385600, 1177977600, 1180656000, 1183248000, 1185926400,
1188604800, 1191196800, 1193875200, 1196467200, 1199145600, 1201824000,
1204329600, 1207008000, 1209600000, 1212278400, 1214870400, 1217548800,
1220227200, 1222819200, 1225497600, 1228089600, 1230768000, 1233446400,
1235865600, 1238544000, 1241136000, 1243814400, 1246406400, 1249084800,
1251763200, 1254355200, 1257033600, 1259625600, 1262304000, 1264982400,
1267401600, 1270080000, 1272672000, 1275350400, 1277942400, 1280620800,
1283299200, 1285891200, 1288569600, 1291161600, 1293840000, 1296518400,
1298937600, 1301616000, 1304208000, 1306886400, 1309478400, 1312156800,
1314835200, 1317427200, 1320105600, 1322697600), tzone = "UTC", class = c("POSIXct",
"POSIXt"))), .Names = c("YEAR", "MONTH", "BIRTH_TOTAL", "DATE"
), row.names = c(NA, -60L), class = "data.frame")