Summarise data into monthly counts by year

Question

I'm not used to working with time series data in R, and I'm a bit stuck with this. I have a data frame of event references and the data the event was recorded. The data runs over a period of 7 years and want to summarise it into the number of event per month over the 7 year period and plot that with ggplot2.

I can't seem to get the date conversions to work together so I end up with a count and a date I can feed to ggplot2's scale_x_date() function

Here's an example of the data:

df <- structure(list(Ref = structure(c(127L, 33L, 232L, 392L, 490L, 
242L, 437L, 346L, 443L, 560L, 598L, 568L, 103L, 262L, 463L, 17L, 
114L, 276L, 361L, 422L), .Label = c("01090013", "0109005", "0109006", 
"0109007", "0109009", "0109010", "0109011", "0109012", "0109014", 
"0109016", "0109022", "0110001", "0110004", "0110007", "0110009", 
"0110011", "0111001", "0111002", "0111012", "0111016", "0111017", 
"0112001", "0112003", "0112008", "0112010", "015004", "015006", 
"015008", "015010", "015013", "016002", "016003", "016004", "016005", 
"016006", "016008", "016009", "016010", "016011", "016013", "016014", 
"016016", "017001", "018001", "018004", "018005", "018007", "018008", 
"018009", "020626", "0209024", "0209025", "0209026", "0209027", 
"0209029", "0209031", "0209035", "0209037", "02100020", "0210017", 
"0210018", "0210023", "0210026", "0210030", "0211018", "0211019", 
"0211020", "0211022", "0211024", "0211025", "0211026", "0212018", 
"0212021", "0212025", "0212027", "025018", "025021", "025022", 
"025023", "025024", "025025", "025026", "025030", "026019", "026020", 
"026021", "026023", "026025", "026027", "026030", "026032", "0270010", 
"027010", "027012", "027013", "027014", "027016", "027017", "0309038", 
"0309039", "0309041", "0309046", "0309050", "0309052", "0309053", 
"0310035", "0310037", "0310041", "0310043", "0310044", "0311028", 
"0311032", "0311035", "0311038", "0312031", "0312036", "0312037", 
"0312043", "0312045", "0312047", "0312056", "0312058", "0312059", 
"0312062", "035033", "035034", "035036", "035037", "035038", 
"035040", "035041", "035042", "035043", "035045", "035049", "036036", 
"036038", "036039", "036041", "036042", "036044", "036045", "036046", 
"036047", "036048", "036050", "036051", "037021", "037026", "037029", 
"038026", "038032", "038034", "038035", "038036", "0409056", 
"0409057", "0409062", "0410046", "0410049", "0410050", "0410051", 
"0410054", "0410055", "0410056", "0410057", "0410058", "0410060", 
"0410062", "0410064", "0411047", "0411051", "0411052", "0411055", 
"0412070", "0412074", "0412075", "0412076", "045054", "045056", 
"045058", "045063", "045064", "045065", "045072", "046054", "046055", 
"046058", "046060", "047035", "047036", "047037", "047038", "047041", 
"047042", "047044", "047045", "047046", "048040", "048043", "048044", 
"048045", "048048", "048050", "048051", "0509073", "0509080", 
"0510066", "0510067", "0510082", "0511062", "0511065", "0511068", 
"0511069", "0511072", "0512084", "0512088", "0512089", "0512091", 
"055073", "055075", "055080", "055086", "055089", "055091", "055093", 
"055094", "055095", "056064", "056066", "056067", "056068", "056070", 
"056071", "056073", "056074", "057049", "057052", "057053", "057054", 
"057058", "057059", "057060", "057061", "057063", "057065", "057066", 
"057067", "057068", "057069", "058053", "058055", "058056", "058059", 
"058062", "058064", "0609082", "0609086", "0609088", "0609089", 
"0609090", "0609093", "0609095", "0609096", "0609097", "0609098", 
"0609103", "0610086", "0610089", "0610095", "0610096", "0610098", 
"0611073", "0611074", "0611080", "0611081", "0612109", "0612115", 
"065096", "065099", "065103", "065105", "065106", "065109", "065114", 
"066075", "066076", "066077", "066078", "066081", "066083", "067080", 
"067081", "067084", "068065", "068070", "068074", "0709106", 
"0709108", "0709113", "0709115", "0709116", "0709117", "0709120", 
"0710104", "0710105", "0710107", "0710108", "0710110", "0710115", 
"0710116", "0710117", "0710123", "0711083", "0711084", "0711085", 
"0711086", "0711087", "0711088", "0711092", "0712122", "0712126", 
"0712127", "0712128", "0712129", "075118", "075119", "075123", 
"075124", "075125", "075126", "075127", "075130", "075132", "075133", 
"076084", "076087", "076088", "076090", "076092", "076093", "076094", 
"077103", "077105", "078079", "078080", "078081", "078082", "078085", 
"078086", "0809126", "0809134", "0809137", "0809141", "0809143", 
"0810125", "0810137", "0811099", "0811101", "0811106", "0811108", 
"0811112", "0811113", "0811114", "0812142", "0812145", "0812150", 
"0812152", "0814143", "085139", "085143", "085145", "085148", 
"085149", "085150", "085154", "085156", "085160", "085163", "086098", 
"086099", "086100", "086101", "086102", "086104", "086107", "086108", 
"086109", "086110", "086111", "086112", "086114", "086115", "087106", 
"087107", "087109", "087112", "088094", "088096", "088097", "088098", 
"0909145", "0909155", "0909158", "0910145", "0910146", "0910147", 
"0910149", "0910150", "0910153", "0910154", "0911116", "0911117", 
"0911120", "0911121", "0911122", "0911123", "0911124", "0911130", 
"0911131", "0912161", "0912163", "0912168", "0912171", "0912172", 
"095166", "095167", "095170", "095171", "095172", "095178", "095180", 
"096116", "096117", "096121", "097120", "097124", "097125", "097126", 
"097132", "097133", "097136", "098110", "098115", "098116", "098119", 
"100006825", "100006830", "1009160", "1009161", "1009162", "1009164", 
"1009165", "1009166", "1009169", "1009170", "1009172", "1009173", 
"1009174", "1010160", "1010162", "1010163", "1010164", "1010166", 
"1010168", "1011133-A", "1011134", "1011140", "1011142", "1012179", 
"1012184", "1012185", "1012194", "105185", "105186", "105187", 
"105188", "105189", "105191", "105192", "105196", "105197", "105198", 
"105199", "105201", "105202", "105207", "105208", "105211", "106127", 
"106130", "106131", "107138", "107140", "107143", "107147", "107148", 
"107149", "107153", "107155", "107156", "108122", "108123", "108127", 
"108129", "108130", "108131", "108132", "108134", "108135", "108136", 
"1109175", "1109176", "1109180", "1109182", "1110173", "1110176", 
"1110177", "1110178", "1110185", "1110186", "1111145", "1111150", 
"1111151", "1112196", "1112197", "1112201", "1112202", "1112206", 
"1112208", "1112209", "1112212", "1112218", "1112220", "1112223", 
"1112225", "1112226", "1112227", "115215", "115216", "115217", 
"115218", "115219", "115223", "115225", "115226", "116139", "116143", 
"116144", "116145", "117161", "117162", "117164", "117165", "117168", 
"117175", "117180", "118139", "118140", "118143", "118147", "118148", 
"118150", "118152", "118154", "118157", "118160", "118161", "1209188", 
"1209189", "1209191", "1209193", "1209199", "1210191", "1210193", 
"1211157", "1211158", "1211168", "1211169", "1211170", "1211171", 
"1211173", "1212233", "1212235", "1212240", "125231", "125238", 
"125241", "126147", "126149", "127182", "127183", "127186", "127187", 
"127192", "127194", "128165", "128168", "128169", "128171", "128172", 
"128175", "128176", "128177", "128182", "128183", "128184", "128186", 
"128189", "128193"), class = "factor"), Date = structure(c(12846, 
13154, 13284, 13391, 13434, 13655, 13766, 14067, 14119, 14183, 
14209, 14211, 14322, 14412, 14897, 14960, 15049, 15155, 15201, 
15597), class = "Date")), .Names = c("Ref", "Date"), row.names = c(NA, 
-20L), class = "data.frame")

This is driving me crazy!

Thanks H

Answer 1

I believe you are looking for this:

df <- transform(df, month = format(Date,"%m"), year = format(Date, "%Y"))

counts <- ddply(df,.(month,year),nrow)

Then to plot the date:

# make a new monthly date
counts <- transform(counts, new_date = as.Date(paste(year,month,'01',sep="-")))

# now plot
ggplot(counts,aes(x=new_date,y=V1)) + geom_point() + scale_x_date()

Answer 2

xts package is very handy for time series manipulations.

First I create the xts object :

 library(xts)
 dat.xts <- xts(df$Ref,order.by=as.POSIXct(df$Date))

Then I use apply.monthly to get the count by day, and plot it as xts object

count.month <- apply.monthly(dat.xts,FUN=length)
plot(count.month, type='b')

If you want to use ggplot2, you can transform the result to a data.frame.

as.data.frame(count.month)

Answer 3

Another option:

data$Month <-  format(as.POSIXct(data$Date), "%Y-%m")
by.month.count <- data.frame(with(data, table(Month)))