在 R 中绘制事件的累积图

Question

I have a list of events and their times. I'm able to plot a histogram of them using hist , but I don't know how to make a cumulative plot of them.

Here's the kind of data I'm starting with. (Assume it's already in POSIXct format)

> events$time

 [1] 2015-10-05 16:58:41.986797 2015-10-05 16:59:23.389583
 [3] 2015-10-05 16:59:44.99402  2015-10-05 16:59:53.225178
 [5] 2015-10-05 16:59:59.594524 2015-10-05 17:00:05.555564
 [7] 2015-10-05 17:00:44.173783 2015-10-05 17:00:46.289552
 [9] 2015-10-05 17:00:56.772485 2015-10-05 17:01:18.937458
[11] 2015-10-05 17:02:04.661378

and so on for ~8000 values

For instance, on my histogram, I have something like:

2015-10-05 4:00: 20 events
2015-10-05 4:15: 30 events
2015-10-05 4:30: 11 events

I want to get a tally like:

2015-10-05 4:00: 20 events
2015-10-05 4:15: 50 events
2015-10-05 4:30: 61 events

How do I do that?

Answer 1

A possible solution:

library(lubridate)

# example time data
time = c(
  "2015-10-05 15:44:41.986797", "2015-10-05 15:59:23.389583", "2015-10-05 16:59:44.99402",
  "2015-10-05 16:59:44.99402", "2015-10-05 16:59:44.99402", "2015-10-05 16:59:44.99402",
  "2015-10-05 17:59:59.594524", "2015-10-05 17:59:59.594524", "2015-10-05 18:00:05.555564"
)

# transform time strings to POSIXct objects for count
time <- ymd_hms(time)

# count by second
event <- data.frame(table(time))

# transform time factors to POSIXct objects for df
event$time <- ymd_hms(event$time)

# find start and end time for 15min sequence
start <- round(min(event$time), "mins")
if (min(event$time) < start) {
  minute(start) <- minute(start) - 1
}
while (minute(start) %% 15 != 0) {
  minute(start) <- minute(start) - 1
}

end <- round(max(event$time), "mins")
if (max(event$time) > end) {
  minute(end) <- minute(end) + 1
}
while (minute(end) %% 15 != 0) {
  minute(end) <- minute(end) + 1
}

# create sequence and result data.frame
ft.seq <- seq(start, end, "15 mins")

ft.event <- data.frame(
  start = ft.seq[1:(length(ft.seq)-1)],
  end = ft.seq[2:(length(ft.seq))],
  sum = 0
)

# ugly, nested loop to attribute values to 15min time slices
for (p1 in 1:nrow(ft.event)) {
  for (p2 in 1:nrow(event)) {
    if (event$time[p2] > ft.event$start[p1] && 
        event$time[p2] < ft.event$end[p1]) {
      ft.event$sum[p1] <- ft.event$sum[p1] + event$Freq[p2]
    }
  }
}

# cumsum
ft.event$cumsum <- cumsum(ft.event$sum)

# example plot
library(ggplot2)

ggplot(ft.event) +
  geom_line(aes(x = end, y = cumsum))

Answer 2

This is an old post, but the given answer is very long.

Use hist() (as OP did) and then just use cumsum() on the resulting object.

Careful about the start and end times in the hist object

library(tidyverse)
library(lubridate)

# example time data
time = c(
  "2015-10-05 15:44:41.986797", "2015-10-05 15:59:23.389583", "2015-10-05 16:59:44.99402",
  "2015-10-05 16:59:44.99402", "2015-10-05 16:59:44.99402", "2015-10-05 16:59:44.99402",
  "2015-10-05 17:59:59.594524", "2015-10-05 17:59:59.594524", "2015-10-05 18:00:05.555564"
)

# transform time strings to POSIXct objects for count
time <- ymd_hms(time)

#Get start and end times
start_time=min(time) %>% floor_date("15 minutes") 
end_time=max(time) %>% ceiling_date("15 minutes") 

start_time
end_time

#get breaks for histogram
breaks=seq(start_time,end_time, by = as.difftime(minutes(15)))

#Create histogram
event_hist=hist(time,breaks, freq=T, plot=F)

#Organize results, calculate cumsum, all in a df
events_df=data.frame(start=as_datetime(event_hist$breaks[1:length(event_hist$breaks)-1], origin="1970-01-01 00:00:00"),  
                 end=as_datetime(event_hist$breaks[2:length(event_hist$breaks)], origin="1970-01-01 00:00:00"),
                 count=event_hist$counts, 
                 cumsum=cumsum(event_hist$counts))

## Now graph
library(ggplot2)

ggplot(events_df) +
  geom_line(aes(x = end, y = cumsum))