Question

如果你们都有更高效或更优雅的方式将事件日志转换为时间序列，那就太好了。

并不是那么整齐的中心，但好奇你是否有一个漂亮的整齐方法心灵？我试图利用dplyr :: mutate的滞后函数在值为NA时进行前瞻性观察，但我似乎无法重复滞后。

这是一个简单的例子

library(dplyr)
set.seed(1)
events <- tibble(
  t = runif(10, 0, 100) %>% sort(),
  value = runif(10, 0, 1)
)

events
# A tibble: 10 x 2
           t     value
       <dbl>     <dbl>
 1  6.178627 0.2059746
 2 20.168193 0.1765568
 3 26.550866 0.6870228
 4 37.212390 0.3841037
 5 57.285336 0.7698414
 6 62.911404 0.4976992
 7 66.079779 0.7176185
 8 89.838968 0.9919061
 9 90.820779 0.3800352
10 94.467527 0.7774452

这是一种超级黑客的做法。时间序列事件：

accordian <- function(events_data, freq = 1){
  t_seq = seq(
    from = min(events_data$t)-freq %>% round(0), 
    to = max(events_data$t) + freq, 
    by = freq)
  timeseries = tibble(
    t = t_seq,
    value = NA
  )
  timeseries = bind_rows(
    events_data,
    timeseries
  ) %>%
    arrange(t) 
  for (i in 2:length(timeseries$value)){
    if (is.na(timeseries$value[i])){ timeseries$value[i] = timeseries$value[i-1] }
  }
  timeseries = timeseries %>%
    filter(t %in% t_seq)

  return(timeseries)
}

accordian(events)
# A tibble: 102 x 3
           t     value       type
       <dbl>     <dbl>      <chr>
 1  6.178627 0.2059746 events log
 2 20.168193 0.1765568 events log
 3 26.550866 0.6870228 events log
 4 37.212390 0.3841037 events log
 5 57.285336 0.7698414 events log
 6 62.911404 0.4976992 events log
 7 66.079779 0.7176185 events log
 8 89.838968 0.9919061 events log
 9 90.820779 0.3800352 events log
10 94.467527 0.7774452 events log
# ... with 92 more rows

并根据事件日志明确事件日志和时间序列之间的区别：

library(ggplot2)
bind_rows(
  events %>%
    mutate(type = "events log"),
  accordian(events) %>%
    mutate(type = "time series"),
) %>%
ggplot(
  aes(x = t, y = value, color = type)
) +
  geom_line()

我很想得到你的建议！

Answer 1

这不是您问题的答案，但根据您的评论，我想向您展示我的基础R方法。也许我们可以把它翻译成一个整齐的解决方案：

async_to_sync <- function(async_df) {
  # Creates a synchronous (multivariate) time series from an asynchronous event log.
  # It is assumed the asynchronous log contains no missing values.

  # creates simple time sequence, could be modified to have a different freuency
  time_sequence <- seq(min(async_df$time), max(async_df$time), by = 1)

  # constructing a new empty dataframe:
  sync_df <- data.frame(matrix(ncol = ncol(async_df), nrow = length(time_sequence)))
  colnames(sync_df) <- colnames(async_df)
  sync_df$time <- time_sequence

  # Fill in already known values in the synchronous time series:
  for(i in 1:nrow(async_df)) {
    time_value <- async_df$time[i]
    sync_df[which(sync_df$time == time_value, arr.ind = TRUE), ] <- async_df[i, ] 
  }

  # Filling in the blanks:
  for(i in 1:nrow(sync_df)) {
    if(sync_df[i, ] %>% is.na %>% any) {
      sync_df[i, ] <- sync_df[i - 1, ]
    }
  }

  return(sync_df)
}

在示例上运行：

> set.seed(1234)
> async_df <- data.frame(time = c(2, 6, 7, 14), x1 = LETTERS[1:4], x2 = 1:4, stringsAsFactors = FALSE)
> async_df
  time x1 x2
1    2  A  1
2    6  B  2
3    7  C  3
4   14  D  4
> async_to_sync(async_df = async_df)
   time x1 x2
1     2  A  1
2     2  A  1
3     2  A  1
4     2  A  1
5     6  B  2
6     7  C  3
7     7  C  3
8     7  C  3
9     7  C  3
10    7  C  3
11    7  C  3
12    7  C  3
13   14  D  4

R - 将事件日志（异步日志）转换为时间序列（同步日志）

1 个答案: