R使用dplyr剪切包含2个或更多变量的固定时间间隔

我有一个数据帧

df <- data.frame(time = c("2015-09-07 00:32:19", "2015-09-07 01:02:30", "2015-09-07 01:31:36", "2015-09-07 01:47:45",
"2015-09-07 02:00:17", "2015-09-07 02:07:30", "2015-09-07 03:39:41", "2015-09-07 04:04:21", "2015-09-07 04:04:21", "2015-09-07 04:04:22"), 
inOut = c("IN", "OUT", "IN", "IN", "IN", "IN", "IN", "OUT", "IN", "OUT")) 

> df
                  time inOut
1  2015-09-07 00:32:19    IN
2  2015-09-07 01:02:30   OUT
3  2015-09-07 01:31:36    IN
4  2015-09-07 01:47:45    IN
5  2015-09-07 02:00:17    IN
6  2015-09-07 02:07:30    IN
7  2015-09-07 03:39:41    IN
8  2015-09-07 04:04:21   OUT
9  2015-09-07 04:04:21    IN
10 2015-09-07 04:04:22   OUT
> 

在创建示例数据集时，您将看到一个可以忽略的警告，或者只使用stringsAsFactors=F。 您还可以在过程中的某个时刻重命名列，并用更有用的内容替换Var1

在创建示例数据集时，您将看到一个可以忽略的警告，或者只使用stringsAsFactors=F。

---

您还可以在过程中的某个时刻重命名列，并用更有用的内容替换Var1。

您可以重新调整表的形状以获得所需的格式

library(reshape2)


df2 <- df %>% 
    group_by(inOut, 
             timeCut= cut(as.POSIXct(time), breaks="15 min")) %>%
    summarise(n = n()) %>% 
    dcast(timeCut ~ inOut, value.var = "n")

添加所有间隔

intervals <- data.frame(timeCut = levels(cut(as.POSIXct(df$time), 
                                             breaks="15 mins")))
df3 <- df2 %>%
    mutate(timeCut = as.character(timeCut)) %>%
    merge(intervals, all = TRUE)

如果需要，将NA值替换为0

df3[is.na(df3)]  <- 0

> df3
               timeCut IN OUT
1  2015-09-07 00:32:00  1   0
2  2015-09-07 00:47:00  0   0
3  2015-09-07 01:02:00  0   1
4  2015-09-07 01:17:00  1   0
5  2015-09-07 01:32:00  0   0
6  2015-09-07 01:47:00  2   0
7  2015-09-07 02:02:00  1   0
8  2015-09-07 02:17:00  0   0
9  2015-09-07 02:32:00  0   0
10 2015-09-07 02:47:00  0   0
11 2015-09-07 03:02:00  0   0
12 2015-09-07 03:17:00  0   0
13 2015-09-07 03:32:00  1   0
14 2015-09-07 03:47:00  0   0
15 2015-09-07 04:02:00  1   2

---

重塑2:：dcast函数现在已被tidyr:：spread替换，但我还不习惯它。有关数据准备的更多详细信息，请参阅。

您可以重新调整表的形状以达到所需的格式

library(reshape2)


df2 <- df %>% 
    group_by(inOut, 
             timeCut= cut(as.POSIXct(time), breaks="15 min")) %>%
    summarise(n = n()) %>% 
    dcast(timeCut ~ inOut, value.var = "n")

添加所有间隔

intervals <- data.frame(timeCut = levels(cut(as.POSIXct(df$time), 
                                             breaks="15 mins")))
df3 <- df2 %>%
    mutate(timeCut = as.character(timeCut)) %>%
    merge(intervals, all = TRUE)

如果需要，将NA值替换为0

df3[is.na(df3)]  <- 0

> df3
               timeCut IN OUT
1  2015-09-07 00:32:00  1   0
2  2015-09-07 00:47:00  0   0
3  2015-09-07 01:02:00  0   1
4  2015-09-07 01:17:00  1   0
5  2015-09-07 01:32:00  0   0
6  2015-09-07 01:47:00  2   0
7  2015-09-07 02:02:00  1   0
8  2015-09-07 02:17:00  0   0
9  2015-09-07 02:32:00  0   0
10 2015-09-07 02:47:00  0   0
11 2015-09-07 03:02:00  0   0
12 2015-09-07 03:17:00  0   0
13 2015-09-07 03:32:00  1   0
14 2015-09-07 03:47:00  0   0
15 2015-09-07 04:02:00  1   2

重塑2:：dcast函数现在已被tidyr:：spread替换，但我还不习惯它。有关数据准备的详细信息，请参阅。

另一种使用dplyr和REGRAPE2的解决方案：

另一个使用dplyr和REGRAPE2的解决方案：

---

您的解决方案缺少时间间隔。谢谢Paul4forest，但根据Miha，此sol缺少2015-09-07 00:47:00 0，不管怎样，我现在对Antoniosk、Miha sol和您的提示已经足够清楚了。您的解决方案缺少时间间隔。谢谢Paul4forest，但根据Miha，此sol缺少2015-09-07 00:47:00 0 0，不管怎样，我现在对安东尼奥斯克、米哈·索尔和你的提示已经很清楚了。谢谢你的dplyr+tidyr sol谢谢你的dplyr+tidyr sol谢谢你的dplyr+REPLACE2 sol谢谢你的dplyr+REPLACE2 sol

library(dplyr)
library(reshape2)

my_levels <-
  data_frame(timeCut = levels(cut(as.POSIXct(df$time), breaks="15 min")))

my_df <- 
  df %>%
  mutate(timeCut = cut(as.POSIXct(time), breaks = "15 min")) %>% 
  mutate_each(funs(as.character)) %>% 
  right_join(., my_levels) %>% 
  select(-time) %>% 
  dcast(timeCut ~ inOut, length)

               timeCut IN OUT NA
1  2015-09-07 00:32:00  1   0  0
2  2015-09-07 00:47:00  0   0  1
3  2015-09-07 01:02:00  0   1  0
4  2015-09-07 01:17:00  1   0  0
5  2015-09-07 01:32:00  0   0  1
6  2015-09-07 01:47:00  2   0  0
7  2015-09-07 02:02:00  1   0  0
8  2015-09-07 02:17:00  0   0  1
9  2015-09-07 02:32:00  0   0  1
10 2015-09-07 02:47:00  0   0  1
11 2015-09-07 03:02:00  0   0  1
12 2015-09-07 03:17:00  0   0  1
13 2015-09-07 03:32:00  1   0  0
14 2015-09-07 03:47:00  0   0  1
15 2015-09-07 04:02:00  1   2  0