在 R 中确定每天的进程数 运行 和开始这些项目的平均天数
Determine the number of process running each day and average days of commencing those projects, in R
我有一个很大的流程数据集（它们的 ID）、开始日期和相应的结束日期。
我想要的分为两部分。首先，每天有多少进程运行。其次，运行 进程的平均天数为 running/commencement。
样本数据集如
> dput(df)
structure(list(Process = c("P001", "P002", "P003", "P004", "P005"
), Start = c("01-01-2020", "02-01-2020", "03-01-2020", "08-01-2020",
"13-01-2020"), End = c("10-01-2020", "09-01-2020", "04-01-2020",
"17-01-2020", "19-01-2020")), class = "data.frame", row.names = c(NA,
-5L))
df
> df
Process Start End
1 P001 01-01-2020 10-01-2020
2 P002 02-01-2020 09-01-2020
3 P003 03-01-2020 04-01-2020
4 P004 08-01-2020 17-01-2020
5 P005 13-01-2020 19-01-2020
第一部分我是这样进行的
library(tidyverse)
df %>% pivot_longer(cols = c(Start, End), names_to = 'event', values_to = 'dates') %>%
mutate(dates = as.Date(dates, format = "%d-%m-%Y")) %>%
mutate(dates = if_else(event == 'End', dates+1, dates)) %>%
arrange(dates, event) %>%
mutate(processes = ifelse(event == 'Start', 1, -1),
processes = cumsum(processes)) %>%
select(-Process, -event) %>%
complete(dates = seq.Date(min(dates), max(dates), by = '1 day')) %>%
fill(processes)
# A tibble: 20 x 2
dates processes
<date> <dbl>
1 2020-01-01 1
2 2020-01-02 2
3 2020-01-03 3
4 2020-01-04 3
5 2020-01-05 2
6 2020-01-06 2
7 2020-01-07 2
8 2020-01-08 3
9 2020-01-09 3
10 2020-01-10 2
11 2020-01-11 1
12 2020-01-12 1
13 2020-01-13 2
14 2020-01-14 2
15 2020-01-15 2
16 2020-01-16 2
17 2020-01-17 2
18 2020-01-18 1
19 2020-01-19 1
20 2020-01-20 0
对于第二部分，所需的输出类似于以下屏幕截图中的列 mean days，并附有解释 -
tidyverse 方法将是首选，请。
这是一种方法：
library(tidyverse)
df %>%
#Convert to date
mutate(across(c(Start, End), lubridate::dmy),
#Create a sequence of dates from start to end
Dates = map2(Start, End, seq, by = 'day')) %>%
#Get data in long format
unnest(Dates) %>%
#Remove columns
select(-Start, -End) %>%
#For each process
group_by(Process) %>%
#Count number of days spent on it
mutate(days_spent = row_number() - 1) %>%
#For each date
group_by(Dates) %>%
#Count number of process running and average days
summarise(process = n(),
mean_days = mean(days_spent))
这个returns:
# Dates process mean_days
# <date> <int> <dbl>
# 1 2020-01-01 1 0
# 2 2020-01-02 2 0.5
# 3 2020-01-03 3 1
# 4 2020-01-04 3 2
# 5 2020-01-05 2 3.5
# 6 2020-01-06 2 4.5
# 7 2020-01-07 2 5.5
# 8 2020-01-08 3 4.33
# 9 2020-01-09 3 5.33
#10 2020-01-10 2 5.5
#11 2020-01-11 1 3
#12 2020-01-12 1 4
#13 2020-01-13 2 2.5
#14 2020-01-14 2 3.5
#15 2020-01-15 2 4.5
#16 2020-01-16 2 5.5
#17 2020-01-17 2 6.5
#18 2020-01-18 1 5
#19 2020-01-19 1 6
我有一个很大的流程数据集（它们的 ID）、开始日期和相应的结束日期。
我想要的分为两部分。首先，每天有多少进程运行。其次，运行 进程的平均天数为 running/commencement。
样本数据集如
> dput(df)
structure(list(Process = c("P001", "P002", "P003", "P004", "P005"
), Start = c("01-01-2020", "02-01-2020", "03-01-2020", "08-01-2020",
"13-01-2020"), End = c("10-01-2020", "09-01-2020", "04-01-2020",
"17-01-2020", "19-01-2020")), class = "data.frame", row.names = c(NA,
-5L))
df
> df
Process Start End
1 P001 01-01-2020 10-01-2020
2 P002 02-01-2020 09-01-2020
3 P003 03-01-2020 04-01-2020
4 P004 08-01-2020 17-01-2020
5 P005 13-01-2020 19-01-2020
第一部分我是这样进行的
library(tidyverse)
df %>% pivot_longer(cols = c(Start, End), names_to = 'event', values_to = 'dates') %>%
mutate(dates = as.Date(dates, format = "%d-%m-%Y")) %>%
mutate(dates = if_else(event == 'End', dates+1, dates)) %>%
arrange(dates, event) %>%
mutate(processes = ifelse(event == 'Start', 1, -1),
processes = cumsum(processes)) %>%
select(-Process, -event) %>%
complete(dates = seq.Date(min(dates), max(dates), by = '1 day')) %>%
fill(processes)
# A tibble: 20 x 2
dates processes
<date> <dbl>
1 2020-01-01 1
2 2020-01-02 2
3 2020-01-03 3
4 2020-01-04 3
5 2020-01-05 2
6 2020-01-06 2
7 2020-01-07 2
8 2020-01-08 3
9 2020-01-09 3
10 2020-01-10 2
11 2020-01-11 1
12 2020-01-12 1
13 2020-01-13 2
14 2020-01-14 2
15 2020-01-15 2
16 2020-01-16 2
17 2020-01-17 2
18 2020-01-18 1
19 2020-01-19 1
20 2020-01-20 0
对于第二部分，所需的输出类似于以下屏幕截图中的列 mean days，并附有解释 -
tidyverse 方法将是首选，请。
这是一种方法：
library(tidyverse)
df %>%
#Convert to date
mutate(across(c(Start, End), lubridate::dmy),
#Create a sequence of dates from start to end
Dates = map2(Start, End, seq, by = 'day')) %>%
#Get data in long format
unnest(Dates) %>%
#Remove columns
select(-Start, -End) %>%
#For each process
group_by(Process) %>%
#Count number of days spent on it
mutate(days_spent = row_number() - 1) %>%
#For each date
group_by(Dates) %>%
#Count number of process running and average days
summarise(process = n(),
mean_days = mean(days_spent))
这个returns:
# Dates process mean_days
# <date> <int> <dbl>
# 1 2020-01-01 1 0
# 2 2020-01-02 2 0.5
# 3 2020-01-03 3 1
# 4 2020-01-04 3 2
# 5 2020-01-05 2 3.5
# 6 2020-01-06 2 4.5
# 7 2020-01-07 2 5.5
# 8 2020-01-08 3 4.33
# 9 2020-01-09 3 5.33
#10 2020-01-10 2 5.5
#11 2020-01-11 1 3
#12 2020-01-12 1 4
#13 2020-01-13 2 2.5
#14 2020-01-14 2 3.5
#15 2020-01-15 2 4.5
#16 2020-01-16 2 5.5
#17 2020-01-17 2 6.5
#18 2020-01-18 1 5
#19 2020-01-19 1 6