根据 joint/left 日期创建数据集 - R
create dataset according to joint/left dates - R
我有以下数据集,其中包含有关员工加入和离开组织的信息:
dataset1 <- read.table(
text = "
Employee Organisation Joint_date Left_date
G223 A123 1993-05-15 2019-05-01
G223 A123 2020-04-11 NA
G233 A123 2018-02-20 NA
G234 A123 2015-09-04 NA
G111 A333 1980-10-03 2019-09-27
G122 A333 2000-11-16 NA
G177 A333 2005-01-19 NA
G330 A333 2002-12-24 NA
G556 A333 2018-05-01 2019-03-04
G555 A445 2015-11-18 NA
G556 A445 2005-09-01 2018-03-04
G557 A445 1989-04-05 NA",
header = TRUE)
dataset1$Employee <- as.factor(dataset1$Employee)
dataset1$Organisation <- as.factor(dataset1$Organisation)
dataset1$Joint_date <- as.Date(dataset1$Joint_date, format="%Y-%m-%d")
dataset1$Left_date <- as.Date(dataset1$Left_date, format="%Y-%m-%d")
我创建了从 2018-01-31 到 2021-06-30 的数据集 2(每月数据集):
dataset2_dates=c("2018-01-31","2018-02-28","2018-03-31","2018-04-30","2018-05-31","2018-06-30","2018-07-31","2018-08-31","2018-09-30","2018-10-31","2018-11-30","2018-12-31","2019-01-31","2019-02-28","2019-03-31","2019-04-30","2019-05-31","2019-06-30","2019-07-31","2019-08-31","2019-09-30","2019-10-31","2019-11-30","2019-12-31","2020-01-31","2020-02-29","2020-03-31","2020-04-30","2020-05-31","2020-06-30","2020-07-31","2020-08-31","2020-09-30","2020-10-31","2020-11-30","2020-12-31","2021-01-31","2021-02-28","2021-03-31","2021-04-30","2021-05-31","2021-06-30")
# add dates
dataset2 <- expand.grid(Organisation = unique(dataset1$Organisation),
Month = dataset2_dates)
## sort
dataset2 <- dataset2[order(dataset2$Organisation, dataset2$Month),]
## reset id
rownames(dataset2) <- NULL
dataset2$Organisation <- as.factor(dataset2$Organisation)
dataset2$Month <- as.Date(dataset2$Month, format="%Y-%m-%d")
我想以下面的方式结束 dataset3
:
Organisation | Month | Nr_employees
A123 | 2018-01-31 | 2
A123 | 2018-02-28 | 3
A123 | 2018-03-31 | 3
A123 | 2018-04-30 | 3
A123 | 2018-05-31 | 3
A123 | 2018-06-30 | 3
A123 | 2018-07-31 | 3
A123 | 2018-08-31 | 3
A123 | 2018-09-30 | 3
A123 | 2018-10-31 | 3
A123 | 2018-11-30 | 3
A123 | 2018-12-31 | 3
A123 | 2019-01-31 | 3
A123 | 2019-02-28 | 3
A123 | 2019-03-31 | 3
A123 | 2019-04-30 | 3
A123 | 2019-05-31 | 3
A123 | 2019-06-30 | 2
A123 | 2019-07-31 | 2
A123 | 2019-08-31 | 2
A123 | 2019-09-30 | 2
A123 | 2019-10-31 | 2
A123 | 2019-11-30 | 2
A123 | 2019-12-31 | 2
A123 | 2020-01-31 | 2
A123 | 2020-02-29 | 2
A123 | 2020-03-31 | 2
A123 | 2020-04-30 | 3
A123 | 2020-05-31 | 3
A123 | 2020-06-30 | 3
A123 | 2020-07-31 | 3
A123 | 2020-08-31 | 3
A123 | 2020-09-30 | 3
A123 | 2020-10-31 | 3
A123 | 2020-11-30 | 3
A123 | 2020-12-31 | 3
A123 | 2021-01-31 | 3
A123 | 2021-02-28 | 3
A123 | 2021-03-31 | 3
A123 | 2021-04-30 | 3
A123 | 2021-05-31 | 3
A123 | 2021-06-30 | 3
.....
注意:如果员工在当月的最后一天加入或在当月的第一天离开,仍然视为该员工整个月都在。
和 dataset4
总结了 2018-01-31 到 2021-06-30 的数据:
Organisation | Average Nr_employees | Nr_employees joined | Nr_employess left | Nr_employess stayed the whole time
A123 | 115/42 = 2.7 | 2 | 1 | 1
....
关于如何生成 dataset3
和 dataset4
有什么想法吗?
我相信这行得通。我的方法是将数据重塑为更长的格式,然后将每个 Joint_date 行计为添加 +1 名员工,否则我们将查看离职和 -1.
中间位将每个日期转换为月底,如果离开则转换为下个月的月底(因为您注意到我们希望当月离开的人仍计入该月; 他们直到下个月才减少总数)。
complete(Organisation, ...
步骤为感兴趣期间内可能没有变化的月份添加空白行。
最后,我们计算每个组织每月净增加和离职的人数,员工人数是这些变化的累计总和 (cumsum
)。
library(tidyverse); library(lubridate)
# convenience function to return the last day of the month
eom <- function(date) { ceiling_date(date, "month") - 1}
dataset1 %>%
pivot_longer(-c(Employee:Organisation)) %>%
filter(!is.na(value)) %>%
mutate(change = if_else(name == "Joint_date", 1, -1),
date = value %>% ymd %>% eom,
Month = if_else(change == -1, eom(date + 10), date)) %>%
complete(Organisation,
Month = ceiling_date(seq.Date(ymd(20180101), ymd(20210601), "month"),"month")-1,
fill = list(change = 0)) %>%
count(Organisation, Month, wt = change, name = "change") %>%
group_by(Organisation) %>%
mutate(Nr_employees = cumsum(change)) %>%
ungroup()
我更喜欢使用 data.table
包 - 对于创建 dataset3
等问题,非等值连接功能非常适合。
library(data.table)
setDT(dataset1)
dataset2 <- CJ(Organisation = dataset1[,unique(Organisation)],
## This is an option to generate the month sequence based on the first date in dataset1 to present
# Month = seq.Date(from = as.Date(cut.Date(dataset1[,min(Joint_date)], breaks = "months")),
# to = as.Date(cut.Date(Sys.Date(), breaks = "months")),
# by = "month") - 1
## Otherwise you can still generate a full sequence of month-end dates with just a start and end
Month = seq.Date(from = as.Date("2018-02-01"),
to = as.Date("2021-07-01"),
by = "month") - 1)
## Simpler to compare month start dates than end
dataset2[,MonthStart := as.Date(cut.Date(Month, breaks = "months"))]
## Fill NA's for Left_date with today's date to properly account for employees still present
dataset1[,Left_date_fill := data.table::fcoalesce(Left_date, Sys.Date())]
## Create columnns with the month start dates of arrivals/departures
dataset1[,Joint_date_month := as.Date(cut.Date(Joint_date, breaks = "months"))]
dataset1[,Left_date_fill_month := as.Date(cut.Date(Left_date_fill, breaks = "months"))]
## Use a non-equijoin to summarize the number of employees present by month
dataset2[dataset1, Nr_employees := .N, by = .(Organisation,
Month), on = .(Organisation = Organisation,
MonthStart >= Joint_date_month,
MonthStart <= Left_date_fill_month)]
## Using this method, the information required for `dataset3` has been added to `dataset2` instead
print(dataset2[seq_len(5), .(Organisation, Month, Nr_employees)])
# Organisation Month Nr_employees
# 1: A123 2018-01-31 2
# 2: A123 2018-02-28 3
# 3: A123 2018-03-31 3
# 4: A123 2018-04-30 3
# 5: A123 2018-05-31 3
# 6: A123 2018-06-30 3
要创建类似于 dataset4
的摘要 table,将每个步骤分解为一个单独的操作对我来说最有意义:
## Start with a table of organizations for dataset4
dataset4 <- data.table(Organisation = dataset1[,unique(Organisation)])
## Join on a summary of dataset2 to get the average over the window of interest
dataset4[dataset2[,.(Avg = mean(fcoalesce(Nr_employees),0.0)), by = .(Organisation)]
,Average_Nr_employees := Avg, on = .(Organisation)]
## Join a summary of dataset1 counting the number that joined in the window of interest
dataset4[dataset1[Joint_date_month >= dataset2[,min(MonthStart)]
& Joint_date_month <= dataset2[,max(MonthStart)]
, .(N = .N)
, by = .(Organisation)], Nr_employees_joined := N, on = .(Organisation)]
## Join a summary of dataset1 counting the number that left in the window of interest
dataset4[dataset1[Left_date_fill_month >= dataset2[,min(MonthStart)]
& Left_date_fill_month <= dataset2[,max(MonthStart)]
, .(N = .N)
, by = .(Organisation)], Nr_employees_left := N, on = .(Organisation)]
## Join a summary of dataset1 counting the number that joined before and left after window of interest
dataset4[dataset1[Joint_date_month <= dataset2[,min(MonthStart)]
& Left_date_fill_month >= dataset2[,max(MonthStart)]
, .(N = .N)
, by = .(Organisation)], Nr_employees_stayed := N, on = .(Organisation)]
print(dataset4)
# Organisation Average_Nr_employees Nr_employees_joined Nr_employees_left Nr_employees_stayed
# 1: A123 2.738095 2 1 1
# 2: A333 3.761905 1 2 3
# 3: A445 2.071429 NA 1 2
这是另一个 data.table
,但采用的方法与 Matt 的答案不同。
代码解释在注释里
library(data.table)
# Set dataset1 to data.table format
setDT(dataset1)
# Faster way to create dataset 2
dataset2_dates <- seq(as.Date("2018-02-01"), as.Date("2021-07-01"), by = "1 months") - 1
dataset2 <- CJ(Organisation = dataset1$Organisation,
Month = dataset2_dates,
unique = TRUE, sorted = TRUE)
# Create dataset3 using a series of two non-equi joins
dataset2[, Nr_employees := 0]
# First non-equi for people that already left (so month should be between joint-left)
dataset2[dataset1[!is.na(Left_date)],
Nr_employees := Nr_employees + .N,
by = .(Organisation, Month),
on = .(Organisation = Organisation, Month >= Joint_date, Month <= Left_date)]
# Second non-equi for people are still around (so month should be after joint)
dataset2[dataset1[is.na(Left_date)],
Nr_employees := Nr_employees + .N,
by = .(Organisation, Month),
on = .(Organisation = Organisation, Month >= Joint_date)]
# Organisation Month Nr_employees
# 1: A123 2018-01-31 2
# 2: A123 2018-02-28 3
# 3: A123 2018-03-31 3
# 4: A123 2018-04-30 3
# 5: A123 2018-05-31 3
# ---
# 122: A445 2021-02-28 2
# 123: A445 2021-03-31 2
# 124: A445 2021-04-30 2
# 125: A445 2021-05-31 2
# 126: A445 2021-06-30 2
# Initialise dataset4
dataset4 <- dataset2[, .(Average_Nr_employees = mean(Nr_employees)), by = .(Organisation)]
# Organisation Average_Nr_employees
# 1: A123 2.714286
# 2: A333 3.714286
# 3: A445 2.047619
#set boundaries to summarise on
minDate <- min(dataset2$Month, na.rm = TRUE)
maxDate <- max(dataset2$Month, na.rm = TRUE)
# Now, get relevant rows from dataset1
dataset4[ dataset1[ is.na(Left_date) | Left_date >= minDate,
.(Nr_employees_joined = uniqueN(Employee[Joint_date >= minDate]),
Nr_employees_left = uniqueN(Employee[!is.na(Left_date) & Left_date <= maxDate]),
Nr_employees_stayed = uniqueN(Employee[Joint_date <= minDate & (is.na(Left_date) | Left_date >= maxDate)])
), by = .(Organisation)],
on = .(Organisation)][]
# Organisation Average_Nr_employees Nr_employees_joined Nr_employees_left Nr_employees_stayed
# 1: A123 2.714286 2 1 1
# 2: A333 3.714286 1 2 3
# 3: A445 2.047619 0 1 2
我有以下数据集,其中包含有关员工加入和离开组织的信息:
dataset1 <- read.table(
text = "
Employee Organisation Joint_date Left_date
G223 A123 1993-05-15 2019-05-01
G223 A123 2020-04-11 NA
G233 A123 2018-02-20 NA
G234 A123 2015-09-04 NA
G111 A333 1980-10-03 2019-09-27
G122 A333 2000-11-16 NA
G177 A333 2005-01-19 NA
G330 A333 2002-12-24 NA
G556 A333 2018-05-01 2019-03-04
G555 A445 2015-11-18 NA
G556 A445 2005-09-01 2018-03-04
G557 A445 1989-04-05 NA",
header = TRUE)
dataset1$Employee <- as.factor(dataset1$Employee)
dataset1$Organisation <- as.factor(dataset1$Organisation)
dataset1$Joint_date <- as.Date(dataset1$Joint_date, format="%Y-%m-%d")
dataset1$Left_date <- as.Date(dataset1$Left_date, format="%Y-%m-%d")
我创建了从 2018-01-31 到 2021-06-30 的数据集 2(每月数据集):
dataset2_dates=c("2018-01-31","2018-02-28","2018-03-31","2018-04-30","2018-05-31","2018-06-30","2018-07-31","2018-08-31","2018-09-30","2018-10-31","2018-11-30","2018-12-31","2019-01-31","2019-02-28","2019-03-31","2019-04-30","2019-05-31","2019-06-30","2019-07-31","2019-08-31","2019-09-30","2019-10-31","2019-11-30","2019-12-31","2020-01-31","2020-02-29","2020-03-31","2020-04-30","2020-05-31","2020-06-30","2020-07-31","2020-08-31","2020-09-30","2020-10-31","2020-11-30","2020-12-31","2021-01-31","2021-02-28","2021-03-31","2021-04-30","2021-05-31","2021-06-30")
# add dates
dataset2 <- expand.grid(Organisation = unique(dataset1$Organisation),
Month = dataset2_dates)
## sort
dataset2 <- dataset2[order(dataset2$Organisation, dataset2$Month),]
## reset id
rownames(dataset2) <- NULL
dataset2$Organisation <- as.factor(dataset2$Organisation)
dataset2$Month <- as.Date(dataset2$Month, format="%Y-%m-%d")
我想以下面的方式结束 dataset3
:
Organisation | Month | Nr_employees
A123 | 2018-01-31 | 2
A123 | 2018-02-28 | 3
A123 | 2018-03-31 | 3
A123 | 2018-04-30 | 3
A123 | 2018-05-31 | 3
A123 | 2018-06-30 | 3
A123 | 2018-07-31 | 3
A123 | 2018-08-31 | 3
A123 | 2018-09-30 | 3
A123 | 2018-10-31 | 3
A123 | 2018-11-30 | 3
A123 | 2018-12-31 | 3
A123 | 2019-01-31 | 3
A123 | 2019-02-28 | 3
A123 | 2019-03-31 | 3
A123 | 2019-04-30 | 3
A123 | 2019-05-31 | 3
A123 | 2019-06-30 | 2
A123 | 2019-07-31 | 2
A123 | 2019-08-31 | 2
A123 | 2019-09-30 | 2
A123 | 2019-10-31 | 2
A123 | 2019-11-30 | 2
A123 | 2019-12-31 | 2
A123 | 2020-01-31 | 2
A123 | 2020-02-29 | 2
A123 | 2020-03-31 | 2
A123 | 2020-04-30 | 3
A123 | 2020-05-31 | 3
A123 | 2020-06-30 | 3
A123 | 2020-07-31 | 3
A123 | 2020-08-31 | 3
A123 | 2020-09-30 | 3
A123 | 2020-10-31 | 3
A123 | 2020-11-30 | 3
A123 | 2020-12-31 | 3
A123 | 2021-01-31 | 3
A123 | 2021-02-28 | 3
A123 | 2021-03-31 | 3
A123 | 2021-04-30 | 3
A123 | 2021-05-31 | 3
A123 | 2021-06-30 | 3
.....
注意:如果员工在当月的最后一天加入或在当月的第一天离开,仍然视为该员工整个月都在。
和 dataset4
总结了 2018-01-31 到 2021-06-30 的数据:
Organisation | Average Nr_employees | Nr_employees joined | Nr_employess left | Nr_employess stayed the whole time
A123 | 115/42 = 2.7 | 2 | 1 | 1
....
关于如何生成 dataset3
和 dataset4
有什么想法吗?
我相信这行得通。我的方法是将数据重塑为更长的格式,然后将每个 Joint_date 行计为添加 +1 名员工,否则我们将查看离职和 -1.
中间位将每个日期转换为月底,如果离开则转换为下个月的月底(因为您注意到我们希望当月离开的人仍计入该月; 他们直到下个月才减少总数)。
complete(Organisation, ...
步骤为感兴趣期间内可能没有变化的月份添加空白行。
最后,我们计算每个组织每月净增加和离职的人数,员工人数是这些变化的累计总和 (cumsum
)。
library(tidyverse); library(lubridate)
# convenience function to return the last day of the month
eom <- function(date) { ceiling_date(date, "month") - 1}
dataset1 %>%
pivot_longer(-c(Employee:Organisation)) %>%
filter(!is.na(value)) %>%
mutate(change = if_else(name == "Joint_date", 1, -1),
date = value %>% ymd %>% eom,
Month = if_else(change == -1, eom(date + 10), date)) %>%
complete(Organisation,
Month = ceiling_date(seq.Date(ymd(20180101), ymd(20210601), "month"),"month")-1,
fill = list(change = 0)) %>%
count(Organisation, Month, wt = change, name = "change") %>%
group_by(Organisation) %>%
mutate(Nr_employees = cumsum(change)) %>%
ungroup()
我更喜欢使用 data.table
包 - 对于创建 dataset3
等问题,非等值连接功能非常适合。
library(data.table)
setDT(dataset1)
dataset2 <- CJ(Organisation = dataset1[,unique(Organisation)],
## This is an option to generate the month sequence based on the first date in dataset1 to present
# Month = seq.Date(from = as.Date(cut.Date(dataset1[,min(Joint_date)], breaks = "months")),
# to = as.Date(cut.Date(Sys.Date(), breaks = "months")),
# by = "month") - 1
## Otherwise you can still generate a full sequence of month-end dates with just a start and end
Month = seq.Date(from = as.Date("2018-02-01"),
to = as.Date("2021-07-01"),
by = "month") - 1)
## Simpler to compare month start dates than end
dataset2[,MonthStart := as.Date(cut.Date(Month, breaks = "months"))]
## Fill NA's for Left_date with today's date to properly account for employees still present
dataset1[,Left_date_fill := data.table::fcoalesce(Left_date, Sys.Date())]
## Create columnns with the month start dates of arrivals/departures
dataset1[,Joint_date_month := as.Date(cut.Date(Joint_date, breaks = "months"))]
dataset1[,Left_date_fill_month := as.Date(cut.Date(Left_date_fill, breaks = "months"))]
## Use a non-equijoin to summarize the number of employees present by month
dataset2[dataset1, Nr_employees := .N, by = .(Organisation,
Month), on = .(Organisation = Organisation,
MonthStart >= Joint_date_month,
MonthStart <= Left_date_fill_month)]
## Using this method, the information required for `dataset3` has been added to `dataset2` instead
print(dataset2[seq_len(5), .(Organisation, Month, Nr_employees)])
# Organisation Month Nr_employees
# 1: A123 2018-01-31 2
# 2: A123 2018-02-28 3
# 3: A123 2018-03-31 3
# 4: A123 2018-04-30 3
# 5: A123 2018-05-31 3
# 6: A123 2018-06-30 3
要创建类似于 dataset4
的摘要 table,将每个步骤分解为一个单独的操作对我来说最有意义:
## Start with a table of organizations for dataset4
dataset4 <- data.table(Organisation = dataset1[,unique(Organisation)])
## Join on a summary of dataset2 to get the average over the window of interest
dataset4[dataset2[,.(Avg = mean(fcoalesce(Nr_employees),0.0)), by = .(Organisation)]
,Average_Nr_employees := Avg, on = .(Organisation)]
## Join a summary of dataset1 counting the number that joined in the window of interest
dataset4[dataset1[Joint_date_month >= dataset2[,min(MonthStart)]
& Joint_date_month <= dataset2[,max(MonthStart)]
, .(N = .N)
, by = .(Organisation)], Nr_employees_joined := N, on = .(Organisation)]
## Join a summary of dataset1 counting the number that left in the window of interest
dataset4[dataset1[Left_date_fill_month >= dataset2[,min(MonthStart)]
& Left_date_fill_month <= dataset2[,max(MonthStart)]
, .(N = .N)
, by = .(Organisation)], Nr_employees_left := N, on = .(Organisation)]
## Join a summary of dataset1 counting the number that joined before and left after window of interest
dataset4[dataset1[Joint_date_month <= dataset2[,min(MonthStart)]
& Left_date_fill_month >= dataset2[,max(MonthStart)]
, .(N = .N)
, by = .(Organisation)], Nr_employees_stayed := N, on = .(Organisation)]
print(dataset4)
# Organisation Average_Nr_employees Nr_employees_joined Nr_employees_left Nr_employees_stayed
# 1: A123 2.738095 2 1 1
# 2: A333 3.761905 1 2 3
# 3: A445 2.071429 NA 1 2
这是另一个 data.table
,但采用的方法与 Matt 的答案不同。
代码解释在注释里
library(data.table)
# Set dataset1 to data.table format
setDT(dataset1)
# Faster way to create dataset 2
dataset2_dates <- seq(as.Date("2018-02-01"), as.Date("2021-07-01"), by = "1 months") - 1
dataset2 <- CJ(Organisation = dataset1$Organisation,
Month = dataset2_dates,
unique = TRUE, sorted = TRUE)
# Create dataset3 using a series of two non-equi joins
dataset2[, Nr_employees := 0]
# First non-equi for people that already left (so month should be between joint-left)
dataset2[dataset1[!is.na(Left_date)],
Nr_employees := Nr_employees + .N,
by = .(Organisation, Month),
on = .(Organisation = Organisation, Month >= Joint_date, Month <= Left_date)]
# Second non-equi for people are still around (so month should be after joint)
dataset2[dataset1[is.na(Left_date)],
Nr_employees := Nr_employees + .N,
by = .(Organisation, Month),
on = .(Organisation = Organisation, Month >= Joint_date)]
# Organisation Month Nr_employees
# 1: A123 2018-01-31 2
# 2: A123 2018-02-28 3
# 3: A123 2018-03-31 3
# 4: A123 2018-04-30 3
# 5: A123 2018-05-31 3
# ---
# 122: A445 2021-02-28 2
# 123: A445 2021-03-31 2
# 124: A445 2021-04-30 2
# 125: A445 2021-05-31 2
# 126: A445 2021-06-30 2
# Initialise dataset4
dataset4 <- dataset2[, .(Average_Nr_employees = mean(Nr_employees)), by = .(Organisation)]
# Organisation Average_Nr_employees
# 1: A123 2.714286
# 2: A333 3.714286
# 3: A445 2.047619
#set boundaries to summarise on
minDate <- min(dataset2$Month, na.rm = TRUE)
maxDate <- max(dataset2$Month, na.rm = TRUE)
# Now, get relevant rows from dataset1
dataset4[ dataset1[ is.na(Left_date) | Left_date >= minDate,
.(Nr_employees_joined = uniqueN(Employee[Joint_date >= minDate]),
Nr_employees_left = uniqueN(Employee[!is.na(Left_date) & Left_date <= maxDate]),
Nr_employees_stayed = uniqueN(Employee[Joint_date <= minDate & (is.na(Left_date) | Left_date >= maxDate)])
), by = .(Organisation)],
on = .(Organisation)][]
# Organisation Average_Nr_employees Nr_employees_joined Nr_employees_left Nr_employees_stayed
# 1: A123 2.714286 2 1 1
# 2: A333 3.714286 1 2 3
# 3: A445 2.047619 0 1 2