R 我能为下面的嵌套函数提供一个简洁的解决方案吗

该函数在包含1000到20000个案例的df上运行良好，但除此之外，还需要几个小时（5个多小时），现在我有一个观察长度为57635985的df

假设df如下所示：

d<-structure(list(ReviewType= c("Review","Review","Review","Correction","Correction","Review","Review","Review","Review","Review","Correction","Correction","Deficiency","Correction","Correction", 
                                "Correction", "Deficiency", "Deficiency", "Correction","Correction","Deficiency","Correction"),
                  Submissiondate= c("2020-08-29 04:32:00","2020-08-28 04:31:00","2020-08-26 04:31:00","2020-08-25 04:31:00","2020-08-24 04:31:00","2020-08-23 04:31:00","2020-08-22 04:31:00","2020-08-21 04:31:00","2020-08-20 04:31:00","2020-08-19 04:31:00",
                                    "2020-09-27 04:31:00","2020-09-27 03:52:59","2020-09-28 17:30:00","2020-09-29 14:01:00",
                                    "2020-09-05 03:00:00","2020-09-05 03:51:00", "2020-09-03 23:59:49",
                                    "2020-09-02 00:03:54","2020-09-01 00:04:48","2020-10-01 04:31:00","2020-10-11 04:31:00","2020-10-21 04:31:00"),
                  CaseNo= c("124","123","125","121","121","125","123","123","123","123","123","123","123","125","123","123","123","124","123","127","127","127")), class = "data.frame", row.names = c(NA, -22L))


d<-d%>%arrange(CaseNo,Submissiondate)

---

感谢您的指导。

我可以让您从

结束状态

数据框开始。我不确定它是否会快得多。因为

dplyr

一次对所有列执行操作（而不是按顺序向下），所以我仍然需要

while（）

循环来完成缺少的几周中的一些填充。也许一个更好的

dplyr

人会提供另一种选择

library(dplyr)
library(tidyr)
cor_df2 <- EndStates %>%
  mutate(count = as.numeric(WeekEndState == "Correction")) %>% 
  select(-WeekEndState) %>% 
  pivot_wider(id_cols="week.end", names_from="CaseNo", values_from="count") %>% 
  arrange(week.end) %>%
  mutate(across(-week.end, function(x)case_when(is.na(x) & week.end == min(week.end) ~ 0, TRUE ~ x)))

while(any(is.na(cor_df2))){
  cor_df2 <- cor_df2 %>% mutate(across(-week.end, function(x)case_when(is.na(x)~lag(x), TRUE ~ x)))
}  
cor_df2 <- cor_df2 %>%   
  mutate(asw = rowSums(.[-1])) %>% 
  select(week.end, asw)

库（dplyr）
图书馆（tidyr）
cor_df2%
变异（计数=as.numeric（WeekEndState==“更正”）%>%
选择（-WeekEndState）%>%
透视图（id\u cols=“week.end”，name\u from=“CaseNo”，value\u from=“count”）%>%
安排（周末）%>%
变异（当（is.na（x）&week.end==min（week.end）~0，TRUE~x）时跨（-week.end，函数（x）case_）
而（任何（is.na（cor_df2）））{
cor_df2%突变（在（-周末，函数（x）情况下，当（is.na（x）~lag（x），TRUE~x）））
}  
cor_df2%
变异（asw=行和（.-1]））%>%
选择（周末，asw）

非常感谢您的帮助！在我的5000箱df上测试过，看起来不错。我的550万美元！

week.end cor_df.asw
1 2020-08-22          0
2 2020-08-29          1
3 2020-09-05          2
4 2020-10-03          3
5 2020-10-17          2
6 2020-10-24          3

library(dplyr)
library(tidyr)
cor_df2 <- EndStates %>%
  mutate(count = as.numeric(WeekEndState == "Correction")) %>% 
  select(-WeekEndState) %>% 
  pivot_wider(id_cols="week.end", names_from="CaseNo", values_from="count") %>% 
  arrange(week.end) %>%
  mutate(across(-week.end, function(x)case_when(is.na(x) & week.end == min(week.end) ~ 0, TRUE ~ x)))

while(any(is.na(cor_df2))){
  cor_df2 <- cor_df2 %>% mutate(across(-week.end, function(x)case_when(is.na(x)~lag(x), TRUE ~ x)))
}  
cor_df2 <- cor_df2 %>%   
  mutate(asw = rowSums(.[-1])) %>% 
  select(week.end, asw)