r - 如何排除 R 中计算均值和标准差的月份

Question

下面的代码生成了一个带有三条水平线的散点图，分别表示均值、均值+标准差和均值-标准差。为了计算这三个因素，我的 data 数据库中的所有日期都被考虑在内。

但是，我想在计算均值和标准差时排除四月份，我该怎么做？

可执行代码如下:

library(dplyr)
library(tidyr)
library(lubridate)


data <- structure(
  list(Id=c(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1),
       date1 = c("2021-06-20","2021-06-20","2021-06-20","2021-06-20","2021-06-20",
                 "2021-06-20","2021-06-20","2021-06-20","2021-06-20","2021-06-20","2021-06-20",
                 "2021-06-20","2021-06-20","2021-06-20","2021-06-20","2021-06-20","2021-06-20",
                 "2021-06-20","2021-06-20","2021-06-20","2021-06-20"),
       date2 = c("2021-07-01","2021-07-01","2021-07-01","2021-07-01","2021-04-02",
                 "2021-04-02","2021-04-02","2021-04-02","2021-04-02","2021-04-02","2021-04-03",
                 "2021-04-03","2021-04-03","2021-04-03","2021-04-03","2021-04-08","2021-04-08",
                 "2021-07-09","2021-07-09","2021-07-10","2021-07-10"),
       Week= c("Thursday","Thursday","Thursday","Thursday","Friday","Friday","Friday","Friday",
               "Friday","Friday","Saturday","Saturday","Saturday","Saturday","Saturday","Thursday",
               "Thursday","Friday","Friday","Saturday","Saturday"),
       DTPE = c("Ho","Ho","Ho","Ho","","","","","","","","","","","","","","","","Ho","Ho"),
       D1 = c(8,1,9, 3,5,4,7,6,3,8,2,3,4,6,7,8,4,2,6,2,3), DR01 = c(4,1,4,3,3,4,3,6,3,7,2,3,4,6,7,8,4,2,6,7,3),
       DR02 = c(8,1,4,3,3,4,1,6,3,7,2,3,4,6,7,8,4,2,6,2,3), DR03 = c(7,5,4,3,3,4,1,5,3,3,2,3,4,6,7,8,4,2,6,4,3),
       DR04= c(4,5,6,7,3,2,7,4,2,1,2,3,4,6,7,8,4,2,6,4,3),DR05 = c(9,5,4,3,3,2,1,5,3,7,2,3,4,7,7,8,4,2,6,4,3)),
  class = "data.frame", row.names = c(NA, -21L))


graph <- function(dt, dta = data) {
  
  dim_data<-dim(data)
  
  day<-c(seq.Date(from = as.Date(data$date2[1]), by = "days",
                  length = dim_data[1]
  )) 
  
  data_grouped <- data %>%
    mutate(across(starts_with("date"), as.Date)) %>%
    group_by(date2) %>%
    summarise(Id = first(Id),
              date1 = first(date1),
              Week = first(Week),
              DTPE = first(DTPE),
              D1 = sum(D1)) %>%
    select(Id,date1,date2,Week,DTPE,D1)

  data_grouped %>% 
    mutate(DTPE = na_if(DTPE, ""))

  df_OC<-subset(data_grouped, DTPE == "")
  ds_CO = df_OC %>% filter(weekdays(date2) %in% weekdays(as.Date(dt)))

  mean<-mean(ds_CO$D1)
  sd<-sd(ds_CO$D1)
  
  
  dta %>%
    filter(date2 == ymd(dt)) %>%
    summarize(across(starts_with("DR"), sum)) %>%
    pivot_longer(everything(), names_pattern = "DR(.+)", values_to = "val") %>%
    mutate(name = as.numeric(name)) %>%
    plot(xlab = "Days", ylab = "Number", xlim = c(0, 45),cex=1.5,cex.lab=1.5, 
         cex.axis=1.5, cex.main=2, cex.sub=2, lwd=2.5, ylim = c((min(.$val) %/% 10) * 15, (max(.$val) %/% 10 + 1) * 100))
  abline(h=mean, col='blue') +
    abline(h=(mean + sd), col='green',lty=2) 
  abline(h=(mean - sd), col='orange',lty=2)
  
}  
graph("2021-07-10",data)

Answer 1

data %>%
  filter("04" != format(as.Date(date2), format = "%m"))
#   Id      date1      date2     Week DTPE D1 DR01 DR02 DR03 DR04 DR05
# 1  1 2021-06-20 2021-07-01 Thursday   Ho  8    4    8    7    4    9
# 2  1 2021-06-20 2021-07-01 Thursday   Ho  1    1    1    5    5    5
# 3  1 2021-06-20 2021-07-01 Thursday   Ho  9    4    4    4    6    4
# 4  1 2021-06-20 2021-07-01 Thursday   Ho  3    3    3    3    7    3
# 5  1 2021-06-20 2021-07-09   Friday       2    2    2    2    2    2
# 6  1 2021-06-20 2021-07-09   Friday       6    6    6    6    6    6
# 7  1 2021-06-20 2021-07-10 Saturday   Ho  2    7    2    4    4    4
# 8  1 2021-06-20 2021-07-10 Saturday   Ho  3    3    3    3    3    3

(我建议您永久在框架中制作 date1 和 date2 合适的 Date 对象，而不是转换它每次你做某事时。虽然转换相对便宜，但也没有必要，忘记它的后果可能是结果的细微差别(即，将其视为分类变量副连续/离散序数)。