跨多个组的累计百分比

假设有一家医院诊所，其中有一份每天有多少患者到医院就诊的清单。我有 10 年的数据 - 但患者并非每天都到诊所就诊。举个例子，数据如下所示（在 R 中）：

library(dplyr)

set.seed(123)

start_date <- as.Date("2010-01-01")
end_date <- as.Date("2019-12-31")
all_dates <- seq.Date(start_date, end_date, by="day")

num_visits <- sample(1:length(all_dates), size = 3000, replace = FALSE)
visit_dates <- all_dates[num_visits]

num_patients <- sample(1:100, size = length(visit_dates), replace = TRUE)

clinic_data <- data.frame(date = visit_dates, num_patients = num_patients)

hospital_data <- clinic_data %>% arrange(date)

       date num_patients
 2010-01-01           90
 2010-01-02           96
 2010-01-04           65
 2010-01-05           80
 2010-01-06           15
 2010-01-07           87

我想尝试回答以下问题： 平均而言 - 对于任何给定的月份，该月所有患者中有多少百分比会在 $y$ 天之前到访过诊所？例如，假设我知道在某个月份有 900 人到访过医院 - 我想知道到 19 日为止，根据之前的趋势，这 900 人中有多少百分比（累计）可能在那时之前到访过医院？

我尝试通过手动识别不同的逻辑步骤来做到这一点：

library(ggplot2)

hospital_data$year <- as.numeric(format(as.Date(hospital_data$date), "%Y"))
hospital_data$month <- as.numeric(format(as.Date(hospital_data$date), "%m"))
hospital_data$day <- as.numeric(format(as.Date(hospital_data$date), "%d"))

hospital_data <- hospital_data[order(hospital_data$date), ]

yearly_totals <- aggregate(num_patients ~ year, data = hospital_data, FUN = sum)
names(yearly_totals)[2] <- "yearly_total"

hospital_data <- merge(hospital_data, yearly_totals, by = "year")

results <- by(hospital_data, hospital_data$year, function(df) {
    df$cumulative_patients <- cumsum(df$num_patients)
    df$cumulative_percentage <- df$cumulative_patients / df$yearly_total * 100
    return(df)
})
results <- do.call(rbind, results)

avg_results <- aggregate(cumulative_percentage ~ day, data = results, FUN = mean, na.rm = TRUE)

avg_results <- avg_results[order(avg_results$day), ]

ggplot(avg_results, aes(x = day, y = cumulative_percentage)) +
    geom_line() +
    geom_point() +
    scale_x_continuous(breaks = seq(1, 31, by = 5)) +
    scale_y_continuous(limits = c(0, 100)) +
    labs(title = "Average Cumulative Percentage of Yearly Patients by Day",
         x = "Day of Month",
         y = "Average Cumulative Percentage of Patients") +
    theme_minimal() +
    theme(panel.grid.minor = element_blank())

但我的图表没有显示这个累积百分比：

有人知道我把事情搞砸了吗？

编辑：

library(tidyverse)

result <- hospital_data %>%
  mutate(month = floor_date(date, "month"),
         day = day(date)) %>%
  group_by(month) %>%
  arrange(month, day) %>%
  mutate(month_total = sum(num_patients),
         cuml = cumsum(num_patients),
         cuml_pct = cuml / month_total) %>%
  ungroup() %>%
  group_by(day) %>%
  summarize(avg_cuml_pct = mean(cuml_pct, na.rm = TRUE)) %>%
  arrange(day)

result <- result %>%
  mutate(avg_cuml_pct = cummax(avg_cuml_pct))

ggplot(result, aes(day, avg_cuml_pct)) +
  geom_line() +
  scale_y_continuous(labels = scales::percent_format(), limits = c(0, 1)) +
  scale_x_continuous(breaks = seq(0, 31, by = 5)) +
  labs(x = "Day of Month", 
       y = "Average Cumulative Percentage of Monthly Patients",
       title = "Average Cumulative Patient Percentage by Day of Month") +
  theme_minimal()