R向量计数每个日期范围内的日期数

Question

我正在寻找实现创建新变量的最佳方法，numWithin365 ，定义如下:
给定一列日期，dates , 计算前 365 天内该列中其他日期的数量。这个问题可以推广到日期向量之外。
这是一种实现；我正在寻找任何可以帮助它更好地扩展的建议。

library(dplyr)

# set seed for reproducibility
set.seed(42)

# function to calculate number of dates in prior year
within365 <- function(col){
  sapply(col, function(x){
    sum(x-365 < col & col <= x-1)
    }
  )
}
# fake data sorted chronologically
df <- data.frame(dates = sample(seq(as.Date('2015/01/01'), as.Date('2020/12/31'), 
                by="day"), 10)) %>% arrange(dates)

# applying the function
df %>% mutate(numWithin365 = within365(dates))

        dates numWithin365
1  2015-12-22            0
2  2016-09-25            1
3  2018-01-02            0
4  2018-02-25            1
5  2018-03-22            2
6  2018-06-05            3
7  2018-08-19            4
8  2019-06-13            1
9  2020-09-02            0
10 2020-09-27            1

Answer 1

如果对 Rcpp 的依赖不是问题，我喜欢它用于此类任务，因为它易于维护。

library(Rcpp)
cppFunction('
  NumericVector count365(const NumericVector x) {
    // assumes that x is sorted
    
    size_t n = x.size(); 
    
    //initialize vector of zeros for counts
    NumericVector N = NumericVector(n);
    
    double lim;
    
    // start loop from second element of x
    for (size_t i = 1; i < n; ++i) {
      lim = x[i] - 365;
      
      //loop backwards from preceding element
      for (size_t j = i-1; j >= 0; --j) {
      
        //check if within 365 day range
        if (x[j] >= lim) {
          N[i]++;
        } else {
          break;
        }
      }
    }
    
    return N;
  }
')

df$numWithin365 <- count365(df$dates)
#        dates numWithin365
#1  2015-12-22            0
#2  2016-09-25            1
#3  2018-01-02            0
#4  2018-02-25            1
#5  2018-03-22            2
#6  2018-06-05            3
#7  2018-08-19            4
#8  2019-06-13            1
#9  2020-09-02            0
#10 2020-09-27            1