Question

在这种情况下（可在此问题中找到更多详细信息：Count how many observations in the rest of the dat fits multiple conditions? (R)）

这是一个名为event的数据集，包含数千个事件（观察）我选择了几行来显示数据结构体。它包含“STATEid”，“发生日期”和地理坐标有两个变量“LON”“LAT”。我写信给为每一行计算一个新变量（列）。这个新变量应该是：“给定任何特定事件，计算数据集的其余部分并计算在同一状态下发生的事件数，在50 / 100KM半径范围内，在接下来的30/60天内。

我已经编写了一个带有while循环的用户定义函数 - 为了使这更容易，我只包括2个条件，在30天内并处于相同的状态：

n = 1

f = function(i) {
  a = i[n,]
  b = a$date
  # c = a$LON
  # d = a$LAT
  e = a$STATEid
  f = a$RID
  g1 = sum(i$CASE  [i$date<= b+30 & i$date>b & i$STATEid==e], na.rm=T)
  # g2 = sum(i$viold [i$date<= b+30 & i$date>b], na.rm=T)
  # g3 = sum(i$CASE  [i$date<= b+60 & i$date>b], na.rm=T)
  # g4 = sum(i$viold [i$date<= b+60 & i$date>b], na.rm=T)
  # h = cbind(g1, g2, g3, g4)
  g1 = data.frame(g1)
  n = n+1
  assign(as.character(f), g1, envir = .GlobalEnv)
}

for（n in 1:20）（f（event2））

这已经花了太长时间，因为它包含23,000个案例。当循环只需要运行两次时，我的带有16GB Ram的PC无法钉住它！所以我认为避免循环会更好。你能否建议一种方法来矢量化我的代码并避免循环？

我的主要问题是当我需要引用每一行时，我不知道如何编写用户定义的问题，当需要多个条件时，每个变量都正确 - 这就是为什么在我的循环函数中，我创建了诸如“a”，“b”，“c”，“d”，“e”正确称呼它们......效率低下 - 我知道......

我的输出结果如下：

     > dput(tail(event2[,c("RID", "STATEid", "date", "LON", "LAT")]))
structure(list(RID = c("023610", "023611", "023613", "023614", 
"023615", "023616"), STATEid = structure(c(36L, 36L, 23L, 23L, 
5L, 14L), .Label = c("alabama", "alaska", "arizona", "arkansas", 
"california", "colorado", "connecticut", "delaware", "district of columbia", 
"florida", "georgia", "hawaii", "idaho", "illinois", "indiana", 
"iowa", "kansas", "kentucky", "louisiana", "maine", "maryland", 
"massachusetts", "michigan", "minnesota", "mississippi", "missouri", 
"montana", "nebraska", "nevada", "new hampshire", "new jersey", 
"new mexico", "new york", "north carolina", "north dakota", "ohio", 
"oklahoma", "oregon", "pennsylvania", "rhode island", "south carolina", 
"south dakota", "tennessee", "texas", "utah", "vermont", "virginia", 
"washington", "west virginia", "wisconsin", "wyoming"), class = "factor"), 
    date = structure(c(3620, -633, 131, -315, 5421, 3558), class = "Date"), 
    LON = c(-80.6495194, -80.6495194, -83.6129939, -83.6129939, 
    -121.6169108, -87.8328505), LAT = c(41.0997803, 41.0997803, 
    42.2411499, 42.2411499, 39.1404477, 42.4461322)), .Names = c("RID", 
"STATEid", "date", "LON", "LAT"), row.names = c(23610L, 23611L, 
23613L, 23614L, 23615L, 23616L), class = "data.frame")
>

非常感谢。感谢您的帮助。

最佳，

---------- 2018年1月20日更新---------

我创建了一个可以正常反映我希望的循环的循环：

g = event2[FALSE,]

USERFUN = function(i) {
  a = i[n,] # retrieve each row from the object, make it a data object
  b = a$date # get date
  # c = a$LON # for now I dropped the idea of calculating radius
  # d = a$LAT # for now I dropped the idea of calculating radius
  e = a$STATEid # get STATE
  f = a$RID # get case ID to name the objects generated!

  PostAct30 = sum(i$CASE [i$date<= b+30 & i$date>b & i$STATEid == e], na.rm=T) # multiple conditions defined here - i is the entire dataset 
  PostAct60 = sum(i$CASE [i$date<= b+60 & i$date>b & i$STATEid == e], na.rm=T) # multiple conditions defined here - b, e are dynamic, retrieving from each line!!!
  PreAct30 = sum(i$CASE [i$date<= b & i$date>b-30 & i$STATEid == e], na.rm=T)
  PreAct60 = sum(i$CASE [i$date<= b & i$date>b-30 & i$STATEid == e], na.rm=T)
  PostVio30 = sum(i$viold [i$date<= b+30 & i$date>b & i$STATEid == e], na.rm=T)
  PostVio60 = sum(i$viold [i$date<= b+60 & i$date>b & i$STATEid == e], na.rm=T)
  PreVio30 = sum(i$viold [i$date<= b & i$date>b-30 & i$STATEid == e], na.rm=T)
  PreVio60 = sum(i$viold [i$date<= b & i$date>b-30 & i$STATEid == e], na.rm=T)
  g1 = data.frame(f, PostAct30, PostAct60, PreAct30, PreAct60, PostVio30, PostVio60, PreVio30, PreVio60)
  n = n+1
  return(g1)
  }
# sum(event2$ca)
n = 1
for (n in 1:19446) {
  g2 = USERFUN(event2)
  g = rbind(g, g2)        
}

AND输出如下：

> tail(event3 [c("date","STATEid", "PostAct30", "PostAct60", "PostVio30", "PostVio60")])
            date    STATEid PostAct30 PostAct60 PostVio30 PostVio60
23611 1968-04-08       ohio         3         4         0         0
23612       <NA>    arizona        NA        NA        NA        NA
23613 1970-05-12   michigan         4         6         2         4
23614 1969-02-20   michigan         2         3         1         1
23615 1984-11-04 california         4         5         0         0
23616 1979-09-29   illinois         0         2         0         1

Answer 1

通过将 date 和 STATEid 元素迭代到已定义的函数中，考虑mapply添加新列。具体来说，mapply生成一个包含7列的矩阵，您可以将其分配给 event2 。

dates_calc_fct <- function(b, e) 
  c(sum(event2$CASE [event2$date<= b+30 & event2$date>b & event2$STATEid == e], na.rm=T),
    sum(event2$CASE [event2$date<= b+60 & event2$date>b & event2$STATEid == e], na.rm=T),
    sum(event2$CASE [event2$date<= b & event2$date>b-30 & event2$STATEid == e], na.rm=T),
    sum(event2$CASE [event2$date<= b & event2$date>b-30 & event2$STATEid == e], na.rm=T),
    sum(event2$viold [event2$date<= b+30 & event2$date>b & event2$STATEid == e], na.rm=T),
    sum(event2$viold [event2$date<= b+60 & event2$date>b & event2$STATEid == e], na.rm=T),
    sum(event2$viold [event2$date<= b & event2$date>b-30 & event2$STATEid == e], na.rm=T),
    sum(event2$viold [event2$date<= b & event2$date>b-30 & event2$STATEid == e], na.rm=T)
   )

event2[c("PostAct30", "PostAct60", 
         "PreAct30", "PreAct60",
         "PostVio30", "PostVio60", 
         "PreVio30", "PreVio60")] <- mapply(dates_calc_fct, event$date, event$STATEid)

R - 如何使用apply family函数进行向量化并避免使用while / for循环？

1 个答案: