DATA

Question

我收到错误，其中我认为根本原因是在我的分组中，所有群组中都没有值。

可以在此处下载数据：https://opendata.miamidade.gov/311/311-Service-Requests-Miami-Dade-County/dj6j-qg5t

我想要做的是拥有一个采用嵌套分组并检测所有漏洞并填充零的函数。让我们采取以下代码示例：

d <- rDSamp %>% 
  FilterDateRange("Ticket.Created.Date...Time", "1/1/2013", "12/31/2013") %>%
  group_by(Ticket.Created.Date...Time, Case.Owner) %>%
  summarise(
    count = n()
  ) %>%
  arrange(Ticket.Created.Date...Time)

总结之后，我需要添加一个遍历每个日期的函数，如果案例所有者在该日期不存在，则创建案例所有者，并添加一个0的计数。

以下是达到这一点的代码：

library("ggvis") 
library("magrittr") 
library("dplyr")
library("tidyr")
library("shiny")
library("checkpoint")

checkpoint("2016-03-29")

rData <- read.csv("C:\\data\\Miami_311.csv", 
                 header=TRUE, 
                 sep=",")
rDSamp <- rData[sample(1:length(rData$Case.Owner), 1000),]
rDSamp = rData %>%
    subset(
      Case.Owner == "Animal_Services" |
        Case.Owner == "Waste_Management" |
        Case.Owner == "Community_Information_and_Outreach" |
        Case.Owner == "Waste_Management")
rDSamp$Case.Owner = factor(rDSamp$Case.Owner)
#Convert to known date time
rDSamp$Ticket.Created.Date...Time <- 
  rDSamp$Ticket.Created.Date...Time %>%
  as.POSIXct(format="%m/%d/%Y") %>%
  as.character()

FilterDateRange = function(data, feature, minDate, maxDate) {
  minDate = minDate %>% 
          as.POSIXct(format="%m/%d/%Y") %>% 
          as.character() 
  maxDate = maxDate %>% 
          as.POSIXct(format="%m/%d/%Y") %>% 
          as.character() 
  result = subset(data, data[feature] <= maxDate)
  subset(result, result[feature] >= minDate)
}

d <- rDSamp %>% 
  FilterDateRange("Ticket.Created.Date...Time", "1/1/2013", "12/31/2013") %>%
  group_by(Ticket.Created.Date...Time, Case.Owner) %>%
  summarise(
count = n()
  ) %>%
  arrange(Ticket.Created.Date...Time)

为了获得最终信息，我尝试使用ggvis layer_smooths并报告了由coersion引入的内容，我的假设是数据中的漏洞导致了这一点。

找到一个解决方案，寻找更通用的解决方案......

FillDataHolesWithZeros = function(input){
  countZero = input %>% 
    group_by(Ticket.Created.Date...Time) %>% 
    summarise(count = n()) %>%
    filter(count < length(levels(input$Case.Owner)))
  for(i in 1:nrow(countZero))
  {
date = countZero[i,]$Ticket.Created.Date...Time
departments = input %>% filter(Ticket.Created.Date...Time == date)
myLevels = levels(input$Case.Owner)
for(j in 1:nrow(departments))
{
  owner = departments[j,]$Case.Owner
  myLevels = myLevels[myLevels != owner]
}
print(paste(i,":",myLevels))
for(k in 1:length(myLevels)){
  input = input %>% rbind(data.frame(
    Ticket.Created.Date...Time = date,
    Case.Owner = myLevels[k],
    count = 0
      ))
    }
  }
  return(input)
}

Answer 1

尝试

例如

DATA

（以便将来尝试展示可重现的数据和具体问题）

Date=c(rep("2016-01-01",2),rep("2016-01-02",3),rep("2016-01-03",4))
CaseOwner=c(letters[1:2],letters[1:3],letters[1:4])
CallCount=1:9
dat1=data.frame(Date, CaseOwner, CallCount)

组+添加行

library(dplyr)
library(tidyr)
dat1%>%group_by(Date,CaseOwner)%>%summarize(cnt=max(CallCount))%>%complete(CaseOwner, fill = list(cnt = 0))

结果

Source: local data frame [12 x 3]

         Date CaseOwner   cnt
       (fctr)    (fctr) (dbl)
1  2016-01-01         a     1
2  2016-01-01         b     2
3  2016-01-01         c     0
4  2016-01-01         d     0
5  2016-01-02         a     3
6  2016-01-02         b     4
7  2016-01-02         c     5
8  2016-01-02         d     0
9  2016-01-03         a     6
10 2016-01-03         b     7
11 2016-01-03         c     8
12 2016-01-03         d     9

附加

1）%in% - 看起来很漂亮|

rDSamp = rData %>%
    subset(
      Case.Owner == "Animal_Services" |
        Case.Owner == "Waste_Management" |
        Case.Owner == "Community_Information_and_Outreach" |
        Case.Owner == "Waste_Management")

可以在

上更改

    rDSamp = rData[rData$Case.Owner %in% 
c("Animal_Services","Waste_Management","Community_Information_and_Outreach","Waste_Management"),]

2）如果你想比较日期，你不需要将它转换为char

maxDate = maxDate %>% 
          as.POSIXct(format="%m/%d/%Y") %>% 
          as.character()

和

data[feature] <= maxDate

将作为字符串进行比较。

填充R组中的所有项目

1 个答案:

DATA

组+添加行

结果

附加