Question

我需要在R中编写一个函数，以返回列值大于0的系列中的第一个日期。我想在数据框中标识每年的日期。

例如，给定此示例数据...

Date         Year     Catch

3/12/2001    2001     0
3/19/2001    2001     7
3/24/2001    2001     9
4/6/2002     2002     12 
4/9/2002     2002     0
4/15/2002    2002     5
4/27/2002    2002     0
3/18/2003    2003     0
3/22/2003    2003     0
3/27/2003    2003     15

我希望R返回每年的第一个日期，渔获> 0

Year    Date 

2001    3/19/2001
2002    4/6/2002
2003    3/27/2003

我一直在使用下面的min函数，但是它只返回行号，而我无法在数据框中返回每年的值。 min(which(data$Catch > 0))

我刚开始使用R编写自己的函数。对您的任何帮助将不胜感激。谢谢。

Answer 1

library(dplyr)

df1 %>% 
  group_by(Year) %>% 
  slice(which.max(Catch > 0))

# # A tibble: 3 x 3
# # Groups:   Year [3]
#   Date        Year Catch
#   <date>     <int> <int>
# 1 2001-03-19  2001     7
# 2 2002-04-06  2002    12
# 3 2003-03-27  2003    15

数据：

df1 <-
structure(list(Date = structure(c(11393, 11400, 11405, 11783, 
11786, 11792, 11804, 12129, 12133, 12138), class = "Date"), Year = c(2001L, 
2001L, 2001L, 2002L, 2002L, 2002L, 2002L, 2003L, 2003L, 2003L
), Catch = c(0L, 7L, 9L, 12L, 0L, 5L, 0L, 0L, 0L, 15L)), .Names = c("Date", 
"Year", "Catch"), row.names = c(NA, -10L), class = "data.frame")

Answer 2

这里是data.table

的一个选项

library(data.table)
setDT(df1)[, .SD[which.max(Catch > 0)], Year]
#   Year       Date Catch
#1: 2001 2001-03-19     7
#2: 2002 2002-04-06    12
#3: 2003 2003-03-27    15

数据

df1 <- structure(list(Date = structure(c(11393, 11400, 11405, 11783, 
11786, 11792, 11804, 12129, 12133, 12138), class = "Date"), Year = c(2001L, 
2001L, 2001L, 2002L, 2002L, 2002L, 2002L, 2003L, 2003L, 2003L
 ), Catch = c(0L, 7L, 9L, 12L, 0L, 5L, 0L, 0L, 0L, 15L)), row.names = c(NA, 
 -10L), class = "data.frame")

Answer 3

这是一个dplyr解决方案。

df1 %>%
  group_by(Year) %>%
  mutate(Inx = first(which(Catch > 0))) %>%
  filter(Inx == row_number()) %>%
  select(-Inx)
## A tibble: 3 x 3
## Groups:   Year [3]
#  Date        Year Catch
#  <date>     <int> <int>
#1 2001-03-19  2001     7
#2 2002-04-06  2002    12
#3 2003-03-27  2003    15

数据。

df1 <- read.table(text = "
Date         Year     Catch
3/12/2001    2001     0
3/19/2001    2001     7
3/24/2001    2001     9
4/6/2002     2002     12 
4/9/2002     2002     0
4/15/2002    2002     5
4/27/2002    2002     0
3/18/2003    2003     0
3/22/2003    2003     0
3/27/2003    2003     15                  
", header = TRUE)

df1$Date <- as.Date(df1$Date, "%m/%d/%Y")

Answer 4

df <- data.frame(Date = as.Date(c("3/12/2001", "3/19/2001", "3/24/2001",
                      "4/6/2002", "4/9/2002", "4/15/2002", "4/27/2002",
                      "3/18/2003", "3/22/2003", "3/27/2003"), "%m/%d/%Y"),
             Year = c(2001, 2001, 2001, 2002, 2002, 2002, 2002, 2003, 2003, 2003),
             Catch = c(0, 7, 9, 12, 0, 5, 0, 0, 0, 15))

如果不需要功能，可以尝试

library(dplyr)
df %>% group_by(Date) %>% filter(Catch > 0 ) %>% group_by(Year) %>% summarize(date = min(Date))

如果您确实想编写一个函数，也许

firstcatch <- function(yr) {
  dd <- subset(df, yr == Year)
  withcatches <- dd[which(dd$Catch > 0), ]
  min(as.character(withcatches$Date))
} 

yrs <- c(2001, 2002, 2003)
dates <- unlist(lapply(yrs, firstcatch))

ndt <- data.frame(Year = yrs, Date = dates)

Answer 5

您可以尝试以下操作：

df <- data %>% 
  group_by(Year) %>%
  mutate(newCol=Date[Catch>0][1]) %>%
  distinct(Year, newCol)

R功能，用于按年份确定第一个阳性观察结果

5 个答案:

数据