根据R中的多列查找数据框中的重复行 [英] Find duplicate rows in data frame based on multiple columns in r

问题描述

我有一个数据集，其中有一些实例，对于给定位置，同一日期和时间的值是不同的。我正在尝试创建一个显示这些实例的子集数据框。这是我的意思的示例：

I have a data set that has some instances where for a given location at the same date and time the value is different. I am trying to create a subset data frame showing these instances. This is an example of what I mean:

我在SO上看过类似的问题，但我可以似乎没有得到我想要的。我不断找回不是这种情况的实例。

I have looked at similar questions on SO but I can't seem to get what I want. I keep getting back instances where this isn't the case.

以下是我正在使用的代码：

dat1<-data_concern_join2%>%
 group_by(locid,stdate,sttime,charnam,valunit)%>%
  filter(n()>1) 

样本数据：

structure(list(orgid = c("USGS-NJ", "USGS-NJ", "USGS-NJ", "USGS-NJ", 
"USGS-NJ", "USGS-NJ", "USGS-NJ", "USGS-NJ", "USGS-NJ", "USGS-NJ", 
"USGS-NJ", "USGS-NJ", "USGS-NJ", "USGS-NJ", "USGS-NJ"), locid = c("USGS-01396030", 
"USGS-01396030", "USGS-01389850", "USGS-01389850", "USGS-01391500", 
"USGS-01391500", "USGS-01391500", "USGS-01391500", "USGS-01393960", 
"USGS-01390610", "USGS-01391500", "USGS-01390610", "USGS-01391500", 
"USGS-01378760", "USGS-01378760"), stdate = structure(c(11359, 
11359, 11359, 11359, 16504, 16504, 16112, 16112, 11367, 13860, 
12401, 13860, 16325, 13006, 13006), class = "Date"), sttime = structure(c(34200, 
34200, 36000, 36000, 40500, 40500, 39600, 39600, 36000, 39600, 
32400, 39600, 38400, 36900, 36900), class = c("hms", "difftime"
), units = "secs"), charnam = c("Specific conductance", "Specific conductance", 
"Specific conductance", "Specific conductance", "Specific conductance", 
"Specific conductance", "Specific conductance", "Specific conductance", 
"Specific conductance", "Specific conductance", "Specific conductance", 
"Specific conductance", "Specific conductance", "Specific conductance", 
"Specific conductance"), val = c(7450, 7300, 3210, 3180, 1930, 
1920, 1740, 1650, 1480, 1390, 1380, 1330, 1300, 1280, 1270), 
    valunit = c("uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", 
    "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", 
    "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", 
    "uS/cm @25C"), swqs = c("FW2-NT", "FW2-NT", "FW2-NT", "FW2-NT", 
    "FW2-NT", "FW2-NT", "FW2-NT", "FW2-NT", "FW2-NT", "FW2-NT", 
    "FW2-NT", "FW2-NT", "FW2-NT", "FW2-NT", "FW2-NT"), WMA = c(7L, 
    7L, 4L, 4L, 4L, 4L, 4L, 4L, 7L, 4L, 4L, 4L, 4L, 6L, 6L), 
    year = c(2001L, 2001L, 2001L, 2001L, 2015L, 2015L, 2014L, 
    2014L, 2001L, 2007L, 2003L, 2007L, 2014L, 2005L, 2005L), 
    HUC14 = c("HUC02030104050090", "HUC02030104050090", "HUC02030103120050", 
    "HUC02030103120050", "HUC02030103140070", "HUC02030103140070", 
    "HUC02030103140070", "HUC02030103140070", "HUC02030104050010", 
    "HUC02030103140010", "HUC02030103140070", "HUC02030103140010", 
    "HUC02030103140070", "HUC02030103010040", "HUC02030103010040"
    )), .Names = c("orgid", "locid", "stdate", "sttime", "charnam", 
"val", "valunit", "swqs", "WMA", "year", "HUC14"), row.names = c(NA, 
-15L), class = c("grouped_df", "tbl_df", "tbl", "data.frame"), vars = c("locid", 
"stdate", "sttime", "charnam", "valunit"), drop = TRUE, indices = list(
    13:14, 2:3, c(9L, 11L), 10L, 6:7, 12L, 4:5, 8L, 0:1), group_sizes = c(2L, 
2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L), biggest_group_size = 2L, labels = structure(list(
    locid = c("USGS-01378760", "USGS-01389850", "USGS-01390610", 
    "USGS-01391500", "USGS-01391500", "USGS-01391500", "USGS-01391500", 
    "USGS-01393960", "USGS-01396030"), stdate = structure(c(13006, 
    11359, 13860, 12401, 16112, 16325, 16504, 11367, 11359), class = "Date"), 
    sttime = structure(c(36900, 36000, 39600, 32400, 39600, 38400, 
    40500, 36000, 34200), class = c("hms", "difftime"), units = "secs"), 
    charnam = c("Specific conductance", "Specific conductance", 
    "Specific conductance", "Specific conductance", "Specific conductance", 
    "Specific conductance", "Specific conductance", "Specific conductance", 
    "Specific conductance"), valunit = c("uS/cm @25C", "uS/cm @25C", 
    "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", "uS/cm @25C", 
    "uS/cm @25C", "uS/cm @25C")), row.names = c(NA, -9L), class = "data.frame", vars = c("locid", 
"stdate", "sttime", "charnam", "valunit"), drop = TRUE, .Names = c("locid", 
"stdate", "sttime", "charnam", "valunit")))

推荐答案

我们可以做到

library(data.table)
unique(setDT(data_concern_join2), 
       by = c('locid', 'stdate', 'sttime', 'charnam', 'valunit'))

这篇关于根据R中的多列查找数据框中的重复行的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！