高效和选择性地组合R中的列

我有以下数据

countrycols = alljson[,c("country_gc_str","country_ipapi_str","country_tm_str")]

head(countrycols)
country_gc_str country_ipapi_str country_tm_str
1           <NA>                RU             RU
2           <NA>                CN             CN
3             US                US             US
4           <NA>                CD             CG
5           <NA>                DE             DE
6           <NA>              <NA>             NG

我还使用以下数据来描述国家收入水平：

wbURL <- "http://api.worldbank.org/countries?per_page=304"
xmlAPI <- xmlParse(wbURL)
xmlDF <- xmlToDataFrame(xmlAPI)
xmlDF$iso2CodeChar <- as.character(xmlDF$iso2Code)
xmlDF$incomeLevelChar <- as.character(xmlDF$incomeLevel)
incomexml <- xmlDF[,c("iso2CodeChar","incomeLevelChar")]
incomexmltable <- as.data.table(incomexml)

---

在三个变量中选取第一个非缺失值后，尝试使用矩阵索引：

countrycols[
  cbind(
    seq_len(nrow(countrycols)), 
    max.col(replace( -col(countrycols), is.na(countrycols), -Inf))
  )
]
#[1] "RU" "CN" "US" "CD" "DE" "NG"

要解释逻辑，请分解每一行：

-col(countrycols)
#     [,1] [,2] [,3]
#[1,]   -1   -2   -3
#[2,]   -1   -2   -3
#[3,]   -1   -2   -3
#[4,]   -1   -2   -3
#[5,]   -1   -2   -3
#[6,]   -1   -2   -3

replace( -col(countrycols), is.na(countrycols), -Inf)
#     [,1] [,2] [,3]
#[1,] -Inf   -2   -3
#[2,] -Inf   -2   -3
#[3,]   -1   -2   -3
#[4,] -Inf   -2   -3
#[5,] -Inf   -2   -3
#[6,] -Inf -Inf   -3

(colindex <- max.col(replace( -col(countrycols), is.na(countrycols), -Inf)) )
#[1] 2 2 1 2 2 3

cbind(rowindex=seq_len(nrow(countrycols)), colindex)
#     rowindex colindex
#[1,]        1        2
#[2,]        2        2
#[3,]        3        1
#[4,]        4        2
#[5,]        5        2
#[6,]        6        3

---

在三个变量中选取第一个非缺失值后，尝试使用矩阵索引：

countrycols[
  cbind(
    seq_len(nrow(countrycols)), 
    max.col(replace( -col(countrycols), is.na(countrycols), -Inf))
  )
]
#[1] "RU" "CN" "US" "CD" "DE" "NG"

要解释逻辑，请分解每一行：

-col(countrycols)
#     [,1] [,2] [,3]
#[1,]   -1   -2   -3
#[2,]   -1   -2   -3
#[3,]   -1   -2   -3
#[4,]   -1   -2   -3
#[5,]   -1   -2   -3
#[6,]   -1   -2   -3

replace( -col(countrycols), is.na(countrycols), -Inf)
#     [,1] [,2] [,3]
#[1,] -Inf   -2   -3
#[2,] -Inf   -2   -3
#[3,]   -1   -2   -3
#[4,] -Inf   -2   -3
#[5,] -Inf   -2   -3
#[6,] -Inf -Inf   -3

(colindex <- max.col(replace( -col(countrycols), is.na(countrycols), -Inf)) )
#[1] 2 2 1 2 2 3

cbind(rowindex=seq_len(nrow(countrycols)), colindex)
#     rowindex colindex
#[1,]        1        2
#[2,]        2        2
#[3,]        3        1
#[4,]        4        2
#[5,]        5        2
#[6,]        6        3

---

您看过

WDI

软件包了吗？很好。你看过

WDI

软件包了吗？这是一个好的。

-col(countrycols)
#     [,1] [,2] [,3]
#[1,]   -1   -2   -3
#[2,]   -1   -2   -3
#[3,]   -1   -2   -3
#[4,]   -1   -2   -3
#[5,]   -1   -2   -3
#[6,]   -1   -2   -3

replace( -col(countrycols), is.na(countrycols), -Inf)
#     [,1] [,2] [,3]
#[1,] -Inf   -2   -3
#[2,] -Inf   -2   -3
#[3,]   -1   -2   -3
#[4,] -Inf   -2   -3
#[5,] -Inf   -2   -3
#[6,] -Inf -Inf   -3

(colindex <- max.col(replace( -col(countrycols), is.na(countrycols), -Inf)) )
#[1] 2 2 1 2 2 3

cbind(rowindex=seq_len(nrow(countrycols)), colindex)
#     rowindex colindex
#[1,]        1        2
#[2,]        2        2
#[3,]        3        1
#[4,]        4        2
#[5,]        5        2
#[6,]        6        3

structure(list(country_gc_str = c(NA, NA, "US", NA, NA, NA), 
    country_ipapi_str = c("RU", "CN", "US", "CD", "DE", NA), 
    country_tm_str = c("RU", "CN", "US", "CG", "DE", "NG")), .Names = c("country_gc_str", 
"country_ipapi_str", "country_tm_str"), row.names = c("1", "2", 
"3", "4", "5", "6"), class = "data.frame")