通过sapply从子集上的一个函数创建多个变量：结果不是真实的？

Question

介绍

# SAMPLE DATA
agyrw <- structure(list(company = c(28, 128, 22, 72, 62, 65, 132, 89, 46, 105), value.1993 = c(79272, 35850, 2124, 32, 0, 0, 0, 26359, 0, 0), value.1994 = c(103974, 10219, 31432, 0, 0, 0, 3997, 469, 0, 0)), .Names = c("company", "value.1993", "value.1994"), row.names = c(9L, 42L, 1L, 30L, 22L, 28L, 51L, 34L, 20L, 40L), class = "data.frame")

agyrw2 <- agyrw     # FOR A LATER COMPARISON

agyrw
#      company value.1993 value.1994
#         28      79272     103974
#        128      35850      10219
#         22       2124      31432
#         72         32          0
#         62          0          0
#         65          0          0
#        132          0       3997
#         89      26359        469
#         46          0          0
#        105          0          0

# SUM TOTAL VALUE BY YEAR
total.1993 <- sum(agyrw$value.1993)
total.1994 <- sum(agyrw$value.1994)

# CALCULATE THE MARKET SHARE FOR EACH IMPORTER, BY YEAR
agyrw$share.1993 <- agyrw$value.1993 / total.1993
agyrw$share.1994 <- agyrw$value.1994 / total.1994

# FORMAT THE MARKET SHARE VARIABLE TO ONLY FOUR DECIMAL PLACES
agyrw$share.1993 <- format(round(agyrw$share.1993, 4), nsmall = 4)
agyrw$share.1994 <- format(round(agyrw$share.1994, 4), nsmall = 4)

# RECONVERT THE MARKET SHARE VARIABLE BACK INTO NUMERIC
agyrw$share.1993 <- as.numeric(agyrw$share.1993)
agyrw$share.1994 <- as.numeric(agyrw$share.1994)

# VIEW
agyrw
#       company value.1993 value.1994 share.1993 share.1994
#          28      79272     103974     0.5519     0.6927
#         128      35850      10219     0.2496     0.0681
#          22       2124      31432     0.0148     0.2094
#          72         32          0     0.0002     0.0000
#          62          0          0     0.0000     0.0000
#          65          0          0     0.0000     0.0000
#         132          0       3997     0.0000     0.0266
#          89      26359        469     0.1835     0.0031
#          46          0          0     0.0000     0.0000
#         105          0          0     0.0000     0.0000

agyrw2$share <- sapply(agyrw2[,2:3], function(x) {
    total <- sum(x)
    share <- as.numeric(format(round(x/total, 4), nsmall = 4))
    return(share)
    }
       )

# VIEW
agyrw2
#      company value.1993 value.1994 share.value.1993 share.value.1994
#          28      79272     103974           0.5519           0.6927
#         128      35850      10219           0.2496           0.0681
#          22       2124      31432           0.0148           0.2094
#          72         32          0           0.0002           0.0000
#          62          0          0           0.0000           0.0000
#          65          0          0           0.0000           0.0000
#         132          0       3997           0.0000           0.0266
#          89      26359        469           0.1835           0.0031
#          46          0          0           0.0000           0.0000
#         105          0          0           0.0000           0.0000

names(agyrw)
#[1] "company"   "value.1993" "value.1994" "share.1993" "share.1994"
names(agyrw2)
#[1] "company"   "value.1993" "value.1994" "share"  

Answer 1

关于：

agyrw2 <- cbind(agyrw2,do.call(cbind, lapply(agyrw2[,2:3], function(x) {
    total <- sum(x)
    share <- as.numeric(format(round(x/total, 4), nsmall = 4))
    return(share)
    })))

或者简单地说：

agyrw2$share.1993 <- as.numeric(format(round(agyrw2$value.1993 / sum(agyrw2$value.1993), 4), nsmall = 4))
agyrw2$share.1994 <- as.numeric(format(round(agyrw2$value.1994 / sum(agyrw2$value.1994), 4), nsmall = 4))