library(plyr)
(mt = mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
## Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
## Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
## Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
## Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
## Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
## AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
## Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
## Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
## Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
## Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
## Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
## Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
## Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
## Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
# 将am变量因子化，并加上字符串标签
mt$am = factor(mt$am, labels = c("automatic", "manual"))
# numcolwise的作用类似于colwise函数（可查看?colwise），但它只对数值变量进行计算，而跳过分类变量，处理类型混杂的数据集非常方便
dlply(mt, .(am), numcolwise(mean))
## $automatic
## mpg cyl disp hp drat wt qsec vs gear carb
## 1 17.15 6.947 290.4 160.3 3.286 3.769 18.18 0.3684 3.211 2.737
##
## $manual
## mpg cyl disp hp drat wt qsec vs gear carb
## 1 24.39 5.077 143.5 126.8 4.05 2.411 17.36 0.5385 4.385 2.923
##
## attr(,"split_type")
## [1] "data.frame"
## attr(,"split_labels")
## am
## 1 automatic
## 2 manual
daply(mt, .(am), numcolwise(mean))
##
## am mpg cyl disp hp drat wt qsec vs gear carb
## automatic 17.15 6.947 290.4 160.3 3.286 3.769 18.18 0.3684 3.211 2.737
## manual 24.39 5.077 143.5 126.8 4.05 2.411 17.36 0.5385 4.385 2.923
ddply(mt, .(am), numcolwise(mean))
## am mpg cyl disp hp drat wt qsec vs gear carb
## 1 automatic 17.15 6.947 290.4 160.3 3.286 3.769 18.18 0.3684 3.211 2.737
## 2 manual 24.39 5.077 143.5 126.8 4.050 2.411 17.36 0.5385 4.385 2.923
# 增加一列分组标签
mt$class = ifelse(mt$wt <= 2, 1, ifelse(mt$wt > 2 & mt$wt <= 4, 2, 3))
mt$class = factor(mt$class, labels = c("wt<=2", "2<wt<=4", "wt>4"))
# 结果
dlply(mt, .(class), summarize, mean.mpg = mean(mpg))
## $`wt<=2`
## mean.mpg
## 1 30.5
##
## $`2<wt<=4`
## mean.mpg
## 1 19.54
##
## $`wt>4`
## mean.mpg
## 1 12.97
##
## attr(,"split_type")
## [1] "data.frame"
## attr(,"split_labels")
## class
## 1 wt<=2
## 2 2<wt<=4
## 3 wt>4
# 如果在daply函数中也使用summarize函数，输出结果会自动变成list形式，所以这里用了另一种方法
daply(mt, .(class), numcolwise(mean))[, 1, drop = F]
##
## class mpg
## wt<=2 30.5
## 2<wt<=4 19.54
## wt>4 12.97
ddply(mt, .(class), summarize, mean.mpg = mean(mpg))
## class mean.mpg
## 1 wt<=2 30.50
## 2 2<wt<=4 19.54
## 3 wt>4 12.97
daply(mt, .(am, class), summarize, mean.mpg = mean(mpg))
## class
## am wt<=2 2<wt<=4 wt>4
## automatic NULL 18.26 12.97
## manual 30.5 21.68 NULL
dlply(mt, .(am, class), summarize, mean.mpg = mean(mpg))
## $`automatic.2<wt<=4`
## mean.mpg
## 1 18.26
##
## $`automatic.wt>4`
## mean.mpg
## 1 12.97
##
## $`manual.wt<=2`
## mean.mpg
## 1 30.5
##
## $`manual.2<wt<=4`
## mean.mpg
## 1 21.68
##
## attr(,"split_type")
## [1] "data.frame"
## attr(,"split_labels")
## am class
## 1 automatic 2<wt<=4
## 2 automatic wt>4
## 3 manual wt<=2
## 4 manual 2<wt<=4
ddply(mt, .(am, class), summarize, mean.mpg = mean(mpg))
## am class mean.mpg
## 1 automatic 2<wt<=4 18.26
## 2 automatic wt>4 12.97
## 3 manual wt<=2 30.50
## 4 manual 2<wt<=4 21.68
ir = as.matrix(iris[, -5])
alply(ir, 2, mean, .dims = T)
## $Sepal.Length
## [1] 5.843
##
## $Sepal.Width
## [1] 3.057
##
## $Petal.Length
## [1] 3.758
##
## $Petal.Width
## [1] 1.199
##
## attr(,"split_type")
## [1] "array"
## attr(,"split_labels")
## X1
## 1 Sepal.Length
## 2 Sepal.Width
## 3 Petal.Length
## 4 Petal.Width
aaply(ir, 2, mean, .drop = T)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 5.843 3.057 3.758 1.199
adply(ir, 2, mean)
## X1 V1
## 1 Sepal.Length 5.843
## 2 Sepal.Width 3.057
## 3 Petal.Length 3.758
## 4 Petal.Width 1.199
# 或者用如下的简单办法
# colMeans(ir)
# 或笨办法
# do.call(colwise(mean),list(iris[,-5]))
# 以下2条语句结果略
alply(ir, 1, mean)
adply(ir, 1, mean)
aaply(ir, 1, mean)
## 1 2 3 4 5 6 7 8 9 10 11 12
## 2.550 2.375 2.350 2.350 2.550 2.850 2.425 2.525 2.225 2.400 2.700 2.500
## 13 14 15 16 17 18 19 20 21 22 23 24
## 2.325 2.125 2.800 3.000 2.750 2.575 2.875 2.675 2.675 2.675 2.350 2.650
## 25 26 27 28 29 30 31 32 33 34 35 36
## 2.575 2.450 2.600 2.600 2.550 2.425 2.425 2.675 2.725 2.825 2.425 2.400
## 37 38 39 40 41 42 43 44 45 46 47 48
## 2.625 2.500 2.225 2.550 2.525 2.100 2.275 2.675 2.800 2.375 2.675 2.350
## 49 50 51 52 53 54 55 56 57 58 59 60
## 2.675 2.475 4.075 3.900 4.100 3.275 3.850 3.575 3.975 2.900 3.850 3.300
## 61 62 63 64 65 66 67 68 69 70 71 72
## 2.875 3.650 3.300 3.775 3.350 3.900 3.650 3.400 3.600 3.275 3.925 3.550
## 73 74 75 76 77 78 79 80 81 82 83 84
## 3.800 3.700 3.725 3.850 3.950 4.100 3.725 3.200 3.200 3.150 3.400 3.850
## 85 86 87 88 89 90 91 92 93 94 95 96
## 3.600 3.875 4.000 3.575 3.500 3.325 3.425 3.775 3.400 2.900 3.450 3.525
## 97 98 99 100 101 102 103 104 105 106 107 108
## 3.525 3.675 2.925 3.475 4.525 3.875 4.525 4.150 4.375 4.825 3.400 4.575
## 109 110 111 112 113 114 115 116 117 118 119 120
## 4.200 4.850 4.200 4.075 4.350 3.800 4.025 4.300 4.200 5.100 4.875 3.675
## 121 122 123 124 125 126 127 128 129 130 131 132
## 4.525 3.825 4.800 3.925 4.450 4.550 3.900 3.950 4.225 4.400 4.550 5.025
## 133 134 135 136 137 138 139 140 141 142 143 144
## 4.250 3.925 3.925 4.775 4.425 4.200 3.900 4.375 4.450 4.350 3.875 4.550
## 145 146 147 148 149 150
## 4.550 4.300 3.925 4.175 4.325 3.950
# 或者用如下的简单办法
# rowMeans(ir)
plyr包提供的summarize(==summarise)函数可以计算一个数据框中变量的各种统计量。
max,min,mean,median,length,unique,fivenum,sqrt,lm等等，凡是能够用到数据集上的统计函数（参见library(help=“stats”)），通通都可以传给summarize函数，最后返回的是各个统计量组成的新数据框。
例如（见?summarise）：
summarise(baseball,
duration = max(year) - min(year),
nteams = length(unique(team)))
duration nteams
1 136 132
在**ply函数中，如果传入的第一个.fun参数是summarize，第二个及以后的.fun参数就都是传给summarize的统计量参数。
为了说明summarize函数的工作原理，我们依次运行以下三条语句：
# 这句表示分组之后什么也不做(.fun=NULL也可以)
dlply(mt, .(class), .fun = function(x) {
x
})
## $`wt<=2`
## mpg cyl disp hp drat wt qsec vs am gear carb class
## 1 30.4 4 75.7 52 4.93 1.615 18.52 1 manual 4 2 wt<=2
## 2 33.9 4 71.1 65 4.22 1.835 19.90 1 manual 4 1 wt<=2
## 3 27.3 4 79.0 66 4.08 1.935 18.90 1 manual 4 1 wt<=2
## 4 30.4 4 95.1 113 3.77 1.513 16.90 1 manual 5 2 wt<=2
##
## $`2<wt<=4`
## mpg cyl disp hp drat wt qsec vs am gear carb class
## 1 21.0 6 160.0 110 3.90 2.620 16.46 0 manual 4 4 2<wt<=4
## 2 21.0 6 160.0 110 3.90 2.875 17.02 0 manual 4 4 2<wt<=4
## 3 22.8 4 108.0 93 3.85 2.320 18.61 1 manual 4 1 2<wt<=4
## 4 21.4 6 258.0 110 3.08 3.215 19.44 1 automatic 3 1 2<wt<=4
## 5 18.7 8 360.0 175 3.15 3.440 17.02 0 automatic 3 2 2<wt<=4
## 6 18.1 6 225.0 105 2.76 3.460 20.22 1 automatic 3 1 2<wt<=4
## 7 14.3 8 360.0 245 3.21 3.570 15.84 0 automatic 3 4 2<wt<=4
## 8 24.4 4 146.7 62 3.69 3.190 20.00 1 automatic 4 2 2<wt<=4
## 9 22.8 4 140.8 95 3.92 3.150 22.90 1 automatic 4 2 2<wt<=4
## 10 19.2 6 167.6 123 3.92 3.440 18.30 1 automatic 4 4 2<wt<=4
## 11 17.8 6 167.6 123 3.92 3.440 18.90 1 automatic 4 4 2<wt<=4
## 12 17.3 8 275.8 180 3.07 3.730 17.60 0 automatic 3 3 2<wt<=4
## 13 15.2 8 275.8 180 3.07 3.780 18.00 0 automatic 3 3 2<wt<=4
## 14 32.4 4 78.7 66 4.08 2.200 19.47 1 manual 4 1 2<wt<=4
## 15 21.5 4 120.1 97 3.70 2.465 20.01 1 automatic 3 1 2<wt<=4
## 16 15.5 8 318.0 150 2.76 3.520 16.87 0 automatic 3 2 2<wt<=4
## 17 15.2 8 304.0 150 3.15 3.435 17.30 0 automatic 3 2 2<wt<=4
## 18 13.3 8 350.0 245 3.73 3.840 15.41 0 automatic 3 4 2<wt<=4
## 19 19.2 8 400.0 175 3.08 3.845 17.05 0 automatic 3 2 2<wt<=4
## 20 26.0 4 120.3 91 4.43 2.140 16.70 0 manual 5 2 2<wt<=4
## 21 15.8 8 351.0 264 4.22 3.170 14.50 0 manual 5 4 2<wt<=4
## 22 19.7 6 145.0 175 3.62 2.770 15.50 0 manual 5 6 2<wt<=4
## 23 15.0 8 301.0 335 3.54 3.570 14.60 0 manual 5 8 2<wt<=4
## 24 21.4 4 121.0 109 4.11 2.780 18.60 1 manual 4 2 2<wt<=4
##
## $`wt>4`
## mpg cyl disp hp drat wt qsec vs am gear carb class
## 1 16.4 8 275.8 180 3.07 4.070 17.40 0 automatic 3 3 wt>4
## 2 10.4 8 472.0 205 2.93 5.250 17.98 0 automatic 3 4 wt>4
## 3 10.4 8 460.0 215 3.00 5.424 17.82 0 automatic 3 4 wt>4
## 4 14.7 8 440.0 230 3.23 5.345 17.42 0 automatic 3 4 wt>4
##
## attr(,"split_type")
## [1] "data.frame"
## attr(,"split_labels")
## class
## 1 wt<=2
## 2 2<wt<=4
## 3 wt>4
# 从分组后的几个数据框中分别取出mpg列
dlply(mt, .(class), summarize, mpg)
## $`wt<=2`
## ..1
## 1 30.4
## 2 33.9
## 3 27.3
## 4 30.4
##
## $`2<wt<=4`
## ..1
## 1 21.0
## 2 21.0
## 3 22.8
## 4 21.4
## 5 18.7
## 6 18.1
## 7 14.3
## 8 24.4
## 9 22.8
## 10 19.2
## 11 17.8
## 12 17.3
## 13 15.2
## 14 32.4
## 15 21.5
## 16 15.5
## 17 15.2
## 18 13.3
## 19 19.2
## 20 26.0
## 21 15.8
## 22 19.7
## 23 15.0
## 24 21.4
##
## $`wt>4`
## ..1
## 1 16.4
## 2 10.4
## 3 10.4
## 4 14.7
##
## attr(,"split_type")
## [1] "data.frame"
## attr(,"split_labels")
## class
## 1 wt<=2
## 2 2<wt<=4
## 3 wt>4
# 对取出的mpg列求均值
dlply(mt, .(class), summarize, mean(mpg))
## $`wt<=2`
## ..1
## 1 30.5
##
## $`2<wt<=4`
## ..1
## 1 19.54
##
## $`wt>4`
## ..1
## 1 12.97
##
## attr(,"split_type")
## [1] "data.frame"
## attr(,"split_labels")
## class
## 1 wt<=2
## 2 2<wt<=4
## 3 wt>4
这就相当于用一个函数取数据框中的变量，再求这个变量的统计量，也就是用fun(dataframe, variable)的形式返回一个变量的数据列。
上面的最后一条语句相当于对每一个分组都进行类似下面的操作：
summarize(subset(mt,class==1), mean(mpg))
而一般我们用基础R包做的时候，只能用方括号的操作stats_func(dataframe[, variable])（例如mean(mt[mt$class==1,“mpg”,drop=F])）。这种形式不利于函数式的处理，无法应用在d*ply函数中。