Visible to members of this folder
lapply(X, FUN, ...)
# 函數結構
> lapply
function (X, FUN, ...)
{
FUN <- match.fun(FUN)
if (!is.vector(X) || is.object(X))
X <- as.list(X)
.Internal(lapply(X, FUN))
}
<bytecode: 0x003ece40>
<environment: namespace:base>
>
# 建立由兩個元素組成的列表"x"
# "a": 一個"1~5"的數列向量、"b": 10個隨機組成的向量
> x <- list(a = 1:5, b = rnorm(10))
> lapply(x, mean) # 利用"lapply()"對每個元素使用"mean(取均值)"函數
$a
[1] 3
$b
[1] -0.4332761
# 建立由四個元素組成的列表"x"
# "a": 一個"1~4"的數列向量
# "b": 10個隨機組成的向量
# "c":
> x <- list(a = 1:4, b = rnorm(10), c = rnorm(20, 1), d = rnorm(100, 5))
> lapply(x, mean)
[1] 2.5
[1] 0.4491021
$c
[1] 0.7762638
$d
[1] 4.970049
> x <- 1:4 # 建立一個"1~4"的數列向量
> lapply(x, runif)
[[1]] # runif(1) -- 產生 1 個均勻隨機數所組成的向量
[1] 0.5073698
[[2]] # runif(2) -- 產生 2 個均勻隨機數所組成的向量
[1] 0.5588365 0.7042169
[[3]] # runif(3) -- 產生 3 個均勻隨機數所組成的向量
[1] 0.5684885 0.9129467 0.1270256
[[4]] # runif(4) -- 產生 4 個均勻隨機數所組成的向量
[1] 0.70262592 0.05725111 0.48480334
[4] 0.63522292
> x <- 1:4
> lapply(x, runif, min = 0, max = 10)
[1] 0.4063026
[1] 1.021453 7.277391
[1] 0.4952116 1.7786254 5.8042937
[1] 3.628411 6.368390 2.289686 4.208043
> x <- list(a = matrix(1:4, 2, 2), b = matrix(1:6, 3, 2))
> x
[,1] [,2]
[1,] 1 3
[2,] 2 4
[1,] 1 4
[2,] 2 5
[3,] 3 6
> lapply(x, function(elt) elt[,1]) # 提取這兩個矩陣的第一列
[1] 1 2
[1] 1 2 3
[1] -0.2601113
[1] 0.9847573
[1] 4.924048
> sapply(x, mean)
a b c d
2.5000000 -0.2601113 0.9847573 4.9240476
> mean(x)
[1] NA
Warning message:
In mean.default(x) : argument is not numeric or logical: returning NA
apply(X, MARGIN, FUN, ...)
> str(apply)
function (X, MARGIN, FUN, ...)
# 建立一個"20行10列的矩陣"，矩陣裡是正態隨機產生的數字
> x <- matrix(rnorm(200), 20, 10)
> # 對所有"列"取平均值
> apply(x, 2, mean) # 保留第2維度(列)、去掉第1維度(行)
[1] 0.11502305 0.08063431 -0.19797862
[4] 0.11195242 -0.02087351 -0.10817816
[7] 0.03090089 -0.15335343 -0.05113633
[10] -0.12698686
> # 對所有"行"取總和
> apply(x, 1, sum) # 保留第1維度(行)、去掉第2維度(列)
[1] 1.1814590 0.4222659 -0.2816117
[4] -6.9120684 -4.0285659 -1.6902687
[7] 2.8261779 1.1060187 0.2605618
[10] -1.6894040 -1.7529009 1.7913958
[13] 0.6159366 -1.3019515 -3.4323064
[16] -1.3998466 2.1456304 1.6717134
[19] -0.4670733 4.5349132
# 使用"quantile()"計算每一行的25和75百分位數
> x <- matrix(rnorm(200), 20, 10) # 產生正態隨機分佈的數字
> apply(x, 1, quantile, probs = c(0.25, 0.75))
[,1] [,2] [,3]
25% -0.2149464 -0.2594548 -0.3561782
75% 0.8696909 0.2799249 0.4112624
[,4] [,5] [,6]
25% -0.6297229 -0.6243486 -0.5973480
75% 0.7634970 1.4804738 0.2396187
[,7] [,8] [,9]
25% -0.6365716 -0.05352821 -0.8346142
75% 0.5377081 0.32721302 0.6480853
[,10] [,11] [,12]
25% -0.2800897 0.2057999 -1.0142844
75% 0.6809832 0.7926215 0.9863733
[,13] [,14] [,15]
25% -0.3001848 -0.81376360 -0.3670811
75% 0.9853322 0.03450025 0.9590299
[,16] [,17] [,18]
25% -1.1587829 -0.6578810 -0.09577613
75% 0.4649419 0.8673224 0.27722560
[,19] [,20]
25% -0.7001218 -0.2333230
75% 0.4112067 0.1800692
# 建立一個"2行兩2"、"第3維度為10"的陣列
> a <- array(rnorm(2*2*10), c(2, 2, 10))
> apply(a, c(1, 2), mean) # 保留第1和第2個維度、消除第3個維度，並取得平均值
[1,] -0.02447451 0.81527620
[2,] -0.55271819 0.03986751
> rowMeans(a, dims = 2)
整理自 R Programming (Week 3) -- Loop Functions (1)
（一）Loop Functions - lapply
lapply(X, FUN, ...)# 函數結構> lapplyfunction (X, FUN, ...){ FUN <- match.fun(FUN) if (!is.vector(X) || is.object(X)) X <- as.list(X) .Internal(lapply(X, FUN))}<bytecode: 0x003ece40><environment: namespace:base>># 建立由兩個元素組成的列表"x"# "a": 一個"1~5"的數列向量、"b": 10個隨機組成的向量> x <- list(a = 1:5, b = rnorm(10))>> lapply(x, mean) # 利用"lapply()"對每個元素使用"mean(取均值)"函數$a[1] 3$b[1] -0.4332761># 建立由四個元素組成的列表"x"# "a": 一個"1~4"的數列向量# "b": 10個隨機組成的向量# "c":> x <- list(a = 1:4, b = rnorm(10), c = rnorm(20, 1), d = rnorm(100, 5))>> lapply(x, mean)$a[1] 2.5$b[1] 0.4491021$c[1] 0.7762638$d[1] 4.970049>> x <- 1:4 # 建立一個"1~4"的數列向量>> lapply(x, runif)[[1]] # runif(1) -- 產生 1 個均勻隨機數所組成的向量[1] 0.5073698[[2]] # runif(2) -- 產生 2 個均勻隨機數所組成的向量[1] 0.5588365 0.7042169[[3]] # runif(3) -- 產生 3 個均勻隨機數所組成的向量[1] 0.5684885 0.9129467 0.1270256[[4]] # runif(4) -- 產生 4 個均勻隨機數所組成的向量[1] 0.70262592 0.05725111 0.48480334[4] 0.63522292>> x <- 1:4>> lapply(x, runif, min = 0, max = 10)[[1]] # runif(1) -- 產生 1 個均勻隨機數所組成的向量[1] 0.4063026[[2]] # runif(2) -- 產生 2 個均勻隨機數所組成的向量[1] 1.021453 7.277391[[3]] # runif(3) -- 產生 3 個均勻隨機數所組成的向量[1] 0.4952116 1.7786254 5.8042937[[4]] # runif(4) -- 產生 4 個均勻隨機數所組成的向量[1] 3.628411 6.368390 2.289686 4.208043>> x <- list(a = matrix(1:4, 2, 2), b = matrix(1:6, 3, 2))>> x$a [,1] [,2][1,] 1 3[2,] 2 4$b [,1] [,2][1,] 1 4[2,] 2 5[3,] 3 6> lapply(x, function(elt) elt[,1]) # 提取這兩個矩陣的第一列$a[1] 1 2$b[1] 1 2 3>> x <- list(a = 1:4, b = rnorm(10), c = rnorm(20, 1), d = rnorm(100, 5))> lapply(x, mean)$a[1] 2.5$b[1] -0.2601113$c[1] 0.9847573$d[1] 4.924048>>> sapply(x, mean) a b c d 2.5000000 -0.2601113 0.9847573 4.9240476>> mean(x)[1] NAWarning message:In mean.default(x) : argument is not numeric or logical: returning NA>（二）Loop Functions - apply
apply(X, MARGIN, FUN, ...)# 函數結構> str(apply)function (X, MARGIN, FUN, ...)# 建立一個"20行10列的矩陣"，矩陣裡是正態隨機產生的數字> x <- matrix(rnorm(200), 20, 10)>> # 對所有"列"取平均值> apply(x, 2, mean) # 保留第2維度(列)、去掉第1維度(行) [1] 0.11502305 0.08063431 -0.19797862 [4] 0.11195242 -0.02087351 -0.10817816 [7] 0.03090089 -0.15335343 -0.05113633[10] -0.12698686>> # 對所有"行"取總和> apply(x, 1, sum) # 保留第1維度(行)、去掉第2維度(列) [1] 1.1814590 0.4222659 -0.2816117 [4] -6.9120684 -4.0285659 -1.6902687 [7] 2.8261779 1.1060187 0.2605618[10] -1.6894040 -1.7529009 1.7913958[13] 0.6159366 -1.3019515 -3.4323064[16] -1.3998466 2.1456304 1.6717134[19] -0.4670733 4.5349132># 使用"quantile()"計算每一行的25和75百分位數> x <- matrix(rnorm(200), 20, 10) # 產生正態隨機分佈的數字> apply(x, 1, quantile, probs = c(0.25, 0.75)) [,1] [,2] [,3]25% -0.2149464 -0.2594548 -0.356178275% 0.8696909 0.2799249 0.4112624 [,4] [,5] [,6]25% -0.6297229 -0.6243486 -0.597348075% 0.7634970 1.4804738 0.2396187 [,7] [,8] [,9]25% -0.6365716 -0.05352821 -0.834614275% 0.5377081 0.32721302 0.6480853 [,10] [,11] [,12]25% -0.2800897 0.2057999 -1.014284475% 0.6809832 0.7926215 0.9863733 [,13] [,14] [,15]25% -0.3001848 -0.81376360 -0.367081175% 0.9853322 0.03450025 0.9590299 [,16] [,17] [,18]25% -1.1587829 -0.6578810 -0.0957761375% 0.4649419 0.8673224 0.27722560 [,19] [,20]25% -0.7001218 -0.233323075% 0.4112067 0.1800692># 建立一個"2行兩2"、"第3維度為10"的陣列> a <- array(rnorm(2*2*10), c(2, 2, 10))> apply(a, c(1, 2), mean) # 保留第1和第2個維度、消除第3個維度，並取得平均值 [,1] [,2][1,] -0.02447451 0.81527620[2,] -0.55271819 0.03986751>>> rowMeans(a, dims = 2) [,1] [,2][1,] -0.02447451 0.81527620[2,] -0.55271819 0.03986751>