前言

虽然但是，还是系统的学了一遍R。但实际体验下来，感觉和Python的pandas包非常的类似，感觉天下的统计的语言都是一家。

视频教程链接

基本数据结构

向量

基本概念

数值型

1
> x <- c(1, 2, 3, 4, 5)

字符串型

1
> y <- c("one", "two", "three")

逻辑型(全部大写)

1
2
> z <- c (T, F, T)
> z <- c (TRUE, FALSE, T)

等差数列

1
2
> c(1:10)
 [1]  1  2  3  4  5  6  7  8  9 10

seq()函数

生成等差数列，from与to控制起始与终点，by控制数列间距，length.out控制数列个数

1
2
3
4
> seq(from = 1, to = 10, by = 5)
[1] 1 6
> seq(from = 1,to =10 , length.out=10)
 [1]  1  2  3  4  5  6  7  8  9 10

rep()函数

重复生成向量，重复项可以是数值也可以是数组

1
2
3
4
5
> rep(2, 5)
[1] 2 2 2 2 2
> x <- c(1, 2, 3, 4, 5)
> rep(x, 3)
 [1] 1 2 3 4 5 1 2 3 4 5 1 2 3 4 5
1
2
3
4
5
6
> rep(x, each = 5)
 [1] 1 1 1 1 1 2 2 2 2 2 3 3 3 3 3 4 4 4 4 4 5 5 5 5 5
> x <- c(1, 2, 3, 4, 5)
> rep(x, each = 3, times = 2)
 [1] 1 1 1 2 2 2 3 3 3 4 4 4 5 5 5 1 1 1 2 2 2 3 3 3 4 4
[27] 4 5 5 5

变量转换

数值型变量统一转换为字符串型变量

1
2
3
4
5
> a <- c(1, 2, "three")
> a
[1] "1"     "2"     "three"
> mode(a)
[1] "character"

向量索引

整数索引

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
> x <- c(1:10)
> x
 [1]  1  2  3  4  5  6  7  8  9 10
> length(x)
[1] 10
> x[1]
[1] 1
> x[0]
integer(0)
> x[-5]
[1]  1  2  3  4  6  7  8  9 10
> x[c(2:8)]
[1] 2 3 4 5 6 7 8
> x[c(1, 5, 9)]
[1] 1 5 9

逻辑向量索引

数值向量

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> x <- c(1:10)
> x
 [1]  1  2  3  4  5  6  7  8  9 10
> x[c(T, F, T, T, F, F, T, T, T, F)]
[1] 1 3 4 7 8 9
> x[c(T)]
 [1]  1  2  3  4  5  6  7  8  9 10
> x[c(F)]
integer(0)
> x[c(T, F)]
[1] 1 3 5 7 9
> x[c(T, F, F)]
[1]  1  4  7 10
> x[c(T, F, T, T, F, F, T, T, T, F, T)]
[1]  1  3  4  7  8  9 NA
> x[x > 3 & x < 7]
[1] 4 5 6

字符串向量

1
2
3
4
5
6
7
8
9
10
11
12
> x <- c("one", "two", "three", "four", "five")
> "one" %in% x
[1] TRUE
> x["one" %in% x]
[1] "one"   "two"   "three" "four"  "five" 
> x %in% c("one", "three")
[1]  TRUE FALSE  TRUE FALSE FALSE
> x[x %in% c("one", "three")]
[1] "one"   "three"
> k <- x %in% c("one", "three")
> x[k]
[1] "one"   "three"

名称索引

1
2
3
4
5
6
7
8
9
10
11
12
> x <- c(1:5)
> names(x)
NULL
> names(x) <- c("one" , "two", "three", "four" , "five")
> names(x)
[1] "one"   "two"   "three" "four"  "five" 
> x
  one   two three  four  five 
    1     2     3     4     5 
> x["two"]
two 
  2

修改向量值

添加值

1
2
3
4
5
6
7
8
9
10
11
12
13
> x <- c(1:5)
> x
[1] 1 2 3 4 5
> x[6] = 6
> x
[1] 1 2 3 4 5 6
> x[c(7, 8, 9)] <- c(7, 8, 9)
> x
[1] 1 2 3 4 5 6 7 8 9
> x[20] = 20
> x
 [1]  1  2  3  4  5  6  7  8  9 NA NA NA NA NA NA NA NA
[18] NA NA 20

append函数

1
2
3
4
5
6
> append(x = x, values = 10, after = 9)
 [1]  1  2  3  4  5  6  7  8  9 10 NA NA NA NA NA NA NA
[18] NA NA NA 20
> append(x = x,values = -99,after = 0)
 [1] -99   1   2   3   4   5   6   7   8   9  NA  NA  NA
[14]  NA  NA  NA  NA  NA  NA  NA  20

删除向量

1
2
3
> rm(x)
> x
Error: object 'x' not found

删除值

1
2
3
4
5
6
7
8
9
> x <- c(1:10)
> x
 [1]  1  2  3  4  5  6  7  8  9 10
> x <- x[-4]
> x
[1]  1  2  3  5  6  7  8  9 10
> x <- x[-c(2:4)]
> x
[1]  1  6  7  8  9 10

通过索引修改值

1
2
3
4
5
6
7
8
9
> x <- c(1:5)
> names(x) <- c("one" , "two", "three", "four" , "five")
> x
  one   two three  four  five 
    1     2     3     4     5 
> x["four"] <- -99
> x
  one   two three  four  five 
    1     2     3   -99     5

数值型的向量，不能赋值给字符串，会把整个向量变成字符型向量

1
2
3
4
5
6
7
> x <- c(1:5)
> x[3] <- -99
> x
[1]   1   2 -99   4   5
> x[4] <- "four"
> x
[1] "1"    "2"    "-99"  "four" "5"

向量运算

数值运算

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> x <- 1:10
> x
 [1]  1  2  3  4  5  6  7  8  9 10
> x + 1
 [1]  2  3  4  5  6  7  8  9 10 11
> x - 3
 [1] -2 -1  0  1  2  3  4  5  6  7
> x <- x + 1
> x
 [1]  2  3  4  5  6  7  8  9 10 11
> y <- seq(2, 20, length.out = 10)
> y
 [1]  2  4  6  8 10 12 14 16 18 20
> x - y
 [1]  0 -1 -2 -3 -4 -5 -6 -7 -8 -9
> x * y
 [1]   4  12  24  40  60  84 112 144 180 220

幂运算：** 求余运算：%% 整除运算：%/%

1
2
3
4
5
6
7
8
9
10
11
> x
 [1]  2  3  4  5  6  7  8  9 10 11
> y
 [1]  2  4  6  8 10 12 14 16 18 20
> x ** y
 [1] 4.000000e+00 8.100000e+01 4.096000e+03 3.906250e+05 6.046618e+07 1.384129e+10 4.398047e+12
 [8] 1.853020e+15 1.000000e+18 6.727500e+20
> x %% y
 [1]  0  3  4  5  6  7  8  9 10 11
> y %/% x
 [1] 1 1 1 1 1 1 1 1 1 1

对应位置进行运算，若向量长度不同，则长向量的长度必须是短向量的整数倍

1
2
3
4
5
6
7
8
9
10
11
12
13
> x <- c(1, 3)
> y <- c(2:11)
> x
[1] 1 3
> y
 [1]  2  3  4  5  6  7  8  9 10 11
> x + y
 [1]  3  6  5  8  7 10  9 12 11 14
> z <- c(1, 2, 3)
> x + z
[1] 2 5 4
Warning message:
In x + z : longer object length is not a multiple of shorter object length

逻辑运算

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
> y <- c(5:-5)
> x <- c(0:10)
> x
 [1]  0  1  2  3  4  5  6  7  8  9 10
> x > 5
 [1] FALSE FALSE FALSE FALSE FALSE FALSE  TRUE
 [8]  TRUE  TRUE  TRUE  TRUE
> y <- c(5:-5)
> x > y
 [1] FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE
 [8]  TRUE  TRUE  TRUE  TRUE
> x == y
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE
 [8] FALSE FALSE FALSE FALSE
> c(1,2,3) %in% c(2,3,6,3)
[1] FALSE  TRUE  TRUE

数学运算符

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
> x <- c(-5:5)
> x
 [1] -5 -4 -3 -2 -1  0  1  2  3  4  5
> abs(x)
 [1] 5 4 3 2 1 0 1 2 3 4 5
> sqrt(x)
 [1]      NaN      NaN      NaN      NaN      NaN 0.000000 1.000000 1.414214 1.732051 2.000000
[11] 2.236068
Warning message:
In sqrt(x) : NaNs produced
> sqrt(abs(x))
 [1] 2.236068 2.000000 1.732051 1.414214 1.000000 0.000000 1.000000 1.414214 1.732051 2.000000
[11] 2.236068
> log(x, base = 3)
 [1]       NaN       NaN       NaN       NaN       NaN      -Inf 0.0000000 0.6309298 1.0000000
[10] 1.2618595 1.4649735
Warning message:
NaNs produced 
> log(abs(x) + 1, base = 3)
 [1] 1.6309298 1.4649735 1.2618595 1.0000000 0.6309298 0.0000000 0.6309298 1.0000000 1.2618595
[10] 1.4649735 1.6309298
> exp(x)
 [1] 6.737947e-03 1.831564e-02 4.978707e-02 1.353353e-01 3.678794e-01 1.000000e+00 2.718282e+00
 [8] 7.389056e+00 2.008554e+01 5.459815e+01 1.484132e+02
> sin(x)
 [1]  0.9589243  0.7568025 -0.1411200 -0.9092974 -0.8414710  0.0000000  0.8414710  0.9092974
 [9]  0.1411200 -0.7568025 -0.9589243
> cos(x)
 [1]  0.2836622 -0.6536436 -0.9899925 -0.4161468  0.5403023  1.0000000  0.5403023 -0.4161468
 [9] -0.9899925 -0.6536436  0.2836622

ceiling()不小于x的最小整数，floor()函数不大于x的最大整数

1
2
3
4
5
6
7
8
9
10
> ceiling(c(-2.3, 3.1415))
[1] -2  4
> floor(c(-2.3, 3.1415))
[1] -3  3
> round(c(-2.3, 3.1415))
[1] -2  3
> round(c(-2.3, 3.1415), digits = 2)
[1] -2.30  3.14
> signif(c(-2.3, 3.1415), digits = 2)
[1] -2.3  3.1

统计函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
> vec <- c(1:100)
> vec
  [1]   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21  22
 [23]  23  24  25  26  27  28  29  30  31  32  33  34  35  36  37  38  39  40  41  42  43  44
 [45]  45  46  47  48  49  50  51  52  53  54  55  56  57  58  59  60  61  62  63  64  65  66
 [67]  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88
 [89]  89  90  91  92  93  94  95  96  97  98  99 100
> sum(vec)
[1] 5050
> max(vec)
[1] 100
> min(vec)
[1] 1
> mean(vec)
[1] 50.5
> var(vec)
[1] 841.6667
> round(var(vec), digits = 2)
[1] 841.67
> sd(vec)
[1] 29.01149
> prod(vec)
[1] 9.332622e+157
> median(vec)
[1] 50.5
> quantile(vec)
    0%    25%    50%    75%   100% 
  1.00  25.75  50.50  75.25 100.00 
> quantile(vec, c(0.4, 0.5, 0.8))
 40%  50%  80% 
40.6 50.5 80.2 
1
2
3
4
5
6
7
8
9
10
> t <- c(1, 2, 4, 6, 7,-2)
> which.max(t)
[1] 5
> which.min(t)
[1] 6
> t[which(t == 7)]
[1] 7
> t[which(t > 5)]
[1] 6 7

多维向量

矩阵

1
2
3
4
5
6
7
> m <- matrix(1:20, nrow = 4, ncol = 5)
> m
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

默认按列进行分布

1
2
3
4
5
6
7
> m <- matrix(1:20, 4)
> m
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

按行分布

1
2
3
4
5
6
7
> m <- matrix(1:20, 4, byrow = T)
> m
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    2    3    4    5
[2,]    6    7    8    9   10
[3,]   11   12   13   14   15
[4,]   16   17   18   19   20

按列分布

1
2
3
4
5
6
7
> m <- matrix(1:20, 4, byrow = F)
> m
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

定义矩阵行与列的名字

1
2
3
4
5
6
7
8
9
> rnames <- c("R1", "R2", "R3", "R4")
> cnames <- c("C1", "C2", "C3", "C4", "C5")
> dimnames(m) <- list(rnames, cnames)
> m
   C1 C2 C3 C4 C5
R1  1  5  9 13 17
R2  2  6 10 14 18
R3  3  7 11 15 19
R4  4  8 12 16 20

矩阵维数

1
2
> dim(m)
[1] 4 5

使向量转化为矩阵

1
2
3
4
5
6
7
8
> x <- c(1:20)
> dim(x) <- c(4:5)
> x
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

多维数组

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
> x <- c(1:20)
> dim(x) <- c(2, 2, 5)
> x
, , 1

     [,1] [,2]
[1,]    1    3
[2,]    2    4

, , 2

     [,1] [,2]
[1,]    5    7
[2,]    6    8

, , 3

     [,1] [,2]
[1,]    9   11
[2,]   10   12

, , 4

     [,1] [,2]
[1,]   13   15
[2,]   14   16

, , 5

     [,1] [,2]
[1,]   17   19
[2,]   18   20

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
> dim1 <- c("A1", "A2")
> dim2 <- c("B1", "B2", "B3")
> dim3 <- c("C1", "C2", "C3", "C4")
> z <- array(1:24, c(2, 3, 4), dimnames = list(dim1, dim2, dim3))
> z
, , C1

   B1 B2 B3
A1  1  3  5
A2  2  4  6

, , C2

   B1 B2 B3
A1  7  9 11
A2  8 10 12

, , C3

   B1 B2 B3
A1 13 15 17
A2 14 16 18

, , C4

   B1 B2 B3
A1 19 21 23
A2 20 22 24

索引

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
> m <- matrix(1:20, 4, 5, byrow = T)
> m
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    2    3    4    5
[2,]    6    7    8    9   10
[3,]   11   12   13   14   15
[4,]   16   17   18   19   20
> m[2, 5]
[1] 10
> m[2, c(2, 3, 5)]
[1]  7  8 10
> m[c(2:4), c(4, 5)]
     [,1] [,2]
[1,]    9   10
[2,]   14   15
[3,]   19   20
> m[3,]
[1] 11 12 13 14 15
> m[, 3]
[1]  3  8 13 18
> m[2]
[1] 6
> m[-1, 2]
[1]  7 12 17
1
2
3
4
5
6
7
8
9
10
11
> rnames <- c("R1", "R2", "R3", "R4")
> cnames <- c("C1", "C2", "C3", "C4", "C5")
> dimnames(m) <- list(rnames, cnames)
> m
   C1 C2 C3 C4 C5
R1  1  2  3  4  5
R2  6  7  8  9 10
R3 11 12 13 14 15
R4 16 17 18 19 20
> m["R2", "C5"]
[1] 10

矩阵的运算

四则运算

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
> rnames <- c("R1", "R2", "R3", "R4")
> cnames <- c("C1", "C2", "C3", "C4", "C5")
> dimnames(m) <- list(rnames, cnames)
> m
   C1 C2 C3 C4 C5
R1  1  2  3  4  5
R2  6  7  8  9 10
R3 11 12 13 14 15
R4 16 17 18 19 20
> m + 1
   C1 C2 C3 C4 C5
R1  2  3  4  5  6
R2  7  8  9 10 11
R3 12 13 14 15 16
R4 17 18 19 20 21
> m * 2
   C1 C2 C3 C4 C5
R1  2  4  6  8 10
R2 12 14 16 18 20
R3 22 24 26 28 30
R4 32 34 36 38 40
> m + m
   C1 C2 C3 C4 C5
R1  2  4  6  8 10
R2 12 14 16 18 20
R3 22 24 26 28 30
R4 32 34 36 38 40
> n <- matrix(1:20, 5, 4)
> n
     [,1] [,2] [,3] [,4]
[1,]    1    6   11   16
[2,]    2    7   12   17
[3,]    3    8   13   18
[4,]    4    9   14   19
[5,]    5   10   15   20
> m + n
Error in m + n : non-conformable arrays

矩阵函数

1
2
3
4
5
6
rnames <- c("R1", "R2", "R3", "R4")
cnames <- c("C1", "C2", "C3", "C4", "C5")
dimnames(m) <- list(rnames, cnames)
m
rowSums(m)
colSums(m)

矩阵内积与外积

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
> m <- matrix(1:9, nrow = 3, ncol = 3)
> n <- matrix(2:10, nrow = 3, ncol = 3)
> m
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
> n
     [,1] [,2] [,3]
[1,]    2    5    8
[2,]    3    6    9
[3,]    4    7   10
> m * n
     [,1] [,2] [,3]
[1,]    2   20   56
[2,]    6   30   72
[3,]   12   42   90
> m %*% n
     [,1] [,2] [,3]
[1,]   42   78  114
[2,]   51   96  141
[3,]   60  114  168

对角线与转置

1
2
3
4
5
6
7
8
9
10
11
12
13
> m <- matrix(1:9, nrow = 3, ncol = 3)
> m
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
> diag(m)
[1] 1 5 9
> t(m)
     [,1] [,2] [,3]
[1,]    1    2    3
[2,]    4    5    6
[3,]    7    8    9

列表

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
> a <- c(1:20)
> b <- matrix(1:20, 4, 5)
> c <- mtcars
> d <- "this is a test"
> mlist <- list(a, b, c, d)
> mlist
[[1]]
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

[[2]]
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

[[3]]
                     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
...
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

[[4]]
[1] "this is a test"

使用名称值

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
> a <- c(1:20)
> b <- matrix(1:20, 4, 5)
> c <- mtcars
> d <- "this is a test"
> mlist <- list(first = a,second = b,third = c,forth = d)
> mlist
$first
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

$second
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

$third
                     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
...
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

$forth
[1] "this is a test"

索引

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
> mlist[1]
$first
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

> mlist[c(1, 4)]
$first
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

$forth
[1] "this is a test"

> mlist[c("second", "third")]
$second
     [,1] [,2] [,3] [,4] [,5]
[1,]    1    5    9   13   17
[2,]    2    6   10   14   18
[3,]    3    7   11   15   19
[4,]    4    8   12   16   20

$third
                     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
...
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

$字符访问

1
2
> mlist$first
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

两个中括号访问数据原本类型，一个中括号只能访问列表

1
2
3
4
5
6
7
8
9
10
> mlist[1]
$first
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20

> class(mlist[1])
[1] "list"
> mlist[[1]]
 [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20
> class(mlist[[1]])
[1] "integer"

给列表赋值

1
2
3
4
5
6
7
8
9
10
11
12
13
14
> mlist[5] <- iris
Warning message:
In mlist[5] <- iris :
  number of items to replace is not a multiple of replacement length
> mlist[[5]] <- iris
> mlist[5]
[[1]]
    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1            5.1         3.5          1.4         0.2     setosa
2            4.9         3.0          1.4         0.2     setosa
...
149          6.2         3.4          5.4         2.3  virginica
150          5.9         3.0          5.1         1.8  virginica

删除元素

赋值NULL

1
2
3
4
> mlist[5] <- NULL
> mlist[5]
$<NA>
NULL

负索引

1
2
3
4
> mlist <- mlist[-5]
> mlist[5]
$<NA>
NULL

数据框

数据框（Data frame）可以理解成我们常说的"表格"。数据框是 R 语言的数据结构，是特殊的二维列表。数据框每一列都有一个唯一的列名，长度都是相等的，同一列的数据类型需要一致，不同列的数据类型可以不一样。

1
2
3
4
5
6
7
8
> mystate <- data.frame(state.name, state.abb, state.region)
> mystate
       state.name state.abb  state.region
1         Alabama        AL         South
2          Alaska        AK          West
...
49      Wisconsin        WI North Central
50        Wyoming        WY          West

索引

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
> mystate <- data.frame(state.name, state.abb, state.region)
> mystate[1]
       state.name
1         Alabama
2          Alaska
...
49      Wisconsin
50        Wyoming
> mystate[c(2, 3)]
   state.abb  state.region
1         AL         South
2         AK          West
...
49        WI North Central
50        WY          West
> mystate[-c(1, 3)]
   state.abb
1         AL
2         AK
...
49        WI
50        WY
> mystate[, "state.abb"]
 [1] "AL" "AK" "AZ" "AR" "CA" "CO" "CT" "DE" "FL" "GA" "HI" "ID" "IL" "IN" "IA"
[16] "KS" "KY" "LA" "ME" "MD" "MA" "MI" "MN" "MS" "MO" "MT" "NE" "NV" "NH" "NJ"
[31] "NM" "NY" "NC" "ND" "OH" "OK" "OR" "PA" "RI" "SC" "SD" "TN" "TX" "UT" "VT"
[46] "VA" "WA" "WV" "WI" "WY"
> mystate["1", ]
  state.name state.abb state.region
1    Alabama        AL        South
> mystate[5, ]
  state.name state.abb state.region
5 California        CA         West
> mystate$state.region
 [1] South         West          West          South         West         
 [6] West          Northeast     South         South         South        
[11] West          West          North Central North Central North Central
[16] North Central South         South         Northeast     South        
[21] Northeast     North Central North Central South         North Central
[26] West          North Central West          Northeast     Northeast    
[31] West          Northeast     South         North Central North Central
[36] South         West          Northeast     Northeast     South        
[41] North Central South         South         West          Northeast    
[46] South         West          South         North Central West         
Levels: Northeast South North Central West

attach()函数加载数据框

1
2
3
4
5
6
7
> attach(mtcars)
> mpg
 [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2 10.4 10.4 14.7
[18] 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4 15.8 19.7 15.0 21.4
> hp
 [1] 110 110  93 110 175 105 245  62  95 123 123 180 180 180 205 215 230  66  52  65  97
[22] 150 150 245 175  66  91 113 264 175 335 109

行名

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
> rownames(mtcars)
 [1] "Mazda RX4"           "Mazda RX4 Wag"       "Datsun 710"         
 [4] "Hornet 4 Drive"      "Hornet Sportabout"   "Valiant"            
 [7] "Duster 360"          "Merc 240D"           "Merc 230"           
[10] "Merc 280"            "Merc 280C"           "Merc 450SE"         
[13] "Merc 450SL"          "Merc 450SLC"         "Cadillac Fleetwood" 
[16] "Lincoln Continental" "Chrysler Imperial"   "Fiat 128"           
[19] "Honda Civic"         "Toyota Corolla"      "Toyota Corona"      
[22] "Dodge Challenger"    "AMC Javelin"         "Camaro Z28"         
[25] "Pontiac Firebird"    "Fiat X1-9"           "Porsche 914-2"      
[28] "Lotus Europa"        "Ford Pantera L"      "Ferrari Dino"       
[31] "Maserati Bora"       "Volvo 142E"         
> 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
...
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

列名

1
2
3
4
5
6
7
8
9
> colnames(mtcars)
 [1] "mpg"  "cyl"  "disp" "hp"   "drat" "wt"   "qsec" "vs"   "am"   "gear" "carb"
> 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
...
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

detach()函数取消加载

1
2
3
4
5
> detach(mtcars)
> mgp
Error: object 'mgp' not found
> hp
Error: object 'hp' not found

with()函数访问数据

1
2
3
4
5
6
7
8
9
10
> with(mtcars,{sum(mpg)})
[1] 642.9
> with(mtcars, {hp})
 [1] 110 110  93 110 175 105 245  62  95 123 123 180 180 180 205 215 230  66  52  65  97
[22] 150 150 245 175  66  91 113 264 175 335 109
> with(mtcars, {mpg})
 [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2 10.4 10.4 14.7
[18] 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4 15.8 19.7 15.0 21.4
> with(mtcars, {sum(mpg)})
[1] 642.9

因子

用于表示一组数据中的类别，可以记录这组数据中的类别名称及类别数目

名义型变量

1
2
3
4
> f <- factor(c("red", "red", "green", "blue", "green", "blue", "blue"))
> f
[1] red   red   green blue  green blue  blue 
Levels: blue green red

有序型变量

1
2
3
4
5
6
7
8
9
10
11
12
13
> week <- factor(c("Mon", "Fri", "Thu", "Wed", "Mon", "Fri", "Sun"))
> week
[1] Mon Fri Thu Wed Mon Fri Sun
Levels: Fri Mon Sun Thu Wed
> week <-
+   factor(
+     c("Mon", "Fri", "Thu", "Wed", "Mon", "Fri", "Sun"),
+     ordered = T,
+     levels = c("Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun")
+   )
> week
[1] Mon Fri Thu Wed Mon Fri Sun
Levels: Mon < Tue < Wed < Thu < Fri < Sat < Sun

因子图

1
2
> plot(mtcars$cyl)
> plot(factor(mtcars$cyl))

向量输出散点图

因子输出条形图

cut()函数

分割数据集

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
> num <- c(1:100)
> num
  [1]   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20  21
 [22]  22  23  24  25  26  27  28  29  30  31  32  33  34  35  36  37  38  39  40  41  42
 [43]  43  44  45  46  47  48  49  50  51  52  53  54  55  56  57  58  59  60  61  62  63
 [64]  64  65  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83  84
 [85]  85  86  87  88  89  90  91  92  93  94  95  96  97  98  99 100
> cut(num, c(seq(0, 100, 10)))
  [1] (0,10]   (0,10]   (0,10]   (0,10]   (0,10]   (0,10]   (0,10]   (0,10]   (0,10]  
 [10] (0,10]   (10,20]  (10,20]  (10,20]  (10,20]  (10,20]  (10,20]  (10,20]  (10,20] 
 [19] (10,20]  (10,20]  (20,30]  (20,30]  (20,30]  (20,30]  (20,30]  (20,30]  (20,30] 
 [28] (20,30]  (20,30]  (20,30]  (30,40]  (30,40]  (30,40]  (30,40]  (30,40]  (30,40] 
 [37] (30,40]  (30,40]  (30,40]  (30,40]  (40,50]  (40,50]  (40,50]  (40,50]  (40,50] 
 [46] (40,50]  (40,50]  (40,50]  (40,50]  (40,50]  (50,60]  (50,60]  (50,60]  (50,60] 
 [55] (50,60]  (50,60]  (50,60]  (50,60]  (50,60]  (50,60]  (60,70]  (60,70]  (60,70] 
 [64] (60,70]  (60,70]  (60,70]  (60,70]  (60,70]  (60,70]  (60,70]  (70,80]  (70,80] 
 [73] (70,80]  (70,80]  (70,80]  (70,80]  (70,80]  (70,80]  (70,80]  (70,80]  (80,90] 
 [82] (80,90]  (80,90]  (80,90]  (80,90]  (80,90]  (80,90]  (80,90]  (80,90]  (80,90] 
 [91] (90,100] (90,100] (90,100] (90,100] (90,100] (90,100] (90,100] (90,100] (90,100]
[100] (90,100]
10 Levels: (0,10] (10,20] (20,30] (30,40] (40,50] (50,60] (60,70] (70,80] ... (90,100]

缺失数据处理

NA表示缺失值

1
2
3
4
5
6
7
8
9
> a <- c(NA, 1:49)
> a
 [1] NA  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27
[29] 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
> is.na(a)
 [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[15] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[29] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[43] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE

缺失值的运算

1
2
3
4
5
6
7
8
9
10
11
12
> NA + 1
[1] NA
> NA == 0
[1] NA
> a <- c(NA, 1:49)
> a
 [1] NA  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27
[29] 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
> sum(a)
[1] NA
> mean(a)
[1] NA

跳过缺失值

1
2
3
4
5
6
7
8
> a <- c(NA, 1:49)
> a
 [1] NA  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27
[29] 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49
> sum(a, na.rm = TRUE)
[1] 1225
> mean(a, na.rm = TRUE)
[1] 25

删除缺失值

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> a <- c(NA, 1:10, NA, 10:20, NA, NA)
> a
 [1] NA  1  2  3  4  5  6  7  8  9 10 NA 10 11 12 13 14 15 16 17 18 19 20 NA NA
> d <- na.omit(a)
> d
 [1]  1  2  3  4  5  6  7  8  9 10 10 11 12 13 14 15 16 17 18 19 20
attr(,"na.action")
[1]  1 12 24 25
attr(,"class")
[1] "omit"
> is.na(d)
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[15] FALSE FALSE FALSE FALSE FALSE FALSE FALSE
> sum(d)
[1] 220
> mean(d)
[1] 10.47619

na.omit()删除数据集中缺失数据所在的行

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
> install.packages("VIM")
> library(VIM)
> sleep
    BodyWgt BrainWgt NonD Dream Sleep  Span  Gest Pred Exp Danger
1  6654.000  5712.00   NA    NA   3.3  38.6 645.0    3   5      3
2     1.000     6.60  6.3   2.0   8.3   4.5  42.0    3   1      3
3     3.385    44.50   NA    NA  12.5  14.0  60.0    1   1      1
4     0.920     5.70   NA    NA  16.5    NA  25.0    5   2      3
...
61    3.500     3.90 12.8   6.6  19.4   3.0  14.0    2   1      1
62    4.050    17.00   NA    NA    NA  13.0  38.0    3   1      1
> sum(is.na(sleep))
[1] 38
> na.omit(sleep)
    BodyWgt BrainWgt NonD Dream Sleep  Span  Gest Pred Exp Danger
2     1.000     6.60  6.3   2.0   8.3   4.5  42.0    3   1      3
5  2547.000  4603.00  2.1   1.8   3.9  69.0 624.0    3   5      4
6    10.550   179.50  9.1   0.7   9.8  27.0 180.0    4   4      4
7     0.023     0.30 15.8   3.9  19.7  19.0  35.0    1   1      1
8   160.000   169.00  5.2   1.0   6.2  30.4 392.0    4   5      4
9     3.300    25.60 10.9   3.6  14.5  28.0  63.0    1   2      1
...
60    4.190    58.00  9.7   0.6  10.3  24.0 210.0    4   3      4
61    3.500     3.90 12.8   6.6  19.4   3.0  14.0    2   1      1
> length(rownames(sleep))
[1] 62
> length(rownames(na.omit(sleep)))
[1] 42

其他缺失值

NaN表示不存在的值

Inf表示无穷值

1
2
3
4
5
6
7
8
9
10
> 1 / 0
[1] Inf
> - 1 / 0
[1] -Inf
> 0 / 0
[1] NaN
> is.nan(0 / 0)
[1] TRUE
> is.infinite(1 / 0)
[1] TRUE

字符串

统计字符串长度

1
2
3
4
5
6
7
8
9
10
11
> nchar("Hello World")
[1] 11
> month.name
 [1] "January"   "February"  "March"     "April"     "May"       "June"      "July"     
 [8] "August"    "September" "October"   "November"  "December" 
> nchar(month.name)
 [1] 7 8 5 5 3 4 4 6 9 7 8 8
> length(month.name)
[1] 12
> nchar(c(12, 3, 100))
[1] 2 1 3

连接字符串

1
2
3
4
5
6
7
> paste("I", "Love", "bnu")
[1] "I Love bnu"
> paste("I", "Love", "bnu", sep = "-")
[1] "I-Love-bnu"
> names <- c("You", "I", "Ta")
> paste(names, "Love bnu")
[1] "You Love bnu" "I Love bnu"   "Ta Love bnu"

截取字符串

1
2
> substr(x = month.name, start = 1, stop = 3)
 [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"

修改字符串大小写

1
2
3
4
5
6
7
8
9
> temp <- substr(x = month.name, start = 1, stop = 3)
> toupper(temp)
 [1] "JAN" "FEB" "MAR" "APR" "MAY" "JUN" "JUL" "AUG" "SEP" "OCT" "NOV" "DEC"
> tolower(temp)
 [1] "jan" "feb" "mar" "apr" "may" "jun" "jul" "aug" "sep" "oct" "nov" "dec"
> gsub("^(\\w)", "\\U\\1", tolower(temp), perl = T)
 [1] "Jan" "Feb" "Mar" "Apr" "May" "Jun" "Jul" "Aug" "Sep" "Oct" "Nov" "Dec"
> gsub("^(\\w)", "\\L\\1", toupper(temp), perl = T)
 [1] "jAN" "fEB" "mAR" "aPR" "mAY" "jUN" "jUL" "aUG" "sEP" "oCT" "nOV" "dEC"

查询字符串元素

1
2
3
4
5
6
7
> x <- c("a", "A", "+", "A+", "+A", "+a", "a+A")
> grep("A+", x, fixed = T)
[1] 4
> grep("A+", x, fixed = F)
[1] 2 4 5 7
> match("A+", x)
[1] 4

分割字符串

输出列表格式

1
2
3
4
5
6
7
8
9
10
11
> path <- "/usr/local/bin/R"
> strsplit(path, "/")
[[1]]
[1] ""      "usr"   "local" "bin"   "R"    

> strsplit(c(path, path), "/")
[[1]]
[1] ""      "usr"   "local" "bin"   "R"    

[[2]]
[1] ""      "usr"   "local" "bin"   "R"

日期与时间

1
2
3
4
> Sys.Date()
[1] "2022-09-28"
> class(Sys.Date())
[1] "Date"

字符串转换为日期

1
2
3
4
5
6
7
> a <- "2022-09-28"
> class(a)
[1] "character"
> as.Date(a, format = "%Y-%m-%d")
[1] "2022-09-28"
> class(as.Date(a, format = "%Y-%m-%d"))
[1] "Date"

日期序列

1
2
3
4
5
6
7
8
> seq(as.Date("2022-08-07"), as.Date("2022-09-28"), by = 3)
 [1] "2022-08-07" "2022-08-10" "2022-08-13" "2022-08-16"
 [5] "2022-08-19" "2022-08-22" "2022-08-25" "2022-08-28"
 [9] "2022-08-31" "2022-09-03" "2022-09-06" "2022-09-09"
[13] "2022-09-12" "2022-09-15" "2022-09-18" "2022-09-21"
[17] "2022-09-24" "2022-09-27"
> class(seq(as.Date("2022-08-07"), as.Date("2022-09-28"), by = 3))
[1] "Date"
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
> scores <- round(runif(48, min = 50, max = 100))
> scores
 [1]  69  95  67  51  78  95  78  55  92  54  55  99  85  75  87
[16]  73  66  64  69  52  96  65  81  88  77  75  81  51  58  79
[31]  91  76  65  92  99  70  70  70  70  74  89  81  95  75  81
[46]  86  59 100
> ts(
+   scores,
+   start = c(2019, 9),
+   end = c(2023, 9),
+   frequency = 1
+ )
Time Series:
Start = 2027 
End = 2031 
Frequency = 1 
[1] 69 95 67 51 78
> ts(
+   scores,
+   start = c(2019, 9),
+   end = c(2023, 9),
+   frequency = 4
+ )
     Qtr1 Qtr2 Qtr3 Qtr4
2021   69   95   67   51
2022   78   95   78   55
2023   92   54   55   99
2024   85   75   87   73
2025   66               
> ts(
+   scores,
+   start = c(2019, 9),
+   end = c(2023, 9),
+   frequency = 12
+ )
     Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
2019                                  69  95  67  51
2020  78  95  78  55  92  54  55  99  85  75  87  73
2021  66  64  69  52  96  65  81  88  77  75  81  51
2022  58  79  91  76  65  92  99  70  70  70  70  74
2023  89  81  95  75  81  86  59 100  69

对文件的操作

读入数据

键盘输入

1
2
3
4
5
6
7
8
9
10
11
12
> patientID <- c(1:4)
> admdate <- c("10/15/2009", "11/01/2009", "10/21/2009", "10/28/2009")
> age <- c(25, 34, 28, 52)
> diabetes <- c("Type1", "Type2", "Type1", "Tpye1")
> ststus <- c("Poor", "Improved", "Excellent", "Poor")
> data <- data.frame(patientID, admdate, age, diabetes, ststus)
> data
  patientID    admdate age diabetes    ststus
1         1 10/15/2009  25    Type1      Poor
2         2 11/01/2009  34    Type2  Improved
3         3 10/21/2009  28    Type1 Excellent
4         4 10/28/2009  52    Tpye1      Poor

edit()函数

1
2
3
4
5
6
7
8
9
> datacopy <-
+   data.frame(
+     patientID = character(0),
+     admdate = character(0),
+     age = numeric(),
+     diabetes = character(),
+     status = character()
+   )
> datecopy <- edit(datacopy)

fix()函数

1
fix(datacopy)

读取外部文件

更改文件路径

1
2
3
> getwd()
[1] "D:/学习/R初体验"
> setwd("D:/学习/R初体验/RData")

read.table()读取文件(相对路径)

1
2
3
4
5
6
7
8
> x <- read.table("input.txt")
> x
    Ozone Solar.R Wind Temp Month Day
1      41     190  7.4   67     5   1
2      36     118  8.0   72     5   2
...
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30

head()与tail()查看数据首尾

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
> head(x)
  Ozone Solar.R Wind Temp Month Day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4
5    NA      NA 14.3   56     5   5
6    28      NA 14.9   66     5   6
> tail(x)
    Ozone Solar.R Wind Temp Month Day
148    14      20 16.6   63     9  25
149    30     193  6.9   70     9  26
150    NA     145 13.2   77     9  27
151    14     191 14.3   75     9  28
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30
> head(x, n = 10)
   Ozone Solar.R Wind Temp Month Day
1     41     190  7.4   67     5   1
2     36     118  8.0   72     5   2
3     12     149 12.6   74     5   3
4     18     313 11.5   62     5   4
5     NA      NA 14.3   56     5   5
6     28      NA 14.9   66     5   6
7     23     299  8.6   65     5   7
8     19      99 13.8   59     5   8
9      8      19 20.1   61     5   9
10    NA     194  8.6   69     5  10

sep分隔符

1
2
3
4
5
6
7
8
> x <- read.table("input.csv", sep = ",")
> x
                    V1   V2  V3    V4  V5   V6    V7    V8 V9 V10  V11  V12
1                       mpg cyl  disp  hp drat    wt  qsec vs  am gear carb
2            Mazda RX4   21   6   160 110  3.9  2.62 16.46  0   1    4    4
...
32       Maserati Bora   15   8   301 335 3.54  3.57  14.6  0   1    5    8
33          Volvo 142E 21.4   4   121 109 4.11  2.78  18.6  1   1    4    2

header = TRUE将第一行数据作为变量名

1
2
3
4
5
6
7
8
9
> x <- read.table("input.csv", sep = ",", header = TRUE)
> head(x)
                  X  mpg cyl disp  hp drat    wt  qsec vs am gear carb
1         Mazda RX4 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
2     Mazda RX4 Wag 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
3        Datsun 710 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
4    Hornet 4 Drive 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
5 Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
6           Valiant 18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

skip跳过文件部分内容(跳过内容多为文件注释)

1
2
3
4
5
6
7
8
9
> x <- read.table("input 1.txt", header = TRUE, skip = 5)
> head(x)
  Ozone Solar.R Wind Temp Month Day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4
5    NA      NA 14.3   56     5   5
6    28      NA 14.9   66     5   6

nrows确定读取文件行数

1
2
3
4
5
6
7
8
> x <- read.table("input 1.txt", skip = 20, nrows = 50)
> x
   V1  V2  V3   V4 V5 V6 V7
1  15  18  65 13.2 58  5 15
2  16  14 334 11.5 64  5 16
...
49 63  49 248  9.2 85  7  2
50 64  32 236  9.2 81  7  3

na.strings确认缺失值

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
> x <- read.table("input.txt", na.strings = "NA")
> x
    Ozone Solar.R Wind Temp Month Day
1      41     190  7.4   67     5   1
2      36     118  8.0   72     5   2
3      12     149 12.6   74     5   3
4      18     313 11.5   62     5   4
5      NA      NA 14.3   56     5   5
...
150    NA     145 13.2   77     9  27
151    14     191 14.3   75     9  28
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30
> is.na(x)
    Ozone Solar.R  Wind  Temp Month   Day
1   FALSE   FALSE FALSE FALSE FALSE FALSE
2   FALSE   FALSE FALSE FALSE FALSE FALSE
3   FALSE   FALSE FALSE FALSE FALSE FALSE
4   FALSE   FALSE FALSE FALSE FALSE FALSE
5    TRUE    TRUE FALSE FALSE FALSE FALSE
...
150  TRUE   FALSE FALSE FALSE FALSE FALSE
151 FALSE   FALSE FALSE FALSE FALSE FALSE
152 FALSE   FALSE FALSE FALSE FALSE FALSE
153 FALSE   FALSE FALSE FALSE FALSE FALSE

stringsAsFactors将字符串数据转化成因子

read.csv()读取csv文件

1
2
3
4
5
6
7
8
> x <- read.csv("input.csv")
> x
                     X  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
...
31       Maserati Bora 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
32          Volvo 142E 21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

读取网络上的文件，将下载到本地

1
> x <- read.table("https://codeload.github.com/mperdeck/LINQtocSV/zip/master", header = TRUE)

读取网页表格

1
2
3
> install.packages("XML")
> library(XML)
> x <- readHTMLTable("https://en.wikipedia.org/wiki/World_population" , which = 3)

读取剪贴板Ctrl C上的文件

1
2
3
4
5
6
7
8
9
10
11
12
13
14
> x <- read.table("clipboard", header =  TRUE, sep = "\t")
> x
                     X  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
...
24          Camaro Z28 13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
25    Pontiac Firebird 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
> readClipboard()
 [1] "\tmpg\tcyl\tdisp\thp\tdrat\twt\tqsec\tvs\tam\tgear\tcarb"            
 [2] "Mazda RX4\t21\t6\t160\t110\t3.9\t2.62\t16.46\t0\t1\t4\t4"            
...  
[25] "Camaro Z28\t13.3\t8\t350\t245\t3.73\t3.84\t15.41\t0\t0\t3\t4"        
[26] "Pontiac Firebird\t19.2\t8\t400\t175\t3.08\t3.845\t17.05\t0\t0\t3\t2"

读取压缩格式的文件

1
2
3
4
5
6
7
8
> x <- read.table(gzfile("input.txt.gz"))
> x
                     X  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
...
15  Cadillac Fleetwood 10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
16 Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4

readLines()读取文件固定行

1
2
3
4
5
6
7
> x <- readLines("input.csv", n = 5)
> x
[1] "\"\",\"mpg\",\"cyl\",\"disp\",\"hp\",\"drat\",\"wt\",\"qsec\",\"vs\",\"am\",\"gear\",\"carb\""
[2] "\"Mazda RX4\",21,6,160,110,3.9,2.62,16.46,0,1,4,4"                                            
[3] "\"Mazda RX4 Wag\",21,6,160,110,3.9,2.875,17.02,0,1,4,4"                                       
[4] "\"Datsun 710\",22.8,4,108,93,3.85,2.32,18.61,1,1,4,1"                                         
[5] "\"Hornet 4 Drive\",21.4,6,258,110,3.08,3.215,19.44,1,0,3,1"

scan()读取文件固定行

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
> x <- scan("scan.txt", what = list(X1 = character(3), X2 = character(0), X3 = character(0)))
Read 20 records
> x
$X1
 [1] "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four" "one"  "four"
[19] "one"  "four"

$X2
 [1] "2" "5" "2" "5" "2" "5" "2" "5" "2" "5" "2" "5" "2" "5" "2" "5" "2" "5" "2" "5"

$X3
 [1] "3" "6" "3" "6" "3" "6" "3" "6" "3" "6" "3" "6" "3" "6" "3" "6" "3" "6" "3" "6"
> class(x)
[1] "list"
> data <- data.frame(x$X1, x$X2, x$X3)
> data
   x.X1 x.X2 x.X3
1   one    2    3
2  four    5    6
...
19  one    2    3
20 four    5    6

访问数据库系统

1
2
> install.packages("RODBC")
> library("RODBC")

写入文件

写入向量

1
2
3
4
5
6
7
8
9
10
11
> x = rivers
> x
  [1]  735  320  325  392  524  450 1459  135  465  600  330  336  280  315  870  906  202  329  290 1000  600  505 1450  840 1243
 [26]  890  350  407  286  280  525  720  390  250  327  230  265  850  210  630  260  230  360  730  600  306  390  420  291  710
 [51]  340  217  281  352  259  250  470  680  570  350  300  560  900  625  332 2348 1171 3710 2315 2533  780  280  410  460  260
 [76]  255  431  350  760  618  338  981 1306  500  696  605  250  411 1054  735  233  435  490  310  460  383  375 1270  545  445
[101] 1885  380  300  380  377  425  276  210  800  420  350  360  538 1100 1205  314  237  610  360  540 1038  424  310  300  444
[126]  301  268  620  215  652  900  525  246  360  529  500  720  270  430  671 1770
> cat(x)
735 320 325 392 524 450 1459 135 465 600 330 336 280 315 870 906 202 329 290 1000 600 505 1450 840 1243 890 350 407 286 280 525 720 390 250 327 230 265 850 210 630 260 230 360 730 600 306 390 420 291 710 340 217 281 352 259 250 470 680 570 350 300 560 900 625 332 2348 1171 3710 2315 2533 780 280 410 460 260 255 431 350 760 618 338 981 1306 500 696 605 250 411 1054 735 233 435 490 310 460 383 375 1270 545 445 1885 380 300 380 377 425 276 210 800 420 350 360 538 1100 1205 314 237 610 360 540 1038 424 310 300 444 301 268 620 215 652 900 525 246 360 529 500 720 270 430 671 1770
> write(x, file = "x.txt")

写入表格

1
2
3
> x <- read.table("input.txt", header = TRUE)
> write.table(x, file = "newfile.txt")
> write.table(x, file = "newfile.csv", sep = ",")

去除行号

1
> write.table(x, file = "newfile.csv", sep = ",", row.names = FALSE)

append将追加到已有文件结尾

1
> write.table(iris, file = "newfile.txt",skip = 1, append = TRUE)

写入压缩文件

1
> write.table(mtcars, gzfile("nwefile.txt.gz"))

读写Excel文件

安装XLConnect包，必须先下载好Java

1
2
> install.packages("XLConnect")
> library(XLConnect)

读取Excel文件

1
2
3
4
5
6
7
8
9
10
> ex <- loadWorkbook("data.xlsx")
> exdata <- readWorksheet(ex, 1)
> head(exdata)
               Col1  mpg cyl disp  hp drat    wt  qsec vs am gear carb
1         Mazda RX4 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
2     Mazda RX4 Wag 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
3        Datsun 710 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
4    Hornet 4 Drive 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
5 Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
6           Valiant 18.1   6  225 105 2.76 3.460 20.22  1  0    3    1
1
2
3
4
5
6
7
8
9
10
11
> readWorksheet(ex, 1, startRow = 0, startCol = 0, endRow = 10, endCol = 3, header = TRUE)
               Col1  mpg cyl
1         Mazda RX4 21.0   6
2     Mazda RX4 Wag 21.0   6
3        Datsun 710 22.8   4
4    Hornet 4 Drive 21.4   6
5 Hornet Sportabout 18.7   8
6           Valiant 18.1   6
7        Duster 360 14.3   8
8         Merc 240D 24.4   4
9          Merc 230 22.8   4

一步完成

1
2
3
4
5
6
7
> readWorksheetFromFile("data.xlsx", 1)
                  Col1  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
...
31       Maserati Bora 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
32          Volvo 142E 21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

写入Excel文件

1
2
3
4
> wb <- loadWorkbook("exfile.xlsx", create = TRUE)
> createSheet(wb, "Sheet 1")
> writeWorksheet(wb, data = mtcars, sheet = "Sheet 1")
> saveWorkbook(wb)

一步完成

1
> writeWorksheetToFile("exfile.xlsx", data = iris, sheet = "Sheet 1")

xlsx包读写Excel文件

1
2
> x <- read.xlsx("data.xlsx", 1, startRow = 1, endRow = 10)
> write.xlsx(x, file = "rdata.xlsx", sheetName = "Sheet 1", append = FALSE)

读写R格式文件

RDS文件

1
> saveRDS(iris, file = "iris.RDS")
1
x <- readRDS("iris.RDS")

Rdata文件

1
2
> save(iris, iris3, file = "iris.Rdata")
> load("iris.Rdata")

保存所有对象

1
> save.image()

数据转换

数据类型转化

is.data.frame()判断数据框

1
2
3
4
5
6
7
8
9
10
11
> library(xlsx)
> cars32 <- read.xlsx("mtcars.xlsx", sheetIndex = 1, header = TRUE)
> cars32
                   NA.  mpg cyl  disp  hp drat    wt  qsec vs am gear carb
1            Mazda RX4 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
2        Mazda RX4 Wag 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
...
31       Maserati Bora 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
32          Volvo 142E 21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2
> is.data.frame(cars32)
[1] TRUE

as.data.frame转化为数据框

1
2
3
4
5
> is.data.frame(state.x77)
[1] FALSE
> dstate.x77 <- as.data.frame(state.x77)
> is.data.frame(dstate.x77)
[1] TRUE

as.matrix()转化为矩阵，但出现字符型时，会将数值全部转化成字符串

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
> data <- data.frame(state.region, state.x77)
> data
                state.region Population Income Illiteracy Life.Exp Murder HS.Grad Frost   Area
Alabama                South       3615   3624        2.1    69.05   15.1    41.3    20  50708
Alaska                  West        365   6315        1.5    69.31   11.3    66.7   152 566432
...
Wisconsin      North Central       4589   4468        0.7    72.48    3.0    54.5   149  54464
Wyoming                 West        376   4566        0.6    70.29    6.9    62.9   173  97203
> as.matrix(data)
               state.region    Population Income Illiteracy Life.Exp Murder HS.Grad Frost Area    
Alabama        "South"         " 3615"    "3624" "2.1"      "69.05"  "15.1" "41.3"  " 20" " 50708"
Alaska         "West"          "  365"    "6315" "1.5"      "69.31"  "11.3" "66.7"  "152" "566432"
...
Wisconsin      "North Central" " 4589"    "4468" "0.7"      "72.48"  " 3.0" "54.5"  "149" " 54464"
Wyoming        "West"          "  376"    "4566" "0.6"      "70.29"  " 6.9" "62.9"  "173" " 97203"

as.vector转化为向量

1
2
3
4
5
6
> as.vector(state.x77)
  [1]   3615.00    365.00   2212.00   2110.00  21198.00   2541.00   3100.00    579.00   8277.00   4931.00    868.00    813.00
 [13]  11197.00   5313.00   2861.00   2280.00   3387.00   3806.00   1058.00   4122.00   5814.00   9111.00   3921.00   2341.00
...
[385]  40975.00  68782.00  96184.00  44966.00   1049.00  30225.00  75955.00  41328.00 262134.00  82096.00   9267.00  39780.00
[397]  66570.00  24070.00  54464.00  97203.00

as.factor()转化为因子

1
2
3
4
5
6
7
8
> x <- state.abb
> x
 [1] "AL" "AK" "AZ" "AR" "CA" "CO" "CT" "DE" "FL" "GA" "HI" "ID" "IL" "IN" "IA" "KS" "KY" "LA" "ME" "MD" "MA" "MI" "MN" "MS" "MO"
[26] "MT" "NE" "NV" "NH" "NJ" "NM" "NY" "NC" "ND" "OH" "OK" "OR" "PA" "RI" "SC" "SD" "TN" "TX" "UT" "VT" "VA" "WA" "WV" "WI" "WY"
> as.factor(x)
 [1] AL AK AZ AR CA CO CT DE FL GA HI ID IL IN IA KS KY LA ME MD MA MI MN MS MO MT NE NV NH NJ NM NY NC ND OH OK OR PA RI SC SD TN
[43] TX UT VT VA WA WV WI WY
50 Levels: AK AL AR AZ CA CO CT DE FL GA HI IA ID IL IN KS KY LA MA MD ME MI MN MO MS MT NC ND NE NH NJ NM NV NY OH OK OR ... WY

as.list()转化为列表

1
2
3
4
5
6
7
8
9
10
> x <- state.abb
> as.list(x)
[[1]]
[1] "AL"

[[2]]
[1] "AK"
...
[[50]]
[1] "WY"

unname()去除列明，unlist()转化为向量

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
> x <- state.abb
> state <- data.frame(x, state.region, state.x77)
> state$Income
 [1] 3624 6315 4530 3378 5114 4884 5348 4809 4815 4091 4963 4119 5107 4458 4628 4669 3712 3545 3694 5299 4755 4751 4675 3098 4254
[26] 4347 4508 5149 4281 5237 3601 4903 3875 5087 4561 3983 4660 4449 4558 3635 4167 3821 4188 4022 3907 4701 4864 3617 4468 4566
> state["Nevada", ]
        x state.region Population Income Illiteracy Life.Exp Murder HS.Grad Frost   Area
Nevada NV         West        590   5149        0.5    69.03   11.5    65.2   188 109889
> is.data.frame(state["Nevada", ])
[1] TRUE
> y <- state["Nevada", ]
> y
        x state.region Population Income Illiteracy Life.Exp Murder HS.Grad Frost   Area
Nevada NV         West        590   5149        0.5    69.03   11.5    65.2   188 109889
> unname(y)
                                                      
Nevada NV West 590 5149 0.5 69.03 11.5 65.2 188 109889
> unlist(y)
           x state.region   Population       Income   Illiteracy     Life.Exp       Murder      HS.Grad        Frost         Area 
        "NV"          "4"        "590"       "5149"        "0.5"      "69.03"       "11.5"       "65.2"        "188"     "109889"

选取子集

索引选取子集

View()打开数据窗口

1
2
3
4
5
6
> who <- read.csv("WHO.csv", header = TRUE)
> View(who)
> who1 <- who[c(1:50), c(1:10)]
> View(who1)
> who2 <- who[c(1, 3, 5, 8), c(2, 4, 6, 8)]
> View(who2)

逻辑判断选取子集

1
2
3
4
> who3 <- who[which(who$Continent == 7), ]
> View(who3)
> who4 <- who[which(who$CountryID > 50 & who$CountryID <= 100), ]
> View(who4)

subset()函数选取子集

1
2
who4 <- subset(who, who$CountryID > 50 & who$CountryID <= 100)
View(who4)

sample()随机抽样

1
2
3
4
5
6
7
8
9
> x <- 1:100
> sample(x, 30)
 [1] 55 92 50 37 48 16  9 20 28 76 10 87 86 17 59 77 21 67 43  8 34 71  3 39  6 83 69 30 14 54
> sample(x, 60, replace = TRUE)
 [1]  74  80  71  81  88  84  52  22  69   9  99  77  62  60  85  48  84  23   1  10  57  92  13 100   2  27  42  64  26  16  81
[32]  55  18  90  84  18  95  92   1   8  48  70  37  84  97  51   2  49  55   9  79  60  64  62  15  50   7  31  15  22
> sort(sample(x, 60, replace = TRUE))
 [1]   1   2   3   5   8   9  10  11  12  15  16  25  26  35  35  35  37  40  40  40  41  46  47  48  49  49  50  51  52  53  53
[32]  55  56  57  58  61  65  66  67  68  69  69  69  71  74  76  76  83  84  86  88  89  89  91  92  93  94  95  97 100
1
2
3
4
5
> who <- read.csv("WHO.csv", header = TRUE)
> sample(who$CountryID, 30, replace = TRUE)
 [1]  76  93 166 197 108  24 174 100  61  65 176 169 127 162 196 193  92 122  77  52 198 118  63  61  38 185  90  25 152 197
> who5 <- who[sample(who$CountryID, 30, replace = TRUE), ]
> View(who5)

删除固定行与列

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
> head(mtcars)
                  cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4           6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag       6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710          4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive      6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout   8  360 175 3.15 3.440 17.02  0  0    3    2
Valiant             6  225 105 2.76 3.460 20.22  1  0    3    1
> head(mtcars[-1:-5, ])
           cyl  disp  hp drat   wt  qsec vs am gear carb
Valiant      6 225.0 105 2.76 3.46 20.22  1  0    3    1
Duster 360   8 360.0 245 3.21 3.57 15.84  0  0    3    4
Merc 240D    4 146.7  62 3.69 3.19 20.00  1  0    4    2
Merc 230     4 140.8  95 3.92 3.15 22.90  1  0    4    2
Merc 280     6 167.6 123 3.92 3.44 18.30  1  0    4    4
Merc 280C    6 167.6 123 3.92 3.44 18.90  1  0    4    4
> head(mtcars[, -1:-5, ])
                   qsec vs am gear carb
Mazda RX4         16.46  0  1    4    4
Mazda RX4 Wag     17.02  0  1    4    4
Datsun 710        18.61  1  1    4    1
Hornet 4 Drive    19.44  1  0    3    1
Hornet Sportabout 17.02  0  0    3    2
Valiant           20.22  1  0    3    1
> mtcars$mpg <- NULL
> head(mtcars)
                  cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4           6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag       6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710          4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive      6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout   8  360 175 3.15 3.440 17.02  0  0    3    2
Valiant             6  225 105 2.76 3.460 20.22  1  0    3    1

数据框的添加与合并

合成一个数据框

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
> USArrests
               Murder Assault UrbanPop Rape
Alabama          13.2     236       58 21.2
Alaska           10.0     263       48 44.5
...
Wisconsin         2.6      53       66 10.8
Wyoming           6.8     161       60 15.6
> state.division
 [1] East South Central Pacific            Mountain           West South Central Pacific            Mountain          
 [7] New England        South Atlantic     South Atlantic     South Atlantic     Pacific            Mountain     ...
[43] West South Central Mountain           New England        South Atlantic     Pacific            South Atlantic    
[49] East North Central Mountain          
9 Levels: New England Middle Atlantic South Atlantic East South Central West South Central ... Pacific
> data.frame(USArrests, state.division)
               Murder Assault UrbanPop Rape     state.division
Alabama          13.2     236       58 21.2 East South Central
Alaska           10.0     263       48 44.5            Pacific
...
Wisconsin         2.6      53       66 10.8 East North Central
Wyoming           6.8     161       60 15.6           Mountain

cbind()与rbind()函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
> cbind(USArrests, state.division)
               Murder Assault UrbanPop Rape     state.division
Alabama          13.2     236       58 21.2 East South Central
Alaska           10.0     263       48 44.5            Pacific
...

Wisconsin         2.6      53       66 10.8 East North Central
Wyoming           6.8     161       60 15.6           Mountain
> data1 <- head(USArrests)
> data2 <- tail(USArrests)
> rbind(data1, data2)
              Murder Assault UrbanPop Rape
Alabama         13.2     236       58 21.2
Alaska          10.0     263       48 44.5
Arizona          8.1     294       80 31.0
Arkansas         8.8     190       50 19.5
California       9.0     276       91 40.6
Colorado         7.9     204       78 38.7
Vermont          2.2      48       32 11.2
Virginia         8.5     156       63 20.7
Washington       4.0     145       73 26.2
West Virginia    5.7      81       39  9.3
Wisconsin        2.6      53       66 10.8
Wyoming          6.8     161       60 15.6

去除重复行

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
> data1 <- head(USArrests, 30)
> data2 <- tail(USArrests, 30)
> data3 <- rbind(data1, data2)
> length(rownames(data3))
[1] 60
> 
> duplicated(data3)
 [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[22] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE FALSE FALSE
[43] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
> data3[duplicated(data3), ]
               Murder Assault UrbanPop Rape
Massachusetts1    4.4     149       85 16.3
Michigan1        12.1     255       74 35.1
Minnesota1        2.7      72       66 14.9
Mississippi1     16.1     259       44 17.1
Missouri1         9.0     178       70 28.2
Montana1          6.0     109       53 16.4
Nebraska1         4.3     102       62 16.5
Nevada1          12.2     252       81 46.0
New Hampshire1    2.1      57       56  9.5
New Jersey1       7.4     159       89 18.8
> data3[!duplicated(data3), ]
               Murder Assault UrbanPop Rape
Alabama          13.2     236       58 21.2
Alaska           10.0     263       48 44.5
...
Wisconsin         2.6      53       66 10.8
Wyoming           6.8     161       60 15.6
> length(rownames(data3[!duplicated(data3), ]))
[1] 50
> 
> unique(data3)
               Murder Assault UrbanPop Rape
Alabama          13.2     236       58 21.2
Alaska           10.0     263       48 44.5
...
Wisconsin         2.6      53       66 10.8
Wyoming           6.8     161       60 15.6
> length(rownames(unique(data3)))
[1] 50

merge()函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
> x <- data.frame(k1 = c(NA, NA, 3, 4, 5), k2 = c(1, NA, NA, 4, 5), data = 1:5)
> y <- data.frame(k1 = c(NA, 2, NA, 4, 5), k2 = c(NA, NA, 3, 4, 5), data = 5:1)
> merge(x, y, by = "k1")
  k1 k2.x data.x k2.y data.y
1  4    4      4    4      2
2  5    5      5    5      1
3 NA    1      1   NA      5
4 NA    1      1    3      3
5 NA   NA      2   NA      5
6 NA   NA      2    3      3
> merge(x, y, by = "k2", incomparables = TRUE)
  k2 k1.x data.x k1.y data.y
1  4    4      4    4      2
2  5    5      5    5      1
3 NA   NA      2   NA      5
4 NA   NA      2    2      4
5 NA    3      3   NA      5
6 NA    3      3    2      4
> merge(x, y, by = "k2", incomparables = NA)
  k2 k1.x data.x k1.y data.y
1  4    4      4    4      2
2  5    5      5    5      1
> merge(x, y, by = c("k1", "k2"))
  k1 k2 data.x data.y
1  4  4      4      2
2  5  5      5      1
3 NA NA      2      5

修改数据的值

t()转置

1
2
> sractm <- t(mtcars)
> View(sractm)

rev()翻转向量

1
2
3
4
> letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
> rev(letters)
 [1] "z" "y" "x" "w" "v" "u" "t" "s" "r" "q" "p" "o" "n" "m" "l" "k" "j" "i" "h" "g" "f" "e" "d" "c" "b" "a"
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
> women
   height weight
1      58    115
2      59    117
...
14     71    159
15     72    164
> rownames(women)
 [1] "1"  "2"  "3"  "4"  "5"  "6"  "7"  "8"  "9"  "10" "11" "12" "13" "14" "15"
> rev(rownames(women))
 [1] "15" "14" "13" "12" "11" "10" "9"  "8"  "7"  "6"  "5"  "4"  "3"  "2"  "1" 
> women[rev(rownames(women)), ]
   height weight
15     72    164
14     71    159
...
2      59    117
1      58    115

transform()函数修改列值

1
2
3
4
5
6
7
8
9
10
11
12
13
14
> transform(women, weight = weight * 2)
   height weight
1      58    230
2      59    234
...
14     71    318
15     72    328
> transform(women, cm = height * 2.54)
   height weight     cm
1      58    115 147.32
2      59    117 149.86
...
14     71    159 180.34
15     72    164 182.88

排序

sort()

向量排序

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
> rivers
  [1]  735  320  325  392  524  450 1459  135  465  600  330  336  280  315  870  906  202  329  290 1000  600  505 1450  840 1243
 [26]  890  350  407  286  280  525  720  390  250  327  230  265  850  210  630  260  230  360  730  600  306  390  420  291  710
 [51]  340  217  281  352  259  250  470  680  570  350  300  560  900  625  332 2348 1171 3710 2315 2533  780  280  410  460  260
 [76]  255  431  350  760  618  338  981 1306  500  696  605  250  411 1054  735  233  435  490  310  460  383  375 1270  545  445
[101] 1885  380  300  380  377  425  276  210  800  420  350  360  538 1100 1205  314  237  610  360  540 1038  424  310  300  444
[126]  301  268  620  215  652  900  525  246  360  529  500  720  270  430  671 1770
> sort(rivers)
  [1]  135  202  210  210  215  217  230  230  233  237  246  250  250  250  255  259  260  260  265  268  270  276  280  280  280
 [26]  281  286  290  291  300  300  300  301  306  310  310  314  315  320  325  327  329  330  332  336  338  340  350  350  350
 [51]  350  352  360  360  360  360  375  377  380  380  383  390  390  392  407  410  411  420  420  424  425  430  431  435  444
 [76]  445  450  460  460  465  470  490  500  500  505  524  525  525  529  538  540  545  560  570  600  600  600  605  610  618
[101]  620  625  630  652  671  680  696  710  720  720  730  735  735  760  780  800  840  850  870  890  900  900  906  981 1000
[126] 1038 1054 1100 1171 1205 1243 1270 1306 1450 1459 1770 1885 2315 2348 2533 3710
> month.name
 [1] "January"   "February"  "March"     "April"     "May"       "June"      "July"      "August"    "September" "October"  
[11] "November"  "December" 
> sort(month.name)
 [1] "April"     "August"    "December"  "February"  "January"   "July"      "June"      "March"     "May"       "November" 
[11] "October"   "September"
> rev(sort(rivers))
  [1] 3710 2533 2348 2315 1885 1770 1459 1450 1306 1270 1243 1205 1171 1100 1054 1038 1000  981  906  900  900  890  870  850  840
 [26]  800  780  760  735  735  730  720  720  710  696  680  671  652  630  625  620  618  610  605  600  600  600  570  560  545
 [51]  540  538  529  525  525  524  505  500  500  490  470  465  460  460  450  445  444  435  431  430  425  424  420  420  411
 [76]  410  407  392  390  390  383  380  380  377  375  360  360  360  360  352  350  350  350  350  340  338  336  332  330  329
[101]  327  325  320  315  314  310  310  306  301  300  300  300  291  290  286  281  280  280  280  276  270  268  265  260  260
[126]  259  255  250  250  250  246  237  233  230  230  217  215  210  210  202  135
> rev(sort(month.name))
 [1] "September" "October"   "November"  "May"       "March"     "June"      "July"      "January"   "February"  "December" 
[11] "August"    "April"

数据框排序

1
2
3
4
5
6
7
8
9
> mtcars[sort(rownames(mtcars)),]
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
...
Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

order()

order()返回排序位置

向量排序

1
2
3
4
5
6
> order(rivers)
  [1]   8  17  39 108 129  52  36  42  91 117 133  34  56  87  76  55  41  75  37 127 138 107  13  30  72  53  29  19  49  61 103
 [32] 124 126  46  94 123 116  14   2   3  35  18  11  65  12  81  51  27  60  78 111  54  43 112 119 134  97 105 102 104  96  33
 [63]  47   4  28  73  88  48 110 122 106 139  77  92 125 100   6  74  95   9  57  93  84 136  22   5  31 132 135 113 120  99  62
 [94]  59  10  21  45  86 118  80 128  64  40 130 140  58  85  50  32 137  44   1  90  79  71 109  24  38  15  26  63 131  16  82
[125]  20 121  89 114  67 115  25  98  83  23   7 141 101  69  66  70  68

数据框排序

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
> mtcars[order(mtcars$mpg), ]
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
...
Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
> mtcars[order(-mtcars$mpg), ]
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
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
...
Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
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

多个条件排序

1
2
3
4
5
6
7
8
9
> mtcars[order(mtcars$mpg, mtcars$disp), ]
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
...
Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1

数学计算

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
> WorldPhones
     N.Amer Europe Asia S.Amer Oceania Africa Mid.Amer
1951  45939  21574 2876   1815    1646     89      555
1956  60423  29990 4708   2568    2366   1411      733
1957  64721  32510 5230   2695    2526   1546      773
1958  68484  35218 6662   2845    2691   1663      836
1959  71799  37598 6856   3000    2868   1769      911
1960  76036  40341 8220   3145    3054   1905     1008
1961  79831  43173 9053   3338    3224   2005     1076
> worldphones <- as.data.frame(WorldPhones)
> rs <- rowSums(worldphones)
> rs
  1951   1956   1957   1958   1959   1960   1961 
 74494 102199 110001 118399 124801 133709 141700 
> cm <- colMeans(worldphones)
> cm
    N.Amer     Europe       Asia     S.Amer    Oceania     Africa   Mid.Amer 
66747.5714 34343.4286  6229.2857  2772.2857  2625.0000  1484.0000   841.7143 
> total <- cbind(worldphones, Total = rs)
> total
     N.Amer Europe Asia S.Amer Oceania Africa Mid.Amer  Total
1951  45939  21574 2876   1815    1646     89      555  74494
1956  60423  29990 4708   2568    2366   1411      733 102199
1957  64721  32510 5230   2695    2526   1546      773 110001
1958  68484  35218 6662   2845    2691   1663      836 118399
1959  71799  37598 6856   3000    2868   1769      911 124801
1960  76036  40341 8220   3145    3054   1905     1008 133709
1961  79831  43173 9053   3338    3224   2005     1076 141700
> rbind(total, Mean = cm)
       N.Amer   Europe     Asia   S.Amer Oceania Africa  Mid.Amer     Total
1951 45939.00 21574.00 2876.000 1815.000    1646     89  555.0000  74494.00
1956 60423.00 29990.00 4708.000 2568.000    2366   1411  733.0000 102199.00
1957 64721.00 32510.00 5230.000 2695.000    2526   1546  773.0000 110001.00
1958 68484.00 35218.00 6662.000 2845.000    2691   1663  836.0000 118399.00
1959 71799.00 37598.00 6856.000 3000.000    2868   1769  911.0000 124801.00
1960 76036.00 40341.00 8220.000 3145.000    3054   1905 1008.0000 133709.00
1961 79831.00 43173.00 9053.000 3338.000    3224   2005 1076.0000 141700.00
Mean 66747.57 34343.43 6229.286 2772.286    2625   1484  841.7143  66747.57
Warning message:
In rbind(deparse.level, ...) :
  number of columns of result, 8, is not a multiple of vector length 7 of arg 2

apply()函数处理数组与数据框

1
2
3
4
5
6
7
8
9
> apply(worldphones, MARGIN = 1, FUN = sum)
  1951   1956   1957   1958   1959   1960   1961 
 74494 102199 110001 118399 124801 133709 141700 
> apply(worldphones, MARGIN =  2, FUN = mean)
    N.Amer     Europe       Asia     S.Amer    Oceania     Africa   Mid.Amer 
66747.5714 34343.4286  6229.2857  2772.2857  2625.0000  1484.0000   841.7143 
> apply(worldphones, MARGIN =  2, FUN = var)
     N.Amer      Europe        Asia      S.Amer     Oceania      Africa    Mid.Amer 
127181160.6  51776902.0   4512287.6    246698.6    273595.0    419524.3     31019.9

lapply()函数处理列表，转化为列表

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
> state.center
$x
 [1]  -86.7509 -127.2500 -111.6250  -92.2992 -119.7730 -105.5130  -72.3573  -74.9841  -81.6850  -83.3736 -126.2500 -113.9300
[13]  -89.3776  -86.0808  -93.3714  -98.1156  -84.7674  -92.2724  -68.9801  -76.6459  -71.5800  -84.6870  -94.6043  -89.8065
[25]  -92.5137 -109.3200  -99.5898 -116.8510  -71.3924  -74.2336 -105.9420  -75.1449  -78.4686 -100.0990  -82.5963  -97.1239
[37] -120.0680  -77.4500  -71.1244  -80.5056  -99.7238  -86.4560  -98.7857 -111.3300  -72.5450  -78.2005 -119.7460  -80.6665
[49]  -89.9941 -107.2560

$y
 [1] 32.5901 49.2500 34.2192 34.7336 36.5341 38.6777 41.5928 38.6777 27.8744 32.3329 31.7500 43.5648 40.0495 40.0495 41.9358
[16] 38.4204 37.3915 30.6181 45.6226 39.2778 42.3645 43.1361 46.3943 32.6758 38.3347 46.8230 41.3356 39.1063 43.3934 39.9637
[31] 34.4764 43.1361 35.4195 47.2517 40.2210 35.5053 43.9078 40.9069 41.5928 33.6190 44.3365 35.6767 31.3897 39.1063 44.2508
[46] 37.5630 47.4231 38.4204 44.5937 43.0504

> lapply(state.center, FUN = length)
$x
[1] 50

$y
[1] 50

> class(lapply(state.center, FUN = length))
[1] "list"

sapply()函数处理列表，转化为列表

1
2
3
4
5
> sapply(state.center, FUN = length)
 x  y 
50 50 
> class(sapply(state.center, FUN = length))
[1] "integer"
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
> state.name
 [1] "Alabama"        "Alaska"         "Arizona"        "Arkansas"       "California"     "Colorado"       "Connecticut"   
 ...  
[43] "Texas"          "Utah"           "Vermont"        "Virginia"       "Washington"     "West Virginia"  "Wisconsin"     
[50] "Wyoming"       
> state.division
 [1] East South Central Pacific            Mountain           West South Central Pacific            Mountain     
 ...
[43] West South Central Mountain           New England        South Atlantic     Pacific            South Atlantic    
[49] East North Central Mountain          
9 Levels: New England Middle Atlantic South Atlantic East South Central West South Central ... Pacific
> tapply(state.name, state.division, FUN = length)
       New England    Middle Atlantic     South Atlantic East South Central West South Central East North Central 
                 6                  3                  8                  4                  4                  5 
West North Central           Mountain            Pacific 
                 7                  8                  5

数据标准化处理\

x∗=x−xˉσx^* = \frac{x - \bar{x}}{\sigma} 

1
heatmap(as.matrix(mtcars))

未标准化处理的热力图

1
2
> x <- scale(mtcars, center = TRUE, scale = TRUE)
> heatmap(x)

标准化处理的热力图

reshape2包

类似数据库的操作

1
2
> install.packages("reshape2")
> library(reshape2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
> airquality
    ozone solar.r wind temp month day
1      41     190  7.4   67     5   1
2      36     118  8.0   72     5   2
...
152    18     131  8.0   76     9  29
153    20     223 11.5   68     9  30
> names(airquality) <- tolower(names(airquality))
> head(airquality)
  ozone solar.r wind temp month day
1    41     190  7.4   67     5   1
2    36     118  8.0   72     5   2
3    12     149 12.6   74     5   3
4    18     313 11.5   62     5   4
5    NA      NA 14.3   56     5   5
6    28      NA 14.9   66     5   6

melt()函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
> melt(airquality)
No id variables; using all as measure variables
    variable value
1      ozone  41.0
2      ozone  36.0
...
152    ozone  18.0
153    ozone  20.0
154  solar.r 190.0
155  solar.r 118.0
...
305  solar.r 131.0
306  solar.r 223.0
...
...
460     temp  67.0
461     temp  72.0
...
499     temp  90.0
500     temp  87.0
 [ reached 'max' / getOption("max.print") -- omitted 418 rows ]
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
> aql <- melt(airquality, id.vars = c("month", "day"))
> aql
    month day variable value
1       5   1    ozone    41
2       5   2    ozone    36
...
29      5  29    ozone    45
30      5  30    ozone   115
31      5  31    ozone    37
32      6   1    ozone    NA
33      6   2    ozone    NA
...
60      6  29    ozone    NA
61      6  30    ozone    NA
...
...
124     9   1    ozone    96
125     9   2    ozone    78
...
152     9  29    ozone    18
153     9  30    ozone    20
154     5   1  solar.r   190
155     5   2  solar.r   118
...
183     5  30  solar.r   223
184     5  31  solar.r   279
185     6   1  solar.r   286
186     6   2  solar.r   287
...
213     6  29  solar.r    31
214     6  30  solar.r   138
...
...
246     8   1  solar.r    83
247     8   2  solar.r    24
248     8   3  solar.r    77
249     8   4  solar.r    NA
250     8   5  solar.r    NA
 [ reached 'max' / getOption("max.print") -- omitted 362 rows ]
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
> aqw <- dcast(aql,month + day ~ variable)
> aqw
    month day ozone solar.r wind temp
1       5   1    41     190  7.4   67
2       5   2    36     118  8.0   72
...
30      5  30   115     223  5.7   79
31      5  31    37     279  7.4   76
32      6   1    NA     286  8.6   78
33      6   2    NA     287  9.7   74
...
60      6  29    NA      31 14.9   77
61      6  30    NA     138  8.0   83
...
...
124     9   1    96     167  6.9   91
125     9   2    78     197  5.1   92
...
152     9  29    18     131  8.0   76
153     9  30    20     223 11.5   68

dcast()函数

类似透视表

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
> aqw2 <- dcast(aql,month ~ variable,fun.aggregate =  mean,na.rm = TRUE)
> aqw2
  month    ozone  solar.r      wind     temp
1     5 23.61538 181.2963 11.622581 65.54839
2     6 29.44444 190.1667 10.266667 79.10000
3     7 59.11538 216.4839  8.941935 83.90323
4     8 59.96154 171.8571  8.793548 83.96774
5     9 31.44828 167.4333 10.180000 76.90000
> aqw2 <- dcast(aql,month ~ variable,fun.aggregate =  sum,na.rm = TRUE)
> aqw2
  month ozone solar.r  wind temp
1     5   614    4895 360.3 2032
2     6   265    5705 308.0 2373
3     7  1537    6711 277.2 2601
4     8  1559    4812 272.6 2603
5     9   912    5023 305.4 2307

tidyr包

1
2
3
> install.packages(c("tidyr", "dplyr"))
> library(tidyr)
> library(dplyr)

gather()函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
> 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
...
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
> tdata <- mtcars[1:10, 1:3]
> tdata <- data.frame(names = rownames(tdata), tdata)
> tdata
                              names  mpg cyl  disp
Mazda RX4                 Mazda RX4 21.0   6 160.0
Mazda RX4 Wag         Mazda RX4 Wag 21.0   6 160.0
...
Merc 230                   Merc 230 22.8   4 140.8
Merc 280                   Merc 280 19.2   6 167.6
> gather(tdata, key = "Key", value = "Value", cyl, disp, mpg)
               names  Key Value
1          Mazda RX4  cyl   6.0
2      Mazda RX4 Wag  cyl   6.0
...
9           Merc 230  cyl   4.0
10          Merc 280  cyl   6.0
11         Mazda RX4 disp 160.0
12     Mazda RX4 Wag disp 160.0
...
19          Merc 230 disp 140.8
20          Merc 280 disp 167.6
21         Mazda RX4  mpg  21.0
22     Mazda RX4 Wag  mpg  21.0
...
29          Merc 230  mpg  22.8
30          Merc 280  mpg  19.2
> gather(tdata, key = "Key", value = "Value", cyl: disp, mpg)
               names  Key Value
1          Mazda RX4  cyl   6.0
2      Mazda RX4 Wag  cyl   6.0
...
9           Merc 230  cyl   4.0
10          Merc 280  cyl   6.0
11         Mazda RX4 disp 160.0
12     Mazda RX4 Wag disp 160.0
...
19          Merc 230 disp 140.8
20          Merc 280 disp 167.6
21         Mazda RX4  mpg  21.0
22     Mazda RX4 Wag  mpg  21.0
...
29          Merc 230  mpg  22.8
30          Merc 280  mpg  19.2
> gather(tdata, key = "Key", value = "Value", cyl, -disp)
               names  mpg  disp Key Value
1          Mazda RX4 21.0 160.0 cyl     6
2      Mazda RX4 Wag 21.0 160.0 cyl     6
...
9           Merc 230 22.8 140.8 cyl     4
10          Merc 280 19.2 167.6 cyl     6
> gather(tdata, key = "Key", value = "Value", 2:4)
               names  Key Value
1          Mazda RX4  mpg  21.0
2      Mazda RX4 Wag  mpg  21.0
...
9           Merc 230  mpg  22.8
10          Merc 280  mpg  19.2
11         Mazda RX4  cyl   6.0
...
19          Merc 230  cyl   4.0
20          Merc 280  cyl   6.0
21         Mazda RX4 disp 160.0
22     Mazda RX4 Wag disp 160.0
...
29          Merc 230 disp 140.8
30          Merc 280 disp 167.6

spread()函数

1
2
3
4
5
6
7
8
9
10
11
12
13
> gdata <- gather(tdata, key = "Key", value = "Value", 2:4)
> spread(gdata, key = "Key", value = "Value")
               names cyl  disp  mpg
1         Datsun 710   4 108.0 22.8
2         Duster 360   8 360.0 14.3
3     Hornet 4 Drive   6 258.0 21.4
4  Hornet Sportabout   8 360.0 18.7
5          Mazda RX4   6 160.0 21.0
6      Mazda RX4 Wag   6 160.0 21.0
7           Merc 230   4 140.8 22.8
8          Merc 240D   4 146.7 24.4
9           Merc 280   6 167.6 19.2
10           Valiant   6 225.0 18.1

separate()函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
> df <- data.frame(x = c(NA, "a.b", "a.d", "b.c"))
> df
     x
1 <NA>
2  a.b
3  a.d
4  b.c
> separate(df, col = x, into = c("A", "B"))
     A    B
1 <NA> <NA>
2    a    b
3    a    d
4    b    c
> df <- data.frame(x = c(NA, "a.b-c", "a-d", "a-b.c"))
> df
      x
1  <NA>
2 a.b-c
3   a-d
4 a-b.c
> separate(df, col = x, into = c("A", "B"), sep = "-")
     A    B
1 <NA> <NA>
2  a.b    c
3    a    d
4    a  b.c

unite()函数

1
2
3
4
5
6
7
> x <- separate(df, col = x, into = c("A", "B"), sep = "-")
> unite(x, col = "AB", A, B, sep = "-")
     AB
1 NA-NA
2 a.b-c
3   a-d
4 a-b.c

dplyr包

1
2
install.packages("dplyr")
library(dplyr)

dplyr::filter()

按条件筛选

1
2
3
4
5
6
7
8
9
10
11
12
13
14
> dplyr::filter(iris, Sepal.Length > 7)
   Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
1           7.1         3.0          5.9         2.1 virginica
2           7.6         3.0          6.6         2.1 virginica
3           7.3         2.9          6.3         1.8 virginica
4           7.2         3.6          6.1         2.5 virginica
5           7.7         3.8          6.7         2.2 virginica
6           7.7         2.6          6.9         2.3 virginica
7           7.7         2.8          6.7         2.0 virginica
8           7.2         3.2          6.0         1.8 virginica
9           7.2         3.0          5.8         1.6 virginica
10          7.4         2.8          6.1         1.9 virginica
11          7.9         3.8          6.4         2.0 virginica
12          7.7         3.0          6.1         2.3 virginica

dplyr::distinct()

去除重复行

1
2
3
4
5
6
7
8
9
10
11
12
13
14
> rbind(iris[1:10, ], iris[1:15, ])
   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1           5.1         3.5          1.4         0.2  setosa
2           4.9         3.0          1.4         0.2  setosa
...
24          4.3         3.0          1.1         0.1  setosa
25          5.8         4.0          1.2         0.2  setosa
> dplyr::distinct(rbind(iris[1:10, ], iris[1:15, ]))
   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1           5.1         3.5          1.4         0.2  setosa
2           4.9         3.0          1.4         0.2  setosa
...
14          4.3         3.0          1.1         0.1  setosa
15          5.8         4.0          1.2         0.2  setosa

dplyr::slice()

取出数据的任意行

1
2
3
4
5
6
7
8
> dplyr::slice(iris, 10:15)
  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          4.9         3.1          1.5         0.1  setosa
2          5.4         3.7          1.5         0.2  setosa
3          4.8         3.4          1.6         0.2  setosa
4          4.8         3.0          1.4         0.1  setosa
5          4.3         3.0          1.1         0.1  setosa
6          5.8         4.0          1.2         0.2  setosa

dplyr::sample()

随机抽取行数

1
2
3
4
5
6
7
8
9
10
11
12
> dplyr::sample_n(iris, 10)
   Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1           7.4         2.8          6.1         1.9  virginica
2           5.1         3.7          1.5         0.4     setosa
3           6.4         2.7          5.3         1.9  virginica
4           4.9         3.1          1.5         0.2     setosa
5           7.1         3.0          5.9         2.1  virginica
6           7.2         3.6          6.1         2.5  virginica
7           4.4         2.9          1.4         0.2     setosa
8           6.5         2.8          4.6         1.5 versicolor
9           6.3         2.5          5.0         1.9  virginica
10          6.4         3.1          5.5         1.8  virginica

按比例抽取行数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
> dplyr::sample_frac(iris, 0.1)
   Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1           7.2         3.0          5.8         1.6  virginica
2           6.6         2.9          4.6         1.3 versicolor
3           5.2         4.1          1.5         0.1     setosa
4           5.4         3.9          1.7         0.4     setosa
5           6.9         3.1          5.1         2.3  virginica
6           6.8         3.2          5.9         2.3  virginica
7           6.1         2.9          4.7         1.4 versicolor
8           5.1         3.8          1.5         0.3     setosa
9           6.6         3.0          4.4         1.4 versicolor
10          5.1         3.8          1.9         0.4     setosa
11          7.7         2.6          6.9         2.3  virginica
12          4.9         2.5          4.5         1.7  virginica
13          5.7         2.9          4.2         1.3 versicolor
14          4.6         3.6          1.0         0.2     setosa
15          5.4         3.0          4.5         1.5 versicolor

dplyr::arrange()

以某一列为基准排序

1
2
3
4
5
6
7
> dplyr::arrange(iris, Sepal.Length)
    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1            4.3         3.0          1.1         0.1     setosa
2            4.4         2.9          1.4         0.2     setosa
...
149          7.7         3.0          6.1         2.3  virginica
150          7.9         3.8          6.4         2.0  virginica
1
2
3
4
5
6
7
> dplyr::arrange(iris, desc(Sepal.Length))
    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
1            7.9         3.8          6.4         2.0  virginica
2            7.7         3.8          6.7         2.2  virginica
...
149          4.4         3.2          1.3         0.2     setosa
150          4.3         3.0          1.1         0.1     setosa

summarise()

1
2
3
4
5
6
> summarise(iris, avg = mean(Sepal.Length))
       avg
1 5.843333
> summarise(iris, sum = sum(Sepal.Length))
    sum
1 876.5

链式操作符 %>%

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
> head(mtcars, 20)
                     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
> head(mtcars, 20) %>% tail(10)
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
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

dplyr::group_by()分组

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
> dplyr::group_by(iris, Species)
# A tibble: 150 × 5
# Groups:   Species [3]
   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
          <dbl>       <dbl>        <dbl>       <dbl> <fct>  
 1          5.1         3.5          1.4         0.2 setosa 
 2          4.9         3            1.4         0.2 setosa 
 3          4.7         3.2          1.3         0.2 setosa 
 4          4.6         3.1          1.5         0.2 setosa 
 5          5           3.6          1.4         0.2 setosa 
 6          5.4         3.9          1.7         0.4 setosa 
 7          4.6         3.4          1.4         0.3 setosa 
 8          5           3.4          1.5         0.2 setosa 
 9          4.4         2.9          1.4         0.2 setosa 
10          4.9         3.1          1.5         0.1 setosa 
# … with 140 more rows
# ℹ Use `print(n = ...)` to see more rows
> iris %>% group_by(Species)
# A tibble: 150 × 5
# Groups:   Species [3]
   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
          <dbl>       <dbl>        <dbl>       <dbl> <fct>  
 1          5.1         3.5          1.4         0.2 setosa 
 2          4.9         3            1.4         0.2 setosa 
 3          4.7         3.2          1.3         0.2 setosa 
 4          4.6         3.1          1.5         0.2 setosa 
 5          5           3.6          1.4         0.2 setosa 
 6          5.4         3.9          1.7         0.4 setosa 
 7          4.6         3.4          1.4         0.3 setosa 
 8          5           3.4          1.5         0.2 setosa 
 9          4.4         2.9          1.4         0.2 setosa 
10          4.9         3.1          1.5         0.1 setosa 
# … with 140 more rows
# ℹ Use `print(n = ...)` to see more rows
> iris %>% group_by(Species) %>% summarise()
# A tibble: 3 × 1
  Species   
  <fct>     
1 setosa    
2 versicolor
3 virginica 
> iris %>% group_by(Species) %>% summarise(avg = mean(Sepal.Width))
# A tibble: 3 × 2
  Species      avg
  <fct>      <dbl>
1 setosa      3.43
2 versicolor  2.77
3 virginica   2.97
> iris %>% group_by(Species) %>% summarise(avg = mean(Sepal.Width)) %>% arrange(avg)
# A tibble: 3 × 2
  Species      avg
  <fct>      <dbl>
1 versicolor  2.77
2 virginica   2.97
3 setosa      3.43

dplyr::mutate()

添加新的变量

1
2
3
4
5
6
7
> dplyr::mutate(iris, new = Sepal.Length + Petal.Length)
    Sepal.Length Sepal.Width Petal.Length Petal.Width    Species  new
1            5.1         3.5          1.4         0.2     setosa  6.5
2            4.9         3.0          1.4         0.2     setosa  6.3
...
149          6.2         3.4          5.4         2.3  virginica 11.6
150          5.9         3.0          5.1         1.8  virginica 11.0

链接函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
> a = data.frame(x1 = c("A", "B", "C"), x2 = c(1, 2, 3))
> b = data.frame(x1 = c("A", "B", "D"), x3 = c(T, F, T))
> a
  x1 x2
1  A  1
2  B  2
3  C  3
> b
  x1    x3
1  A  TRUE
2  B FALSE
3  D  TRUE
> dplyr::left_join(a, b, by = "x1")
  x1 x2    x3
1  A  1  TRUE
2  B  2 FALSE
3  C  3    NA
> dplyr::right_join(a, b, by = "x1")
  x1 x2    x3
1  A  1  TRUE
2  B  2 FALSE
3  D NA  TRUE
> dplyr::full_join(a, b, by = "x1")
  x1 x2    x3
1  A  1  TRUE
2  B  2 FALSE
3  C  3    NA
4  D NA  TRUE
> dplyr::semi_join(a, b, by = "x1")
  x1 x2
1  A  1
2  B  2
> dplyr::anti_join(a, b, by = "x1")
  x1 x2
1  C  3

交集并集补集

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
> mtcars <- mutate(mtcars, Model = rownames(mtcars))
> mtcars
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb               Model
Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4           Mazda RX4
Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4       Mazda RX4 Wag
Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1          Datsun 710
Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1      Hornet 4 Drive
Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2   Hornet Sportabout
Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1             Valiant
Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4          Duster 360
Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2           Merc 240D
Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2            Merc 230
Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4            Merc 280
Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4           Merc 280C
Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3          Merc 450SE
Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3          Merc 450SL
Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3         Merc 450SLC
Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4  Cadillac Fleetwood
Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4 Lincoln Continental
Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4   Chrysler Imperial
Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1            Fiat 128
Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2         Honda Civic
Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1      Toyota Corolla
Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1       Toyota Corona
Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2    Dodge Challenger
AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2         AMC Javelin
Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4          Camaro Z28
Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2    Pontiac Firebird
Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1           Fiat X1-9
Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2       Porsche 914-2
Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2        Lotus Europa
Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4      Ford Pantera L
Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6        Ferrari Dino
Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8       Maserati Bora
Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2          Volvo 142E
> first <- slice(mtcars, 1:20)
> second <- slice(mtcars, 10:30)

交集

1
2
3
4
5
6
7
8
9
10
11
12
13
> intersect(first, second)
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb               Model
Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4            Merc 280
Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4           Merc 280C
Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3          Merc 450SE
Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3          Merc 450SL
Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3         Merc 450SLC
Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4  Cadillac Fleetwood
Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4 Lincoln Continental
Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4   Chrysler Imperial
Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1            Fiat 128
Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2         Honda Civic
Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1      Toyota Corolla

并集

1
2
3
4
5
6
7
8
9
10
11
12
> dplyr::union_all(first, second)
                          mpg cyl  disp  hp drat    wt  qsec vs am gear carb               Model
Mazda RX4                21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4           Mazda RX4
Mazda RX4 Wag            21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4       Mazda RX4 Wag
...
Honda Civic...19         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2         Honda Civic
Toyota Corolla...20      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1      Toyota Corolla
Merc 280...21            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4            Merc 280
Merc 280C...22           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4           Merc 280C
...
Ford Pantera L           15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4      Ford Pantera L
Ferrari Dino             19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6        Ferrari Dino

不交并

1
2
3
4
5
6
7
> dplyr::union(first, second)
                     mpg cyl  disp  hp drat    wt  qsec vs am gear carb               Model
Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4           Mazda RX4
Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4       Mazda RX4 Wag
...
Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4      Ford Pantera L
Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6        Ferrari Dino

补集

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
> setdiff(first, second)
                   mpg cyl  disp  hp drat    wt  qsec vs am gear carb             Model
Mazda RX4         21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4         Mazda RX4
Mazda RX4 Wag     21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4     Mazda RX4 Wag
Datsun 710        22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1        Datsun 710
Hornet 4 Drive    21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1    Hornet 4 Drive
Hornet Sportabout 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2 Hornet Sportabout
Valiant           18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1           Valiant
Duster 360        14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4        Duster 360
Merc 240D         24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2         Merc 240D
Merc 230          22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2          Merc 230
> setdiff(second, first)
                  mpg cyl  disp  hp drat    wt  qsec vs am gear carb            Model
Toyota Corona    21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1    Toyota Corona
Dodge Challenger 15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2 Dodge Challenger
AMC Javelin      15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2      AMC Javelin
Camaro Z28       13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4       Camaro Z28
Pontiac Firebird 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2 Pontiac Firebird
Fiat X1-9        27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1        Fiat X1-9
Porsche 914-2    26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2    Porsche 914-2
Lotus Europa     30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2     Lotus Europa
Ford Pantera L   15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4   Ford Pantera L
Ferrari Dino     19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6     Ferrari Dino

数据分析