数据框的来源

数据框一般有四种来源：在R中新建；由已有数据转换或处理得到；从文件中读取；内置数据集

新建和读取数据框

新建数据框需要用data.frame()函数

> df <- data.frame(gene    = paste0("gene",1:4),
+                  change  = rep(c("up","down"),each = 2),
+                  score   = c(5,3,-2,-4))
> df
   gene change score
1 gene1     up     5
2 gene2     up     3
3 gene3   down    -2
4 gene4   down    -4

读取数据框需要将csv文件放在【Project文件夹内】，需要read.csv()函数

> df2 <- read.csv("gene.csv")
> df2
   gene change score
1 gene1     up     5
2 gene2     up     3
3 gene3   down    -2
4 gene4   down    -4

数据框属性

查看数据框的行数列数、行名列名

> df <- data.frame(gene    = paste0("gene",1:4),
+                  change  = rep(c("up","down"),each = 2),
+                  score   = c(5,3,-2,-4))
> df
   gene change score
1 gene1     up     5
2 gene2     up     3
3 gene3   down    -2
4 gene4   down    -4
> dim(df)
[1] 4 3
> nrow(df)
[1] 4
> ncol(df)
[1] 3
> rownames(df)
[1] "1" "2" "3" "4"
> colnames(df)
[1] "gene"   "change" "score"

数据框取子集

按坐标取子集

> df[2,2]
[1] "up"
> df[2,]
   gene change score
2 gene2     up     3
> df[,2]
[1] "up"   "up"   "down" "down"
> df[c(1,3),1:2]
   gene change
1 gene1     up
3 gene3   down

按名字取子集

> df[,"gene"]
[1] "gene1" "gene2" "gene3" "gene4"
> df[,c('gene','change')]
   gene change
1 gene1     up
2 gene2     up
3 gene3   down
4 gene4   down

按条件取子集（逻辑值）

> df[df$score>0,]
   gene change score
1 gene1     up     5
2 gene2     up     3

取最后一列（或者除最后一列）

> df[,3]
[1]  5  3 -2 -4
> df[,ncol(df)]
[1]  5  3 -2 -4
> df[,-ncol(df)]
   gene change
1 gene1     up
2 gene2     up
3 gene3   down
4 gene4   down

筛选score>0的基因

> df[df$score>0,1]
[1] "gene1" "gene2"
> df$gene[df$score>0]
[1] "gene1" "gene2"

数据框编辑

改一个格子

> df <- data.frame(gene    = paste0("gene",1:4),
+                  change  = rep(c("up","down"),each = 2),
+                  score   = c(5,3,-2,-4))
> df
   gene change score
1 gene1     up     5
2 gene2     up     3
3 gene3   down    -2
4 gene4   down    -4
> df[3,3]<- 5
> df
   gene change score
1 gene1     up     5
2 gene2     up     3
3 gene3   down     5
4 gene4   down    -4

改一整列

> df$score<-c(12,23,50,2)     
> df
   gene change score
1 gene1     up    12
2 gene2     up    23
3 gene3   down    50
4 gene4   down     2

新增一列

> df$p.value <-c(0.01,0.02,0.07,0.05) 
> df
   gene change score p.value
1 gene1     up    12    0.01
2 gene2     up    23    0.02
3 gene3   down    50    0.07
4 gene4   down     2    0.05

改行名和列名

> rownames(df) <- c("r1","r2","r3","r4")
> df
    gene change score p.value
r1 gene1     up    12    0.01
r2 gene2     up    23    0.02
r3 gene3   down    50    0.07
r4 gene4   down     2    0.05

只修改某一行/列的名字

> colnames(df)[2]="CHANGE"
> df
    gene CHANGE score p.value
r1 gene1     up    12    0.01
r2 gene2     up    23    0.02
r3 gene3   down    50    0.07
r4 gene4   down     2    0.05

数据框进阶

行数较多的数据框可截取前/后几行查看

> iris
    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
3            4.7         3.2          1.3         0.2     setosa
4            4.6         3.1          1.5         0.2     setosa
5            5.0         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            5.0         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
11           5.4         3.7          1.5         0.2     setosa
12           4.8         3.4          1.6         0.2     setosa
13           4.8         3.0          1.4         0.1     setosa
14           4.3         3.0          1.1         0.1     setosa
15           5.8         4.0          1.2         0.2     setosa
16           5.7         4.4          1.5         0.4     setosa
17           5.4         3.9          1.3         0.4     setosa
18           5.1         3.5          1.4         0.3     setosa
19           5.7         3.8          1.7         0.3     setosa
20           5.1         3.8          1.5         0.3     setosa
21           5.4         3.4          1.7         0.2     setosa
22           5.1         3.7          1.5         0.4     setosa
23           4.6         3.6          1.0         0.2     setosa
24           5.1         3.3          1.7         0.5     setosa
25           4.8         3.4          1.9         0.2     setosa
26           5.0         3.0          1.6         0.2     setosa
27           5.0         3.4          1.6         0.4     setosa
28           5.2         3.5          1.5         0.2     setosa
29           5.2         3.4          1.4         0.2     setosa
30           4.7         3.2          1.6         0.2     setosa
31           4.8         3.1          1.6         0.2     setosa
32           5.4         3.4          1.5         0.4     setosa
33           5.2         4.1          1.5         0.1     setosa
34           5.5         4.2          1.4         0.2     setosa
35           4.9         3.1          1.5         0.2     setosa
36           5.0         3.2          1.2         0.2     setosa
37           5.5         3.5          1.3         0.2     setosa
38           4.9         3.6          1.4         0.1     setosa
39           4.4         3.0          1.3         0.2     setosa
40           5.1         3.4          1.5         0.2     setosa
41           5.0         3.5          1.3         0.3     setosa
42           4.5         2.3          1.3         0.3     setosa
43           4.4         3.2          1.3         0.2     setosa
44           5.0         3.5          1.6         0.6     setosa
45           5.1         3.8          1.9         0.4     setosa
46           4.8         3.0          1.4         0.3     setosa
47           5.1         3.8          1.6         0.2     setosa
48           4.6         3.2          1.4         0.2     setosa
49           5.3         3.7          1.5         0.2     setosa
50           5.0         3.3          1.4         0.2     setosa
51           7.0         3.2          4.7         1.4 versicolor
52           6.4         3.2          4.5         1.5 versicolor
53           6.9         3.1          4.9         1.5 versicolor
54           5.5         2.3          4.0         1.3 versicolor
55           6.5         2.8          4.6         1.5 versicolor
56           5.7         2.8          4.5         1.3 versicolor
57           6.3         3.3          4.7         1.6 versicolor
58           4.9         2.4          3.3         1.0 versicolor
59           6.6         2.9          4.6         1.3 versicolor
60           5.2         2.7          3.9         1.4 versicolor
61           5.0         2.0          3.5         1.0 versicolor
62           5.9         3.0          4.2         1.5 versicolor
63           6.0         2.2          4.0         1.0 versicolor
64           6.1         2.9          4.7         1.4 versicolor
65           5.6         2.9          3.6         1.3 versicolor
66           6.7         3.1          4.4         1.4 versicolor
67           5.6         3.0          4.5         1.5 versicolor
68           5.8         2.7          4.1         1.0 versicolor
69           6.2         2.2          4.5         1.5 versicolor
70           5.6         2.5          3.9         1.1 versicolor
71           5.9         3.2          4.8         1.8 versicolor
72           6.1         2.8          4.0         1.3 versicolor
73           6.3         2.5          4.9         1.5 versicolor
74           6.1         2.8          4.7         1.2 versicolor
75           6.4         2.9          4.3         1.3 versicolor
76           6.6         3.0          4.4         1.4 versicolor
77           6.8         2.8          4.8         1.4 versicolor
78           6.7         3.0          5.0         1.7 versicolor
79           6.0         2.9          4.5         1.5 versicolor
80           5.7         2.6          3.5         1.0 versicolor
81           5.5         2.4          3.8         1.1 versicolor
82           5.5         2.4          3.7         1.0 versicolor
83           5.8         2.7          3.9         1.2 versicolor
84           6.0         2.7          5.1         1.6 versicolor
85           5.4         3.0          4.5         1.5 versicolor
86           6.0         3.4          4.5         1.6 versicolor
87           6.7         3.1          4.7         1.5 versicolor
88           6.3         2.3          4.4         1.3 versicolor
89           5.6         3.0          4.1         1.3 versicolor
90           5.5         2.5          4.0         1.3 versicolor
91           5.5         2.6          4.4         1.2 versicolor
92           6.1         3.0          4.6         1.4 versicolor
93           5.8         2.6          4.0         1.2 versicolor
94           5.0         2.3          3.3         1.0 versicolor
95           5.6         2.7          4.2         1.3 versicolor
96           5.7         3.0          4.2         1.2 versicolor
97           5.7         2.9          4.2         1.3 versicolor
98           6.2         2.9          4.3         1.3 versicolor
99           5.1         2.5          3.0         1.1 versicolor
100          5.7         2.8          4.1         1.3 versicolor
101          6.3         3.3          6.0         2.5  virginica
102          5.8         2.7          5.1         1.9  virginica
103          7.1         3.0          5.9         2.1  virginica
104          6.3         2.9          5.6         1.8  virginica
105          6.5         3.0          5.8         2.2  virginica
106          7.6         3.0          6.6         2.1  virginica
107          4.9         2.5          4.5         1.7  virginica
108          7.3         2.9          6.3         1.8  virginica
109          6.7         2.5          5.8         1.8  virginica
110          7.2         3.6          6.1         2.5  virginica
111          6.5         3.2          5.1         2.0  virginica
112          6.4         2.7          5.3         1.9  virginica
113          6.8         3.0          5.5         2.1  virginica
114          5.7         2.5          5.0         2.0  virginica
115          5.8         2.8          5.1         2.4  virginica
116          6.4         3.2          5.3         2.3  virginica
117          6.5         3.0          5.5         1.8  virginica
118          7.7         3.8          6.7         2.2  virginica
119          7.7         2.6          6.9         2.3  virginica
120          6.0         2.2          5.0         1.5  virginica
121          6.9         3.2          5.7         2.3  virginica
122          5.6         2.8          4.9         2.0  virginica
123          7.7         2.8          6.7         2.0  virginica
124          6.3         2.7          4.9         1.8  virginica
125          6.7         3.3          5.7         2.1  virginica
126          7.2         3.2          6.0         1.8  virginica
127          6.2         2.8          4.8         1.8  virginica
128          6.1         3.0          4.9         1.8  virginica
129          6.4         2.8          5.6         2.1  virginica
130          7.2         3.0          5.8         1.6  virginica
131          7.4         2.8          6.1         1.9  virginica
132          7.9         3.8          6.4         2.0  virginica
133          6.4         2.8          5.6         2.2  virginica
134          6.3         2.8          5.1         1.5  virginica
135          6.1         2.6          5.6         1.4  virginica
136          7.7         3.0          6.1         2.3  virginica
137          6.3         3.4          5.6         2.4  virginica
138          6.4         3.1          5.5         1.8  virginica
139          6.0         3.0          4.8         1.8  virginica
140          6.9         3.1          5.4         2.1  virginica
141          6.7         3.1          5.6         2.4  virginica
142          6.9         3.1          5.1         2.3  virginica
143          5.8         2.7          5.1         1.9  virginica
144          6.8         3.2          5.9         2.3  virginica
145          6.7         3.3          5.7         2.5  virginica
146          6.7         3.0          5.2         2.3  virginica
147          6.3         2.5          5.0         1.9  virginica
148          6.5         3.0          5.2         2.0  virginica
149          6.2         3.4          5.4         2.3  virginica
150          5.9         3.0          5.1         1.8  virginica
> head(iris)
  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
3          4.7         3.2          1.3         0.2  setosa
4          4.6         3.1          1.5         0.2  setosa
5          5.0         3.6          1.4         0.2  setosa
6          5.4         3.9          1.7         0.4  setosa
> head(iris,3)
  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
3          4.7         3.2          1.3         0.2  setosa
> tail(iris)
    Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
145          6.7         3.3          5.7         2.5 virginica
146          6.7         3.0          5.2         2.3 virginica
147          6.3         2.5          5.0         1.9 virginica
148          6.5         3.0          5.2         2.0 virginica
149          6.2         3.4          5.4         2.3 virginica
150          5.9         3.0          5.1         1.8 virginica

行列数都多的数据框可取前几行前几列查看

> iris[1:3,1:3]
  Sepal.Length Sepal.Width Petal.Length
1          5.1         3.5          1.4
2          4.9         3.0          1.4
3          4.7         3.2          1.3

查看每一列的数据类型和具体内容

> str(df)
'data.frame':    4 obs. of  4 variables:
 $ gene   : chr  "gene1" "gene2" "gene3" "gene4"
 $ CHANGE : chr  "up" "up" "down" "down"
 $ score  : num  12 23 50 2
 $ p.value: num  0.01 0.02 0.07 0.05
> str(iris)
'data.frame':    150 obs. of  5 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

去除含有缺失值的行

> df<-data.frame(X1 = LETTERS[1:5],X2 = 1:5)
> df[2,2] <- NA
> df[4,1] <- NA
> df
    X1 X2
1    A  1
2    B NA
3    C  3
4 <NA>  4
5    E  5
> na.omit(df)
  X1 X2
1  A  1
3  C  3
5  E  5

两个表格的链接

> test1 <- data.frame(name = c('jimmy','nicker','doodle'), 
+                     blood_type = c("A","B","O"))
> test1
    name blood_type
1  jimmy          A
2 nicker          B
3 doodle          O
> test2 <- data.frame(name = c('doodle','jimmy','nicker','tony'),
+                     group = c("group1","group1","group2","group2"),
+                     vision = c(4.2,4.3,4.9,4.5))
> test2 
    name  group vision
1 doodle group1    4.2
2  jimmy group1    4.3
3 nicker group2    4.9
4   tony group2    4.5
> 
> test3 <- data.frame(NAME = c('doodle','jimmy','lucy','nicker'),
+                     weight = c(140,145,110,138))
> tmp  =merge(test1,test2,by="name")
> merge(test1,test3,by.x = "name",by.y = "NAME")
    name blood_type weight
1 doodle          O    140
2  jimmy          A    145
3 nicker          B    138

矩阵和列表

矩阵

> m <- matrix(1:9, nrow = 3)
> colnames(m) <- c("a","b","c")
> m
     a b c
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9
> m[2,]
a b c 
2 5 8 
> m[,1]
[1] 1 2 3
> m[2,3]
c 
8 
> m[2:3,1:2]
     a b
[1,] 2 5
[2,] 3 6
> m
     a b c
[1,] 1 4 7
[2,] 2 5 8
[3,] 3 6 9
> t(m)
  [,1] [,2] [,3]
a    1    2    3
b    4    5    6
c    7    8    9
> as.data.frame(m)
  a b c
1 1 4 7
2 2 5 8
3 3 6 9

列表

> l <- list(m=matrix(1:9, nrow = 3),
+           df=data.frame(gene  = paste0("gene",1:3),
+                         sam   = paste0("sample",1:3),
+                         exp   = c(32,34,45)),
+           x=c(1,3,5))
> l
$m
     [,1] [,2] [,3]
[1,]    1    4    7
[2,]    2    5    8
[3,]    3    6    9
$df
   gene     sam exp
1 gene1 sample1  32
2 gene2 sample2  34
3 gene3 sample3  45
$x
[1] 1 3 5

给元素命名

> scores = c(100,59,73,95,45)
> names(scores) = c("jimmy","nicker","lucy","doodle","tony")
> scores
 jimmy nicker   lucy doodle   tony 
   100     59     73     95     45 
> scores["jimmy"]
jimmy 
  100 
> scores[c("jimmy","nicker")]
 jimmy nicker 
   100     59 
> 
> names(scores)[scores>60]
[1] "jimmy"  "lucy"   "doodle"

删除

> rm(l)
> rm(df,m)
> rm(list = ls())