1.data.fram(), 2.head(),tail(),str() 3.names(),colnames() 4.访问数据框[],$,subset() 5.新增列，删除列$

1.data.fram(), 2.head(),tail(),str() 3.names(),colnames() 4.访问数据框[],$,subset()5.新增列，删除列$

 #1.数据框的创建 data.frame()
> company <- c("A", "A", "B","C","D","C")
> cash_flow <- c(100, 200, 300,800,500,1000)
> year <- c(1, 3, 2,5,3,8)
> 
> cash=data.frame(company, cash_flow, year)
> cashcompany cash_flow year
1       A       100    1
2       A       200    3
3       B       300    2
4       C       800    5
5       D       500    3
6       C      1000    8
> 
> a=data.frame(company = c("A", "A", "B","C","D","C"), cash_flow = c(100, 200, 300,800,500,1000), year = c(1, 3, 2,5,3,8))
> acompany cash_flow year
1       A       100    1
2       A       200    3
3       B       300    2
4       C       800    5
5       D       500    3
6       C      1000    8
> #2. head()和tail()函数访问数据的首末行
> #head() 返回数据框的前几行。默认情况下是6。若要更改此，请使用 head(数据, n = ___)。
> #tail() 返回数据框的最后几行。默认情况下是6。若要更改此，请使用tail(数据, n = ___)。
> #str() 检查一个物体的结构。这个奇妙的函数将显示您传入的对象的数据类型(在这里是数据.框架)，并列出每个列变量及其数据类型。
> head(cash,2)company cash_flow year
1       A       100    1
2       A       200    3
> tail(cash,2)company cash_flow year
5       D       500    3
6       C      1000    8
> str(cash)
'data.frame':	6 obs. of  3 variables:$ company  : chr  "A" "A" "B" "C" ...$ cash_flow: num  100 200 300 800 500 1000$ year     : num  1 3 2 5 3 8
> 
> #3.names函数,colnames函数给变量修改元素名称
> names(cash) <- c('comp','cash','yr')
> cashcomp cash yr
1    A  100  1
2    A  200  3
3    B  300  2
4    C  800  5
5    D  500  3
6    C 1000  8
> 
> names(cash)[1] <-  c('company')
> cashcompany cash yr
1       A  100  1
2       A  200  3
3       B  300  2
4       C  800  5
5       D  500  3
6       C 1000  8
> 
> colnames(cash)[1:2] <- c('co','ca')
> cashco   ca yr
1  A  100  1
2  A  200  3
3  B  300  2
4  C  800  5
5  D  500  3
6  C 1000  8
> 
> names(cash) <-  c('company')
> cashcompany   NA NA
1       A  100  1
2       A  200  3
3       B  300  2
4       C  800  5
5       D  500  3
6       C 1000  8
> 
> 
> #4. 访问和子集化数据框
> #(1)  [ ] 形式访问
> cash=data.frame(company = c("A", "A", "B","C","D","C"), cash_flow = c(100, 200, 300,800,500,1000), year = c(1, 3, 2,5,3,8))
> cashcompany cash_flow year
1       A       100    1
2       A       200    3
3       B       300    2
4       C       800    5
5       D       500    3
6       C      1000    8
> cash[1,]company cash_flow year
1       A       100    1
> cash[,1]
[1] "A" "A" "B" "C" "D" "C"
> cash[3,2]
[1] 300
> cash[5,'year']
[1] 3
> 
> 
> #（2）$ 形式访问
> cash$cash_flow
[1]  100  200  300  800  500 1000
> #他等价于
> cash[,"cash_flow"]
[1]  100  200  300  800  500 1000
> > #(3) subset( )访问
> cash=data.frame(company = c("A", "A", "B","C","D","C"), cash_flow = c(100, 200, 300,800,500,1000), year = c(1, 3, 2,5,3,8))
> cashcompany cash_flow year
1       A       100    1
2       A       200    3
3       B       300    2
4       C       800    5
5       D       500    3
6       C      1000    8
> subset(cash, company =="A")company cash_flow year
1       A       100    1
2       A       200    3
> 
> 
> #5. 增加新列
>  # step 1.四分之一现金流添加到数据框
>  cash$quarter_cash <- cash$cash_flow *1/4
>  # step 2.双倍年数回收你的钱到数据框
> cash$double_year <- cash$year *2
> cashcompany cash_flow year quarter_cash double_year
1       A       100    1           25           2
2       A       200    3           50           6
3       B       300    2           75           4
4       C       800    5          200          10
5       D       500    3          125           6
6       C      1000    8          250          16
> 
> library(MASS)
> b<-biopsy   #复制数据
> head(b)ID V1 V2 V3 V4 V5 V6 V7 V8 V9     class
1 1000025  5  1  1  1  2  1  3  1  1    benign
2 1002945  5  4  4  5  7 10  3  2  1    benign
3 1015425  3  1  1  1  2  2  3  1  1    benign
4 1016277  6  8  8  1  3  4  3  7  1    benign
5 1017023  4  1  1  3  2  1  3  1  1    benign
6 1017122  8 10 10  8  7 10  9  7  1 malignant
> 
> b$classn[b$class=="benign"]<-0  #重新赋值
> b$classn[b$class=="malignant"]<-1
> bID V1 V2 V3 V4 V5 V6 V7 V8 V9     class classn
1  1000025  5  1  1  1  2  1  3  1  1    benign      0
2  1002945  5  4  4  5  7 10  3  2  1    benign      0
3  1015425  3  1  1  1  2  2  3  1  1    benign      0
4  1016277  6  8  8  1  3  4  3  7  1    benign      0
5  1017023  4  1  1  3  2  1  3  1  1    benign      0
6  1017122  8 10 10  8  7 10  9  7  1 malignant      1> > #(3)可以通过指定NULL来删除列。运行代码来删除company。
> cash$company <- NULL
> cashcash_flow year
1       100    1
2       200    3
3       300    2
4       800    5
5       500    3
6      1000    8
>