R语言数据预处理基础

包含了数据的创建、缺失值判断处理、日期处理、数据排序以及选取，并从三个方面进行了数据的入选观测，包括了SQL语句，需要先下载包。

类型转换函数没有进行测试：
其中涉及转换的有as.numeric() as.character() as.vector() as.matrix() as.data.frame() as.factor() as.logical() 等。

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

> date <- c("10/24/08","10/28/08","10/1/08","10/12/08","5/1/09")

> country <- c("US","US","UK","UK","UK")

> gender <- c("M","F","F","M","F")

> age <- c(32,42,25,39,99)

> q1 <- c(5,3,3,3,2)

> q2 <- c(4,5,5,3,2)

> q3 <- c(5,2,5,4,1)

> q4 <- c(5,5,5,NA,2)

> q5 <- c(5,5,2,NA,1)

> leadership <- data.frame(manager,date,country,gender,age,
+                          q1,q2,q3,q4,q5,stringsAsFactors = FALSE)

> leadership
  manager     date country gender age q1 q2 q3 q4 q5
1       1 10/24/08      US      M  32  5  4  5  5  5
2       2 10/28/08      US      F  42  3  5  2  5  5
3       3  10/1/08      UK      F  25  3  5  5  5  2
4       4 10/12/08      UK      M  39  3  3  4 NA NA
5       5   5/1/09      UK      F  99  2  2  1  2  1

> #对测试数据的缺失值判断
> is.na(leadership[,6:10])
        q1    q2    q3    q4    q5
[1,] FALSE FALSE FALSE FALSE FALSE
[2,] FALSE FALSE FALSE FALSE FALSE
[3,] FALSE FALSE FALSE FALSE FALSE
[4,] FALSE FALSE FALSE  TRUE  TRUE
[5,] FALSE FALSE FALSE FALSE FALSE

> #去除缺失值
> newdata <- na.omit(leadership)

> newdata
  manager     date country gender age q1 q2 q3 q4 q5
1       1 10/24/08      US      M  32  5  4  5  5  5
2       2 10/28/08      US      F  42  3  5  2  5  5
3       3  10/1/08      UK      F  25  3  5  5  5  2
5       5   5/1/09      UK      F  99  2  2  1  2  1

> #数据排序
> newdata1 <- leadership[order(leadership$age),]

> attach(leadership)
The following objects are masked _by_ .GlobalEnv:

    age, country, date, gender, manager, q1, q2, q3, q4, q5

> #按age排序
> newdata1
  manager     date country gender age q1 q2 q3 q4 q5
3       3  10/1/08      UK      F  25  3  5  5  5  2
1       1 10/24/08      US      M  32  5  4  5  5  5
4       4 10/12/08      UK      M  39  3  3  4 NA NA
2       2 10/28/08      US      F  42  3  5  2  5  5
5       5   5/1/09      UK      F  99  2  2  1  2  1

> newdata2 <- leadership[order(gender,age),]

> detach(leadership)

> #按性别分组，年龄升序排序
> newdata2
  manager     date country gender age q1 q2 q3 q4 q5
3       3  10/1/08      UK      F  25  3  5  5  5  2
2       2 10/28/08      US      F  42  3  5  2  5  5
5       5   5/1/09      UK      F  99  2  2  1  2  1
1       1 10/24/08      US      M  32  5  4  5  5  5
4       4 10/12/08      UK      M  39  3  3  4 NA NA

> attach(leadership)
The following objects are masked _by_ .GlobalEnv:

    age, country, date, gender, manager, q1, q2, q3, q4, q5


> newdata3 <- leadership[order(gender,-age),]

> detach(leadership)

> #按性别分组，降序年龄
> newdata3
  manager     date country gender age q1 q2 q3 q4 q5
5       5   5/1/09      UK      F  99  2  2  1  2  1
2       2 10/28/08      US      F  42  3  5  2  5  5
3       3  10/1/08      UK      F  25  3  5  5  5  2
4       4 10/12/08      UK      M  39  3  3  4 NA NA
1       1 10/24/08      US      M  32  5  4  5  5  5

> #入选观测，选择1-3行
> newdata4 <- leadership[1:3,]

> #逻辑比较
> newdata5 <- leadership[leadership$gender=="M" & leadership$age >30]

> attach(leadership)
The following objects are masked _by_ .GlobalEnv:

    age, country, date, gender, manager, q1, q2, q3, q4, q5


> newdata5
  manager gender q1 q4
1       1      M  5  5
2       2      F  3  5
3       3      F  3  5
4       4      M  3 NA
5       5      F  2  2

> #入选观测性别为男，年龄大于30
> newdata6 <- leadership[gender=='M' & age > 30]

> detach(leadership)

> newdata6
  manager gender q1 q4
1       1      M  5  5
2       2      F  3  5
3       3      F  3  5
4       4      M  3 NA
5       5      F  2  2

> #subset()函数实现选择观测
> 
> newdata7 <- subset(leadership,age >= 35 | age<24,select = c(q1,q2,q3,q4))

> newdata7
  q1 q2 q3 q4
2  3  5  2  5
4  3  3  4 NA
5  2  2  1  2

> newdata8 <- subset(leadership,gender=="M" & age>25,select = gender:q4)

> newdata8
  gender age q1 q2 q3 q4
1      M  32  5  4  5  5
4      M  39  3  3  4 NA

> #直接使用sql语句查询
> newdf <- sqldf("select * from leadership where country='US'",row.names = TRUE)

> newdf
  manager     date country gender age q1 q2 q3 q4 q5
1       1 10/24/08      US      M  32  5  4  5  5  5
2       2 10/28/08      US      F  42  3  5  2  5  5

> #日期格式的观测
> 
> #默认方式
> mydates <- as.Date(c("2021-06-22","2022-02-13"))

> mydates
[1] "2021-06-22" "2022-02-13"

> #将默认格式转换为对应日期
> 
> strDates <- c("01/05/2022","08/16/2021")

> dates <- as.Date(strDates,"%m/%d/%Y")

> dates
[1] "2022-01-05" "2021-08-16"

> #将原本数据框里的日期格式转为字符型的
> 
> myformat <- "%m/%d/%y"

> leadership$date <- as.Date(leadership$date,myformat)

> leadership$date
[1] "2008-10-24" "2008-10-28" "2008-10-01" "2008-10-12" "2009-05-01"

> #变量的创建
> mydata <- data.frame(x1=c(2,2,6,4),x2=c(3,4,2,8))

> mydata$sumx <- mydata$x1+mydata$x2

> mydata$meanx <- (mydata$x1 + mydata$x2)/2

> attach(mydata)

> mydata
  x1 x2 sumx meanx
1  2  3    5   2.5
2  2  4    6   3.0
3  6  2    8   4.0
4  4  8   12   6.0

> mydata$sumx <- x1+x2

> mydata$meanx <- (x1+x2)/2

> detach(mydata)

> mydata
  x1 x2 sumx meanx
1  2  3    5   2.5
2  2  4    6   3.0
3  6  2    8   4.0
4  4  8   12   6.0

> mydata <- transform(mydata,sumx=x1+x2,meanx=(x1+x2)/2)

> mydata
  x1 x2 sumx meanx
1  2  3    5   2.5
2  2  4    6   3.0
3  6  2    8   4.0
4  4  8   12   6.0