利用R语言进行基本数据管理

####创建leadership数据框
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, 45, 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)

####创建新变量
my_data <- data.frame(x1 = c(2, 2, 6, 4),
                      x2 = c(3, 4, 2, 8))
my_data <- transform(my_data,
                     sum_x = x1 + x2,
                     mean_x = (x1 + x2)/2)
my_data


####变量的重编码
leadership
leadership$age[leadership$age == 99] <- NA
leadership$age[leadership$age >  75] <- "Elder"
leadership$age[leadership$age >= 55 &
               leadership$age <= 75] <- "Middle Aged"
leadership$age[leaders