R语言与数据科学教育：如何培养学生数据分析技能

    # 方式1：使用 <- 或 = 来赋值
    x <- 1   # x 为 numeric 类型
    y <- 'hello'    # y 为 character 类型
    
    # 方式2：使用 assign() 函数赋值
    assign('z', 'world')  # z 为 character 类型
    
      
      
      
      
      
    

    x <- 1    
    y <- a      # ERROR! 不存在的变量 a ，此时 R 会自动创建变量 a 。
    
      
    

    # 这是单行注释
    
    /*
    这是块注释，
    可以跨越多行。
    */
    
      
      
      
      
      
    

    if (条件1){
    表达式1
    } else if (条件2){
    表达式2
    } else{
    表达式3
    }
    
      
      
      
      
      
      
    

    # 判断年龄是否大于18岁
    age <- as.numeric(readline(prompt="请输入你的年龄:"))
    if (age > 18) {
      message("你今年已满18岁！")
    } else {
      message("你还未满18岁！")
    }
    
      
      
      
      
      
      
    

    for (变量 in 值1:值2){
    循环体
    }
    
      
      
    

    for (i in seq_len(10)){
    print(i)
    }
    
      
      
    

    while (条件){
    循环体
    }
    
      
      
    

    num <- 1
    while (num <= 10){
    cat(num, "
    ")
    num <- num + 1
    }
    
      
      
      
      
      
    

    # 读取文本文件
    myfile <- file("example.txt", open = "r")
    text <- readLines(myfile)
    close(myfile)
    
      
      
      
    

    # 读取CSV文件
    myfile <- file("example.csv", open = "r")
    data <- read.csv(myfile)
    close(myfile)
    
      
      
      
    

    # 安装和加载readxl包
    install.packages("readxl")
    library(readxl)
    
    # 读取Excel文件
    myfile <- "example.xlsx"
    data <- read_excel(myfile)
    
      
      
      
      
      
      
    

    # 创建数据集1
    set1 <- data.frame(id=c(1:5), name=c("Alice", "Bob", "Charlie", "David", "Emily"))
    
    # 创建数据集2
    set2 <- data.frame(id=c(3:5), gender=c("Male", "Female", "Male"), city=c("New York", "Chicago", "Los Angeles"))
    
    # 数据合并
    mergedSet <- merge(set1, set2, by.x="id", by.y="id")
    print(mergedSet)
    
      
      
      
      
      
      
      
      
    

    # 把字符型转换为数值型
    x <- "3"
    as.numeric(x) # Output: [1] 3
    
    # 把列表转换为数据框
    list <- list(name=c("Alice", "Bob", "Charlie"), age=c(25, 30, 35))
    df <- data.frame(unlist(list))
    names(df)<- names(list)
    print(df)
    
      
      
      
      
      
      
      
      
    

    # 创建数据集
    mydata <- data.frame(
      id=c(1, 1, 2, 2, 3, 3), 
      value=c(2, 3, 5, 7, 11, 13)
    )
    
    # 对数据集进行聚合
    aggdata <- aggregate(value ~ id, mydata, mean)
    print(aggdata)
    
      
      
      
      
      
      
      
      
    

    # 删除空值
    mydata[complete.cases(mydata), ]
    
    # 按条件筛选
    filter(mydata, value > 5)
    
      
      
      
      
    

    # 生成数据
    values <- c(22, 25, 21, 23, 26, 20, 24)
    groups <- c("A", "A", "B", "B", "C", "C", "D")
    
    # 绘制柱状图
    barplot(height = values, 
        names.arg = groups,
        main = "Sample Bar Chart", 
        xlab = "Groups", 
        ylab = "Values")
    
      
      
      
      
      
      
      
      
      
    

    # 生成数据
    ages <- rnorm(100)
    gender <- sample(c("Male", "Female"), size = 100, replace = T)
    
    # 绘制箱线图
    boxplot(ages~gender,
        main = "Box Plot of Ages vs Gender",
        xlab = "Gender",
        ylab = "Ages",
        col = c("#E74C3C", "#2ECC71"),
        notch = F,
        boxwex =.5)
    
      
      
      
      
      
      
      
      
      
      
      
    

    # 生成数据
    x <- rnorm(100)
    y <- runif(100)
    
    # 绘制散点图
    pairs(cbind(x,y))
    
      
      
      
      
      
    

    # 生成数据
    numbers <- c(22, 25, 21, 23, 26, 20, 24)
    categories <- c("A", "A", "B", "B", "C", "C", "D")
    
    # 绘制条形图
    barplot(numbers, 
        horiz = T,
        names.arg = categories,
        main = "Bar Chart of Numbers per Category", 
        xlab = "Categories", 
        ylab = "Numbers", 
        width = 0.5,
        border = "blue",
        space = 0)
    
      
      
      
      
      
      
      
      
      
      
      
      
      
    

    # 生成数据
    grades <- c(80, 75, 85, 90, 65, 95, 80, 85, 95, 70)
    
    # 绘制直方图
    hist(grades, 
     breaks = seq(from = min(grades)-1, to = max(grades)+1, length.out = 10),
     freq = F,
     main = "Histogram of Grades", 
     xlab = "Grades", 
     ylab = "Frequency", 
     col = "lightblue")
    
      
      
      
      
      
      
      
      
      
      
    

    # 导入CSV文件
    myfile <- "example.csv"
    data <- read.csv(myfile)
    
      
      
    

    # 导出CSV文件
    write.csv(data, file="output.csv")
    
      
    

    # 生成10个随机数
    set.seed(123)
    randNums <- sample(1:100, 10, replace = T)
    
      
      
    

    # 生成10个服从标准正态分布的随机数
    set.seed(123)
    normalRandNums <- rnorm(10)
    
      
      
    

    # 构造测试数据
    testData <- c(12, 10, 8, 9, 8, 6, 12, 11, 10, 9, 10, 12, 11, 9, 9, 10, 8, 12)
    
    # 执行卡方检验
    myTestRes <- chisq.test(testData)
    print(myTestRes$p.value)