print("Hello R World!")

x <- c(1, 2, 3, 4, 5)
mean(x)

install.packages("tidyverse")
library(tidyverse)

# 📘 R 語言介紹與應用（教案簡報內容）

## 🧠 R 是什麼？

R 是一種專門用來進行「統計分析與資料處理」的程式語言。

- 免費、開源，可自由擴充  
- 擅長數據分析、圖表視覺化、模型建構  
- 全球學術界與資料分析師廣泛使用  



## ✨ R 的特色

- 免費開源，自由使用與擴充  
- 有數千個套件支援統計、圖表、機器學習等  
- 搭配 RStudio 使用體驗更佳  
- 支援 R Markdown 報告與互動教學  
- 適合學生與非資工背景學習  


## 📦 R 常見應用範圍

- 🎓 教育與學術：統計推論、回歸分析、論文報表  
- 📊 商業分析：顧客行為分析、視覺化報表  
- 🧬 生物醫學：基因資料、生存分析、臨床統計  
- 🏦 金融應用：股票分析、風險管理、回測模型  
- 🤖 資料科學與機器學習：模型建立與預測  



## 🧪 R 語法範例

```r
# 建立向量
scores <- c(80, 90, 70, 100)

# 計算平均
mean(scores)

# 繪製直方圖
hist(scores, main = "分數分布圖", col = "lightblue")

a=100
class(a)

a=100L
class(a)

a=FALSE
class(a)

a="hello"
class(a)

a=Sys.Date()
class(a)
a
as.numeric(a)

a=Sys.time()
a

is.numeric(a)

a <- c(1,5.3,6,-2) 
a 

length(a)
rep(a, 3)
seq(1, 5, 2)
1 %in% a

a = c(1, 3, 5, 7, 9, 11)
a[1]
a[1:3]
a[a>8|a<2]

x <- c(TRUE, FALSE, TRUE)
y <- c(TRUE, TRUE, FALSE)

x & y
x[1] && y[1]

# Create a list.
list1 <- list(c(2,5,3), 21.3, sin)

# Print the list.
print(list1)

# Create list and asign variable names.
list2  <- list(vector = c(2,5,3),
               numeric = 21.3,
               func = sin)

# Print names of list and list itself.
names(list2)
print(list2)

# array(data, dim = c(列, 欄, 頁))
a <- array(1:12, dim = c(3, 2, 2))
print(a)

a[1, 2, 1]   # 第一頁、第一列、第二欄 → 取出 4
a[,,2]       # 第二頁整張矩陣

# Create a vector.
apple_colors <- c('green','green','yellow','red','red','red','green')

# Create a factor object.
factor_apple <- factor(apple_colors)

# Print the factor.
print(factor_apple)
print(nlevels(factor_apple))

# Create a matrix.
M <- matrix( c('a','a','b','c','b','a'), nrow = 2, ncol = 3)
print(M)

# Create a matrix and fill in by row.
M <- matrix( c('a','a','b','c','b','a'), nrow = 2, ncol = 3, byrow = TRUE)
print(M)

name <- c("David", "Hsi", "Jessie")
age <- c("24", "25", "36")
gender <- c("Male", "Male", "Female")

# Create by variables
data1 <- data.frame(name, age, gender)
data1

data2 <- data.frame(
  name = c("David", "Hsi", "Jessie"),
  age = c("24", "25", "36"),
  gender = c("Male", "Male", "Female")
)
data2

head(data2)
colnames(data2) <- c("Var_1", "Var_2","Var_3")
rownames(data2) <- c("1", "2", "3")
data2
summary(data2)

#head：取得資料框架前六比資料(預設是 6)。
#tail：取得資料框架後六比資料(預設是 6)。
#colnames：修改或查詢 column 名稱。
#rownames：設定 row 的名稱
#summary：顯示資料基本資訊。
#dim：回傳資料物件的維度(列數, 欄數)

library(tibble)

# 建立 tibble
tb <- tibble(
  name = c("Amy", "Ben", "Cindy"),
  score = c(90, 85, 88)
)

tb

#data.frame 和 tibble 互轉
df <- as.data.frame(tb)  # 將 tibble 轉為 data.frame
tb2 <- as_tibble(df)      # 將 data.frame 轉為 tibble

x <- c(1, 1, 2, 2, 3, 3, 4, 4)
length(x)
unique(x)

data2 <- data.frame(
  name = c("David", "Hsi", "Jessie", "David", "Hsi"),
  age = c("24", "25", "36", "24", "30"),
  gender = c("Male", "Male", "Female", "Male", "Male")
)
data2
unique(data2)
str(data2)
class(data2)
names(data2)

df <- data.frame( 
	product = c("A", "B", "C", "D"), 
    price = c(150, 80, 120, 200), 
    in_stock = c(TRUE, FALSE, TRUE, TRUE) 
    )

df <- data.frame(
  name = c("Amy", "Ben", "Cindy", "David"),
  score = c(88, 76, 92, 60)
)

df[df$score > 80, ]
df[df$score >= 60 & df$score < 90, ]
df$pass <- df$score >= 60

sales <- array(1:12, dim = c(3, 2, 2))
sales[, , 1]
sales[3, 2, 2]
sum(sales)
dim(sales)

df <- data.frame(
  product = c("A", "B", "C", "D"),
  price = c(150, 80, 120, 200),
  in_stock = c(TRUE, FALSE, TRUE, TRUE)
)
df[df$in_stock & df$price < 150, ]
nrow(df)
ncol(df)
names(df)
is.numeric(df$price)

df <- data.frame(
  a = rnorm(10), # Generate 10 standard normal random numbers
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
)

df$a <- (df$a - min(df$a, na.rm = TRUE)) / 
  (max(df$a, na.rm = TRUE) - min(df$a, na.rm = TRUE))
df$b <- (df$b - min(df$b, na.rm = TRUE)) / 
  (max(df$b, na.rm = TRUE) - min(df$a, na.rm = TRUE))
df$c <- (df$c - min(df$c, na.rm = TRUE)) / 
  (max(df$c, na.rm = TRUE) - min(df$c, na.rm = TRUE))
df$d <- (df$d - min(df$d, na.rm = TRUE)) / 
  (max(df$d, na.rm = TRUE) - min(df$d, na.rm = TRUE))

df <- data.frame(
  a = rnorm(10),
  b = rnorm(10),
  c = rnorm(10),
  d = rnorm(10)
)

RescaleByRange <- function(x){
  rng <- range(x, na.rm = TRUE)
  return((x - rng[1]) / (rng[2] - rng[1]))
}
RescaleByRange(df$a)

SummarizeData <- function(x){
  summary.df <- data.frame(x_mean = mean(x, na.rm = TRUE),
                           x_var = var(x, na.rm = TRUE),
                           x_max = max(x, na.rm = TRUE),
                           x_min = min(x, na.rm = TRUE),
                           x_median = median(x, na.rm = TRUE))
  return(summary.df)
}

SummarizeData(rnorm(10))