# ----------------------------------- 
# 1. Setting up our workspace 
# ----------------------------------- 

# Check current working directory 
getwd() 

# Set your working directory to your project folder 
setwd("C:/Users/kgi062/ML_2025") 

# ----------------------------------- 
# 2. Basic R Commands and Data Types 
# ----------------------------------- 

# Printing 
print("Hello, world!") 

# Simple arithmetic 
2 + 2 

# Variables and Data Types 
x <- 10               # Numeric Variable 
name <- "Alice"       # Character Variable 
flag <- TRUE          # Logical Variable 


# Creating a numeric vector 
numbers <- c(1, 2, 3, 4, 5) 

# Calculating mean and sum of the vector 
mean_numbers <- mean(numbers) 
sum_numbers <- sum(numbers) 

# Display results 
print(paste("Mean:", mean_numbers)) 
print(paste("Sum:", sum_numbers)) 

# ----------------------------------- 
# 3. Exploring Built-in Datasets 
# ----------------------------------- 

# Accessing dataset help 
?CO2 

# Viewing the dataset in RStudio's viewer 
View(CO2) 

# Exploring dataset structure 
head(CO2)               # First few rows 
tail(CO2)               # Last few rows 
colnames(CO2)           # Column names 
dim(CO2)                # Dimensions (rows, columns) 
str(CO2)                # Structure of the dataset 
summary(CO2)            # Summary statistics 
summary(CO2$uptake)     # Summary of a specific column 
median(CO2$uptake)      # Median value of 'uptake' 
class(CO2$uptake)       # Data type of 'uptake' 
unique(CO2$Treatment)   # Unique treatment groups 
subset(CO2, conc == min(CO2$conc))  # Subset for minimum concentration 

# ----------------------------------- 
# 4. Basic Data Visualization 
# ----------------------------------- 

# Creating a numeric vector 
numbers <- c(1, 2, 3, 4, 5) 
 
# Calculating mean and sum of the vector 
mean_numbers <- mean(numbers) 
sum_numbers <- sum(numbers) 
 
# Display results 
print(paste("Mean:", mean_numbers)) 
print(paste("Sum:", sum_numbers)) 
 
# ----------------------------------- 
# 3. Exploring Built-in Datasets 
# ----------------------------------- 
 
# Accessing dataset help 
?CO2 
 
# Viewing the dataset in RStudio's viewer 
View(CO2) 
 
# Exploring dataset structure 
head(CO2)               # First few rows 
tail(CO2)               # Last few rows 
colnames(CO2)           # Column names 
dim(CO2)                # Dimensions (rows, columns) 
str(CO2)                # Structure of the dataset 
summary(CO2)            # Summary statistics 
summary(CO2$uptake)     # Summary of a specific column 
median(CO2$uptake)      # Median value of 'uptake' 
class(CO2$uptake)       # Data type of 'uptake' 
unique(CO2$Treatment)   # Unique treatment groups 
subset(CO2, conc == min(CO2$conc))  # Subset for minimum concentration 
 
# ----------------------------------- 
# 4. Basic Data Visualization 
# ----------------------------------- 

# Creating a numeric vector 
numbers <- c(1, 2, 3, 4, 5) 
 
# Calculating mean and sum of the vector 
mean_numbers <- mean(numbers) 
sum_numbers <- sum(numbers) 
 
# Display results 
print(paste("Mean:", mean_numbers)) 
print(paste("Sum:", sum_numbers)) 
 
# ----------------------------------- 
# 3. Exploring Built-in Datasets 
# ----------------------------------- 
 
# Accessing dataset help 
?CO2 
 
# Viewing the dataset in RStudio's viewer 
View(CO2) 
 
# Exploring dataset structure 
head(CO2)               # First few rows 
tail(CO2)               # Last few rows 
colnames(CO2)           # Column names 
dim(CO2)                # Dimensions (rows, columns) 
str(CO2)                # Structure of the dataset 
summary(CO2)            # Summary statistics 
summary(CO2$uptake)     # Summary of a specific column 
median(CO2$uptake)      # Median value of 'uptake' 
class(CO2$uptake)       # Data type of 'uptake' 
unique(CO2$Treatment)   # Unique treatment groups 
subset(CO2, conc == min(CO2$conc))  # Subset for minimum concentration 
 
# ----------------------------------- 
# 4. Basic Data Visualization 
# ----------------------------------- 

# Histogram of 'uptake' 
hist(CO2[,5], main="Histogram of CO2 Uptake", xlab="Uptake x axis",ylab="Freq", col="red") 

# Scatter plot: Orange dataset 
my_title = "My alternative title"
plot(x=Orange$age, y=Orange$circumference,  
     main=my_title, 
     xlab="Age (days)", ylab="Circumference (mm)") 

# Customized scatter plot 
plot(Orange$age, Orange$circumference,  
     xlab="Age", ylab="Circumference",  
     main="Circumference vs. Age in Orange Trees",  
     col="blue", pch=20) 

# ----------------------------------- 
# 5. Importing External Data 
# ----------------------------------- 

# Reading CSV file (update the path accordingly) 
# Make sure 'external_file.csv' exists in your working directory 
data <- read.csv("external_file (1).csv") # download it via opencourses 
# Visualize the imported data 
hist(data[,1])  # bug correction: data is read as a data.frame, not a vector

# ----------------------------------- 
# 6. Generating Random Data 
# ----------------------------------- 

# Generate 100 normally distributed random points with mean=5 and sd=1 
d <- rnorm(100, mean = 5, sd = 1) 
hist(d)

# Plot the generated data 
plot(d, main="Random Normal Data", xlab="Index", ylab="Value") 

# Access help for functions 
# e.g., ?mean, ?plot