1# Install R
2brew install r
3 
4# Install RStudio (download from RStudio.com or use Homebrew)
5brew install --cask rstudio

# Download and install from:
# R: https://cran.r-project.org/bin/windows/base/
# RStudio: https://posit.co/download/rstudio-desktop/

1# Install tidyverse (includes dplyr, ggplot2, and more)
2install.packages("tidyverse")
3 
4# Install additional useful packages
5install.packages(c("readr", "lubridate", "stringr"))
6 
7# Load tidyverse
8library(tidyverse)

# In VS Code, install the R extension
# Press Cmd+Shift+X (Mac) or Ctrl+Shift+X (Windows)
# Search for "R" by REditorSupport and install

1# Numeric
2age <- 25
3height <- 5.9
4temperature <- 98.6
5 
6# Character (strings)
7name <- "Alice"
8city <- "San Francisco"
9 
10# Logical (boolean)
11is_student <- TRUE
12has_experience <- FALSE
13 
14# Print values
15print(paste("Name:", name))
16print(paste("Age:", age))

Explain the difference between <- and = in R.
When should I use each one?

1# Numeric vector
2temperatures <- c(72, 75, 68, 71, 73, 76, 74)
3print(temperatures)
4 
5# Character vector
6days <- c("Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun")
7print(days)
8 
9# Vector operations
10mean_temp <- mean(temperatures)
11max_temp <- max(temperatures)
12 
13print(paste("Average temperature:", mean_temp))
14print(paste("Maximum temperature:", max_temp))
15 
16# Indexing (R uses 1-based indexing!)
17first_day <- days[1]  # "Mon"
18weekend <- days[6:7]  # "Sat", "Sun"

1# Create a data frame
2weather_data <- data.frame(
3  day = days,
4  temperature = temperatures,
5  sunny = c(TRUE, TRUE, FALSE, TRUE, TRUE, TRUE, FALSE)
6)
7 
8# View the data
9print(weather_data)
10head(weather_data)  # First 6 rows
11str(weather_data)   # Structure
12 
13# Access columns
14weather_data$temperature
15weather_data$day
16 
17# Filter rows
18sunny_days <- weather_data[weather_data$sunny == TRUE, ]
19print(sunny_days)

1Create a data frame with student information including:
2- names (5 students)
3- ages
4- test scores
5- pass/fail status
6 
7Then calculate the average score and find students who passed.

1library(tidyverse)
2 
3# Create sample dataset
4sales_data <- tibble(
5  date = seq(as.Date("2025-01-01"), as.Date("2025-01-31"), by = "day"),
6  product = sample(c("Laptop", "Phone", "Tablet"), 31, replace = TRUE),
7  quantity = sample(1:10, 31, replace = TRUE),
8  price = sample(c(999, 699, 399), 31, replace = TRUE),
9  region = sample(c("West", "East", "North", "South"), 31, replace = TRUE)
10)
11 
12# View the data
13glimpse(sales_data)
14head(sales_data, 10)

1# Traditional way (hard to read)
2result1 <- filter(sales_data, product == "Laptop")
3result2 <- select(result1, date, quantity, price)
4result3 <- arrange(result2, desc(quantity))
5 
6# With pipe operator (easy to read)
7result <- sales_data %>%
8  filter(product == "Laptop") %>%
9  select(date, quantity, price) %>%
10  arrange(desc(quantity))

1# Filter laptops
2laptops <- sales_data %>%
3  filter(product == "Laptop")
4 
5# Multiple conditions
6high_value_sales <- sales_data %>%
7  filter(product == "Laptop", quantity > 5)
8 
9# Filter by date range
10january_first_week <- sales_data %>%
11  filter(date <= as.Date("2025-01-07"))
12 
13print(high_value_sales)

1# Select specific columns
2sales_summary <- sales_data %>%
3  select(date, product, quantity)
4 
5# Select range of columns
6sales_details <- sales_data %>%
7  select(product:price)
8 
9# Drop columns
10without_region <- sales_data %>%
11  select(-region)
12 
13head(sales_summary)

1# Add calculated column
2sales_with_total <- sales_data %>%
3  mutate(total_revenue = quantity * price)
4 
5# Multiple new columns
6sales_enhanced <- sales_data %>%
7  mutate(
8    total_revenue = quantity * price,
9    weekday = weekdays(date),
10    month = month(date)
11  )
12 
13head(sales_enhanced)

1# Summary statistics by product
2product_summary <- sales_data %>%
3  mutate(revenue = quantity * price) %>%
4  group_by(product) %>%
5  summarize(
6    total_sales = n(),
7    total_quantity = sum(quantity),
8    total_revenue = sum(revenue),
9    avg_quantity = mean(quantity)
10  )
11 
12print(product_summary)
13 
14# Multiple grouping
15region_product_summary <- sales_data %>%
16  mutate(revenue = quantity * price) %>%
17  group_by(region, product) %>%
18  summarize(
19    total_revenue = sum(revenue),
20    avg_price = mean(price)
21  )
22 
23print(region_product_summary)

Using the sales_data:
1. Find the total revenue per region
2. Identify the top 5 highest revenue days
3. Calculate average quantity sold per product per region

1library(ggplot2)
2 
3# Basic structure:
4# ggplot(data, aes(x = ..., y = ...)) + geom_*()
5 
6# Scatter plot
7ggplot(sales_data, aes(x = date, y = quantity)) +
8  geom_point() +
9  labs(title = "Sales Quantity Over Time",
10       x = "Date",
11       y = "Quantity Sold")
12 
13# Add color by product
14ggplot(sales_data, aes(x = date, y = quantity, color = product)) +
15  geom_point(size = 3) +
16  labs(title = "Sales by Product",
17       x = "Date",
18       y = "Quantity")

1# Revenue by product
2sales_data %>%
3  mutate(revenue = quantity * price) %>%
4  group_by(product) %>%
5  summarize(total_revenue = sum(revenue)) %>%
6  ggplot(aes(x = product, y = total_revenue, fill = product)) +
7  geom_col() +
8  labs(title = "Total Revenue by Product",
9       x = "Product",
10       y = "Revenue ($)") +
11  theme_minimal()

1# Daily revenue trend
2sales_data %>%
3  mutate(revenue = quantity * price) %>%
4  group_by(date) %>%
5  summarize(daily_revenue = sum(revenue)) %>%
6  ggplot(aes(x = date, y = daily_revenue)) +
7  geom_line(color = "blue", size = 1) +
8  geom_point(color = "darkblue", size = 2) +
9  labs(title = "Daily Revenue Trend") +
10  theme_minimal()

1# Quantity by product
2ggplot(sales_data, aes(x = product, y = quantity, fill = product)) +
3  geom_boxplot() +
4  labs(title = "Quantity Distribution by Product") +
5  theme_minimal()

Create visualizations showing:
1. A stacked bar chart of revenue by region
2. A line chart showing cumulative revenue
3. A faceted plot for each product

1# Write to CSV
2write_csv(sales_data, "sales_january_2025.csv")
3 
4# Read from CSV
5sales_imported <- read_csv("sales_january_2025.csv")

1# Install packages if needed
2install.packages("readxl")
3install.packages("writexl")
4 
5library(readxl)
6library(writexl)
7 
8# Write to Excel
9write_xlsx(sales_data, "sales_january_2025.xlsx")
10 
11# Read from Excel
12excel_data <- read_excel("sales_january_2025.xlsx")