# Step 1
# install Packages - If you already have these packages installed in your system, go to Step 2
install.packages("ggplot2")
install.packages("readxl")
install.packages("ggplot2")
install.packages("dplyr")

# Step 2
# Load Package 
library(readxl)
library(ggplot2)
library(dplyr)

# Step 3

# Define the file path - adjust the Path to the location of the downloaded data in your system
file_path <- "C:/......./Data Visualization Example Final.xlsx"


###################################################################

#       Bar Chart example

###########################################

# Import the sheet "Car prices - Bar"
data <- read_excel(file_path, sheet = "Car prices - Bar")

# Clean the Price column
data <- data %>%
  mutate(Price = as.numeric(gsub("[\\$,]", "", `Car  Price`)))  # Remove '$' and ','

# Plot the bar chart
ggplot(data, aes(x = Model, y = Price)) +
  geom_bar(stat = "identity", fill = "red") +  # Set all bars to the same color
  labs(title = "Car Model Prices", x = "Car Model", y = "Price (USD)") +
  theme_minimal() +
  theme(legend.position = "none") +  # Remove legend
  theme(axis.line = element_line(colour = "black"))


############################################

#       Scatter plot example

###############################################


# Read the data from the sheet
scatterplot_data <- read_excel(file_path, sheet = "TV Adv and Sales - Scatter plot")

# Clean the numeric columns by removing "$" and converting to numeric
scatterplot_data <- scatterplot_data %>%
  mutate(across(everything(), ~ as.numeric(gsub("[\\$,]", "", .))))

# Plot the scatter plot
ggplot(scatterplot_data, aes(x = `TV Ad Budget ($)`, y = `Sales ($)`)) +
  geom_point(color = "#1f77b4", size = 3) +  # Set point color and size
  labs(title = "Relationship between Sales and TV Ad Budget", x = "TV Ad Budget ($)", y = "Sales ($)") +
  ylim(0, max(scatterplot_data$`Sales ($)`, na.rm = TRUE)) +
  theme_minimal() +
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank(), 
        panel.border = element_blank(), 
        axis.line = element_line(colour = "black"))


#####################################################################

#       Pie Chart Example

################################################################

education_data <- read_excel(file_path, sheet = "Education Attainment - Pie")


# Compute percentage
education_data <- education_data %>%
  mutate(Percentage = (`Educational Attainment Distribution` / sum(`Educational Attainment Distribution`)) * 100)


# Plot pie chart with percentage values
ggplot(education_data, aes(x = "", y = `Educational Attainment Distribution`, fill = `Level of Education Attainment`, label = paste0(round(Percentage, 1), "%"))) +
  geom_bar(stat = "identity", width = 1) +
  coord_polar(theta = "y") +  # Convert to pie chart
  labs(title = "Educational Attainment Distribution") +
  theme_minimal() +
  theme(axis.text = element_blank(), 
        axis.ticks = element_blank(), 
        panel.grid = element_blank()) +
  scale_fill_brewer(palette = "Pastel1") +  # Set color palette
  geom_text(position = position_stack(vjust = 0.5), size = 4)  # Add percentage labels to the pie chart



###########################################################################
#       Business Case Challenge

############################################################


tax_data <- read_excel(file_path, sheet = "Business Case")

# Plot bar chart with one color and no legend
ggplot(tax_data, aes(x = factor(Year), y = `Tax Rate`)) +
  geom_bar(stat = "identity", fill = "orange") +  # Use one color for both bars
  labs(title = "Highest Marginal Income Tax Rate", 
       x = "Year", 
       y = "Tax Rate (%)") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) + # Rotate x-axis labels
  theme(axis.line = element_line(colour = "black"),
        legend.position = "none")  # Remove the legend