R Notebook

plot(cars)

#install.packages("tidyverse")

library(tidyverse)

#library(ggplot2)

# Load the mtcars dataset (built into R)
data_mtcars <- mtcars

# View the first few rows to understand the data
head(data_mtcars)

Here we can see that am is a numerical variable but in fact should be a factor.

# Convert 'am' (transmission type) and 'cyl' (number of cylinders) to factors for categorical plotting
data_mtcars$am <- as.factor(data_mtcars$am)
data_mtcars$cyl <- as.factor(data_mtcars$cyl)

#head(data_mtcars)

We changed the variable am to factor.

# Create a scatter plot of car weight vs. miles per gallon, colored by cylinder count
ggplot(data_mtcars, aes(x = wt, y = mpg, color = cyl)) +
  geom_point() + # Add points to the plot
  labs(title = "Miles Per Gallon vs Weight", x = "Weight (1000 lbs)", y = "Miles Per Gallon") # Add plot labels

Instead of weight be one important variable to understand the spending of miles per gallon of a vehicle, I can see that the cylinders are more important to determinate hoew much miles per gallon a car spends.

#Create a line graph of ordered mpg by the row number.
data_mtcars_line <- data_mtcars %>% mutate(index = row_number()) #add index column so we can plot it

ggplot(data_mtcars_line, aes(x = index, y = mpg)) +
  geom_line() + # add a line to the plot
  labs(title = "Miles Per Gallon by Index", x = "Index", y = "Miles Per Gallon") # add plot labels

We can see that some part of index, probably high cylinder cars, spend more gallons. However is a small percentage comparing to other cylinders.

# Create a horizontal bar chart of the average horsepower grouped by cylinder count
hp_by_cyl <- data_mtcars %>% group_by(cyl) %>% summarize(avg_hp = mean(hp)) # Calculate average horsepower for each cylinder group

ggplot(hp_by_cyl, aes(y = cyl, x = avg_hp)) +
  geom_bar(stat = 'identity') + # Create bars based on the calculated averages
  labs(title = "Average HP by Cylinder Count", y = "Cylinder Count", x = "Average Horsepower") # Add plot labels

As higher the cylinder, higher the housepower

#Create a stacked bar chart of average mpg, disp, hp, and wt, grouped by cyl.
bar_data_mtcars <- data_mtcars %>% group_by(cyl) %>% summarize(mpg = mean(mpg), disp = mean(disp), hp = mean(hp), wt = mean(wt)) %>% pivot_longer(cols = c("mpg", "disp", "hp", "wt"), names_to = "Measurement", values_to = "Average") #Calculate average values for each measurement, and pivot the data into a long format.

ggplot(bar_data_mtcars, aes(x = cyl, fill = Measurement, y = Average)) +
  geom_bar(stat = "identity") + #Create bars based on the calculated averages
  labs(title = "Average Measurements by Cylinder Count", x = "Cylinder Count", y = "Average Measurement") #add plot labels

This shows all of our conclusions from before are correct