install.packages("tidyverse")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.0
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggplot2) # Load ggplot2 for creating plots
# Load the mtcars dataset (built into R)
data_mtcars <- mtcars
# View the first few rows to understand the data
head(data_mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
# 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)
# View the first few rows to understand the data
head(data_mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
# 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
#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
# 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
#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
