Practice: Cleaning and Summarizing Data with dplyr

# Load required packages
if (!require(tidyverse)) {
  install.packages("tidyverse")
  library(tidyverse)
}

## Loading required package: tidyverse

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.2     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.2     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── 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

# Load the dataset
data(mtcars)

# View the dataset
head(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

# Inspect the structure
str(mtcars)

## 'data.frame':    32 obs. of  11 variables:
##  $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
##  $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
##  $ disp: num  160 160 108 258 360 ...
##  $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
##  $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
##  $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
##  $ qsec: num  16.5 17 18.6 19.4 17 ...
##  $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
##  $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
##  $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
##  $ carb: num  4 4 1 1 2 1 4 2 2 4 ...

# Convert categorical variables to factors
mtcars <- mtcars %>%
  mutate(
    cyl = as.factor(cyl),
    am = as.factor(am)
  )

# Check structure again
str(mtcars)

## 'data.frame':    32 obs. of  11 variables:
##  $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
##  $ cyl : Factor w/ 3 levels "4","6","8": 2 2 1 2 3 2 3 1 1 2 ...
##  $ disp: num  160 160 108 258 360 ...
##  $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
##  $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
##  $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
##  $ qsec: num  16.5 17 18.6 19.4 17 ...
##  $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
##  $ am  : Factor w/ 2 levels "0","1": 2 2 2 1 1 1 1 1 1 1 ...
##  $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
##  $ carb: num  4 4 1 1 2 1 4 2 2 4 ...

# Select relevant variables
cars_clean <- mtcars %>%
  select(mpg, hp, wt, cyl, am)

# Filter cars with more than 100 horsepower
cars_hp <- cars_clean %>%
  filter(hp > 100)

# Check number of rows
nrow(cars_hp)

## [1] 23

# Create power-to-weight ratio
cars_hp <- cars_hp %>%
  mutate(power_to_weight = hp / wt)

# Summary by number of cylinders
summary_cyl <- cars_hp %>%
  group_by(cyl) %>%
  summarise(
    mean_mpg = mean(mpg),
    mean_hp = mean(hp),
    n = n()
  )

# Display summary
summary_cyl

## # A tibble: 3 × 4
##   cyl   mean_mpg mean_hp     n
##   <fct>    <dbl>   <dbl> <int>
## 1 4         25.9    111      2
## 2 6         19.7    122.     7
## 3 8         15.1    209.    14

# Summary by transmission type
summary_transmission <- cars_hp %>%
  group_by(am) %>%
  summarise(
    mean_mpg = mean(mpg),
    mean_power_to_weight = mean(power_to_weight)
  )

# Display transmission summary
summary_transmission

## # A tibble: 2 × 3
##   am    mean_mpg mean_power_to_weight
##   <fct>    <dbl>                <dbl>
## 1 0         16.1                 44.6
## 2 1         20.6                 62.1