#installing necessary packages
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 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ 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 errorsdata(mpg)
head(mpg,10)## # A tibble: 10 × 11
## manufacturer model displ year cyl trans drv cty hwy fl class
## <chr> <chr> <dbl> <int> <int> <chr> <chr> <int> <int> <chr> <chr>
## 1 audi a4 1.8 1999 4 auto… f 18 29 p comp…
## 2 audi a4 1.8 1999 4 manu… f 21 29 p comp…
## 3 audi a4 2 2008 4 manu… f 20 31 p comp…
## 4 audi a4 2 2008 4 auto… f 21 30 p comp…
## 5 audi a4 2.8 1999 6 auto… f 16 26 p comp…
## 6 audi a4 2.8 1999 6 manu… f 18 26 p comp…
## 7 audi a4 3.1 2008 6 auto… f 18 27 p comp…
## 8 audi a4 quattro 1.8 1999 4 manu… 4 18 26 p comp…
## 9 audi a4 quattro 1.8 1999 4 auto… 4 16 25 p comp…
## 10 audi a4 quattro 2 2008 4 manu… 4 20 28 p comp…str(mpg)## tibble [234 × 11] (S3: tbl_df/tbl/data.frame)
## $ manufacturer: chr [1:234] "audi" "audi" "audi" "audi" ...
## $ model : chr [1:234] "a4" "a4" "a4" "a4" ...
## $ displ : num [1:234] 1.8 1.8 2 2 2.8 2.8 3.1 1.8 1.8 2 ...
## $ year : int [1:234] 1999 1999 2008 2008 1999 1999 2008 1999 1999 2008 ...
## $ cyl : int [1:234] 4 4 4 4 6 6 6 4 4 4 ...
## $ trans : chr [1:234] "auto(l5)" "manual(m5)" "manual(m6)" "auto(av)" ...
## $ drv : chr [1:234] "f" "f" "f" "f" ...
## $ cty : int [1:234] 18 21 20 21 16 18 18 18 16 20 ...
## $ hwy : int [1:234] 29 29 31 30 26 26 27 26 25 28 ...
## $ fl : chr [1:234] "p" "p" "p" "p" ...
## $ class : chr [1:234] "compact" "compact" "compact" "compact" ...names(mpg)## [1] "manufacturer" "model" "displ" "year" "cyl"
## [6] "trans" "drv" "cty" "hwy" "fl"
## [11] "class"#This step included simplification of the dataset to allow it to be more clear to read.
mpg_selected <- mpg %>% select(manufacturer,class,cty,hwy)###Step 2: Create a Summary Table
#avg_mpg was created to take the average of the city and highway miles per gallon.
mpg_avg <- mpg_selected %>% mutate(avg_mpg = (cty + hwy)/ 2, avg_mpg = as.numeric(avg_mpg))#Rows 2 and 5 were removed. The vehicles with an MPG of 25 were filtered to stay in but anything less than that were removed.
mpg_filtered <- mpg_avg %>% filter(avg_mpg >= 25, !is.na(class)) %>% slice(-c(2,5))##This step was renaming brand as manufactureer and vehicle_type was renamed as class.
mpg_renamed <- mpg_filtered %>% rename(brand= manufacturer, vehicle_type = class)#A summary tale was created to clearly show the number of vehicles and average MPG values.
mpg_summary <- mpg_renamed %>% group_by(brand, vehicle_type) %>% summarise(mean_avg_mpg = mean(avg_mpg), vehicle_count =n(),.groups = "drop")
mpg_summary## # A tibble: 11 × 4
## brand vehicle_type mean_avg_mpg vehicle_count
## <chr> <chr> <dbl> <int>
## 1 audi compact 25.2 2
## 2 chevrolet midsize 26 1
## 3 honda subcompact 28.2 8
## 4 hyundai midsize 25.8 2
## 5 nissan compact 25 1
## 6 nissan midsize 27.2 2
## 7 toyota compact 28.3 8
## 8 toyota midsize 25.7 3
## 9 volkswagen compact 26.6 9
## 10 volkswagen midsize 25 2
## 11 volkswagen subcompact 33.2 3