Lab 6

Adding my data…

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.3     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.0
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ 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

car_data = data.frame("ID" = c(1, 2, 3, 4, 1),
            "Make" = c("Nissan", "Mazda", "Ford", "Mazda", "Nissan"),
            "Car.Model" = c("Rogue", "CX-5", "Focus", "CX-3", "Rogue"),
            "Miles" = c("180,000", "140,000", "80,000", "30,000", "180,000"),
            "Car.Driver" = c("Sophia", "Betsy", "Nathan", "Tim", "Sophia"),
            "Heated.Seats" = c("No", "Yes", "No", "Yes", "No"))
  
car_data

##   ID   Make Car.Model   Miles Car.Driver Heated.Seats
## 1  1 Nissan     Rogue 180,000     Sophia           No
## 2  2  Mazda      CX-5 140,000      Betsy          Yes
## 3  3   Ford     Focus  80,000     Nathan           No
## 4  4  Mazda      CX-3  30,000        Tim          Yes
## 5  1 Nissan     Rogue 180,000     Sophia           No

Removing unnecessary information and removing duplicates…

cars_data = car_data[1:5]

cars_data = distinct(cars_data)
cars_data

##   ID   Make Car.Model   Miles Car.Driver
## 1  1 Nissan     Rogue 180,000     Sophia
## 2  2  Mazda      CX-5 140,000      Betsy
## 3  3   Ford     Focus  80,000     Nathan
## 4  4  Mazda      CX-3  30,000        Tim

Renaming column names and checking for missing data…

cars_data = rename(cars_data, Model = Car.Model, Driver = Car.Driver)
cars_data

##   ID   Make Model   Miles Driver
## 1  1 Nissan Rogue 180,000 Sophia
## 2  2  Mazda  CX-5 140,000  Betsy
## 3  3   Ford Focus  80,000 Nathan
## 4  4  Mazda  CX-3  30,000    Tim

anyNA(cars_data)

## [1] FALSE

Fixing numeric data…

cars_data$Miles = as.numeric(str_replace_all(cars_data$Miles, "[,]", ""))
cars_data

##   ID   Make Model  Miles Driver
## 1  1 Nissan Rogue 180000 Sophia
## 2  2  Mazda  CX-5 140000  Betsy
## 3  3   Ford Focus  80000 Nathan
## 4  4  Mazda  CX-3  30000    Tim

Merging and combining data…

old_cars = data.frame("ID" = 5,
                      "Make" = "Dodge", 
                      "Model" = "Charger",
                      "Miles" = "20,000",
                      "Driver" = "Tim")
old_cars

##   ID  Make   Model  Miles Driver
## 1  5 Dodge Charger 20,000    Tim

old_cars$Miles = as.numeric(str_replace_all(old_cars$Miles, "[,]", ""))
old_cars

##   ID  Make   Model Miles Driver
## 1  5 Dodge Charger 20000    Tim

cars_data = rbind(cars_data, old_cars)
cars_data

##   ID   Make   Model  Miles Driver
## 1  1 Nissan   Rogue 180000 Sophia
## 2  2  Mazda    CX-5 140000  Betsy
## 3  3   Ford   Focus  80000 Nathan
## 4  4  Mazda    CX-3  30000    Tim
## 5  5  Dodge Charger  20000    Tim

extra_data = data.frame("ID" = c(1, 2, 3, 4, 5),
                        "Color" = c("Grey", "Red", "Black", "Black", "Navy"))
extra_data

##   ID Color
## 1  1  Grey
## 2  2   Red
## 3  3 Black
## 4  4 Black
## 5  5  Navy

cars_data = merge(cars_data, extra_data, by = "ID")
cars_data

##   ID   Make   Model  Miles Driver Color
## 1  1 Nissan   Rogue 180000 Sophia  Grey
## 2  2  Mazda    CX-5 140000  Betsy   Red
## 3  3   Ford   Focus  80000 Nathan Black
## 4  4  Mazda    CX-3  30000    Tim Black
## 5  5  Dodge Charger  20000    Tim  Navy

Final data set…

cars_data

##   ID   Make   Model  Miles Driver Color
## 1  1 Nissan   Rogue 180000 Sophia  Grey
## 2  2  Mazda    CX-5 140000  Betsy   Red
## 3  3   Ford   Focus  80000 Nathan Black
## 4  4  Mazda    CX-3  30000    Tim Black
## 5  5  Dodge Charger  20000    Tim  Navy

Lab 6

Sophia Schmidt

2023-10-25