knitr::opts_chunk$set(echo = FALSE, message = FALSE, warning = FALSE, results = "unhide")
# Install packages
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 3.4.3 ✔ 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
library(readxl) # for importing excel files
Import data
## # A tibble: 1,155 × 13
## movie_name release_year director age_difference couple_number actor_1_name
## <chr> <dbl> <chr> <dbl> <dbl> <chr>
## 1 Venus 2006 Roger M… 50 1 Peter O'Too…
## 2 The Quiet Am… 2002 Phillip… 49 1 Michael Cai…
## 3 The Big Lebo… 1998 Joel Co… 45 1 David Huddl…
## 4 Poison Ivy 1992 Katt Sh… 42 1 Tom Skerritt
## 5 Whatever Wor… 2009 Woody A… 40 1 Larry David
## 6 Entrapment 1999 Jon Ami… 39 1 Sean Connery
## 7 Husbands and… 1992 Woody A… 38 1 Woody Allen
## 8 Magnolia 1999 Paul Th… 38 1 Jason Robar…
## 9 Indiana Jone… 1989 Steven … 36 1 Sean Connery
## 10 Mr. Peabody … 1948 Irving … 36 1 William Pow…
## # ℹ 1,145 more rows
## # ℹ 7 more variables: actor_2_name <chr>, character_1_gender <chr>,
## # character_2_gender <chr>, actor_1_birthdate <dttm>,
## # actor_2_birthdate <dttm>, actor_1_age <dbl>, actor_2_age <dbl>
Apply the following dplyr verbs to your data
Filter rows
## # A tibble: 50 × 13
## movie_name release_year director age_difference couple_number actor_1_name
## <chr> <dbl> <chr> <dbl> <dbl> <chr>
## 1 Entrapment 1999 Jon Ami… 39 1 Sean Connery
## 2 Magnolia 1999 Paul Th… 38 1 Jason Robar…
## 3 American Bea… 1999 Sam Men… 20 1 Kevin Spacey
## 4 Pushing Tin 1999 Mike Ne… 20 1 Billy Bob T…
## 5 Random Hearts 1999 Sydney … 18 1 Harrison Fo…
## 6 Runaway Bride 1999 Garry M… 18 1 Richard Gere
## 7 The World Is… 1999 Michael… 18 1 Pierce Bros…
## 8 Sleepy Hollow 1999 Tim Bur… 17 1 Johnny Depp
## 9 Analyze This 1999 Harold … 15 1 Billy Cryst…
## 10 The Sixth Se… 1999 M. Nigh… 13 1 Bruce Willis
## # ℹ 40 more rows
## # ℹ 7 more variables: actor_2_name <chr>, character_1_gender <chr>,
## # character_2_gender <chr>, actor_1_birthdate <dttm>,
## # actor_2_birthdate <dttm>, actor_1_age <dbl>, actor_2_age <dbl>
Arrange rows
## # A tibble: 1,155 × 13
## movie_name release_year director age_difference couple_number actor_1_name
## <chr> <dbl> <chr> <dbl> <dbl> <chr>
## 1 The Bubble 2022 Judd Ap… 21 1 Pedro Pascal
## 2 The Northman 2022 Robert … 20 1 Alexander S…
## 3 Top Gun: Mav… 2022 Joseph … 8 1 Tom Cruise
## 4 The Lost City 2022 Adam Ne… 16 1 Sandra Bull…
## 5 Everything E… 2022 Dan Kwa… 9 1 Michelle Ye…
## 6 Free Guy 2021 Shawn L… 17 1 Ryan Reynol…
## 7 Red Notice 2021 Rawson … 13 1 Dwayne John…
## 8 Malcolm & Ma… 2021 Sam Lev… 12 1 John David …
## 9 Nightmare Al… 2021 Guiller… 10 1 Bradley Coo…
## 10 In the Heigh… 2021 John M.… 12 1 Daphne Rubi…
## # ℹ 1,145 more rows
## # ℹ 7 more variables: actor_2_name <chr>, character_1_gender <chr>,
## # character_2_gender <chr>, actor_1_birthdate <dttm>,
## # actor_2_birthdate <dttm>, actor_1_age <dbl>, actor_2_age <dbl>
Select columns
## # A tibble: 1,155 × 3
## movie_name director age_difference
## <chr> <chr> <dbl>
## 1 Venus Roger Michell 50
## 2 The Quiet American Phillip Noyce 49
## 3 The Big Lebowski Joel Coen 45
## 4 Poison Ivy Katt Shea 42
## 5 Whatever Works Woody Allen 40
## 6 Entrapment Jon Amiel 39
## 7 Husbands and Wives Woody Allen 38
## 8 Magnolia Paul Thomas Anderson 38
## 9 Indiana Jones and the Last Crusade Steven Spielberg 36
## 10 Mr. Peabody and the Mermaid Irving Pichel 36
## # ℹ 1,145 more rows
Add columns
Summarize by groups
## # A tibble: 1 × 1
## ageDifference
## <dbl>
## 1 10.4