Install necessary packages for this project

#install.packages('rvest')
#Loading the rvest package
library(rvest)
## Loading required package: xml2
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --
## v ggplot2 3.2.1     v purrr   0.3.3
## v tibble  2.1.3     v dplyr   0.8.4
## v tidyr   1.0.2     v stringr 1.4.0
## v readr   1.3.1     v forcats 0.4.0
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter()         masks stats::filter()
## x readr::guess_encoding() masks rvest::guess_encoding()
## x dplyr::lag()            masks stats::lag()
## x purrr::pluck()          masks rvest::pluck()
library(plotly)
## Warning: package 'plotly' was built under R version 3.6.3
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout

Scrape the IMDB website to create a dataframe of information from 2016 top 100 movies

http://www.imdb.com/search/title?count=100&release_date=2016,2016&title_type=feature

#Specifying the url for desired website to be scraped
url <- 'http://www.imdb.com/search/title?count=100&release_date=2016,2016&title_type=feature'

#Reading the HTML code from the website
webpage <- read_html(url)

Load various elements and clean data using gsub.

Use the command, length, to ensure that each list contains 100 elements or NAs for missing data to sum to 100 elements.

#Using CSS selectors to scrape the rankings section
rank_data_html <- html_nodes(webpage,'.text-primary')

#Converting the ranking data to text
rank_data <- html_text(rank_data_html)

#Let's have a look at the rankings
head(rank_data)
## [1] "1." "2." "3." "4." "5." "6."
length(rank_data)
## [1] 100
#Data-Preprocessing: Converting rankings to numerical
rank_data<-as.numeric(rank_data)

#Let's have another look at the rankings
head(rank_data)
## [1] 1 2 3 4 5 6
#Using CSS selectors to scrape the title section
title_data_html <- html_nodes(webpage,'.lister-item-header a')

#Converting the title data to text
title_data <- html_text(title_data_html)

#Let's have a look at the title
head(title_data)
## [1] "Split"                         "Ghostbusters: Answer the Call"
## [3] "Suicide Squad"                 "Train to Busan"               
## [5] "The Conjuring 2"               "Hush"
length(title_data)
## [1] 100
#Using CSS selectors to scrape the description section
description_data_html <- html_nodes(webpage,'.ratings-bar+ .text-muted')

#Converting the description data to text
description_data <- html_text(description_data_html)

#Let's have a look at the description data
head(description_data)
## [1] "\n    Three girls are kidnapped by a man with a diagnosed 23 distinct personalities. They must try to escape before the apparent emergence of a frightful new 24th."                                                
## [2] "\n    Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engineer Jillian Holtzmann, and subway worker Patty Tolan band together to stop the otherworldly threat."
## [3] "\n    A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive task force. Their first mission: save the world from the apocalypse."                          
## [4] "\n    While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."                                                                                             
## [5] "\n    Ed and Lorraine Warren travel to North London to help a single mother raising four children alone in a house plagued by a supernatural spirit."                                                               
## [6] "\n    A deaf and mute writer who retreated into the woods to live a solitary life must fight for her life in silence when a masked killer appears at her window."
#Data-Preprocessing: removing '\n'
description_data<-gsub("\n","",description_data)

#Let's have another look at the description data 
head(description_data)
## [1] "    Three girls are kidnapped by a man with a diagnosed 23 distinct personalities. They must try to escape before the apparent emergence of a frightful new 24th."                                                
## [2] "    Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engineer Jillian Holtzmann, and subway worker Patty Tolan band together to stop the otherworldly threat."
## [3] "    A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive task force. Their first mission: save the world from the apocalypse."                          
## [4] "    While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."                                                                                             
## [5] "    Ed and Lorraine Warren travel to North London to help a single mother raising four children alone in a house plagued by a supernatural spirit."                                                               
## [6] "    A deaf and mute writer who retreated into the woods to live a solitary life must fight for her life in silence when a masked killer appears at her window."
length(description_data)
## [1] 100
#Using CSS selectors to scrape the Movie runtime section
runtime_data_html <- html_nodes(webpage,'.text-muted .runtime')

#Converting the runtime data to text
runtime_data <- html_text(runtime_data_html)

#Let's have a look at the runtime
head(runtime_data)
## [1] "117 min" "117 min" "123 min" "118 min" "134 min" "82 min"
#Data-Preprocessing: removing mins and converting it to numerical

runtime_data<-gsub(" min","",runtime_data)
runtime_data<-as.numeric(runtime_data)

#Let's have another look at the runtime data
head(runtime_data)
## [1] 117 117 123 118 134  82
length(runtime_data)
## [1] 100
#Using CSS selectors to scrape the Movie genre section
genre_data_html <- html_nodes(webpage,'.genre')

#Converting the genre data to text
genre_data <- html_text(genre_data_html)

#Let's have a look at the genre
head(genre_data)
## [1] "\nHorror, Thriller            "          
## [2] "\nAction, Comedy, Fantasy            "   
## [3] "\nAction, Adventure, Fantasy            "
## [4] "\nAction, Horror, Thriller            "  
## [5] "\nHorror, Mystery, Thriller            " 
## [6] "\nHorror, Thriller            "
#Data-Preprocessing: removing \n
genre_data<-gsub("\n","",genre_data)

#Data-Preprocessing: removing excess spaces
genre_data<-gsub(" ","",genre_data)

#taking only the first genre of each movie
genre_data<-gsub(",.*","",genre_data)

#Convering each genre from text to factor
genre_data<-as.factor(genre_data)

#Let's have another look at the genre data
head(genre_data)
## [1] Horror Action Action Action Horror Horror
## Levels: Action Adventure Animation Biography Comedy Crime Drama Horror
length(genre_data)
## [1] 100
#Using CSS selectors to scrape the IMDB rating section
rating_data_html <- html_nodes(webpage,'.ratings-imdb-rating strong')

#Converting the ratings data to text
rating_data <- html_text(rating_data_html)

#Let's have a look at the ratings
head(rating_data)
## [1] "7.3" "6.5" "6.0" "7.6" "7.3" "6.6"
#Data-Preprocessing: converting ratings to numerical
rating_data<-as.numeric(rating_data)

#Let's have another look at the ratings data
head(rating_data)
## [1] 7.3 6.5 6.0 7.6 7.3 6.6
length(rating_data)
## [1] 100
#Using CSS selectors to scrape the votes section
votes_data_html <- html_nodes(webpage,'.sort-num_votes-visible span:nth-child(2)')

#Converting the votes data to text
votes_data <- html_text(votes_data_html)

#Let's have a look at the votes data
head(votes_data)
## [1] "413,339" "201,710" "591,549" "158,291" "221,168" "100,262"
#Data-Preprocessing: removing commas
votes_data<-gsub(",","",votes_data)

#Data-Preprocessing: converting votes to numerical
votes_data<-as.numeric(votes_data)

#Let's have another look at the votes data
head(votes_data)
## [1] 413339 201710 591549 158291 221168 100262
length(votes_data)
## [1] 100
#Using CSS selectors to scrape the directors section
directors_data_html <- html_nodes(webpage,'.text-muted+ p a:nth-child(1)')

#Converting the directors data to text
directors_data <- html_text(directors_data_html)

#Let's have a look at the directors data
head(directors_data)
## [1] "M. Night Shyamalan" "Paul Feig"          "David Ayer"        
## [4] "Sang-ho Yeon"       "James Wan"          "Mike Flanagan"
#Data-Preprocessing: converting directors data into factors
directors_data<-as.factor(directors_data)
length(directors_data)
## [1] 100
#Using CSS selectors to scrape the actors section
actors_data_html <- html_nodes(webpage,'.lister-item-content .ghost+ a')

#Converting the gross actors data to text
actors_data <- html_text(actors_data_html)

#Let's have a look at the actors data
head(actors_data)
## [1] "James McAvoy"       "Melissa McCarthy"   "Will Smith"        
## [4] "Yoo Gong"           "Vera Farmiga"       "John Gallagher Jr."
#Data-Preprocessing: converting actors data into factors
actors_data<-as.factor(actors_data)
length(actors_data)
## [1] 100
#Using CSS selectors to scrape the metascore section
metascore_data_html <- html_nodes(webpage,'.metascore')

#Converting the runtime data to text
metascore_data <- html_text(metascore_data_html)

#Let's have a look at the metascore data
head(metascore_data)
## [1] "62        " "60        " "40        " "72        " "65        "
## [6] "67        "
#Data-Preprocessing: removing extra space in metascore
metascore_data<-gsub(" ","",metascore_data)

#Lets check the length of metascore data
length(metascore_data)
## [1] 96
for (i in c(33,58,74,89)){
  a<-metascore_data[1:(i-1)]

  b<-metascore_data[i:length(metascore_data)]

  metascore_data<-append(a,list("NA"))

  metascore_data<-append(metascore_data,b)

}



#Data-Preprocessing: converting metascore to numerical
metascore_data<-as.numeric(metascore_data)
## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion
#Let's have another look at length of the metascore data

length(metascore_data)
## [1] 100
#Let's look at summary statistics
summary(metascore_data)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   22.00   47.00   60.00   59.54   72.00   99.00       4
#Using CSS selectors to scrape the gross revenue section
gross_data_html <- html_nodes(webpage,'.ghost~ .text-muted+ span')

#Converting the gross revenue data to text
gross_data <- html_text(gross_data_html)

#Let's have a look at the votes data
head(gross_data)
## [1] "$138.29M" "$128.34M" "$325.10M" "$2.13M"   "$102.47M" "$6.86M"
#Data-Preprocessing: removing '$' and 'M' signs
gross_data<-gsub("M","",gross_data)

gross_data<-substring(gross_data,2,6)

#Let's check the length of gross data
length(gross_data)
## [1] 90
#Filling missing entries with NA
for (i in c(6,11,33,53,58,80,85,86,88,94)){
 
   a<-gross_data[1:(i-1)]

  b<-gross_data[i:length(gross_data)]

  gross_data<-append(a,list("NA"))

  gross_data<-append(gross_data,b)

}



#Data-Preprocessing: converting gross to numerical
gross_data<-as.numeric(gross_data)
## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion

## Warning: NAs introduced by coercion
#Let's have another look at the length of gross data
length(gross_data)
## [1] 100
summary(gross_data)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.02   10.71   53.75   86.42  101.92  532.10      10
#Combining all the lists to form a data frame
movies_df<-data.frame(Rank = rank_data, Title = title_data,

Description = description_data, Runtime = runtime_data,

Genre = genre_data, Rating = rating_data,

Metascore = metascore_data, Votes = votes_data,                                                             Gross_Earning_in_Mil = gross_data,

Director = directors_data, Actor = actors_data)

#Structure of the data frame

str(movies_df)
## 'data.frame':    100 obs. of  11 variables:
##  $ Rank                : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ Title               : Factor w/ 100 levels "10 Cloverfield Lane",..: 66 29 68 92 74 36 73 23 98 51 ...
##  $ Description         : Factor w/ 100 levels "    A corporate risk-management consultant must decide whether or not to terminate an artificially created humanoid being.",..: 88 52 21 97 47 3 19 26 66 63 ...
##  $ Runtime             : num  117 117 123 118 134 82 83 108 144 107 ...
##  $ Genre               : Factor w/ 8 levels "Action","Adventure",..: 8 1 1 1 8 8 1 1 1 3 ...
##  $ Rating              : num  7.3 6.5 6 7.6 7.3 6.6 6.2 8 6.9 7.6 ...
##  $ Metascore           : num  62 60 40 72 65 67 44 65 52 81 ...
##  $ Votes               : num  413339 201710 591549 158291 221168 ...
##  $ Gross_Earning_in_Mil: num  138.2 128.3 325.1 2.13 102.4 ...
##  $ Director            : Factor w/ 96 levels "Adam Wingard",..: 54 69 21 79 40 61 52 90 12 76 ...
##  $ Actor               : Factor w/ 91 levels "Aamir Khan","Adam Sandler",..: 38 60 90 91 88 42 76 74 38 7 ...

Question 1: Based on the above data, which movie from which Genre had the longest runtime?

Answer: (82) American Honey Drama Runtime 163 minutes

p1 <- qplot(data = movies_df,Runtime,fill = Genre,bins = 30)

p1 <- movies_df %>%
  ggplot(aes(x=Runtime, fill = Genre)) +
  geom_histogram(position="identity", alpha=0.5, binwidth = 5, color = "white")+
  scale_fill_discrete(name = "Genre") +
  labs(title = "Top 100 Movies of 2016 Runtime by Genre")  
ggplotly(p1)
# Answer: (82)  American Honey      Drama     Runtime 163 minutes
movies_df %>%
  rownames_to_column(var = "Name") %>% 
  filter(Runtime == max(Runtime))
##   Name Rank          Title
## 1   82   82 American Honey
##                                                                                                                                                                                                              Description
## 1     A teenage girl with nothing to lose joins a traveling magazine sales crew, and gets caught up in a whirlwind of hard partying, law bending and young love as she criss-crosses the Midwest with a band of misfits.
##   Runtime Genre Rating Metascore Votes Gross_Earning_in_Mil      Director
## 1     163 Drama      7        80 37541                 0.66 Andrea Arnold
##        Actor
## 1 Sasha Lane
# Answer: (82)  American Honey      Drama     Runtime 163 minutes

Question 2: Based on the above data, in the Runtime of 130-160 mins, which genre has the highest votes?

Answer: Action

p2 <- ggplot(movies_df,aes(x=Runtime,y=Rating))+
  geom_point(aes(size=Votes,col=Genre)) +
  labs(title = "Top 100 Movies of 2016 Runtime by Ratings")
p2

Question 3: Based on the above data, across all genres which genre has the highest average gross earnings in runtime 100 to 120.

Answer: Action, $103.1 Million average gross earnings in runtime 100-120.

p3 <- ggplot(movies_df,aes(x=Runtime,y=Gross_Earning_in_Mil))+
geom_point(aes(size=Rating,col=Genre)) +
   labs(title = "Top 100 Movies of 2016 Runtime by Gross Earnings in Millions")

(p3)
## Warning: Removed 10 rows containing missing values (geom_point).

movies_df %>%
  rownames_to_column(var = "Name") %>% 
  filter(Runtime == c(100,120)) %>%
  group_by(Genre) %>%
  summarize(averageGross = mean(Gross_Earning_in_Mil)) %>%
  filter(averageGross == max(averageGross))
## # A tibble: 1 x 2
##   Genre  averageGross
##   <fct>         <dbl>
## 1 Action         103.