w9_homework

Web Scraping data source from IMDB

#Loading the rvest package
#install.packages('rvest')
library('rvest')
library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.5     v dplyr   1.0.7
## v tidyr   1.1.4     v stringr 1.4.0
## v readr   2.0.2     v forcats 0.5.1

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter()         masks stats::filter()
## x readr::guess_encoding() masks rvest::guess_encoding()
## x dplyr::lag()            masks stats::lag()

library(dplyr)
#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)

Step1: Scarping the rankings Step2: Copy the selections

#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."

Step4: Convert the rankings to numerical format

#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

Step5 & 6: clear the selector section and select all titles/Scraping the title

#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] "Arrival"                       "Ghostbusters: Answer the Call"
## [3] "Train to Busan"                "Suicide Squad"                
## [5] "Hacksaw Ridge"                 "Hush"

Step7: scraping the description.

#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] "\nA linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appear around the world."                                                                                  
## [2] "\nFollowing 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] "\nWhile a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."                                                                                                    
## [4] "\nA 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."                                 
## [5] "\nWorld War II American Army Medic Desmond T. Doss, who served during the Battle of Okinawa, refuses to kill people and becomes the first man in American history to receive the Medal of Honor without firing a shot."
## [6] "\nA 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."

& clean up the description data

#Data-Preprocessing: removing '\n'
description_data<-gsub("\n","",description_data)

#Let's have another look at the description data 
head(description_data)

## [1] "A linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appear around the world."                                                                                  
## [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] "While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan."                                                                                                    
## [4] "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."                                 
## [5] "World War II American Army Medic Desmond T. Doss, who served during the Battle of Okinawa, refuses to kill people and becomes the first man in American history to receive the Medal of Honor without firing a shot."
## [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."

Step7: scraping the movie runtime

#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] "116 min" "117 min" "118 min" "123 min" "139 min" "82 min"

& Removing mins

#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] 116 117 118 123 139  82

Step7: Scraping the genre

#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 runtime
head(genre_data)

## [1] "\nDrama, Sci-Fi            "             
## [2] "\nAction, Comedy, Fantasy            "   
## [3] "\nAction, Horror, Thriller            "  
## [4] "\nAction, Adventure, Fantasy            "
## [5] "\nBiography, Drama, History            " 
## [6] "\nHorror, Thriller            "

& Removing in genre

#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] Drama     Action    Action    Action    Biography Horror   
## 9 Levels: Action Adventure Animation Biography Comedy Crime Drama ... Mystery

Step7: Scraping the IMDB rating

#Using CSS selectors to scrape the IMDB rating section
rating_data_html <- html_nodes(webpage,'.ratings-imdb-rating')

#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] "\n        \n        7.9\n    " "\n        \n        6.5\n    "
## [3] "\n        \n        7.6\n    " "\n        \n        5.9\n    "
## [5] "\n        \n        8.1\n    " "\n        \n        6.6\n    "

& Converting the ratings

#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] 7.9 6.5 7.6 5.9 8.1 6.6

Step7: Scraping the votes

#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] "641,620" "214,273" "192,862" "654,712" "472,043" "119,086"

& Removing commas in votes

#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] 641620 214273 192862 654712 472043 119086

Step7: Scraping the directors

#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] "Denis Villeneuve" "Paul Feig"        "Sang-ho Yeon"     "David Ayer"      
## [5] "Mel Gibson"       "Mike Flanagan"

& Converting the directors, actors and gross_actors

#Data-Preprocessing: converting directors data into factors
directors_data<-as.factor(directors_data)

#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] "Amy Adams"          "Melissa McCarthy"   "Gong Yoo"          
## [4] "Will Smith"         "Andrew Garfield"    "John Gallagher Jr."

& Converting actors data

#Data-Preprocessing: converting actors data into factors
actors_data<-as.factor(actors_data)

step7: Scraping the metscore

#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 
head(metascore_data)

## [1] "81        " "60        " "72        " "40        " "71        "
## [6] "67        "

& Removing extra space

#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(39,73,80,89)){

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

& Look at summary

#Let's look at summary statistics
summary(metascore_data)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   18.00   48.75   63.50   61.02   74.25   99.00       4

Step7: Scraping the gross revenue

#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] "$100.55M" "$128.34M" "$2.13M"   "$325.10M" "$67.21M"  "$89.22M"

& Remove $ and M

#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] 89

& Filling and converting gross to numerical

#Filling missing entries with NA
for (i in c(17,39,49,52,57,64,66,73,76,77,80,87,88,89)){

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

## 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] 103

summary(gross_data)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.15   14.43   52.85   87.35  102.40  532.10      14

Step7_alt: Find metascore data with missing values and replace with NAs

## Find metascore data with missing values and replace with NAs (this is an automated method) 
ratings_bar_data <- html_nodes(webpage,'.ratings-bar') %>% 
# scrape the ratings bar and convert to text
  html_text2()
head(ratings_bar_data)                                # look at the ratings bar

## [1] "7.9\nRate this\n 1 2 3 4 5 6 7 8 9 10 7.9/10 X \n81 Metascore"
## [2] "6.5\nRate this\n 1 2 3 4 5 6 7 8 9 10 6.5/10 X \n60 Metascore"
## [3] "7.6\nRate this\n 1 2 3 4 5 6 7 8 9 10 7.6/10 X \n72 Metascore"
## [4] "5.9\nRate this\n 1 2 3 4 5 6 7 8 9 10 5.9/10 X \n40 Metascore"
## [5] "8.1\nRate this\n 1 2 3 4 5 6 7 8 9 10 8.1/10 X \n71 Metascore"
## [6] "6.6\nRate this\n 1 2 3 4 5 6 7 8 9 10 6.6/10 X \n67 Metascore"

metascore_data <- str_match(ratings_bar_data, "\\d{2} Metascore") %>%  
# extract Metascore 
  str_match("\\d{2}") %>% 
  as.numeric()                                         # convert to number  
length(metascore_data)

## [1] 100

metascore_data

##   [1] 81 60 72 40 71 67 71 67 62 65 81 65 72 81 57 75 94 48 84 65 52 44 54 51 79
##  [26] 66 70 72 51 81 78 65 82 NA 59 76 41 99 25 74 32 48 96 58 NA 57 51 88 68 68
##  [51] 62 65 49 35 NA 58 45 42 74 35 23 69 44 79 18 42 42 60 78 23 81 59 77 46 68
##  [76] 58 66 66 78 52 42 36 49 45 55 77 62 70 76 28 79 77 55 90 32 NA 72 58 51 47

summary(metascore_data)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   18.00   48.75   63.50   61.02   74.25   99.00       4

Step7_alt: Scraping and convert the votes

# scrape the votes bar and convert to text
votes_bar_data <- html_nodes(webpage,'.sort-num_votes-visible') %>% 
  html_text2()
head(votes_bar_data)                                      # look at the votes bar data

## [1] "Votes: 641,620 | Gross: $100.55M" "Votes: 214,273 | Gross: $128.34M"
## [3] "Votes: 192,862 | Gross: $2.13M"   "Votes: 654,712 | Gross: $325.10M"
## [5] "Votes: 472,043 | Gross: $67.21M"  "Votes: 119,086"

gross_data <- str_match(votes_bar_data, "\\$.+$")          # extract the gross earnings
gross_data <- gsub("M","",gross_data)                      # clean data: remove 'M' sign 
gross_data <- substring(gross_data,2,6) %>%               # clean data: remove '$' sign                    
  as.numeric()
length(gross_data)

## [1] 100

Last step: Combine all

#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               : chr  "Arrival" "Ghostbusters: Answer the Call" "Train to Busan" "Suicide Squad" ...
##  $ Description         : chr  "A linguist works with the military to communicate with alien lifeforms after twelve mysterious spacecraft appea"| __truncated__ "Following a ghost invasion of Manhattan, paranormal enthusiasts Erin Gilbert and Abby Yates, nuclear engineer J"| __truncated__ "While a zombie virus breaks out in South Korea, passengers struggle to survive on the train from Seoul to Busan." "A secret government agency recruits some of the most dangerous incarcerated super-villains to form a defensive "| __truncated__ ...
##  $ Runtime             : num  116 117 118 123 139 82 88 116 117 134 ...
##  $ Genre               : Factor w/ 9 levels "Action","Adventure",..: 7 1 1 1 4 8 6 7 8 8 ...
##  $ Rating              : num  7.9 6.5 7.6 5.9 8.1 6.6 7.1 7.5 7.3 7.3 ...
##  $ Metascore           : num  81 60 72 40 71 67 71 67 62 65 ...
##  $ Votes               : num  641620 214273 192862 654712 472043 ...
##  $ Gross_Earning_in_Mil: num  100.5 128.3 2.13 325.1 67.21 ...
##  $ Director            : Factor w/ 97 levels "Alex Proyas",..: 26 72 84 21 59 61 31 94 54 41 ...
##  $ Actor               : Factor w/ 91 levels "Aamir Khan","Aaron Poole",..: 5 68 39 91 6 48 82 5 42 89 ...

p1: the first graph from the tutorial

library('ggplot2')
p1<-qplot(data = movies_df,Runtime,fill=Genre,bins=20)
p1

p2: filtered graph to response the question 1 Question 1: Based on the above data, which movie from which Genre had the longest runtime? Adventure has the longest runtime. Now, filter Adventure to find out a longest movie in Adventure.

movies_ad <-filter( movies_df, Genre=="Adventure")
qplot (data = movies_ad,Runtime, fill=Title, bin=30, main = "Movies and Rumtime in Adventure")

## Warning: Ignoring unknown parameters: bin

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

p3: the second graph from the tutorial

p3 <-ggplot(movies_df,aes(x=Runtime,y=Rating)) +
  geom_point(aes(size=Votes,col=Genre))
p3

p4: filtered graph to response the question 2 Question 2: Based on the above data, in the Runtime of 130-160 mins, which genre has the highest votes?

library(plotly)

## 
## 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

movies_vo<-movies_df %>% 
  select(Runtime,Genre,Votes,Rating) %>% 
  filter(Runtime >= 130) %>% filter(Runtime < 160)
p4 <-ggplot(movies_vo,aes(x=Runtime,y=Rating,size=Votes,text=paste("Genre",Genre))) +
  geom_point(aes(size=Votes,col=Genre)) + xlim(130,160) + ylim(6,10) +
  ggtitle ("Votes by Genre")+
  xlab ("Runtime (min.)") +
  ylab ("Rate (Count)") +
  theme_minimal (base_size =12)

p4 <-ggplotly (p4)
p4

p5: the third graph from the tutorial

p5 <-ggplot(movies_df,aes(x=Runtime,y=Gross_Earning_in_Mil))+
  geom_point(aes(size=Rating,col=Genre))
p5

## Warning: Removed 11 rows containing missing values (geom_point).

p6: filtered graph to response the question 3 Question 3: Based on the above data, across all genres which genre has the highest average gross earnings in runtime 100 to 120.

movies_gr<-movies_df %>% 
  select(Runtime,Genre,Gross_Earning_in_Mil,Rating) %>% 
  filter(Runtime >= 100) %>% filter(Runtime < 120)
p6 <-ggplot(movies_gr,aes(x=Runtime,y=Gross_Earning_in_Mil))+
  geom_point(aes(size=Rating,col=Genre))
p6

## Warning: Removed 1 rows containing missing values (geom_point).