Credits dataset

glimpse(credits)

## Observations: 4,803
## Variables: 4
## $ movie_id <dbl> 19995, 285, 206647, 49026, 49529, 559, 38757, 99861, ...
## $ title    <chr> "Avatar", "Pirates of the Caribbean: At World's End",...
## $ cast     <chr> "[{\"cast_id\": 242, \"character\": \"Jake Sully\", \...
## $ crew     <chr> "[{\"credit_id\": \"52fe48009251416c750aca23\", \"dep...

summary(credits)

##     movie_id         title               cast               crew          
##  Min.   :     5   Length:4803        Length:4803        Length:4803       
##  1st Qu.:  9014   Class :character   Class :character   Class :character  
##  Median : 14629   Mode  :character   Mode  :character   Mode  :character  
##  Mean   : 57166                                                           
##  3rd Qu.: 58611                                                           
##  Max.   :459488

#Cleaning the Movie Dataset

genredf=movie %>% filter(nchar(genres)>2) %>% mutate(js=lapply(genres,fromJSON)) %>% unnest(js) %>% select(id,title,genre=name) #Convert JSON format into data frame
slice(genredf)

## # A tibble: 12,160 x 3
##        id title                                    genre          
##     <dbl> <chr>                                    <chr>          
##  1  19995 Avatar                                   Action         
##  2  19995 Avatar                                   Adventure      
##  3  19995 Avatar                                   Fantasy        
##  4  19995 Avatar                                   Science Fiction
##  5    285 Pirates of the Caribbean: At World's End Adventure      
##  6    285 Pirates of the Caribbean: At World's End Fantasy        
##  7    285 Pirates of the Caribbean: At World's End Action         
##  8 206647 Spectre                                  Action         
##  9 206647 Spectre                                  Adventure      
## 10 206647 Spectre                                  Crime          
## # ... with 12,150 more rows

#Wordcloud of Genre Representation

temp=genredf %>% group_by(genre) %>% summarise(count=length(genre)) %>% arrange(desc(count))

wordcloud(words=temp$genre,freq=temp$count,min.freq=100,max.words = 20,random.order=FALSE,random.color=FALSE,rot.per=0.35,colors = brewer.pal(20,"Dark2"),scale=c(5,.2))

## Warning in brewer.pal(20, "Dark2"): n too large, allowed maximum for palette Dark2 is 8
## Returning the palette you asked for with that many colors

Comedy,Drama,Thriller and Action are most represented.

#Movies with highest budget

movie %>% select(original_title,budget) %>% drop_na(original_title)%>% arrange(desc(budget)) %>% head(10) %>%  ggplot(aes(reorder(original_title,budget),budget,fill=original_title))+geom_bar(stat="identity")+theme(axis.text.x = element_text(angle=90),plot.title=element_text(color="Red",face="italic"),legend.position="none")+scale_y_continuous(labels=scales::comma)+labs(x="",y="Total Budget in $",title="Most Expensive Movies -Top 10")

#Highest grossing movies

movie %>% select(original_title,revenue) %>% drop_na(original_title)%>% arrange(desc(revenue)) %>% head(10)  %>% ggplot(aes(reorder(original_title,revenue),revenue,fill=original_title))+geom_bar(stat="identity")+theme(axis.text.x = element_text(angle=90),plot.title=element_text(color="Red",face="italic"),legend.position="none")+scale_y_continuous(limits=c(0,3000000000),breaks=seq(0,3000000000,500000000),labels=scales::comma)+labs(x="",y="Total Revenue in $",title="Highest Grossing Movies -Top 10")

#Movies with highest popularity

movie %>% group_by(original_title) %>% arrange(desc(popularity)) %>% head(10) %>% ggplot(aes(factor(original_title,levels=original_title),popularity,fill=original_title))+geom_bar(stat="identity")+theme_few()+theme(axis.text.x=element_text(angle=90,hjust=0.5),plot.title=element_text(hjust=0.5,size=15,color="red"),legend.position="none")+labs(x="Title",y="Rating",title="Popularity of Movies")+scale_x_discrete(labels=function(x)str_wrap(x,width=15))

#Production companies

production=movie%>% filter(nchar(production_companies)>2)%>% mutate(js=lapply(production_companies,fromJSON)) %>% unnest(js)%>% select(budget,revenue,company=name)
lapply(production,class)

## $budget
## [1] "numeric"
## 
## $revenue
## [1] "numeric"
## 
## $company
## [1] "character"

temp=production %>% group_by(company) %>% summarise(count=n()) %>% arrange(desc(count)) 
wordcloud(words=temp$company,freq=temp$count,max.words = 25,color =rainbow(7),scale=c(2,0.2))

Warner Bros,Universal Pictures,Parmount Pictures,20th century fox are represented more in this dataset.

Wordcloud:

par(mfrow=c(1,2))
wordcloud(positive$text,positive$freq_tag, min.freq=10,rot.per=0,vfont=c("sans serif","plain"))
text(x=0.5, y=1.05, "Positive",col=brewer.pal(4, "Reds"))
wordcloud(negative$text,negative$freq_tag, min.freq=7,rot.per=0,vfont=c("sans serif","plain"))
text(x=0.5, y=1.05, "Negative",col=brewer.pal(4, "Reds"))

#Release date,year,month

Which year has seen maximum release of movies ?

class(movie$release_date)

## [1] "Date"

movie$Year=as.factor(format(movie$release_date,"%Y"))
movie$Date=as.factor(format(movie$release_date,"%d"))
movie$month=month.abb[(as.factor(format(movie$release_date,"%m")))]
movie %>% group_by(month) %>% drop_na(month) %>% summarise(count=n()) %>% arrange(desc(month)) %>% ggplot(aes(reorder(month,count),count,fill=month))+geom_bar(stat="identity")+theme(plot.title=element_text(size=14,face="italic",colour="red"),axis.text.x = element_text(angle=90),legend.position="none")+labs(x="",y="Total number of movies released",title="Number of Movies Releases per month")+coord_flip()+geom_label(aes(label=count))

Does higher number correlate to higher quality content ?

movie %>% drop_na(month) %>% ggplot(aes(month,vote_average,fill=month))+geom_boxplot(outlier.colour = "red",na.rm=TRUE)+theme(plot.title=element_text(size=14,face="italic",colour="red"),axis.text.x = element_text(angle=90),legend.position="none")+labs(x="",y="Average Vote",title="Boxplot of Average votes received by month")+coord_flip()

movie$month=factor(movie$month,levels=month.abb,ordered=TRUE)
#temp=movie %>% group_by(month) %>% filter(vote_average!=0)%>%  #summarise(median=median(vote_average),low=min(vote_average),high=max(vote_average)) %>% mutate(score=paste(low,"/",high))
temp=movie %>% drop_na(vote_average,month) %>% filter(vote_average!=0) %>% ddply(.(month),function(x){c(mid=median(x$vote_average),low=min(x$vote_average),high=max(x$vote_average))})
temp=temp[order(temp$month),]
formattable(temp,align=c("l","c","c","c"),list(mid=color_tile('lightblue','white'),low=color_bar('orange'),high=color_bar('lightgreen')))

credit=credits %>% filter(nchar(cast)>2) %>% mutate(js=lapply(cast,fromJSON)) %>% unnest(js)
cat("Before JS the columns are ",names(credit),sep='\n')

## Before JS the columns are 
## movie_id
## title
## cast
## crew
## cast_id
## character
## credit_id
## gender
## id
## name
## order

credit= credit%>% select(-c(crew,cast_id,credit_id,id))
cat("After removing id columns the names are",names(credit),sep='\n')

## After removing id columns the names are
## movie_id
## title
## cast
## character
## gender
## name
## order

#Artist with most movies: Let us see which artist has acted in more movies

credit %>% group_by(name) %>% tally() %>% arrange(desc(n)) %>% head(10) %>% ggplot(aes(factor(name,levels=name),n,fill=name))+geom_bar(stat="identity")+labs(x="Artist",y="Count",title="Top 10 artist with most movies")+theme_few()+theme(axis.text.x=element_text(angle=90),plot.title=element_text(hjust=0.5,color="red"),legend.position="none")

db=movie %>% left_join(credits,by=c("id"="movie_id"))
db_credit=db %>% filter(nchar(cast)>2) %>% mutate(js=lapply(cast,fromJSON)) %>% unnest(js)
revenue=function (df,col_name,x,y,title){
 temp_df=df %>% filter(name==col_name) %>% arrange(desc(revenue)) %>% head(10)
 df_plot= ggplot(temp_df,aes(reorder(original_title,revenue),revenue,fill=original_title))+geom_bar(stat="identity")+theme_few()+theme(axis.text.x = element_text(angle=90,vjust=0.5),plot.title=element_text(hjust=0.5,size=15),legend.position="none")+labs(x=x,y=y,title=title)+coord_flip()+scale_x_discrete(labels=function(x)str_wrap(x,width=15))+scale_y_continuous(labels=scales::comma)
 print(df_plot)
 
}