Final Project - Movie Data - Business Case

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

##Clean Data
#Filter years - greater 2005
imbdclean <- imbd_rating[imbd_rating$year > 2005, ]

#Get rid of null rows
finalimbd <- imbdclean[complete.cases(imbdclean), ]
#Clean title
actionmovies$title <- gsub("Â", '', actionmovies$title)
#Clean Director 
actionmovies$director <- gsub("Â", '', actionmovies$director)

#filter genre
actionmovies <- filter(finalimbd, grepl('Action', genres))

#filter aspect ratio
actionmovies <- actionmovies[actionmovies$aspect_ratio == "2.35", ]

#histogram
imbdclean$aspect_ratio <- as.factor(imbdclean$aspect_ratio)
count <- count(imbdclean, aspect_ratio)
counts <- table(imbdclean$aspect_ratio)
barplot(counts, main = "Aspect Ratio", xlab = "Dimensions")

#histogram
imbdclean$genres <- as.factor(imbdclean$genres)
countgenres <- count(imbdclean,'Action', genres)
counts <- table(imbdclean$genres)
barplot(counts, main = "Genres", xlab = "Type")

#regression model
reg <- lm(actionmovies$gross ~ actionmovies$budget + actionmovies$score + actionmovies$critic_reviews)
summary(reg)

Call:
lm(formula = actionmovies$gross ~ actionmovies$budget + actionmovies$score + 
    actionmovies$critic_reviews)

Residuals:
       Min         1Q     Median         3Q        Max 
-320804488  -30651992   -5086208   23817116  252130825 

Coefficients:
                              Estimate Std. Error t value Pr(>|t|)    
(Intercept)                 -1.398e+08  2.248e+07  -6.217 1.39e-09 ***
actionmovies$budget          5.410e-01  5.269e-02  10.268  < 2e-16 ***
actionmovies$score           1.589e+07  3.945e+06   4.028 6.84e-05 ***
actionmovies$critic_reviews  2.758e+05  2.962e+04   9.312  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 59470000 on 364 degrees of freedom
Multiple R-squared:  0.6166,    Adjusted R-squared:  0.6135 
F-statistic: 195.2 on 3 and 364 DF,  p-value: < 2.2e-16

plot(actionmovies$budget, actionmovies$gross, xlab = "Budget of Action movies with 2.35 AR", ylab = "Gross of Action movies with 2.35 AR")
abline(9.892e+06, 8.960e-01)

lm(actionmovies$gross ~ actionmovies$budget)

Call:
lm(formula = actionmovies$gross ~ actionmovies$budget)

Coefficients:
        (Intercept)  actionmovies$budget  
          9.892e+06            8.960e-01  

summary(actionmovies)

    title              genres            director            actor1             actor2             actor3              length          budget          director_fb_likes actor1_fb_likes   
 Length:368         Length:368         Length:368         Length:368         Length:368         Length:368         Min.   : 81.0   Min.   :  2000000   Min.   :    0.0   Min.   :    21.0  
 Class :character   Class :character   Class :character   Class :character   Class :character   Class :character   1st Qu.:101.0   1st Qu.: 35000000   1st Qu.:   25.0   1st Qu.:   966.8  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character   Mode  :character   Mode  :character   Median :110.5   Median : 65000000   Median :  135.0   Median : 11000.0  
                                                                                                                   Mean   :114.5   Mean   : 89085685   Mean   :  730.5   Mean   : 11583.1  
                                                                                                                   3rd Qu.:123.0   3rd Qu.:140000000   3rd Qu.:  340.5   3rd Qu.: 18000.0  
                                                                                                                   Max.   :215.0   Max.   :553632000   Max.   :22000.0   Max.   :137000.0  
 actor2_fb_likes   actor3_fb_likes   total_cast_likes    fb_likes      critic_reviews  users_reviews     users_votes          score        aspect_ratio      gross                year     
 Min.   :   17.0   Min.   :    7.0   Min.   :    58   Min.   :     0   Min.   : 30.0   Min.   :  23.0   Min.   :   2508   Min.   :2.700   Min.   :2.35   Min.   :      162   Min.   :2006  
 1st Qu.:  551.8   1st Qu.:  308.8   1st Qu.:  2908   1st Qu.:     0   1st Qu.:188.8   1st Qu.: 178.8   1st Qu.:  54076   1st Qu.:5.875   1st Qu.:2.35   1st Qu.: 23047736   1st Qu.:2009  
 Median :  899.5   Median :  559.0   Median : 14968   Median : 15000   Median :265.0   Median : 342.5   Median : 119483   Median :6.400   Median :2.35   Median : 56114221   Median :2011  
 Mean   : 3475.1   Mean   : 1258.9   Mean   : 17760   Mean   : 24942   Mean   :290.3   Mean   : 497.3   Mean   : 174112   Mean   :6.371   Mean   :2.35   Mean   : 89708090   Mean   :2011  
 3rd Qu.: 3000.0   3rd Qu.:  903.0   3rd Qu.: 25210   3rd Qu.: 38000   3rd Qu.:372.0   3rd Qu.: 637.0   3rd Qu.: 229681   3rd Qu.:6.925   3rd Qu.:2.35   3rd Qu.:126248948   3rd Qu.:2014  
 Max.   :27000.0   Max.   :23000.0   Max.   :137712   Max.   :197000   Max.   :813.0   Max.   :4667.0   Max.   :1676169   Max.   :9.000   Max.   :2.35   Max.   :533316061   Max.   :2016  

lm(actionmovies$gross ~ actionmovies$score)

Call:
lm(formula = actionmovies$gross ~ actionmovies$score)

Coefficients:
       (Intercept)  actionmovies$score  
        -218685712            48408514  

lm(actionmovies$gross ~ actionmovies$critic_reviews)

Call:
lm(formula = actionmovies$gross ~ actionmovies$critic_reviews)

Coefficients:
                (Intercept)  actionmovies$critic_reviews  
                  -48611078                       476463  

plot(actionmovies$score, actionmovies$gross, xlab = "Score of Action movies with 2.35 AR", ylab = "Gross of Action movies with 2.35 AR")
abline(-218685712, 48408514)

plot(actionmovies$critic_reviews, actionmovies$gross, xlab = "Critics Reviews of Action movies with 2.35 AR", ylab = "Gross of Action movies with 2.35 AR")
abline(-48611078, 476463)

summary(actionmovies$gross)

     Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
      162  23050000  56110000  89710000 126200000 533300000 

summary(actionmovies$budget)

     Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
  2000000  35000000  65000000  89090000 140000000 553600000 

summary(actionmovies$score)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  2.700   5.875   6.400   6.371   6.925   9.000 

summary(actionmovies$critic_reviews)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   30.0   188.8   265.0   290.3   372.0   813.0 

summary(actionmovies)

    title              genres            director            actor1             actor2         
 Length:368         Length:368         Length:368         Length:368         Length:368        
 Class :character   Class :character   Class :character   Class :character   Class :character  
 Mode  :character   Mode  :character   Mode  :character   Mode  :character   Mode  :character  
                                                                                               
                                                                                               
                                                                                               
    actor3              length          budget          director_fb_likes actor1_fb_likes   
 Length:368         Min.   : 81.0   Min.   :  2000000   Min.   :    0.0   Min.   :    21.0  
 Class :character   1st Qu.:101.0   1st Qu.: 35000000   1st Qu.:   25.0   1st Qu.:   966.8  
 Mode  :character   Median :110.5   Median : 65000000   Median :  135.0   Median : 11000.0  
                    Mean   :114.5   Mean   : 89085685   Mean   :  730.5   Mean   : 11583.1  
                    3rd Qu.:123.0   3rd Qu.:140000000   3rd Qu.:  340.5   3rd Qu.: 18000.0  
                    Max.   :215.0   Max.   :553632000   Max.   :22000.0   Max.   :137000.0  
 actor2_fb_likes   actor3_fb_likes   total_cast_likes    fb_likes      critic_reviews  users_reviews   
 Min.   :   17.0   Min.   :    7.0   Min.   :    58   Min.   :     0   Min.   : 30.0   Min.   :  23.0  
 1st Qu.:  551.8   1st Qu.:  308.8   1st Qu.:  2908   1st Qu.:     0   1st Qu.:188.8   1st Qu.: 178.8  
 Median :  899.5   Median :  559.0   Median : 14968   Median : 15000   Median :265.0   Median : 342.5  
 Mean   : 3475.1   Mean   : 1258.9   Mean   : 17760   Mean   : 24942   Mean   :290.3   Mean   : 497.3  
 3rd Qu.: 3000.0   3rd Qu.:  903.0   3rd Qu.: 25210   3rd Qu.: 38000   3rd Qu.:372.0   3rd Qu.: 637.0  
 Max.   :27000.0   Max.   :23000.0   Max.   :137712   Max.   :197000   Max.   :813.0   Max.   :4667.0  
  users_votes          score        aspect_ratio      gross                year     
 Min.   :   2508   Min.   :2.700   Min.   :2.35   Min.   :      162   Min.   :2006  
 1st Qu.:  54076   1st Qu.:5.875   1st Qu.:2.35   1st Qu.: 23047736   1st Qu.:2009  
 Median : 119483   Median :6.400   Median :2.35   Median : 56114221   Median :2011  
 Mean   : 174112   Mean   :6.371   Mean   :2.35   Mean   : 89708090   Mean   :2011  
 3rd Qu.: 229681   3rd Qu.:6.925   3rd Qu.:2.35   3rd Qu.:126248948   3rd Qu.:2014  
 Max.   :1676169   Max.   :9.000   Max.   :2.35   Max.   :533316061   Max.   :2016  

sd(actionmovies$gross)

[1] 95662525

#gross
sd(actionmovies$budget)

[1] 70341395

#budget
sd(actionmovies$critic_reviews)

[1] 140.6367

#critic reviews
sd(actionmovies$score)

[1] 0.9166386

#score

snrgross = mean(actionmovies$gross)/sd(actionmovies$gross)
snrbudget = mean(actionmovies$budget)/sd(actionmovies$budget)
snrcriticreviews = mean(actionmovies$critic_reviews)/sd(actionmovies$critic_reviews)
snrscore = mean(actionmovies$score)/sd(actionmovies$score)

corr01 = actionmovies[c(8,20)]
cor(corr01)

          budget     gross
budget 1.0000000 0.6587992
gross  0.6587992 1.0000000

corr02 = actionmovies[c(15,20)]
cor(corr02)

               critic_reviews     gross
critic_reviews      1.0000000 0.7004639
gross               0.7004639 1.0000000

corr03 = actionmovies[c(18,20)]
cor(corr03)

          score     gross
score 1.0000000 0.4638505
gross 0.4638505 1.0000000

plot(corr02)
abline(-48611078, 476463)

lm(actionmovies$gross~actionmovies$critic_reviews)

Call:
lm(formula = actionmovies$gross ~ actionmovies$critic_reviews)

Coefficients:
                (Intercept)  actionmovies$critic_reviews  
                  -48611078                       476463  

#predicting gross by budget, critic reviews, and score
lm1 = lm(actionmovies$gross ~ actionmovies$budget + actionmovies$critic_reviews + actionmovies$score)
lm1

Call:
lm(formula = actionmovies$gross ~ actionmovies$budget + actionmovies$critic_reviews + 
    actionmovies$score)

Coefficients:
                (Intercept)          actionmovies$budget  actionmovies$critic_reviews  
                 -1.398e+08                    5.410e-01                    2.758e+05  
         actionmovies$score  
                  1.589e+07  

plot(corr01)
abline(9.892e+06, 8.960e-01)

plot(corr03)
abline(-218685712, 48408514)

summary(actionmovies$gross)

     Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
      162  23050000  56110000  89710000 126200000 533300000 

hist(actionmovies$gross)

hist(actionmovies$budget)

hist(actionmovies$score)

hist(actionmovies$critic_reviews)

scatter.smooth(actionmovies$critic_reviews,actionmovies$gross)

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).