Movie Review Analysis
Arun Kumar
July 26, 2015
Required R libraries
## Loading required package: plyr
## Loading required package: ggplot2Objective
To analyse a dataset of movie rating
Starting Point
The dataset if obtained from the below site: http://vincentarelbundock.github.io/ Dataset reference: Movie information and user ratings from IMDB.com.
Obtaining the data
- Download the data in a csv sheet
theURL <- "http://vincentarelbundock.github.io/Rdatasets/csv/ggplot2/movies.csv";
movie_data <- read.table(file = theURL, header = TRUE, sep = ",");
head(movie_data);
#State column is named as 'X". Changing the column name to US_State
colnames(movie_data)[1] <- "RefNo";
head(movie_data);
#Write the data to a CSV
write.table(movie_data, file = "movie_data.csv", sep = ",", row.names = FALSE);
#The saved file is uploaded to githib and below is the URL which will be used hereafter.
#https://raw.githubusercontent.com/arunk13/MSDA-Assignments/master/BridgeCourse/Week5/movie_data.csv Note: The tips provided in the below link is followed to clean up the data (Introduction to data cleaning)https://cran.r-project.org/doc/contrib/de_Jonge+van_der_Loo-Introduction_to_data_cleaning_with_R.pdf
Raw Data
## RefNo title year length budget rating votes r1 r2
## 1 1 $ 1971 121 NA 6.4 348 4.5 4.5
## 2 2 $1000 a Touchdown 1939 71 NA 6.0 20 0.0 14.5
## 3 3 $21 a Day Once a Month 1941 7 NA 8.2 5 0.0 0.0
## 4 4 $40,000 1996 70 NA 8.2 6 14.5 0.0
## 5 5 $50,000 Climax Show, The 1975 71 NA 3.4 17 24.5 4.5
## 6 6 $pent 2000 91 NA 4.3 45 4.5 4.5
## r3 r4 r5 r6 r7 r8 r9 r10 mpaa Action Animation Comedy
## 1 4.5 4.5 14.5 24.5 24.5 14.5 4.5 4.5 0 0 1
## 2 4.5 24.5 14.5 14.5 14.5 4.5 4.5 14.5 0 0 1
## 3 0.0 0.0 0.0 24.5 0.0 44.5 24.5 24.5 0 1 0
## 4 0.0 0.0 0.0 0.0 0.0 0.0 34.5 45.5 0 0 1
## 5 0.0 14.5 14.5 4.5 0.0 0.0 0.0 24.5 0 0 0
## 6 4.5 14.5 14.5 14.5 4.5 4.5 14.5 14.5 0 0 0
## Drama Documentary Romance Short
## 1 1 0 0 0
## 2 0 0 0 0
## 3 0 0 0 1
## 4 0 0 0 0
## 5 0 0 0 0
## 6 1 0 0 0Cleaning and subsetting
#First column can be removed.
movie_data <- movie_data_raw[-1];+Summary
summary(movie_data);## title year length
## Alice in Wonderland : 7 Min. :1893 Min. : 1.00
## Three Musketeers, The : 7 1st Qu.:1958 1st Qu.: 74.00
## Midsummer Night's Dream, A: 6 Median :1983 Median : 90.00
## Skin Deep : 6 Mean :1976 Mean : 82.34
## Underground : 6 3rd Qu.:1997 3rd Qu.: 100.00
## Anna Karenina : 5 Max. :2005 Max. :5220.00
## (Other) :58751
## budget rating votes r1
## Min. : 0 Min. : 1.000 Min. : 5.0 Min. : 0.000
## 1st Qu.: 250000 1st Qu.: 5.000 1st Qu.: 11.0 1st Qu.: 0.000
## Median : 3000000 Median : 6.100 Median : 30.0 Median : 4.500
## Mean : 13412513 Mean : 5.933 Mean : 632.1 Mean : 7.014
## 3rd Qu.: 15000000 3rd Qu.: 7.000 3rd Qu.: 112.0 3rd Qu.: 4.500
## Max. :200000000 Max. :10.000 Max. :157608.0 Max. :100.000
## NA's :53573
## r2 r3 r4 r5
## Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.: 4.500
## Median : 4.500 Median : 4.500 Median : 4.500 Median : 4.500
## Mean : 4.022 Mean : 4.721 Mean : 6.375 Mean : 9.797
## 3rd Qu.: 4.500 3rd Qu.: 4.500 3rd Qu.: 4.500 3rd Qu.: 14.500
## Max. :84.500 Max. :84.500 Max. :100.000 Max. :100.000
##
## r6 r7 r8 r9
## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.000
## 1st Qu.: 4.50 1st Qu.: 4.50 1st Qu.: 4.50 1st Qu.: 4.500
## Median :14.50 Median : 14.50 Median : 14.50 Median : 4.500
## Mean :13.04 Mean : 15.55 Mean : 13.88 Mean : 8.954
## 3rd Qu.:14.50 3rd Qu.: 24.50 3rd Qu.: 24.50 3rd Qu.: 14.500
## Max. :84.50 Max. :100.00 Max. :100.00 Max. :100.000
##
## r10 mpaa Action Animation
## Min. : 0.00 :53864 Min. :0.00000 Min. :0.00000
## 1st Qu.: 4.50 NC-17: 16 1st Qu.:0.00000 1st Qu.:0.00000
## Median : 14.50 PG : 528 Median :0.00000 Median :0.00000
## Mean : 16.85 PG-13: 1003 Mean :0.07974 Mean :0.06277
## 3rd Qu.: 24.50 R : 3377 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :100.00 Max. :1.00000 Max. :1.00000
##
## Comedy Drama Documentary Romance
## Min. :0.0000 Min. :0.000 Min. :0.00000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.000 1st Qu.:0.00000 1st Qu.:0.0000
## Median :0.0000 Median :0.000 Median :0.00000 Median :0.0000
## Mean :0.2938 Mean :0.371 Mean :0.05906 Mean :0.0807
## 3rd Qu.:1.0000 3rd Qu.:1.000 3rd Qu.:0.00000 3rd Qu.:0.0000
## Max. :1.0000 Max. :1.000 Max. :1.00000 Max. :1.0000
##
## Short
## Min. :0.0000
## 1st Qu.:0.0000
## Median :0.0000
## Mean :0.1609
## 3rd Qu.:0.0000
## Max. :1.0000
## - Out of 58788 records, 53573 record does not have information about the budget. I will remove the budget column from my dataset, as i feel that as the most of the observation is missing this variable data, hence it will not help me infer any understanding.
movie_data <- movie_data[-4];Similarly 53864 movies are missing mpaa ratings. Lets find out the types of movies which are missing the mpaa ratings.
## year freq
## 1 2005 289
## 2 2004 1596
## 3 2003 1747
## 4 2002 1667
## 5 2001 1611Binning observation into decades of year
Number of observation with missing year information : 0
For ease of analysis, we will subset the data from 1900 - till date.
Number of movies in by decade
freq_decade_movie <- count(movie_data, c("decade"));
g_movie <- ggplot(data = freq_decade_movie, aes(y = freq, x = decade, fill = decade));
g_movie + geom_bar(stat = "identity", width = 0.2, , position = "identity") + guides(fill = FALSE) + xlab("Decades") + ylab("Number of movies") + ggtitle("Frequency of movies by decades") + theme(axis.text.x = element_text(angle = 45, hjust = 1));
A Study on the popularity of movies
Note: The dataset is not in a structure where we can compare the distribution of the ratings for various genres. Hence, the data frame is first melted using reshape2 package
require(reshape2);## Loading required package: reshape2movie_data_sub <- movie_data[, c(1,2,4,5,17,18,19,20,21,22)];
movie_data_sub <- melt(movie_data_sub, c(1,2,3,4));
names(movie_data_sub)[5] <- c("Genre");
movie_data_sub <- subset(movie_data_sub, value == 1);
g_genre <- ggplot(data = movie_data_sub, aes(x = Genre, y = rating, fill = Genre));
g_genre + geom_boxplot() + xlab("Genre") + ylab("Rating") + ggtitle("Distribution of ratings for various genre");
Before inferring popularity of each genre, we will also have to see the frequency of movies in each genre.
Evolution of animation movies
Summary of ratings for animation movie
summary(movie_anim$rating);## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 6.000 6.700 6.584 7.300 9.800Probability
Probability(animation movie) = total number of animation movie/total movie in sample space = 0.0628
Probability(movie rating > 6 and movie being animation) = 0.0454
Probability of a movie getting rating greater than 6 provided movie is animation movie =
0.7228 = 72.2764 %