-
Notifications
You must be signed in to change notification settings - Fork 31
/
Movie-Recommendation-System-using-R_Project.R
190 lines (184 loc) · 8.77 KB
/
Movie-Recommendation-System-using-R_Project.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
# Build a recommendation engine that recommends movies to users.
# Item Based Collaborative Filter recommendation system
library(recommenderlab)
library(ggplot2)
library(data.table)
library(reshape2)
# Retrieve and display data
setwd("/Users/arpitabhattacharya/Desktop/Warwick /Internship/Github uploads/Movie recommendation - R/IMDB-Dataset")
movie_data <- read.csv("movies.csv",stringsAsFactors=FALSE)
rating_data <- read.csv("ratings.csv")
str(movie_data)
# Overview the summary
summary(movie_data)
head(movie_data)
summary(rating_data)
head(rating_data)
# Data pre-processing
# Creating a one-hot encoding to create a matrix that comprises of corresponding genres for each of the films.
movie_genre <- as.data.frame(movie_data$genres, stringsAsFactors=FALSE)
library(data.table)
movie_genre2 <- as.data.frame(tstrsplit(movie_genre[,1], '[|]',
type.convert=TRUE),
stringsAsFactors=FALSE)
colnames(movie_genre2) <- c(1:10)
list_genre <- c("Action", "Adventure", "Animation", "Children",
"Comedy", "Crime","Documentary", "Drama", "Fantasy",
"Film-Noir", "Horror", "Musical", "Mystery","Romance",
"Sci-Fi", "Thriller", "War", "Western")
genre_mat1 <- matrix(0,10330,18)
genre_mat1[1,] <- list_genre
colnames(genre_mat1) <- list_genre
for (index in 1:nrow(movie_genre2)) {
for (col in 1:ncol(movie_genre2)) {
gen_col = which(genre_mat1[1,] == movie_genre2[index,col])
genre_mat1[index+1,gen_col] <- 1
}
}
genre_mat2 <- as.data.frame(genre_mat1[-1,], stringsAsFactors=FALSE) #remove first row, which was the genre list
for (col in 1:ncol(genre_mat2)) {
genre_mat2[,col] <- as.integer(genre_mat2[,col]) #convert from characters to integers
}
str(genre_mat2)
# Creating a ‘search matrix’ - searching films by specifying the genre
SearchMatrix <- cbind(movie_data[,1:2], genre_mat2[])
head(SearchMatrix)
ratingMatrix <- dcast(rating_data, userId~movieId, value.var = "rating", na.rm=FALSE)
ratingMatrix <- as.matrix(ratingMatrix[,-1]) #remove userIds
#Convert rating matrix into a recommenderlab sparse matrix
ratingMatrix <- as(ratingMatrix, "realRatingMatrix")
ratingMatrix
# Overview some important parameters for building recommendation systems for movies
recommendation_model <- recommenderRegistry$get_entries(dataType = "realRatingMatrix")
names(recommendation_model)
lapply(recommendation_model, "[[", "description")
# Implementing a single model in the R project – Item Based Collaborative Filtering
recommendation_model$IBCF_realRatingMatrix$parameters
# Collaborative Filtering involves suggesting movies to the users that are based on collecting preferences from many other users.
# With the help of recommenderlab, we can compute similarities between users
similarity_mat <- similarity(ratingMatrix[1:4, ],
method = "cosine",
which = "users")
as.matrix(similarity_mat)
image(as.matrix(similarity_mat), main = "User's Similarities")
# Portray the similarity that is shared between the films
movie_similarity <- similarity(ratingMatrix[, 1:4], method =
"cosine", which = "items")
as.matrix(movie_similarity)
image(as.matrix(movie_similarity), main = "Movies similarity")
rating_values <- as.vector(ratingMatrix@data)
unique(rating_values) # extracting unique ratings
Table_of_Ratings <- table(rating_values) # creating a count of movie ratings
Table_of_Ratings
# Most viewed movies visualization
library(ggplot2)
movie_views <- colCounts(ratingMatrix) # count views for each movie
table_views <- data.frame(movie = names(movie_views),
views = movie_views) # create dataframe of views
table_views <- table_views[order(table_views$views,
decreasing = TRUE), ] # sort by number of views
table_views$title <- NA
for (index in 1:10325){
table_views[index,3] <- as.character(subset(movie_data,
movie_data$movieId == table_views[index,1])$title)
}
table_views[1:6,]
# Visualize a bar plot for the total number of views of the top films
ggplot(table_views[1:6, ], aes(x = title, y = views)) +
geom_bar(stat="identity", fill = 'steelblue') +
geom_text(aes(label=views), vjust=-0.3, size=3.5) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
ggtitle("Total Views of the Top Films")
# Heatmap of Movie Ratings
# Visualize a heatmap of the movie ratings
image(ratingMatrix[1:20, 1:25], axes = FALSE, main = "Heatmap of the first 25 rows and 25 columns")
# Data Preparation
movie_ratings <- ratingMatrix[rowCounts(ratingMatrix) > 50,
colCounts(ratingMatrix) > 50]
movie_ratings
# describing matrix of relevant users
minimum_movies<- quantile(rowCounts(movie_ratings), 0.98)
minimum_users <- quantile(colCounts(movie_ratings), 0.98)
image(movie_ratings[rowCounts(movie_ratings) > minimum_movies,
colCounts(movie_ratings) > minimum_users],
main = "Heatmap of the top users and movies")
# Visualizing the distribution of the average ratings per user
average_ratings <- rowMeans(movie_ratings)
qplot(average_ratings, fill=I("steelblue"), col=I("red")) +
ggtitle("Distribution of the average rating per user")
# Data Normalization
normalized_ratings <- normalize(movie_ratings)
sum(rowMeans(normalized_ratings) > 0.00001)
image(normalized_ratings[rowCounts(normalized_ratings) > minimum_movies,
colCounts(normalized_ratings) > minimum_users],
main = "Normalized Ratings of the Top Users")
# Data Binarization
binary_minimum_movies <- quantile(rowCounts(movie_ratings), 0.95)
binary_minimum_users <- quantile(colCounts(movie_ratings), 0.95)
#movies_watched <- binarize(movie_ratings, minRating = 1)
good_rated_films <- binarize(movie_ratings, minRating = 3)
image(good_rated_films[rowCounts(movie_ratings) > binary_minimum_movies,
colCounts(movie_ratings) > binary_minimum_users],
main = "Heatmap of the top users and movies")
# Collaborative Filtering System
# Splitting the dataset into 80% training set and 20% test set
sampled_data<- sample(x = c(TRUE, FALSE),
size = nrow(movie_ratings),
replace = TRUE,
prob = c(0.8, 0.2))
training_data <- movie_ratings[sampled_data, ]
testing_data <- movie_ratings[!sampled_data, ]
# Building the Recommendation System
recommendation_system <- recommenderRegistry$get_entries(dataType ="realRatingMatrix")
recommendation_system$IBCF_realRatingMatrix$parameters
recommen_model <- Recommender(data = training_data,
method = "IBCF",
parameter = list(k = 30))
recommen_model
class(recommen_model)
# Exploring the data science recommendation system model
model_info <- getModel(recommen_model)
class(model_info$sim)
dim(model_info$sim)
top_items <- 20
image(model_info$sim[1:top_items, 1:top_items],
main = "Heatmap of the first rows and columns")
# Visualize sum of rows and columns with the similarity of the objects above 0
sum_rows <- rowSums(model_info$sim > 0)
table(sum_rows)
sum_cols <- colSums(model_info$sim > 0)
qplot(sum_cols, fill=I("steelblue"), col=I("red"))+ ggtitle("Distribution of the column count")
# the number of items to recommend to each user
top_recommendations <- 10
predicted_recommendations <- predict(object = recommen_model,
newdata = testing_data,
n = top_recommendations)
predicted_recommendations
# recommendation for the first user
user1 <- predicted_recommendations@items[[1]]
movies_user1 <- predicted_recommendations@itemLabels[user1]
movies_user2 <- movies_user1
for (index in 1:10){
movies_user2[index] <- as.character(subset(movie_data,
movie_data$movieId == movies_user1[index])$title)
}
movies_user2
# matrix with the recommendations for each user
recommendation_matrix <- sapply(predicted_recommendations@items,
function(x){ as.integer(colnames(movie_ratings)[x]) })
#dim(recc_matrix)
recommendation_matrix[,1:4]
# Distribution of the Number of Items for IBCF
number_of_items <- factor(table(recommendation_matrix))
chart_title <- "Distribution of the Number of Items for IBCF"
qplot(number_of_items, fill=I("steelblue"), col=I("red")) + ggtitle(chart_title)
number_of_items_sorted <- sort(number_of_items, decreasing = TRUE)
number_of_items_top <- head(number_of_items_sorted, n = 4)
table_top <- data.frame(as.integer(names(number_of_items_top)),
number_of_items_top)
for(i in 1:4) {
table_top[i,1] <- as.character(subset(movie_data,
movie_data$movieId == table_top[i,1])$title)
}
colnames(table_top) <- c("Movie Title", "No. of Items")
head(table_top)