Product Recommendation systems

# Extract transform and analyze
# Load recommenderlab library
library("recommenderlab")
setwd("C:/Users/Tanishka/Desktop/R Datasets")
# Read dataset
rating<- read.csv("product_ratings_data.csv")
#Create rating matrixfrom data
ratings_matrix<- as(rating,"realRatingMatrix")
# display transformed data
image(ratings_matrix[1:6,1:10])

# Extract a sample from ratings matrix
sample_ratings <- sample(ratings_matrix,1000)
# Compute the mean product ratings for the first User
rowMeans(sample_ratings[1])

  u10048 
2.611765 

# Compute distribution of item ratings
hist(getRatings(sample_ratings),breaks=100,xlab="Product Ratings", main="Histogram of Product Ratings")

# Get distribution of normalized item ratings
hist(getRatings(normalize(sample_ratings)),breaks=100, xlab="Normalized Product Ratings", main= "Histogram of Normalized Product Ratings")

# Number of items rated per user
hist(rowCounts(sample_ratings), breaks = 50, xlab = "Number of Products", main = "Histogram of Product Count Distribution")

# Model preparation and prediction
# Create "User Based collaborative filtering" Model
ubcf_recommender <- Recommender(ratings_matrix[1:10], "UBCF")
# Predict list of product which can be recommended to potential user
recommendations<- predict(ubcf_recommender,
                          ratings_matrix[1010:1011], n=5)
# Display recommendation in form of the list
as(recommendations,"list")

$u14521
[1] "prod_85" "prod_72" "prod_94" "prod_80" "prod_84"

$u14530
[1] "prod_83" "prod_72" "prod_81" "prod_85" "prod_73"

# Model evaluation
# Evaluation scheme
eval_scheme <- evaluationScheme(ratings_matrix[1:500], method="split", train=0.9, given=15)
# Display the evaluation scheme
eval_scheme

Evaluation scheme with 15 items given
Method: ‘split’ with 1 run(s).
Training set proportion: 0.900
Good ratings: NA
Data set: 500 x 100 rating matrix of class ‘realRatingMatrix’ with 35514 ratings.

# Training model
training_recommender <- Recommender(getData(eval_scheme, "train"), "UBCF")
                                    
# Predictions on the test dataset
test_rating <- predict(training_recommender, getData(eval_scheme,"known"), type="ratings")
# Error
error <- calcPredictionAccuracy(test_rating,getData(eval_scheme, "unknown"))
error

     RMSE       MSE       MAE 
1.1618838 1.3499739 0.9272752 

#To Evalate the performance of UBCF algorithm, we use IBCF as comparision
# Training model using IBCF 
training_recommender_2 <- Recommender(getData(eval_scheme, "train"), "IBCF")
# Prediction on test dataset
test_rating_2 <- predict(training_recommender_2, getData(eval_scheme,"known"), type="ratings")
error_compare <- rbind(calcPredictionAccuracy(test_rating, getData(eval_scheme,"unknown")), calcPredictionAccuracy(test_rating_2, getData(eval_scheme, "unknown")))
rownames(error_compare)<- c("User Based CF", "Item Based CF")

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).