Final Project
Joshua Registe
7/12/2020
library(tidyverse)
library(readr)
library(sqldf)
library(dplyr)
library(tidyr)
library(tinytex)
library(recommenderlab)
library(kableExtra)
library(gridExtra)Final Project Goal
The goal for the final project is for you to build out a recommender system using a large dataset (ex: 1M+ ratings or 10k+ users, 10k+ items. There are three deliverables, with separate dates:
[1] Planning Document Find an interesting dataset and describe the system you plan to build out. If you would like to use one of the datasets you have already worked with, you should add a unique element or incorporate additional data. (i.e. explicit features you scrape from another source, like image analysis on movie posters). The overall goal, however, will be to produce quality recommendations by extracting insights from a large dataset. You may do so using Spark, or another distributed computing method, OR by effectively applying one of the more advanced mathematical techniques we have covered. There is no preference for one over the other, as long as the recommender works!
[2] Implementation. In this final project deliverable, you’ll build out the system that you describe in the planning document.
Final Project Dataset
The dataset that is used for this final project is the the books dataset by zygmuntz. This dataset contains 6 million ratings for ten thousand of the most popular books. Information included in this dataset include books marked to be read by the users, metadata for books (author, year, etc.) and tags/shelves/genres. The dataset for this project complies with the requirement for having enough users and items to develop a robust recommender system. The link to the dataset can be found on href = https://github.com/zygmuntz/goodbooks-10k> github here.
Data Exploration
To start off, data exploration was done on the books dataset. A few histograms are presented below which suggest a few things. Book rating distributions are skewed left with most individuals giving high ratings of 4 and 5. Most books do not receive ranks of 1. Additionally, The scrollable table below provides a list of the top 1000 most rated books with The Hunger Games and Harry Potter leading the pack. The subsequent bar plot shows the top 15 rated books.
data_package <- data(package = "recommenderlab")
update_geom_defaults('bar',list(color = 'blue', fill = 'skyblue', alpha = .5))
update_geom_defaults('col',list(color = 'blue', fill = 'skyblue', alpha = .5))
BookData<-read_csv(url("https://raw.githubusercontent.com/zygmuntz/goodbooks-10k/master/ratings.csv"))
BookDataMeta<-read_csv(url("https://raw.githubusercontent.com/zygmuntz/goodbooks-10k/master/books.csv"))
recommender_models <- recommenderRegistry$get_entries(dataType =
"realRatingMatrix")
plottheme<-
theme(panel.background = element_blank(),
panel.grid = element_blank())
BookData %>%
ggplot()+
geom_histogram(mapping = aes(x = rating), alpha = 0.5, color = "blue", fill = 'skyblue')+
plottheme
BookDataMatrix<-BookData %>%
pivot_wider(names_from = book_id,values_from = rating)
rownames(BookDataMatrix)<-BookDataMatrix$user_id## Warning: Setting row names on a tibble is deprecated.BookDataMatrix<- BookDataMatrix %>% select(-'user_id')
?arrange
left_join(BookData,BookDataMeta[c('book_id','authors','title','language_code')]) %>%
group_by(title)%>%
tally() %>%
top_n(1000) %>% rename(Number_of_Ratings = n) %>%
arrange(desc(Number_of_Ratings)) %>%
kable() %>%
kable_styling(
bootstrap_options = c("hover", "condensed", "responsive"),
full_width = F) %>%
scroll_box(height = "300px")| title | Number_of_Ratings |
|---|---|
| The Hunger Games (The Hunger Games, #1) | 22806 |
| Harry Potter and the Sorcerer’s Stone (Harry Potter, #1) | 21850 |
| To Kill a Mockingbird | 19088 |
| Twilight (Twilight, #1) | 16931 |
| The Great Gatsby | 16604 |
| Catching Fire (The Hunger Games, #2) | 16549 |
| Mockingjay (The Hunger Games, #3) | 15953 |
| Harry Potter and the Prisoner of Azkaban (Harry Potter, #3) | 15855 |
| Harry Potter and the Chamber of Secrets (Harry Potter, #2) | 15657 |
| The Hobbit | 15558 |
| Harry Potter and the Goblet of Fire (Harry Potter, #4) | 15523 |
| Harry Potter and the Deathly Hallows (Harry Potter, #7) | 15304 |
| Harry Potter and the Order of the Phoenix (Harry Potter, #5) | 15258 |
| Harry Potter and the Half-Blood Prince (Harry Potter, #6) | 15081 |
| 1984 | 14693 |
| The Catcher in the Rye | 14472 |
| The Girl with the Dragon Tattoo (Millennium, #1) | 14382 |
| Animal Farm | 14328 |
| Lord of the Flies | 13556 |
| Angels & Demons (Robert Langdon, #1) | 13451 |
| Pride and Prejudice | 13445 |
| The Lion, the Witch, and the Wardrobe (Chronicles of Narnia, #1) | 13089 |
| The Da Vinci Code (Robert Langdon, #2) | 13072 |
| The Help | 12727 |
| The Kite Runner | 12698 |
| The Fellowship of the Ring (The Lord of the Rings, #1) | 12530 |
| Gone Girl | 12105 |
| The Diary of a Young Girl | 12101 |
| Of Mice and Men | 11921 |
| Divergent (Divergent, #1) | 11780 |
| The Lovely Bones | 11677 |
| Romeo and Juliet | 11578 |
| Memoirs of a Geisha | 11304 |
| The Fault in Our Stars | 11264 |
| The Giver (The Giver, #1) | 10949 |
| A Game of Thrones (A Song of Ice and Fire, #1) | 10692 |
| Little Women (Little Women, #1) | 10649 |
| The Book Thief | 10394 |
| Water for Elephants | 10361 |
| Fahrenheit 451 | 10312 |
| Jane Eyre | 10308 |
| Life of Pi | 10175 |
| The Time Traveler’s Wife | 9977 |
| The Hitchhiker’s Guide to the Galaxy (Hitchhiker’s Guide to the Galaxy, #1) | 9960 |
| New Moon (Twilight, #2) | 9712 |
| Eclipse (Twilight, #3) | 9620 |
| Brave New World | 9612 |
| Wuthering Heights | 9584 |
| Breaking Dawn (Twilight, #4) | 9433 |
| Charlotte’s Web | 9391 |
| The Adventures of Huckleberry Finn | 9323 |
| The Girl on the Train | 9090 |
| The Curious Incident of the Dog in the Night-Time | 9035 |
| The Alchemist | 8916 |
| Ender’s Game (Ender’s Saga, #1) | 8849 |
| The Secret Life of Bees | 8383 |
| Where the Sidewalk Ends | 8297 |
| Insurgent (Divergent, #2) | 8263 |
| The Golden Compass (His Dark Materials, #1) | 8192 |
| Slaughterhouse-Five | 8179 |
| A Wrinkle in Time (A Wrinkle in Time Quintet, #1) | 8109 |
| Eat, Pray, Love | 7885 |
| Frankenstein | 7727 |
| Fifty Shades of Grey (Fifty Shades, #1) | 7724 |
| Gone with the Wind | 7714 |
| The Scarlet Letter | 7667 |
| A Thousand Splendid Suns | 7662 |
| The Secret Garden | 7626 |
| The Lightning Thief (Percy Jackson and the Olympians, #1) | 7606 |
| The Girl Who Played with Fire (Millennium, #2) | 7563 |
| The Handmaid’s Tale | 7543 |
| The Grapes of Wrath | 7458 |
| The Adventures of Tom Sawyer | 7214 |
| My Sister’s Keeper | 7192 |
| Sense and Sensibility | 7110 |
| Eragon (The Inheritance Cycle, #1) | 7040 |
| The Giving Tree | 7002 |
| Catch-22 | 6944 |
| Hamlet | 6899 |
| The Shining (The Shining #1) | 6861 |
| A Clash of Kings (A Song of Ice and Fire, #2) | 6854 |
| The Little Prince | 6848 |
| The Road | 6779 |
| The Notebook (The Notebook, #1) | 6717 |
| The Girl Who Kicked the Hornet’s Nest (Millennium, #3) | 6702 |
| Dracula | 6615 |
| Jurassic Park (Jurassic Park, #1) | 6601 |
| Wicked: The Life and Times of the Wicked Witch of the West (The Wicked Years, #1) | 6598 |
| A Tale of Two Cities | 6592 |
| Anne of Green Gables (Anne of Green Gables, #1) | 6536 |
| City of Bones (The Mortal Instruments, #1) | 6504 |
| The Two Towers (The Lord of the Rings, #2) | 6478 |
| Night (The Night Trilogy #1) | 6466 |
| Macbeth | 6421 |
| One Flew Over the Cuckoo’s Nest | 6414 |
| The Picture of Dorian Gray | 6406 |
| Where the Wild Things Are | 6401 |
| The Poisonwood Bible | 6343 |
| The Return of the King (The Lord of the Rings, #3) | 6331 |
| The Host (The Host, #1) | 6313 |
| Great Expectations | 6305 |
| The Odyssey | 6301 |
| Allegiant (Divergent, #3) | 6300 |
| The Old Man and the Sea | 6273 |
| A Storm of Swords (A Song of Ice and Fire, #3) | 6237 |
| Bridget Jones’s Diary (Bridget Jones, #1) | 6229 |
| The Joy Luck Club | 6212 |
| The Outsiders | 6190 |
| The Firm (Penguin Readers, Level 5) | 6135 |
| The Princess Bride | 6102 |
| All the Light We Cannot See | 6082 |
| Holes (Holes, #1) | 6039 |
| Charlie and the Chocolate Factory (Charlie Bucket, #1) | 6034 |
| The Perks of Being a Wallflower | 5990 |
| The Stand | 5973 |
| Me Before You (Me Before You, #1) | 5897 |
| Dune (Dune Chronicles #1) | 5864 |
| The Glass Castle | 5847 |
| A Time to Kill | 5844 |
| Interview with the Vampire (The Vampire Chronicles, #1) | 5764 |
| A Feast for Crows (A Song of Ice and Fire, #4) | 5705 |
| American Gods (American Gods, #1) | 5681 |
| The Pillars of the Earth (The Kingsbridge Series, #1) | 5672 |
| Middlesex | 5615 |
| Emma | 5602 |
| Room | 5554 |
| The Color Purple | 5531 |
| The Five People You Meet in Heaven | 5495 |
| One Hundred Years of Solitude | 5492 |
| The Count of Monte Cristo | 5489 |
| Tuesdays with Morrie | 5467 |
| The Martian | 5408 |
| The Stranger | 5365 |
| The Red Tent | 5358 |
| Bossypants | 5346 |
| Divine Secrets of the Ya-Ya Sisterhood | 5326 |
| The Lord of the Rings (The Lord of the Rings, #1-3) | 5316 |
| The Chronicles of Narnia (Chronicles of Narnia, #1-7) | 5306 |
| Angela’s Ashes (Frank McCourt, #1) | 5302 |
| Outlander (Outlander, #1) | 5297 |
| The Goldfinch | 5275 |
| Lolita | 5274 |
| The Memory Keeper’s Daughter | 5257 |
| Green Eggs and Ham | 5249 |
| Me Talk Pretty One Day | 5199 |
| The Bell Jar | 5178 |
| Girl with a Pearl Earring | 5171 |
| The Night Circus | 5154 |
| A Dance with Dragons (A Song of Ice and Fire, #5) | 5086 |
| A Clockwork Orange | 5076 |
| Anna Karenina | 5073 |
| Atonement | 5052 |
| The Maze Runner (Maze Runner, #1) | 5014 |
| A Christmas Carol | 5006 |
| Into the Wild | 4921 |
| The Guernsey Literary and Potato Peel Pie Society | 4904 |
| A Midsummer Night’s Dream | 4898 |
| Miss Peregrine’s Home for Peculiar Children (Miss Peregrine’s Peculiar Children, #1) | 4868 |
| It | 4853 |
| Flowers for Algernon | 4810 |
| Matilda | 4810 |
| The Other Boleyn Girl (The Plantagenet and Tudor Novels, #9) | 4759 |
| Watership Down (Watership Down, #1) | 4753 |
| Les Misérables | 4750 |
| The Devil Wears Prada (The Devil Wears Prada, #1) | 4723 |
| Alice’s Adventures in Wonderland & Through the Looking-Glass | 4722 |
| Looking for Alaska | 4682 |
| Crime and Punishment | 4679 |
| Freakonomics: A Rogue Economist Explores the Hidden Side of Everything (Freakonomics, #1) | 4658 |
| Siddhartha | 4610 |
| The Devil in the White City: Murder, Magic, and Madness at the Fair That Changed America | 4606 |
| Unbroken: A World War II Story of Survival, Resilience, and Redemption | 4577 |
| East of Eden | 4576 |
| In Cold Blood | 4467 |
| The Metamorphosis | 4463 |
| A Tree Grows in Brooklyn | 4460 |
| Love in the Time of Cholera | 4459 |
| Fifty Shades Darker (Fifty Shades, #2) | 4452 |
| City of Glass (The Mortal Instruments, #3) | 4451 |
| ’Salem’s Lot | 4433 |
| City of Ashes (The Mortal Instruments, #2) | 4415 |
| Dead Until Dark (Sookie Stackhouse, #1) | 4409 |
| Deception Point | 4405 |
| Heart of Darkness | 4377 |
| Bridge to Terabithia | 4295 |
| Persuasion | 4274 |
| The Client | 4260 |
| Paper Towns | 4247 |
| Ready Player One | 4239 |
| The Gunslinger (The Dark Tower, #1) | 4229 |
| Atlas Shrugged | 4227 |
| Rebecca | 4220 |
| The Lost Symbol (Robert Langdon, #3) | 4213 |
| Misery | 4199 |
| Fifty Shades Freed (Fifty Shades, #3) | 4185 |
| The Sisterhood of the Traveling Pants (Sisterhood, #1) | 4180 |
| The Sun Also Rises | 4161 |
| Carrie | 4118 |
| The Voyage of the Dawn Treader (Chronicles of Narnia, #3) | 4080 |
| The Pelican Brief | 4067 |
| The Sea of Monsters (Percy Jackson and the Olympians, #2) | 4056 |
| Digital Fortress | 4041 |
| Moby-Dick or, The Whale | 4034 |
| The Battle of the Labyrinth (Percy Jackson and the Olympians, #4) | 4021 |
| James and the Giant Peach | 4017 |
| The Ocean at the End of the Lane | 4015 |
| And Then There Were None | 4011 |
| The Husband’s Secret | 4003 |
| Where the Red Fern Grows | 4000 |
| Wild: From Lost to Found on the Pacific Crest Trail | 3998 |
| Sarah’s Key | 3995 |
| Treasure Island | 3959 |
| Dark Places | 3950 |
| The Name of the Wind (The Kingkiller Chronicle, #1) | 3948 |
| Fight Club | 3917 |
| A Light in the Attic | 3916 |
| The Art of Racing in the Rain | 3889 |
| The Last Olympian (Percy Jackson and the Olympians, #5) | 3881 |
| The Cat in the Hat | 3871 |
| A Prayer for Owen Meany | 3868 |
| Artemis Fowl (Artemis Fowl, #1) | 3851 |
| She’s Come Undone | 3850 |
| Beloved | 3842 |
| Never Let Me Go | 3837 |
| Watchmen | 3825 |
| Confessions of a Shopaholic (Shopaholic, #1) | 3792 |
| The Immortal Life of Henrietta Lacks | 3777 |
| A Walk to Remember | 3760 |
| Eleanor & Park | 3756 |
| Pet Sematary | 3748 |
| 11/22/63 | 3737 |
| Running with Scissors | 3724 |
| The Thorn Birds | 3721 |
| World War Z: An Oral History of the Zombie War | 3720 |
| The Titan’s Curse (Percy Jackson and the Olympians, #3) | 3717 |
| The Iliad | 3715 |
| The Tipping Point: How Little Things Can Make a Big Difference | 3709 |
| Big Little Lies | 3705 |
| The Nightingale | 3666 |
| The Time Machine | 3659 |
| The Fountainhead | 3656 |
| Number the Stars | 3646 |
| The Call of the Wild | 3625 |
| Neverwhere | 3612 |
| Inferno (Robert Langdon, #4) | 3608 |
| Uglies (Uglies, #1) | 3600 |
| On the Road | 3596 |
| Cutting for Stone | 3575 |
| The Crucible | 3560 |
| The Shack | 3559 |
| Sharp Objects | 3549 |
| Matched (Matched, #1) | 3538 |
| Cat’s Cradle | 3532 |
| Good Omens: The Nice and Accurate Prophecies of Agnes Nutter, Witch | 3532 |
| The Shadow of the Wind (The Cemetery of Forgotten Books, #1) | 3531 |
| Extremely Loud and Incredibly Close | 3519 |
| If I Stay (If I Stay, #1) | 3512 |
| Goodnight Moon | 3507 |
| The Silence of the Lambs (Hannibal Lecter, #2) | 3480 |
| Into Thin Air: A Personal Account of the Mount Everest Disaster | 3479 |
| The Subtle Knife (His Dark Materials, #2) | 3479 |
| The Magician’s Nephew (Chronicles of Narnia, #6) | 3461 |
| White Oleander | 3449 |
| Outliers: The Story of Success | 3428 |
| Oliver Twist | 3421 |
| Othello | 3414 |
| The Cuckoo’s Calling (Cormoran Strike, #1) | 3413 |
| Marley and Me: Life and Love With the World’s Worst Dog | 3412 |
| Island of the Blue Dolphins (Island of the Blue Dolphins, #1) | 3409 |
| Where’d You Go, Bernadette | 3403 |
| The Graveyard Book | 3401 |
| Orphan Train | 3378 |
| Blink: The Power of Thinking Without Thinking | 3371 |
| Clockwork Angel (The Infernal Devices, #1) | 3366 |
| One for the Money (Stephanie Plum, #1) | 3365 |
| The Light Between Oceans | 3363 |
| Prince Caspian (Chronicles of Narnia, #2) | 3353 |
| Snow Flower and the Secret Fan | 3346 |
| The Nanny Diaries (Nanny, #1) | 3331 |
| Oh, The Places You’ll Go! | 3321 |
| Like Water for Chocolate | 3314 |
| I Know This Much Is True | 3312 |
| Alice in Wonderland | 3298 |
| Three Cups of Tea: One Man’s Mission to Promote Peace … One School at a Time | 3284 |
| The Wonderful Wizard of Oz (Oz, #1) | 3275 |
| All Quiet on the Western Front | 3273 |
| The Ultimate Hitchhiker’s Guide to the Galaxy | 3270 |
| Stardust | 3250 |
| The Rosie Project (Don Tillman, #1) | 3244 |
| The World According to Garp | 3233 |
| How the Grinch Stole Christmas! | 3231 |
| Harry Potter and the Cursed Child - Parts One and Two (Harry Potter, #8) | 3230 |
| For Whom the Bell Tolls | 3222 |
| A Farewell to Arms | 3204 |
| Thirteen Reasons Why | 3186 |
| Ella Enchanted | 3177 |
| Cold Mountain | 3174 |
| The Runaway Jury | 3168 |
| Winnie-the-Pooh (Winnie-the-Pooh, #1) | 3161 |
| Bel Canto | 3144 |
| City of Fallen Angels (The Mortal Instruments, #4) | 3140 |
| The Good Earth (House of Earth, #1) | 3137 |
| Coraline | 3132 |
| The Lost Hero (The Heroes of Olympus, #1) | 3128 |
| Vampire Academy (Vampire Academy, #1) | 3125 |
| The Unbearable Lightness of Being | 3120 |
| Fried Green Tomatoes at the Whistle Stop Cafe | 3113 |
| The Bad Beginning (A Series of Unfortunate Events, #1) | 3092 |
| The Bourne Identity (Jason Bourne, #1) | 3091 |
| The Amber Spyglass (His Dark Materials, #3) | 3075 |
| Beautiful Creatures (Caster Chronicles, #1) | 3067 |
| I Know Why the Caged Bird Sings | 3067 |
| The Three Musketeers | 3062 |
| The Very Hungry Caterpillar Board Book | 3057 |
| Midnight in the Garden of Good and Evil | 3037 |
| The Scorch Trials (Maze Runner, #2) | 3031 |
| A Walk in the Woods | 3029 |
| Foundation (Foundation #1) | 3026 |
| The Wise Man’s Fear (The Kingkiller Chronicle, #2) | 3026 |
| The Andromeda Strain | 3004 |
| A Confederacy of Dunces | 2999 |
| Along Came a Spider (Alex Cross, #1) | 2985 |
| Eldest (The Inheritance Cycle, #2) | 2963 |
| Little Bee | 2962 |
| The Thirteenth Tale | 2959 |
| The Clan of the Cave Bear (Earth’s Children, #1) | 2931 |
| The Strange Case of Dr. Jekyll and Mr. Hyde | 2926 |
| And the Mountains Echoed | 2925 |
| The Eye of the World (Wheel of Time, #1) | 2924 |
| Inkheart (Inkworld, #1) | 2919 |
| The Name of the Rose | 2910 |
| The Selection (The Selection, #1) | 2903 |
| The Tell-Tale Heart and Other Writings | 2897 |
| The BFG | 2889 |
| Dress Your Family in Corduroy and Denim | 2885 |
| The Velveteen Rabbit | 2882 |
| Things Fall Apart (The African Trilogy, #1) | 2878 |
| Something Borrowed (Darcy & Rachel, #1) | 2877 |
| Do Androids Dream of Electric Sheep? | 2864 |
| The Casual Vacancy | 2863 |
| Speak | 2854 |
| Gulliver’s Travels | 2848 |
| The Lorax | 2847 |
| Still Alice | 2836 |
| A Child Called “It” (Dave Pelzer #1) | 2834 |
| The Importance of Being Earnest | 2831 |
| Their Eyes Were Watching God | 2825 |
| The Historian | 2780 |
| The Godfather | 2772 |
| The Horse and His Boy (Chronicles of Narnia, #5) | 2769 |
| Dear John | 2746 |
| City of Lost Souls (The Mortal Instruments, #5) | 2744 |
| Naked | 2744 |
| The Green Mile | 2744 |
| The Invention of Wings | 2735 |
| Cinder (The Lunar Chronicles, #1) | 2734 |
| Mansfield Park | 2725 |
| The Canterbury Tales | 2723 |
| The Witches | 2713 |
| Fear and Loathing in Las Vegas | 2712 |
| A Discovery of Witches (All Souls Trilogy, #1) | 2705 |
| Breakfast of Champions | 2704 |
| The Namesake | 2700 |
| Much Ado About Nothing | 2696 |
| The Boy in the Striped Pajamas | 2694 |
| The Hunt for Red October (Jack Ryan Universe, #4) | 2689 |
| Nineteen Minutes | 2654 |
| Robinson Crusoe | 2653 |
| Northanger Abbey | 2651 |
| Wonder | 2648 |
| Kiss the Girls (Alex Cross, #2) | 2644 |
| Beowulf | 2643 |
| The Prince of Tides | 2643 |
| Black Beauty | 2638 |
| The Paris Wife | 2634 |
| Hotel on the Corner of Bitter and Sweet | 2631 |
| Stranger in a Strange Land | 2629 |
| The Final Empire (Mistborn, #1) | 2626 |
| The No. 1 Ladies’ Detective Agency (No. 1 Ladies’ Detective Agency, #1) | 2622 |
| Speaker for the Dead (Ender’s Saga, #2) | 2618 |
| The Complete Stories and Poems | 2618 |
| The Pact | 2616 |
| Under the Dome | 2609 |
| Is Everyone Hanging Out Without Me? (And Other Concerns) | 2606 |
| Hush, Hush (Hush, Hush, #1) | 2601 |
| A Separate Peace | 2599 |
| Where the Heart Is | 2592 |
| Graceling (Graceling Realm, #1) | 2588 |
| The Phantom Tollbooth | 2587 |
| Cujo | 2583 |
| Marked (House of Night, #1) | 2583 |
| The Silver Chair (Chronicles of Narnia, #4) | 2558 |
| Station Eleven | 2556 |
| The Brief Wondrous Life of Oscar Wao | 2553 |
| Delirium (Delirium, #1) | 2549 |
| I, Robot (Robot #0.1) | 2549 |
| Under the Tuscan Sun | 2545 |
| Fallen (Fallen, #1) | 2541 |
| Snow Falling on Cedars | 2533 |
| The Secret History | 2522 |
| Tess of the D’Urbervilles | 2516 |
| The Amazing Adventures of Kavalier & Clay | 2513 |
| A Million Little Pieces | 2511 |
| What Alice Forgot | 2507 |
| We Were Liars | 2503 |
| The Screwtape Letters | 2497 |
| The Last Lecture | 2488 |
| Beautiful Disaster (Beautiful, #1) | 2487 |
| Living Dead in Dallas (Sookie Stackhouse, #2) | 2485 |
| Little House on the Prairie (Little House, #2) | 2483 |
| Red Dragon (Hannibal Lecter, #1) | 2483 |
| A Little Princess | 2480 |
| Dragonfly in Amber (Outlander, #2) | 2472 |
| Are You There God? It’s Me, Margaret | 2471 |
| The Last Song | 2471 |
| Needful Things | 2470 |
| A Heartbreaking Work of Staggering Genius | 2463 |
| The Color of Magic (Discworld, #1; Rincewind #1) | 2463 |
| A Streetcar Named Desire | 2457 |
| Brisingr (The Inheritance Cycle, #3) | 2455 |
| The Cider House Rules | 2448 |
| The Death Cure (Maze Runner, #3) | 2446 |
| A Man Called Ove | 2441 |
| The Son of Neptune (The Heroes of Olympus, #2) | 2437 |
| Storm Front (The Dresden Files, #1) | 2431 |
| The God of Small Things | 2427 |
| Timeline | 2426 |
| The Last Battle (Chronicles of Narnia, #7) | 2412 |
| Shiver (The Wolves of Mercy Falls, #1) | 2411 |
| Fangirl | 2409 |
| The War of the Worlds | 2404 |
| The Tales of Beedle the Bard | 2403 |
| Death of a Salesman | 2400 |
| War and Peace | 2398 |
| Hatchet (Brian’s Saga, #1) | 2392 |
| Club Dead (Sookie Stackhouse, #3) | 2387 |
| Clockwork Prince (The Infernal Devices, #2) | 2380 |
| The Mists of Avalon (Avalon, #1) | 2380 |
| Yes Please | 2378 |
| Dead to the World (Sookie Stackhouse, #4) | 2375 |
| Tuck Everlasting | 2375 |
| Cloud Atlas | 2373 |
| The Brothers Karamazov | 2369 |
| David Copperfield | 2364 |
| Madame Bovary | 2361 |
| An Abundance of Katherines | 2357 |
| Christine | 2352 |
| The Dead Zone | 2348 |
| Firestarter | 2344 |
| Franny and Zooey | 2343 |
| The Rainmaker | 2339 |
| King Lear | 2333 |
| Congo | 2325 |
| The Magicians (The Magicians #1) | 2311 |
| Peter Pan | 2310 |
| Life After Life | 2309 |
| Good in Bed (Cannie Shapiro, #1) | 2307 |
| Defending Jacob | 2297 |
| The Things They Carried | 2278 |
| Uncle Tom’s Cabin | 2278 |
| I Am Number Four (Lorien Legacies, #1) | 2265 |
| The Vampire Lestat (The Vampire Chronicles, #2) | 2263 |
| Zen and the Art of Motorcycle Maintenance: An Inquiry Into Values | 2258 |
| Guns, Germs, and Steel: The Fates of Human Societies | 2255 |
| 2001: A Space Odyssey (Space Odyssey, #1) | 2253 |
| Jonathan Strange & Mr Norrell | 2251 |
| Neuromancer | 2243 |
| Anansi Boys | 2238 |
| Don Quixote | 2236 |
| Candide | 2235 |
| Go Set a Watchman | 2233 |
| The Virgin Suicides | 2233 |
| Go Ask Alice | 2232 |
| The Drawing of the Three (The Dark Tower, #2) | 2231 |
| A Short History of Nearly Everything | 2230 |
| High Fidelity | 2229 |
| Legend (Legend, #1) | 2225 |
| The Taming of the Shrew | 2225 |
| Frostbite (Vampire Academy, #2) | 2219 |
| The Great Hunt (Wheel of Time, #2) | 2217 |
| Pretties (Uglies, #2) | 2208 |
| Dead as a Doornail (Sookie Stackhouse, #5) | 2207 |
| The Adventures of Sherlock Holmes | 2203 |
| The Restaurant at the End of the Universe (Hitchhiker’s Guide, #2) | 2200 |
| The Elite (The Selection, #2) | 2195 |
| One Day | 2192 |
| The Martian Chronicles | 2189 |
| The Prince | 2189 |
| Oryx and Crake (MaddAddam, #1) | 2181 |
| Sphere | 2181 |
| The Corrections | 2177 |
| The Wind in the Willows | 2175 |
| The Tale of Peter Rabbit | 2174 |
| When You Are Engulfed in Flames | 2172 |
| Heidi | 2170 |
| Fall of Giants (The Century Trilogy, #1) | 2157 |
| The Pearl | 2147 |
| A Wizard of Earthsea (Earthsea Cycle, #1) | 2143 |
| Little House in the Big Woods (Little House, #1) | 2141 |
| Definitely Dead (Sookie Stackhouse, #6) | 2139 |
| In the Woods (Dublin Murder Squad, #1) | 2132 |
| The Kitchen House | 2131 |
| Stargirl (Stargirl, #1) | 2123 |
| The Language of Flowers | 2122 |
| Perfume: The Story of a Murderer | 2121 |
| Odd Thomas (Odd Thomas, #1) | 2118 |
| The Reader | 2104 |
| Shadow Kiss (Vampire Academy, #3) | 2098 |
| The Dragon Reborn (Wheel of Time, #3) | 2096 |
| All Together Dead (Sookie Stackhouse, #7) | 2095 |
| Fast Food Nation: The Dark Side of the All-American Meal | 2095 |
| The Prophet | 2094 |
| The Hound of the Baskervilles | 2093 |
| American Psycho | 2082 |
| Voyager (Outlander, #3) | 2081 |
| Julius Caesar | 2075 |
| The 7 Habits of Highly Effective People: Powerful Lessons in Personal Change | 2073 |
| Can You Keep a Secret? | 2065 |
| Everything Is Illuminated | 2056 |
| Jonathan Livingston Seagull | 2054 |
| Throne of Glass (Throne of Glass, #1) | 2051 |
| Snow Crash | 2050 |
| The Tempest | 2049 |
| Bared to You (Crossfire, #1) | 2048 |
| Prey | 2045 |
| State of Wonder | 2040 |
| Different Seasons | 2035 |
| Everything I Never Told You | 2032 |
| Maus I: A Survivor’s Tale: My Father Bleeds History (Maus, #1) | 2027 |
| A Study in Scarlet | 2024 |
| Thinner | 2021 |
| 1st to Die (Women’s Murder Club, #1) | 2019 |
| Blood Promise (Vampire Academy, #4) | 2013 |
| The Well of Ascension (Mistborn, #2) | 2007 |
| Invisible Man | 2004 |
| The Shipping News | 2003 |
| The Red Pyramid (Kane Chronicles, #1) | 2000 |
| Clockwork Princess (The Infernal Devices, #3) | 1999 |
| Mrs. Frisby and the Rats of NIMH (Rats of NIMH, #1) | 1998 |
| The Waste Lands (The Dark Tower, #3) | 1998 |
| From Dead to Worse (Sookie Stackhouse, #8) | 1996 |
| The City of Ember (Book of Ember, #1) | 1991 |
| The Silkworm (Cormoran Strike, #2) | 1990 |
| Choke | 1987 |
| The Passage (The Passage, #1) | 1981 |
| The One (The Selection, #3) | 1980 |
| From the Mixed-Up Files of Mrs. Basil E. Frankweiler | 1977 |
| Before I Go to Sleep | 1976 |
| Wizard’s First Rule (Sword of Truth, #1) | 1975 |
| A Visit from the Goon Squad | 1973 |
| Bag of Bones | 1971 |
| V for Vendetta | 1965 |
| The Sound and the Fury | 1960 |
| After You (Me Before You, #2) | 1957 |
| Dead and Gone (Sookie Stackhouse, #9) | 1955 |
| The Mark of Athena (The Heroes of Olympus, #3) | 1952 |
| Are You My Mother? | 1951 |
| The Forgotten Garden | 1949 |
| The Storied Life of A.J. Fikry | 1948 |
| Murder on the Orient Express (Hercule Poirot, #10) | 1947 |
| Freedom | 1946 |
| The 5th Wave (The 5th Wave, #1) | 1944 |
| Kafka on the Shore | 1938 |
| Mrs. Dalloway | 1932 |
| Roots: The Saga of an American Family | 1930 |
| Spirit Bound (Vampire Academy, #5) | 1925 |
| Lonesome Dove | 1920 |
| Under the Banner of Heaven: A Story of Violent Faith | 1919 |
| Harry Potter Boxset (Harry Potter, #1-7) | 1915 |
| The Omnivore’s Dilemma: A Natural History of Four Meals | 1915 |
| Love You Forever | 1912 |
| The Merchant of Venice | 1904 |
| Cell | 1903 |
| The House of the Spirits | 1902 |
| The Little House Collection (Little House, #1-9) | 1897 |
| Beautiful Ruins | 1895 |
| The Silmarillion (Middle-Earth Universe) | 1890 |
| If You Give a Mouse a Cookie | 1889 |
| Norwegian Wood | 1887 |
| The Awakening | 1886 |
| Patriot Games (Jack Ryan Universe, #2) | 1885 |
| Where She Went (If I Stay, #2) | 1885 |
| World Without End (The Kingsbridge Series, #2) | 1885 |
| Interpreter of Maladies | 1884 |
| Alexander and the Terrible, Horrible, No Good, Very Bad Day | 1877 |
| Wizard and Glass (The Dark Tower, #4) | 1875 |
| The Art of War | 1873 |
| Life, the Universe and Everything (Hitchhiker’s Guide, #3) | 1872 |
| Twelfth Night | 1871 |
| Walden | 1869 |
| Midwives | 1866 |
| The Polar Express | 1865 |
| The Lincoln Lawyer (Mickey Haller, #1; Harry Bosch Universe, #16) | 1863 |
| On Writing: A Memoir of the Craft | 1862 |
| Scarlet (The Lunar Chronicles, #2) | 1854 |
| The Wind-Up Bird Chronicle | 1853 |
| The Hero of Ages (Mistborn, #3) | 1849 |
| Shōgun (Asian Saga, #1) | 1847 |
| A Brief History of Time | 1845 |
| The Lucky One | 1834 |
| Breakfast at Tiffany’s | 1830 |
| Dreamcatcher | 1829 |
| Madeline | 1826 |
| Who Moved My Cheese? | 1826 |
| City of Heavenly Fire (The Mortal Instruments, #6) | 1821 |
| Corduroy | 1821 |
| A Great and Terrible Beauty (Gemma Doyle, #1) | 1820 |
| The Remains of the Day | 1819 |
| Twilight: The Complete Illustrated Movie Companion | 1818 |
| Twenty Thousand Leagues Under the Sea | 1817 |
| Mere Christianity | 1815 |
| Crossed (Matched, #2) | 1813 |
| In Her Shoes | 1812 |
| The Chamber | 1810 |
| Starship Troopers | 1809 |
| The Complete Grimm’s Fairy Tales | 1809 |
| Night Shift | 1806 |
| Last Sacrifice (Vampire Academy, #6) | 1798 |
| Ender’s Shadow (Ender’s Shadow, #1) | 1792 |
| The Shadow Rising (Wheel of Time, #4) | 1789 |
| The Way of Kings (The Stormlight Archive, #1) | 1789 |
| Red Queen (Red Queen, #1) | 1785 |
| P.S. I Love You | 1782 |
| The Hobbit: Graphic Novel | 1782 |
| Dead in the Family (Sookie Stackhouse, #10) | 1780 |
| Message in a Bottle | 1779 |
| Nickel and Dimed: On (Not) Getting By in America | 1778 |
| Fantastic Beasts and Where to Find Them | 1776 |
| Around the World in Eighty Days | 1775 |
| Dark Lover (Black Dagger Brotherhood, #1) | 1774 |
| Kitchen Confidential: Adventures in the Culinary Underbelly | 1774 |
| How to Win Friends and Influence People | 1767 |
| Killing Floor (Jack Reacher, #1) | 1767 |
| Assassin’s Apprentice (Farseer Trilogy, #1) | 1765 |
| The Jungle | 1764 |
| House of Sand and Fog | 1755 |
| The Blind Assassin | 1755 |
| Dolores Claiborne | 1752 |
| Xenocide (Ender’s Saga, #3) | 1742 |
| Insomnia | 1741 |
| The Queen of the Damned (The Vampire Chronicles, #3) | 1735 |
| Safe Haven | 1734 |
| Daughter of Smoke & Bone (Daughter of Smoke & Bone, #1) | 1733 |
| Drums of Autumn (Outlander, #4) | 1733 |
| The Angel Experiment (Maximum Ride, #1) | 1732 |
| Steve Jobs | 1731 |
| The Phantom of the Opera | 1731 |
| The Bean Trees (Greer Family, #1) | 1730 |
| Empire Falls | 1729 |
| Inheritance (The Inheritance Cycle, #4) | 1727 |
| Specials (Uglies, #3) | 1727 |
| Gerald’s Game | 1720 |
| The Hiding Place: The Triumphant True Story of Corrie Ten Boom | 1718 |
| The Hunchback of Notre-Dame | 1717 |
| Oedipus Rex (The Theban Plays, #1) | 1716 |
| Pippi Longstocking | 1714 |
| The Absolutely True Diary of a Part-Time Indian | 1713 |
| The Boys in the Boat: Nine Americans and Their Epic Quest for Gold at the 1936 Berlin Olympics | 1710 |
| A Portrait of the Artist as a Young Man | 1705 |
| The Bonesetter’s Daughter | 1705 |
| Postmortem (Kay Scarpetta, #1) | 1704 |
| A Room with a View | 1703 |
| Flowers in the Attic (Dollanganger, #1) | 1701 |
| The Bluest Eye | 1700 |
| Hopeless (Hopeless, #1) | 1699 |
| Mr. Mercedes (Bill Hodges Trilogy, #1) | 1696 |
| The English Patient | 1694 |
| Plain Truth | 1691 |
| Reading Lolita in Tehran | 1684 |
| The Undomestic Goddess | 1682 |
| The Dark Half | 1681 |
| About a Boy | 1680 |
| In the Garden of Beasts: Love, Terror, and an American Family in Hitler’s Berlin | 1680 |
| Olive Kitteridge | 1673 |
| Evermore (The Immortals, #1) | 1670 |
| The Trial | 1669 |
| Holy Bible: King James Version | 1668 |
| Half Broke Horses | 1666 |
| The Secret (The Secret, #1) | 1665 |
| The Alienist (Dr. Laszlo Kreizler, #1) | 1662 |
| Lamb: The Gospel According to Biff, Christ’s Childhood Pal | 1659 |
| The Age of Innocence | 1658 |
| Man’s Search for Meaning | 1656 |
| The Dark Tower (The Dark Tower, #7) | 1655 |
| The Witch of Blackbird Pond | 1649 |
| The Hours | 1647 |
| The Princess Diaries (The Princess Diaries, #1) | 1647 |
| Girl, Interrupted | 1646 |
| Heaven is for Real: A Little Boy’s Astounding Story of His Trip to Heaven and Back | 1643 |
| My Ántonia | 1638 |
| Orange Is the New Black | 1635 |
| Mort (Death, #1; Discworld, #4) | 1634 |
| Wolves of the Calla (The Dark Tower, #5) | 1633 |
| Paradise Lost | 1632 |
| One Fish, Two Fish, Red Fish, Blue Fish | 1628 |
| As I Lay Dying | 1623 |
| Doctor Sleep (The Shining, #2) | 1621 |
| Pandemonium (Delirium, #2) | 1619 |
| White Fang | 1619 |
| The Tommyknockers | 1616 |
| Something Blue (Darcy & Rachel, #2) | 1615 |
| Julie and Julia: 365 Days, 524 Recipes, 1 Tiny Apartment Kitchen: How One Girl Risked Her Marriage, Her Job, and Her Sanity to Master the Art of Living | 1611 |
| Because of Winn-Dixie | 1608 |
| The Girl Who Loved Tom Gordon | 1608 |
| Shanghai Girls (Shanghai Girls #1) | 1606 |
| Before I Fall | 1601 |
| The Exorcist | 1596 |
| The Lies of Locke Lamora (Gentleman Bastard, #1) | 1596 |
| The Complete Sherlock Holmes | 1591 |
| Betrayed (House of Night, #2) | 1589 |
| The True Story of the 3 Little Pigs | 1589 |
| The Elegance of the Hedgehog | 1587 |
| Foundation and Empire (Foundation #2) | 1579 |
| The Storyteller | 1576 |
| Desperation | 1575 |
| Song of Susannah (The Dark Tower, #6) | 1572 |
| Cress (The Lunar Chronicles, #3) | 1568 |
| His Dark Materials (His Dark Materials #1-3) | 1568 |
| Major Pettigrew’s Last Stand | 1566 |
| Blindness | 1565 |
| The Westing Game | 1565 |
| 1Q84 | 1563 |
| Fool Moon (The Dresden Files, #2) | 1562 |
| No Country for Old Men | 1562 |
| The House of Hades (The Heroes of Olympus, #4) | 1562 |
| Walk Two Moons | 1561 |
| Wool Omnibus (Silo, #1) | 1557 |
| The God Delusion | 1556 |
| Mr. Penumbra’s 24-Hour Bookstore (Mr. Penumbra’s 24-Hour Bookstore, #1) | 1555 |
| Curious George | 1553 |
| Slammed (Slammed, #1) | 1553 |
| Will Grayson, Will Grayson | 1553 |
| Sabriel (Abhorsen, #1) | 1552 |
| The Marriage Plot | 1552 |
| Aesop’s Fables | 1548 |
| This is Where I Leave You | 1547 |
| Untamed (House of Night, #4) | 1545 |
| Preludes & Nocturnes (The Sandman #1) | 1543 |
| The Master and Margarita | 1543 |
| Remember Me? | 1541 |
| The Neverending Story | 1539 |
| Anna and the French Kiss (Anna and the French Kiss, #1) | 1538 |
| Quiet: The Power of Introverts in a World That Can’t Stop Talking | 1535 |
| Skeleton Crew | 1535 |
| Gathering Blue (The Giver, #2) | 1534 |
| Crown of Midnight (Throne of Glass, #2) | 1532 |
| Watchers | 1531 |
| Seabiscuit: An American Legend | 1530 |
| Reflected in You (Crossfire, #2) | 1529 |
| The Glass Menagerie | 1527 |
| Shutter Island | 1526 |
| Americanah | 1525 |
| Wolf Hall (Thomas Cromwell, #1) | 1525 |
| Nine Stories | 1521 |
| Hamlet: Screenplay, Introduction And Film Diary | 1514 |
| So Long, and Thanks for All the Fish (Hitchhiker’s Guide to the Galaxy, #4) | 1513 |
| Hyperion (Hyperion Cantos, #1) | 1511 |
| Daughter of Fortune | 1508 |
| The Talisman (The Talisman, #1) | 1507 |
| Crescendo (Hush, Hush, #2) | 1506 |
| The Bourne Supremacy (Jason Bourne, #2) | 1503 |
| Waiting for Godot | 1501 |
| Guards! Guards! (Discworld, #8) | 1500 |
| Inferno (The Divine Comedy #1) | 1496 |
| Brave New World / Brave New World Revisited | 1494 |
| People of the Book | 1493 |
| Journey to the Center of the Earth (Extraordinary Voyages, #3) | 1491 |
| The Once and Future King (The Once and Future King #1-4) | 1490 |
| Stiff: The Curious Lives of Human Cadavers | 1487 |
| Sophie’s World | 1486 |
| The Five Love Languages: How to Express Heartfelt Commitment to Your Mate | 1485 |
| Falling Up | 1484 |
| Contact | 1483 |
| The Accidental Tourist | 1483 |
| The Fires of Heaven (Wheel of Time, #5) | 1482 |
| Presumed Innocent | 1479 |
| Landline | 1477 |
| Four Past Midnight | 1474 |
| Red Rising (Red Rising, #1) | 1474 |
| The Fiery Cross (Outlander, #5) | 1472 |
| Second Foundation (Foundation #3) | 1469 |
| I Am Legend and Other Stories | 1463 |
| The Sense of an Ending | 1462 |
| Jaws | 1459 |
| Eye of the Needle | 1457 |
| Lord of Chaos (Wheel of Time, #6) | 1456 |
| Persepolis: The Story of a Childhood (Persepolis, #1) | 1454 |
| The Eyes of the Dragon | 1452 |
| The Deep End of the Ocean (Cappadora Family, #1) | 1451 |
| The Complete Fairy Tales | 1447 |
| A Wind in the Door (A Wrinkle in Time Quintet, #2) | 1445 |
| Year of Wonders | 1445 |
| Firefly Lane (Firefly Lane, #1) | 1438 |
| The Prince and the Pauper | 1435 |
| The White Tiger | 1433 |
| The Republic | 1431 |
| Shadow of Night (All Souls Trilogy, #2) | 1430 |
| A is for Alibi (Kinsey Millhone, #1) | 1428 |
| Dirk Gently’s Holistic Detective Agency (Dirk Gently #1) | 1427 |
| The Year of Magical Thinking | 1426 |
| Left Behind (Left Behind, #1) | 1425 |
| A Fine Balance | 1424 |
| The Short Second Life of Bree Tanner: An Eclipse Novella (Twilight, #3.5) | 1423 |
| Just Listen | 1422 |
| The Bone Collector (Lincoln Rhyme, #1) | 1420 |
| The Partner | 1418 |
| The Plague | 1415 |
| All Creatures Great and Small (All Creatures Great and Small, #1-2) | 1414 |
| The Lost World (Jurassic Park, #2) | 1414 |
| The Unlikely Pilgrimage of Harold Fry (Harold Fry, #1) | 1413 |
| The Reptile Room (A Series of Unfortunate Events, #2) | 1409 |
| Grave Peril (The Dresden Files, #3) | 1406 |
| Two for the Dough (Stephanie Plum, #2) | 1405 |
| Animal Farm / 1984 | 1404 |
| Chosen (House of Night, #3) | 1400 |
| J.R.R. Tolkien 4-Book Boxed Set: The Hobbit and The Lord of the Rings | 1400 |
| Howl’s Moving Castle (Howl’s Moving Castle, #1) | 1396 |
| Anthem | 1394 |
| Calvin and Hobbes | 1394 |
| Cloudy With a Chance of Meatballs | 1394 |
| The Testament | 1393 |
| The Truth About Forever | 1391 |
| Career of Evil (Cormoran Strike, #3) | 1388 |
| Dead Reckoning (Sookie Stackhouse, #11) | 1384 |
| Harold and the Purple Crayon | 1383 |
| The Interestings | 1383 |
| Darkly Dreaming Dexter (Dexter, #1) | 1382 |
| Eats, Shoots & Leaves: The Zero Tolerance Approach to Punctuation | 1382 |
| A Crown of Swords (Wheel of Time, #7) | 1381 |
| The Street Lawyer | 1380 |
| Middlemarch | 1379 |
| White Teeth | 1378 |
| Pride and Prejudice and Zombies (Pride and Prejudice and Zombies, #1) | 1375 |
| Shatter Me (Shatter Me, #1) | 1373 |
| Words of Radiance (The Stormlight Archive, #2) | 1373 |
| Abraham Lincoln: Vampire Hunter | 1370 |
| Ulysses | 1369 |
| The History of Love | 1368 |
| Fire (Graceling Realm, #2) | 1366 |
| Men Are from Mars, Women Are from Venus | 1365 |
| One Plus One | 1362 |
| The Girls | 1362 |
| The Art of Fielding | 1361 |
| Cold Sassy Tree | 1357 |
| Prodigy (Legend, #2) | 1356 |
| Torment (Fallen, #2) | 1355 |
| Sophie’s Choice | 1350 |
| Tales of a Fourth Grade Nothing (Fudge, #1) | 1348 |
| Tell the Wolves I’m Home | 1348 |
| The Gathering Storm (Wheel of Time, #12) | 1348 |
| A People’s History of the United States | 1347 |
| Holidays on Ice | 1346 |
| The Swiss Family Robinson | 1346 |
| Obsidian (Lux, #1) | 1345 |
| House Rules | 1338 |
| Equal Rites (Discworld, #3; Witches #1) | 1336 |
| Vanity Fair | 1335 |
| Maniac Magee | 1334 |
| Three to Get Deadly (Stephanie Plum, #3) | 1334 |
| We Need to Talk About Kevin | 1333 |
| Cannery Row | 1332 |
| Exodus | 1329 |
| The Good Girl | 1329 |
| Easy (Contours of the Heart, #1) | 1328 |
| Let’s Pretend This Never Happened: A Mostly True Memoir | 1327 |
| The Dinner | 1327 |
| Anne of Avonlea (Anne of Green Gables, #2) | 1326 |
| The Red Badge of Courage | 1325 |
| The Invention of Hugo Cabret | 1323 |
| The Tenth Circle | 1322 |
| The Man Who Mistook His Wife for a Hat and Other Clinical Tales | 1320 |
| Chocolat (Chocolat, #1) | 1319 |
| Are You There, Vodka? It’s Me, Chelsea | 1318 |
| John Adams | 1318 |
| Luckiest Girl Alive | 1316 |
| Summer Knight (The Dresden Files, #4) | 1316 |
| The Scarlet Pimpernel | 1315 |
| To the Lighthouse | 1315 |
| Stuart Little | 1314 |
| Dubliners | 1313 |
| Steelheart (The Reckoners, #1) | 1311 |
| Truly Madly Guilty | 1308 |
| The Divine Comedy | 1307 |
| The Monster at the End of this Book | 1307 |
| Nights in Rodanthe | 1303 |
| Hollow City (Miss Peregrine’s Peculiar Children, #2) | 1301 |
| Brown Bear, Brown Bear, What Do You See? | 1300 |
| The Circle | 1300 |
| The Constant Princess (The Plantagenet and Tudor Novels, #6) | 1298 |
| Leaving Time | 1296 |
| The Witching Hour (Lives of the Mayfair Witches, #1) | 1296 |
| Dune Messiah (Dune Chronicles #2) | 1293 |
| Heir of Fire (Throne of Glass, #3) | 1293 |
| The Path of Daggers (Wheel of Time, #8) | 1293 |
| Guess How Much I Love You | 1291 |
| The Silver Linings Playbook | 1291 |
| Born to Run: A Hidden Tribe, Superathletes, and the Greatest Race the World Has Never Seen | 1289 |
| Royal Assassin (Farseer Trilogy, #2) | 1289 |
| Midnight Sun (Twilight, #1.5) | 1286 |
| Rose Madder | 1286 |
| The Girl with All the Gifts | 1286 |
| The Rescue | 1285 |
| The Wide Window (A Series of Unfortunate Events, #3) | 1285 |
| The White Queen (The Plantagenet and Tudor Novels, #2) | 1284 |
| The Sweetness at the Bottom of the Pie (Flavia de Luce, #1) | 1283 |
| Trainspotting | 1283 |
| Midnight’s Children | 1281 |
| The Nest | 1280 |
| We Were the Mulvaneys | 1280 |
| Schindler’s List | 1278 |
| Four to Score (Stephanie Plum, #4) | 1277 |
| A Court of Thorns and Roses (A Court of Thorns and Roses, #1) | 1276 |
| The Brethren | 1276 |
| The Girls’ Guide to Hunting and Fishing | 1276 |
| 1776 | 1274 |
| Clear and Present Danger (Jack Ryan Universe, #6) | 1274 |
| Helter Skelter: The True Story of the Manson Murders | 1274 |
| Stone Soup | 1274 |
| Dragonflight (Dragonriders of Pern, #1) | 1271 |
| Let the Great World Spin | 1267 |
| The Mysterious Affair at Styles (Hercule Poirot, #1) | 1267 |
| The Story of Edgar Sawtelle | 1266 |
| Hearts in Atlantis | 1262 |
| The Indian in the Cupboard (The Indian in the Cupboard, #1) | 1261 |
| The Chosen | 1259 |
| The Long Walk | 1259 |
| Duma Key | 1258 |
| Far from the Madding Crowd | 1258 |
| Reconstructing Amelia | 1258 |
| The Beach House | 1258 |
| The Blade Itself (The First Law, #1) | 1258 |
| Mystic River | 1257 |
| The Alchemyst (The Secrets of the Immortal Nicholas Flamel, #1) | 1257 |
| Elantris (Elantris, #1) | 1256 |
| Reached (Matched, #3) | 1256 |
| The Raven Boys (The Raven Cycle, #1) | 1256 |
| The Guardian | 1254 |
| The Last of the Mohicans (The Leatherstocking Tales #2) | 1254 |
| The Hundred-Year-Old Man Who Climbed Out of the Window and Disappeared | 1253 |
| Old Man’s War (Old Man’s War, #1) | 1252 |
| The Purpose Driven Life: What on Earth Am I Here for? | 1251 |
| A Breath of Snow and Ashes (Outlander, #6) | 1250 |
| The Arctic Incident (Artemis Fowl, #2) | 1250 |
| The Essential Calvin and Hobbes: A Calvin and Hobbes Treasury | 1249 |
| Unwind (Unwind, #1) | 1248 |
| Wicked Lovely (Wicked Lovely, #1) | 1248 |
| Rendezvous with Rama (Rama, #1) | 1247 |
| The Complete Anne of Green Gables Boxed Set (Anne of Green Gables, #1-8) | 1247 |
| Death Masks (The Dresden Files, #5) | 1245 |
| Silence (Hush, Hush, #3) | 1245 |
| America (The Book): A Citizen’s Guide to Democracy Inaction | 1242 |
| Batman: The Dark Knight Returns (The Dark Knight Saga, #1) | 1242 |
| Sh*t My Dad Says | 1242 |
| The Heart is a Lonely Hunter | 1242 |
| Shadow and Bone (Shadow and Bone, #1) | 1239 |
| The Secret Keeper | 1239 |
| Children of the Mind (Ender’s Saga, #4) | 1237 |
| Hunted (House of Night, #5) | 1237 |
| Stones from the River | 1237 |
| Suzanne’s Diary for Nicholas | 1237 |
| Winter’s Heart (Wheel of Time, #9) | 1233 |
| The Man in the High Castle | 1232 |
| Childhood’s End | 1231 |
| Bloodlines (Bloodlines, #1) | 1227 |
| The Eyre Affair (Thursday Next, #1) | 1227 |
| A Long Way Gone: Memoirs of a Boy Soldier | 1226 |
| The Round House | 1222 |
| The Mist | 1219 |
| One Thousand White Women: The Journals of May Dodd (One Thousand White Women#1) | 1218 |
| Prodigal Summer | 1216 |
| Roll of Thunder, Hear My Cry (Logans, #4) | 1216 |
| The Amulet of Samarkand (Bartimaeus, #1) | 1216 |
| The Iron King (The Iron Fey, #1) | 1216 |
| I’ve Got Your Number | 1215 |
| Towers of Midnight (Wheel of Time, #13) | 1212 |
| Hot Six (Stephanie Plum, #6) | 1211 |
| Lady Chatterley’s Lover | 1210 |
| Anne of the Island (Anne of Green Gables, #3) | 1209 |
| Let’s Explore Diabetes with Owls | 1209 |
| The Wedding (The Notebook, #2) | 1209 |
| The Pilot’s Wife | 1207 |
| The Aeneid | 1206 |
| The Autobiography of Malcolm X | 1203 |
| Perfect Chemistry (Perfect Chemistry, #1) | 1202 |
| Guilty Pleasures (Anita Blake, Vampire Hunter, #1) | 1201 |
| High Five (Stephanie Plum, #5) | 1201 |
| Tender Is the Night | 1201 |
| Gone (Gone, #1) | 1200 |
| The Forever War (The Forever War, #1) | 1199 |
| A Swiftly Tilting Planet (A Wrinkle in Time Quintet, #3) | 1197 |
| Tempted (House of Night, #6) | 1196 |
| Ethan Frome | 1195 |
| The Alloy of Law (Mistborn, #4) | 1195 |
| The Little Engine That Could | 1193 |
| The Bonfire of the Vanities | 1190 |
| Walking Disaster (Beautiful, #2) | 1190 |
| The Invisible Man | 1189 |
| Blood Rites (The Dresden Files, #6) | 1187 |
| Fates and Furies | 1187 |
| Lover Eternal (Black Dagger Brotherhood, #2) | 1185 |
left_join(BookData,BookDataMeta[c('book_id','authors','title','language_code')]) %>%
group_by(title)%>%
tally() %>%
top_n(15) %>%
ggplot(aes(x = fct_reorder(title, -n), y = n))+
geom_col()+
plottheme+
theme(axis.text.x = element_text(angle = 45,hjust = 1))+
labs(x = "Books", y = "Number of Views")
average_book_ratings<- apply(BookDataMatrix, 2, mean, na.rm = T)
average_user_ratings<- apply(BookDataMatrix, 1, mean, na.rm = T)
p1<-qplot(average_book_ratings,alpha = 0.5)+plottheme+theme(legend.position = 'none')+coord_cartesian(xlim = c(1,5))
p2<-qplot(average_user_ratings, alpha = 0.5 )+plottheme+theme(legend.position = 'none')+coord_cartesian(xlim = c(1,5))
grid.arrange(p1,p2, ncol = 1)
As shown in the figure above, diving a little bit further into the dataset allows us to see what kind of biases are exhibited in our dataset’s distribution. It is clear that there are few users with an average rating less than 3, and that there are few books with average ratings less than 3. It is likely that users with average ratings less than 3 have very few reviews and may have only rated a book when there was dislike.
Recommender Systems
About
The following describes some of the recommender systems produced in this final project as learned throughout Data 612’s coursework.
IBCF is a method that looks at similarities between items (books) and makes recommendations. The algorithm considers user’s purchases (items) and recommends similar items and the core of this algorithm is based on: how similar 2 items are when receiving similar ratings from similar users, identifying the k-most similar items and identifying user specific recommendations based on user purchase history. The results of the top 20 most recommended books are shown in the following figure.
UBCF is a method that looks at similarities between users and makes recommendations to users based on this similarity. The algorithm measures how similar each user is to another and a similarity matrix can define the top similar users via an algorithm like k-nearest neighbors, or similarity can be determined by some threshold similarity value. The user ratings are used as a weight on the books and this is multiplied by the similarity coefficient in order to prioritize recommendations. We can apply the same code and thought process to the recommender function and use method UBCF and the most recommended books can be found in the following figure.
Singular value decomposition (SVD) is a common dimensionality reduction technique that identifies latent semantic factors for retrieving information. Some of the difficulties associated with this technique can be contributed to sparse data (missing values) often present in user-item matrices. Unfortunately filling huge matrices with missing values can often be expensive or even misleading. Regularization models (penalty-based error minimizing) can assist with this.
Model Setup
There are many different recommender systems and there are several methods to define which models produce greater results. Some common metrics for model evaluations are: root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), receiver operating characteristic (ROC), area under the ROC curve (AUC). The metric that will be presented here is the ROC curve for all models (IBCF and UBCF) for each model, three methods will be evaluated, each measure the similarity between two vectors through different techniques. These include Cosine similarity function, pearson similarity function, and jaccard similarity function. In addition to these, a random or “guessing” recommendation will be produced in order to have a baseline to compare model performance to. The plot below shows the results of this evaluation and the IBCF consistently outperforms the UBCF models and the jaccard IBCF is our best.
data_package <- data(package = "recommenderlab")
data("BookDataMatrix")## Warning in data("BookDataMatrix"): data set 'BookDataMatrix' not foundrecmodels<-recommenderRegistry$get_entries(dataType = "realRatingMatrix")
kable(names(recmodels)) %>%
kable_styling(full_width = FALSE,
position = "center",
bootstrap_options = c("hover", "condense","responsive")) %>%
add_header_above(header = "Available Recommender Models")| x |
|---|
| ALS_realRatingMatrix |
| ALS_implicit_realRatingMatrix |
| IBCF_realRatingMatrix |
| LIBMF_realRatingMatrix |
| POPULAR_realRatingMatrix |
| RANDOM_realRatingMatrix |
| RERECOMMEND_realRatingMatrix |
| SVD_realRatingMatrix |
| SVDF_realRatingMatrix |
| UBCF_realRatingMatrix |
The ratings for the books are taking from the BookDataMatrix dataset and we will remove books with less than 1500 reviews, as well as users with less than 175 ratings to work with a smaller dataset. Our rating threshold will be defined with “4” as our positive rating since most ratings are between 3 and 5 so books rated 4 or greater are considered positive. Our training percentage will be an 80/20 split of the data and we will compute 10 recommendations per user for calculating RMSE. when calculating ROC curve, we will look at different quantities of recommendations produced by the models and see how the models perform.
BookData$user_id <- as.factor(BookData$user_id)
BookData$book_id <- as.factor(BookData$book_id)
BookDataMatrix<-as(data.frame(BookData), 'realRatingMatrix')
ratings_books <- BookDataMatrix[rowCounts(BookDataMatrix) > 175,
colCounts(BookDataMatrix) > 1500]
train_percent<-0.8
kept_items<-10
rating_threshold<-3
n_eval<-8
no_recommendations<-10
eval_sets <- evaluationScheme(data = ratings_books, method = "cross-validation",
train = train_percent, given = kept_items, goodRating = rating_threshold, k = n_eval)
#used to train
recc_train<- getData(eval_sets,'train')
#used to predict
recc_known<-getData(eval_sets,'known')
#used to test
recc_unknown<-getData(eval_sets,'unknown')Model Evaluation
We initially start by making 10 book recommendations to users in our testing dataset. The table below provides a measure of accuracy on our models with root mean square error (RMSE), mean square error (MSE), and MAE, mean absolute error (MAE). Our preliminary results indicate that our UBCF jaccard, UBCF cosine, and SVD methods are our least erroneous recommender systems.
UBCF_pearson_eval<-Recommender(recc_train,method = "UBCF", parameter = list(method = "pearson"))
UBCF_jaccard_eval<-Recommender(recc_train,method = "UBCF", parameter = list(method = "jaccard"))
UBCF_cosine_eval<-Recommender(recc_train,method = "UBCF", parameter = list(method = "cosine"))
IBCF_pearson_eval<-Recommender(recc_train,method = "IBCF", parameter = list(method = "pearson"))
IBCF_jaccard_eval<-Recommender(recc_train,method = "IBCF", parameter = list(method = "jaccard"))
IBCF_cosine_eval<-Recommender(recc_train,method = "IBCF", parameter = list(method = "cosine"))
SVD_eval<-Recommender(recc_train,method = "SVD")
ALS_eval<-Recommender(recc_train,method = "ALS")
recommendations<-function(eval){
recc_predicted<-predict(object = eval,newdata=recc_known,n=no_recommendations)
recc_matrix <- sapply(recc_predicted@items, function(x){
colnames(ratings_books)[x]
})
number_of_items<-recc_matrix %>% unlist() %>% table() %>% as.data.frame()
table_top <- data.frame("names.number_of_items_top." = number_of_items$.,
"number_of_items_top"= number_of_items$Freq)
BookDataMeta$book_id<-as.factor(BookDataMeta$book_id)
table_top %>% left_join(BookDataMeta, by = c("names.number_of_items_top."="book_id" )) %>%
top_n(20) %>%
ggplot(mapping = aes(x=fct_reorder(title,-as.numeric(number_of_items_top)), y = as.numeric(number_of_items_top)))+
geom_col(aes(fill = as.numeric(number_of_items_top)),color = 'black', alpha = 0.5)+
theme(axis.text.x = element_text(angle = 90),
legend.position = 'none',
panel.grid = element_blank(),
panel.background = element_blank())+
labs(x = "Book Title",
y = "Number of Recommendations",
title = "Top 20 Book Recomendations")
}ModelErrors<-function(eval){
recc_predicted<-predict(object = eval,newdata=recc_known,n=no_recommendations, type= "ratings")
calcPredictionAccuracy(recc_predicted,recc_unknown, byUser = F)
}
rbind(
UBCF_pearson= ModelErrors(UBCF_pearson_eval),
UBCF_jaccard= ModelErrors(UBCF_jaccard_eval),
UBCF_cosine= ModelErrors(UBCF_cosine_eval),
IBCF_pearson= ModelErrors(IBCF_pearson_eval),
IBCF_jaccard= ModelErrors(IBCF_jaccard_eval),
IBCF_cosine= ModelErrors(IBCF_cosine_eval),
SVD= ModelErrors(SVD_eval),
ALS= ModelErrors(ALS_eval))## RMSE MSE MAE
## UBCF_pearson 0.9682550 0.9375178 0.7700317
## UBCF_jaccard 0.9631783 0.9277125 0.7605164
## UBCF_cosine 0.9678766 0.9367851 0.7634025
## IBCF_pearson 1.2998168 1.6895237 0.8932116
## IBCF_jaccard 1.2653267 1.6010517 0.9252416
## IBCF_cosine 1.3281864 1.7640792 0.9325961
## SVD 0.9703118 0.9415049 0.7685797
## ALS 0.9872877 0.9747370 0.7869963
Finally, We can look at the ROC curve and tune the models on various normalization techniques to see if this provides and adjustments to model accuracy. The normalization techniques include “center” where the data is adjusted so that the mean of each user is 0. “Z-Score” normalization allows the dataset to be adjusted by measuring the distance (number of standard deviations) a rating is from the mean for a given user.
Our ROC curve below indicates that the most accurate recommender system from the models are consistent with the RMSE showing that our singular value decomposition and user based collaborative filtering methods are optimal. Using the function that we created called “recommendations” we can produce a figure showing the top 20 book recommendations for any of our models, in this case we’ll use the best performing one as shown in the final figure.
models_to_evaluate <- list(
UBCF_pearson = list(name = "UBCF", param = list(method =
"pearson")),
UBCF_jaccard = list(name = "UBCF", param = list(method =
"jaccard")),
UBCF_cosine = list(name = "UBCF", param = list(method =
"cosine")),
IBCF_pearson = list(name = "IBCF", param = list(method =
"pearson")),
IBCF_jaccard = list(name = "IBCF", param = list(method =
"jaccard")),
IBCF_cosine = list(name = "IBCF", param = list(method =
"cosine")),
SVD_Z = list(name = "SVD", param = list(normalize = "Z-score")),
SVD_Center = list(name = "SVD", param = list(normalize = "center")),
ALS_Z = list(name = "ALS", param = list(normalize = "Z-score")),
ALS_Center = list(name = "ALS", param = list(normalize = "center")),
random = list(name = "RANDOM", param=NULL)
)
n_recommendations <- c(1, 5, seq(10, 100, 10))
list_results <- evaluate(x = eval_sets, method = models_to_evaluate, n= n_recommendations)## UBCF run fold/sample [model time/prediction time]
## 1 [0sec/0.12sec]
## 2 [0sec/0.14sec]
## 3 [0sec/0.13sec]
## 4 [0.02sec/0.11sec]
## 5 [0sec/0.11sec]
## 6 [0sec/0.12sec]
## 7 [0sec/0.11sec]
## 8 [0sec/0.11sec]
## UBCF run fold/sample [model time/prediction time]
## 1 [0sec/0.13sec]
## 2 [0sec/0.11sec]
## 3 [0sec/0.11sec]
## 4 [0sec/0.12sec]
## 5 [0sec/0.11sec]
## 6 [0sec/0.12sec]
## 7 [0sec/0.11sec]
## 8 [0.01sec/0.11sec]
## UBCF run fold/sample [model time/prediction time]
## 1 [0sec/0.1sec]
## 2 [0sec/0.11sec]
## 3 [0sec/0.11sec]
## 4 [0sec/0.11sec]
## 5 [0sec/0.12sec]
## 6 [0sec/0.12sec]
## 7 [0sec/0.13sec]
## 8 [0sec/0.12sec]
## IBCF run fold/sample [model time/prediction time]
## 1 [0.5sec/0.01sec]
## 2 [0.5sec/0.02sec]
## 3 [0.5sec/0.01sec]
## 4 [0.48sec/0.02sec]
## 5 [0.49sec/0.01sec]
## 6 [0.5sec/0.02sec]
## 7 [0.5sec/0.02sec]
## 8 [0.48sec/0.02sec]
## IBCF run fold/sample [model time/prediction time]
## 1 [0.47sec/0.01sec]
## 2 [0.45sec/0.01sec]
## 3 [0.47sec/0.02sec]
## 4 [0.47sec/0.01sec]
## 5 [0.47sec/0.01sec]
## 6 [0.47sec/0.02sec]
## 7 [0.52sec/0.01sec]
## 8 [0.47sec/0.02sec]
## IBCF run fold/sample [model time/prediction time]
## 1 [0.47sec/0.01sec]
## 2 [0.52sec/0.02sec]
## 3 [0.47sec/0.02sec]
## 4 [0.48sec/0.02sec]
## 5 [0.49sec/0sec]
## 6 [0.5sec/0.02sec]
## 7 [0.48sec/0.02sec]
## 8 [0.49sec/0.01sec]
## SVD run fold/sample [model time/prediction time]
## 1 [0.05sec/0.03sec]
## 2 [0.05sec/0.03sec]
## 3 [0.06sec/0.03sec]
## 4 [0.07sec/0.03sec]
## 5 [0.06sec/0.03sec]
## 6 [0.07sec/0.03sec]
## 7 [0.06sec/0.03sec]
## 8 [0.03sec/0.03sec]
## SVD run fold/sample [model time/prediction time]
## 1 [0.05sec/0.03sec]
## 2 [0.05sec/0.03sec]
## 3 [0.05sec/0.03sec]
## 4 [0.05sec/0.03sec]
## 5 [0.04sec/0.03sec]
## 6 [0.04sec/0.02sec]
## 7 [0.07sec/0.03sec]
## 8 [0.04sec/0.02sec]
## ALS run fold/sample [model time/prediction time]
## 1 [0sec/11.02sec]
## 2 [0sec/10.9sec]
## 3 [0sec/12.15sec]
## 4 [0sec/10.94sec]
## 5 [0sec/11.76sec]
## 6 [0sec/11.3sec]
## 7 [0sec/11.3sec]
## 8 [0sec/11.04sec]
## ALS run fold/sample [model time/prediction time]
## 1 [0sec/11.17sec]
## 2 [0sec/11.48sec]
## 3 [0sec/10.87sec]
## 4 [0sec/11.18sec]
## 5 [0sec/10.99sec]
## 6 [0sec/11.15sec]
## 7 [0sec/11.23sec]
## 8 [0sec/11.04sec]
## RANDOM run fold/sample [model time/prediction time]
## 1 [0sec/0.03sec]
## 2 [0sec/0.01sec]
## 3 [0sec/0.01sec]
## 4 [0sec/0.03sec]
## 5 [0sec/0.03sec]
## 6 [0sec/0.03sec]
## 7 [0sec/0.03sec]
## 8 [0sec/0.03sec]avg_matrices <- lapply(list_results, avg)
plot(list_results, annotate = 1, legend = "topleft")
title("ROC curve")
recommendations(UBCF_pearson_eval)## Warning: Column `names.number_of_items_top.`/`book_id` joining factors with
## different levels, coercing to character vector