Nearest to Fallout 4: Kinetic Void, Viscera Cleanup Detail Shadow Warrior, Alice Madness Returns, Gratuitous Space Battles, Desktop Dungeons, Peggle Extreme, Star Wars - Battlefront II, The Misadventures of P.B. Nearest to Team Fortress 2: Stronghold 2, Nexus The Jupiter Incident, Larva Mortus, Cossacks II Napoleonic Wars, Edge of Space, Don Bradman Cricket 14, Samantha Swift and the Golden Touch, Worms Crazy Golf, Nearest to Far Cry 3: Ubersoldier II, BookWorm Deluxe, Bridge Constructor Medieval, Nimble Writer, Fieldrunners 2, Carpe Diem, Dark Void, Sacred Gold, Nearest to Counter-Strike Global Offensive: Majesty 2, Nancy Drew Danger on Deception Island, Amazing Adventures Around the World, X2 The Threat, Pirates, Vikings, & Knights II, Stargate Resistance, Heroes Over Europe, Duck Dynasty, Nearest to Mirror's Edge: Critter Crunch, Lost Planet Extreme Condition - Colonies Edition, Tom Clancy's Splinter Cell Chaos Theory, Operation Flashpoint Red River, Year Walk, Ys I, Petz Horsez 2, Third Eye Crime,
DUNGEON LORDS STEAM EDITION LOAD TIMES FULL
2, Full Mojo Rampage, Freight Tycoon Inc., GRID Autosport, 100% Orange Juice, Gunscape, Deus Ex Game of the Year Edition, Nearest to Deus Ex Human Revolution: Duke Nukem Forever, Tom Clancy's H.A.W.X. Nearest to Company of Heroes: Gods Will Be Watching, Cloud Chamber, Oil Rush, Stealth Inc 2, Mordheim City of the Damned, FINAL FANTASY XIII-2, Amazing World, Perpetuum, There are 3600 unique games in the data set.
npy file containing embeddings, dictionary, and reverse dictionary: train_skipgram.py - training using Skip-gram, using both purchase and play actions into account as user context.Įach script outputs an image with the game embeddings visualised using t-SNE, and a.train_cbow_weighted.py - same as above, but, only play actions are taken into consideration, and the label is selected based on time played (more time played the game - higher the probability of being selected).train_cbow.py - training using CBOW, using both purchase and play actions into account as user context.Explained: Deriving Mikolov et al.’s Negative-Sampling Word-Embedding Method.Distributed Representations of Words and Phrases and their Compositionality.Skip-gram: (Rocket League -> (Dota 2, CS: GO)), (CS: GO -> (Dota 2, Rocket League)), (Dota 2 -> (CS: GO, Rocket League))įor more reference, please have a look at this papers:.CBOW: ((Dota 2, CS: GO) -> Rocket League), ((Dota 2, Rocket League) -> CS: GO), ((CS: GO, Rocket League) -> Dota 2).For example if a user has three games: Dota 2, CS: GO, and Rocket League, this (input -> label) pairs can be generated: TensorFlow implementation of word2vec applied on dataset, using both CBOW and Skip-gram.Ĭontext for each game is extracted from the other games that the user owns.
0 kommentar(er)
