| """Turn a catalog row into the text document the embedding model reads.""" |
| import numpy as np |
|
|
| KEEP_CATEGORIES = { |
| "Single-player", "Multi-player", "Co-op", "Online Co-op", "LAN Co-op", "Shared/Split Screen Co-op", |
| "PvP", "Online PvP", "Shared/Split Screen PvP", "MMO", "VR Support", "VR Only", "Cross-Platform Multiplayer", |
| } |
|
|
|
|
| def build_doc(row, rng: np.random.Generator | None = None, drop_tags: bool = False, max_tags: int = 15) -> str: |
| """Deterministic when rng is None. With rng, returns a randomly degraded view for contrastive training.""" |
| aug = rng is not None |
| tags = list(row["tags"])[:max_tags] |
| if drop_tags or (aug and rng.random() < 0.5): |
| tags = [] |
| elif aug and tags: |
| keep = rng.random(len(tags)) >= 0.3 |
| tags = [t for t, k in zip(tags, keep) if k] |
| genres = list(row["genres"]) |
| cats = [c for c in row["categories"] if c in KEEP_CATEGORIES][:5] |
| desc = (row["short"] + " " + row["about"]).strip() |
| if aug and desc: |
| if rng.random() < 0.3 and (tags or genres): |
| desc = "" |
| else: |
| words = desc.split() |
| cut = int(len(words) * rng.uniform(0.3, 1.0)) if len(words) > 20 else len(words) |
| desc = " ".join(words[:cut]) |
|
|
| parts = [row["name"] + "."] |
| if genres: |
| parts.append("Genres: " + ", ".join(genres) + ".") |
| if tags: |
| parts.append("Tags: " + ", ".join(tags) + ".") |
| if cats: |
| parts.append("Modes: " + ", ".join(cats) + ".") |
| if len(row["developers"]): |
| parts.append("Developer: " + ", ".join(list(row["developers"])[:2]) + ".") |
| if desc: |
| parts.append(desc) |
| return " ".join(parts) |
|
|
