| 1 | #!/usr/bin/env python3 |
| 2 | """Hype risk scoring model for SquadScope. |
| 3 | |
| 4 | Classifies repos based on the relationship between press coverage |
| 5 | and GitHub activity patterns. |
| 6 | """ |
| 7 | |
| 8 | from __future__ import annotations |
| 9 | |
| 10 | import argparse |
| 11 | import json |
| 12 | import sys |
| 13 | from pathlib import Path |
| 14 | |
| 15 | sys.path.insert(0, str(Path(__file__).resolve().parent)) |
| 16 | |
| 17 | |
| 18 | # Risk level definitions |
| 19 | RISK_LEVELS = { |
| 20 | "very_low": "Organic growth", |
| 21 | "low": "Press-validated, community-sustained", |
| 22 | "medium": "Announced but unbuilt", |
| 23 | "high": "Press-driven hype, fading", |
| 24 | "none": "No press signal", |
| 25 | } |
| 26 | |
| 27 | |
| 28 | def classify_repo( |
| 29 | repo_name: str, |
| 30 | press_correlated: bool, |
| 31 | current_stars: int | None = None, |
| 32 | current_stars_gained: int | None = None, |
| 33 | previous_stars: int | None = None, |
| 34 | previous_stars_gained: int | None = None, |
| 35 | ) -> dict: |
| 36 | """Classify a single repo's hype risk. |
| 37 | |
| 38 | Returns an assessment dict with risk level, label, confidence, and reasoning. |
| 39 | """ |
| 40 | if not press_correlated: |
| 41 | return _assessment( |
| 42 | repo_name, |
| 43 | risk="none", |
| 44 | press_correlated=False, |
| 45 | stars_trend="unknown", |
| 46 | confidence=0.9, |
| 47 | reasoning="No press correlation detected", |
| 48 | ) |
| 49 | |
| 50 | # Press correlated but no previous data |
| 51 | if previous_stars is None or previous_stars_gained is None: |
| 52 | return _assessment( |
| 53 | repo_name, |
| 54 | risk="medium", |
| 55 | press_correlated=True, |
| 56 | stars_trend="unknown", |
| 57 | confidence=0.4, |
| 58 | reasoning="Press correlated but insufficient historical data to assess sustainability", |
| 59 | ) |
| 60 | |
| 61 | # Press correlated with previous data available |
| 62 | current_gained = current_stars_gained or 0 |
| 63 | previous_gained = previous_stars_gained or 0 |
| 64 | |
| 65 | # Check decay first: previous spike much larger than current → fading |
| 66 | if previous_gained > 0 and current_gained < previous_gained * 0.5: |
| 67 | return _assessment( |
| 68 | repo_name, |
| 69 | risk="high", |
| 70 | press_correlated=True, |
| 71 | stars_trend="decaying", |
| 72 | confidence=0.7, |
| 73 | reasoning=( |
| 74 | f"Stars spiked after press but are fading " |
| 75 | f"(previous: +{previous_gained}, current: +{current_gained})" |
| 76 | ), |
| 77 | ) |
| 78 | |
| 79 | # Check if stars were already growing before press (organic) |
| 80 | if previous_gained > 0 and current_gained > 0: |
| 81 | if previous_gained >= current_gained * 0.5: |
| 82 | # Growth was already happening before press |
| 83 | return _assessment( |
| 84 | repo_name, |
| 85 | risk="very_low", |
| 86 | press_correlated=True, |
| 87 | stars_trend="organic", |
| 88 | confidence=0.8, |
| 89 | reasoning=( |
| 90 | f"Stars were already growing before press coverage " |
| 91 | f"(previous: +{previous_gained}, current: +{current_gained})" |
| 92 | ), |
| 93 | ) |
| 94 | |
| 95 | # Stars spiked after article - check sustainability |
| 96 | if current_gained > 0 and previous_gained >= 0: |
| 97 | total_recent_gain = current_gained + previous_gained |
| 98 | if total_recent_gain > 0 and current_gained > total_recent_gain * 0.5: |
| 99 | # Current week still has significant growth - sustained |
| 100 | return _assessment( |
| 101 | repo_name, |
| 102 | risk="low", |
| 103 | press_correlated=True, |
| 104 | stars_trend="sustained", |
| 105 | confidence=0.75, |
| 106 | reasoning=( |
| 107 | f"Stars grew after press coverage and maintained " |
| 108 | f"(+{current_gained} this week, +{previous_gained} previous)" |
| 109 | ), |
| 110 | ) |
| 111 | |
| 112 | # Fallback: press correlated but no clear activity spike |
| 113 | return _assessment( |
| 114 | repo_name, |
| 115 | risk="medium", |
| 116 | press_correlated=True, |
| 117 | stars_trend="flat", |
| 118 | confidence=0.5, |
| 119 | reasoning="Press coverage detected but no significant GitHub activity spike", |
| 120 | ) |
| 121 | |
| 122 | |
| 123 | def _assessment( |
| 124 | repo: str, |
| 125 | risk: str, |
| 126 | press_correlated: bool, |
| 127 | stars_trend: str, |
| 128 | confidence: float, |
| 129 | reasoning: str, |
| 130 | ) -> dict: |
| 131 | return { |
| 132 | "repo": repo, |
| 133 | "hype_risk": risk, |
| 134 | "label": RISK_LEVELS[risk], |
| 135 | "press_correlated": press_correlated, |
| 136 | "stars_trend": stars_trend, |
| 137 | "confidence": confidence, |
| 138 | "reasoning": reasoning, |
| 139 | } |
| 140 | |
| 141 | |
| 142 | def _find_repo_in_raw(raw_repos: list[dict], repo_name: str) -> dict | None: |
| 143 | """Find a repo entry in raw data by name.""" |
| 144 | for repo in raw_repos: |
| 145 | name = repo.get("full_name") or repo.get("repo") or repo.get("name", "") |
| 146 | if name == repo_name: |
| 147 | return repo |
| 148 | return None |
| 149 | |
| 150 | |
| 151 | def score_hype_risk( |
| 152 | correlations: dict, |
| 153 | raw_data: dict | list | None = None, |
| 154 | previous_data: dict | list | None = None, |
| 155 | ) -> list[dict]: |
| 156 | """Score hype risk for all repos in correlations data. |
| 157 | |
| 158 | Args: |
| 159 | correlations: Correlation analysis output with correlated repos. |
| 160 | raw_data: Current week raw GitHub data. |
| 161 | previous_data: Previous week raw GitHub data. |
| 162 | |
| 163 | Returns: |
| 164 | List of assessment dicts. |
| 165 | """ |
| 166 | # Extract correlated repos |
| 167 | correlated_repos = set() |
| 168 | corr_entries = correlations.get("correlations", correlations.get("repos", [])) |
| 169 | if isinstance(corr_entries, list): |
| 170 | for entry in corr_entries: |
| 171 | repo_name = entry.get("repo") or entry.get("full_name", "") |
| 172 | if entry.get("press_correlated", False): |
| 173 | correlated_repos.add(repo_name) |
| 174 | |
| 175 | # Normalize raw data to lists |
| 176 | raw_repos = _normalize_raw(raw_data) |
| 177 | prev_repos = _normalize_raw(previous_data) |
| 178 | |
| 179 | # Collect all repo names from raw data |
| 180 | all_repos = set() |
| 181 | for repo in raw_repos: |
| 182 | name = repo.get("full_name") or repo.get("repo") or repo.get("name", "") |
| 183 | if name: |
| 184 | all_repos.add(name) |
| 185 | # Also include correlated repos even if not in current raw |
| 186 | all_repos.update(correlated_repos) |
| 187 | |
| 188 | assessments = [] |
| 189 | for repo_name in sorted(all_repos): |
| 190 | press_correlated = repo_name in correlated_repos |
| 191 | |
| 192 | current = _find_repo_in_raw(raw_repos, repo_name) |
| 193 | previous = _find_repo_in_raw(prev_repos, repo_name) |
| 194 | |
| 195 | current_stars = current.get("stars") if current else None |
| 196 | current_gained = current.get("stars_gained") if current else None |
| 197 | prev_stars = previous.get("stars") if previous else None |
| 198 | prev_gained = previous.get("stars_gained") if previous else None |
| 199 | |
| 200 | assessment = classify_repo( |
| 201 | repo_name, |
| 202 | press_correlated=press_correlated, |
| 203 | current_stars=current_stars, |
| 204 | current_stars_gained=current_gained, |
| 205 | previous_stars=prev_stars, |
| 206 | previous_stars_gained=prev_gained, |
| 207 | ) |
| 208 | assessments.append(assessment) |
| 209 | |
| 210 | return assessments |
| 211 | |
| 212 | |
| 213 | def _normalize_raw(data: dict | list | None) -> list[dict]: |
| 214 | """Normalize raw data to a list of repo dicts.""" |
| 215 | if data is None: |
| 216 | return [] |
| 217 | if isinstance(data, list): |
| 218 | return data |
| 219 | # Could be wrapped in a dict with 'repos' or 'repositories' key |
| 220 | if isinstance(data, dict): |
| 221 | for key in ("repos", "repositories", "items"): |
| 222 | if key in data and isinstance(data[key], list): |
| 223 | return data[key] |
| 224 | return [] |
| 225 | return [] |
| 226 | |
| 227 | |
| 228 | def extract_week(filepath: str | Path | None) -> str: |
| 229 | """Try to extract week identifier from a filepath like 2026-W21.json.""" |
| 230 | if filepath is None: |
| 231 | return "unknown" |
| 232 | name = Path(filepath).stem |
| 233 | # Remove suffixes like -correlations, -hype-risk |
| 234 | for suffix in ("-correlations", "-hype-risk", "-metrics"): |
| 235 | if name.endswith(suffix): |
| 236 | name = name[: -len(suffix)] |
| 237 | return name |
| 238 | |
| 239 | |
| 240 | def main(argv: list[str] | None = None) -> None: |
| 241 | parser = argparse.ArgumentParser(description="Hype risk scoring model") |
| 242 | parser.add_argument( |
| 243 | "--correlations", |
| 244 | help="Path to correlations JSON file", |
| 245 | ) |
| 246 | parser.add_argument( |
| 247 | "--raw", |
| 248 | help="Path to current week raw data JSON", |
| 249 | ) |
| 250 | parser.add_argument( |
| 251 | "--previous", |
| 252 | help="Path to previous week raw data JSON", |
| 253 | ) |
| 254 | parser.add_argument( |
| 255 | "--output", |
| 256 | help="Output path for hype risk JSON", |
| 257 | ) |
| 258 | parser.add_argument( |
| 259 | "--topic", |
| 260 | help="Topic ID for path resolution", |
| 261 | ) |
| 262 | args = parser.parse_args(argv) |
| 263 | |
| 264 | # Resolve paths |
| 265 | corr_path = Path(args.correlations) if args.correlations else None |
| 266 | raw_path = Path(args.raw) if args.raw else None |
| 267 | prev_path = Path(args.previous) if args.previous else None |
| 268 | out_path = Path(args.output) if args.output else None |
| 269 | |
| 270 | if corr_path is None: |
| 271 | print("Error: --correlations is required", file=sys.stderr) |
| 272 | sys.exit(1) |
| 273 | |
| 274 | # Load data |
| 275 | with open(corr_path, encoding="utf-8") as f: |
| 276 | correlations = json.load(f) |
| 277 | |
| 278 | raw_data = None |
| 279 | if raw_path and raw_path.exists(): |
| 280 | with open(raw_path, encoding="utf-8") as f: |
| 281 | raw_data = json.load(f) |
| 282 | |
| 283 | previous_data = None |
| 284 | if prev_path and prev_path.exists(): |
| 285 | with open(prev_path, encoding="utf-8") as f: |
| 286 | previous_data = json.load(f) |
| 287 | |
| 288 | # Score |
| 289 | assessments = score_hype_risk(correlations, raw_data, previous_data) |
| 290 | |
| 291 | # Build output |
| 292 | week = extract_week(args.raw or args.correlations) |
| 293 | output = { |
| 294 | "week": week, |
| 295 | "assessments": assessments, |
| 296 | } |
| 297 | |
| 298 | # Write or print |
| 299 | if out_path: |
| 300 | out_path.parent.mkdir(parents=True, exist_ok=True) |
| 301 | with open(out_path, "w", encoding="utf-8") as f: |
| 302 | json.dump(output, f, indent=2) |
| 303 | print(f"Wrote {len(assessments)} assessments to {out_path}") |
| 304 | else: |
| 305 | print(json.dumps(output, indent=2)) |
| 306 | |
| 307 | |
| 308 | if __name__ == "__main__": |
| 309 | main() |