Upload eval/eval_bert_router.py

eval/eval_bert_router.py

@@ -0,0 +1,61 @@
+"""Evaluate BERT router on SWE-Router and compare with v11 XGBoost."""
+import json, os, sys, random, pickle, math
+import numpy as np
+from collections import defaultdict
+
+# ── Constants ──
+MODELS = ['claude-opus-4.7','gpt-5-mini','gpt-5-nano','gpt-5.2',
+          'gemini-2.5-pro','gemini-3-pro','deepseek-v3.2','deepseek-v4-flash']
+
+MODEL_TIER = {
+    'deepseek-v4-flash': 1, 'gpt-5-nano': 1,
+    'gpt-5-mini': 2, 'deepseek-v3.2': 2,
+    'gemini-2.5-pro': 3,
+    'claude-opus-4.7': 4, 'gpt-5.2': 4,
+    'gemini-3-pro': 5,
+}
+TIER_COST = {1:0.01, 2:0.05, 3:0.15, 4:0.30, 5:0.50}
+TIER_TO_SWE = {
+    1: 'deepseek-v4-flash', 2: 'gpt-5-mini',
+    3: 'gemini-2.5-pro', 4: 'claude-opus-4.7', 5: 'gemini-3-pro',
+}
+
+# ── Feature extraction (same as training) ──
+CODE_KW = ["python","javascript","code","function","bug","debug","refactor","implement","test",
+           "compile","runtime","segfault","thread","async","class","module","import","error","traceback"]
+LEGAL_KW = ["contract","legal","compliance","gdpr","privacy","policy","regulatory","liability"]
+RESEARCH_KW = ["research","investigate","compare","analyze","survey","paper"]
+TOOL_KW = ["search","fetch","retrieve","query","api","database","scrape","aggregate"]
+CRITICAL_KW = ["critical","production","urgent","emergency","live","deployed","safety","security"]
+SIMPLE_KW = ["typo","simple","quick","brief","minor","small","easy","trivial","just"]
+LONG_KW = ["plan","project","roadmap","orchestrate","migrate","pipeline","deploy","architecture"]
+MATH_KW = ["calculate","compute","solve","equation","formula","optimize","probability"]
+
+def extract_features(problem_text):
+    r = problem_text.lower()
+    feats = {
+        'req_len': len(problem_text), 'num_words': len(problem_text.split()),
+        'has_code': int(any(k in r for k in CODE_KW)),
+        'n_code': sum(1 for k in CODE_KW if k in r),
+        'has_legal': int(any(k in r for k in LEGAL_KW)),
+        'has_research': int(any(k in r for k in RESEARCH_KW)),
+        'has_tool': int(any(k in r for k in TOOL_KW)),
+        'has_critical': int(any(k in r for k in CRITICAL_KW)),
+        'has_simple': int(any(k in r for k in SIMPLE_KW)),
+        'has_long': int(any(k in r for k in LONG_KW)),
+        'has_math': int(any(k in r for k in MATH_KW)),
+        'has_error_msg': int('error' in r or 'traceback' in r or 'exception' in r),
+        'has_file_path': int('/' in r),
+        'n_lines': problem_text.count('\n') + 1,
+        'has_version': int('version' in r or 'update' in r or 'upgrade' in r),
+        'has_add': int('add' in r or 'new' in r or 'create' in r),
+        'has_fix': int('fix' in r or 'bug' in r or 'issue' in r or 'broken' in r),
+        'has_change': int('change' in r or 'modify' in r or 'update' in r),
+        'has_remove': int('remove' in r or 'delete' in r or 'drop' in r),
+        'has_test': int('test' in r or 'spec' in r or 'assert' in r),
+        'has_doc': int('doc' in r or 'readme' in r or 'comment' in r),
+    }
+    return feats
+
+print("BERT Router Evaluation on SWE-Router")
+print("="*60)