Improve generator quality and sync data (May 2026)

Data:
- Add missing draw 2026-05-16 (7 11 20 23 27 30 SZ:9) via GitHub archive
- Run retroactive learning for skipped 2026-01-07 draw

Generator improvements (ported from Eurojackpot):
- Add hard structural filters (sum 100-200, min 1 even + 1 odd per tip)
- Add long-term frequency prior as learner dampener (alpha=0.2)
- Fix ENSEMBLE strategy generating duplicate tips (greedy → weighted random)
- Fix Division-by-Zero edge case in set_frequency_prior
- Fix freq_alpha boundary and clip final adjusted value to [0,1]
- Prevent negative weights in random.choices (floor at 0.001)
- Use vectorized stack().value_counts() for frequency calculation

.gitignore:
- Exclude data/backups/, weekly tip CSVs, performance reports, data/data/

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

data/ultimate_ml_models/deep_learning/lstm_config_49.json

@@ -1,9 +1,9 @@
 {
-  "trained_at": "2026-02-04T09:51:16.756987",
-  "num_samples": 3076,
+  "trained_at": "2026-05-19T12:56:08.778673",
+  "num_samples": 3106,
   "num_features": 20,
-  "final_loss": 0.3723479768672547,
-  "final_val_loss": 0.3735503777861595,
-  "best_val_loss": 0.3733456790447235,
+  "final_loss": 0.3726997012511278,
+  "final_val_loss": 0.37363722175359726,
+  "best_val_loss": 0.373420712351799,
   "epochs_trained": 30
 }