Add Deep Learning (LSTM) + Quick Wins automation features

Major improvements:
- Deep Learning integration with PyTorch LSTM (dual models: main 1-50 + euro 1-12)
- Hybrid predictor: 40% RandomForest + 60% Deep Learning
- LaunchAgent for automatic weekly tip generation (Mon/Thu 21:00)
- Health-Check system with auto-recovery and Telegram alerts
- Fixed health checks for Eurojackpot-specific paths and file names
- Model caching and intelligent retraining logic
- Updated CSV data and generated tips
- Performance reports for recent draws

Technical details:
- PyTorch used instead of TensorFlow (Python 3.14 compatibility)
- Separate LSTM models for main numbers (1-50) and euro numbers (1-12)
- Apple Silicon MPS acceleration support
- Sequence learning with 20-draw history
- Health-check adapted for eurojackpot_ml_models/ and learning_log.json

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

data/eurojackpot_ml_models/deep_learning_euro/lstm_config_12.json

@@ -0,0 +1,9 @@
+{
+  "trained_at": "2026-01-06T21:00:43.268063",
+  "num_samples": 895,
+  "num_features": 20,
+  "final_loss": 0.3324819803237915,
+  "final_val_loss": 0.3310294995705287,
+  "best_val_loss": 0.3291587332884471,
+  "epochs_trained": 25
+}

data/eurojackpot_ml_models/deep_learning_main/lstm_config_50.json

@@ -0,0 +1,9 @@
+{
+  "trained_at": "2026-01-06T21:00:33.679894",
+  "num_samples": 895,
+  "num_features": 20,
+  "final_loss": 0.33361901148505835,
+  "final_val_loss": 0.33026839792728424,
+  "best_val_loss": 0.32894887030124664,
+  "epochs_trained": 21
+}

data/eurojackpot_ml_models/learning_state.json

@@ -0,0 +1,78 @@
+{
+  "adjustments_main": {
+    "1": -0.014850499375000001,
+    "2": -0.014850499375000001,
+    "3": -0.014850499375000001,
+    "4": -0.014850499375000001,
+    "5": -0.014850499375000001,
+    "6": -0.014850499375000001,
+    "7": -0.014850499375000001,
+    "8": -0.014850499375000001,
+    "9": -0.014850499375000001,
+    "10": 0.014775998750000002,
+    "11": -0.014850499375000001,
+    "12": -0.014850499375000001,
+    "13": -0.014850499375000001,
+    "14": -0.014850499375000001,
+    "15": 0.014775998750000002,
+    "16": -0.014850499375000001,
+    "17": -0.014850499375000001,
+    "18": -0.014850499375000001,
+    "19": -0.014850499375000001,
+    "20": -0.014850499375000001,
+    "21": 7.450062499999855e-05,
+    "22": -0.014850499375000001,
+    "23": 7.450062499999855e-05,
+    "24": -0.014850499375000001,
+    "25": -0.014850499375000001,
+    "26": -0.014850499375000001,
+    "27": -0.014850499375000001,
+    "28": -0.014850499375000001,
+    "29": 0.014775998750000002,
+    "30": 7.450062499999855e-05,
+    "31": -0.014850499375000001,
+    "32": -0.014850499375000001,
+    "33": 7.450062499999855e-05,
+    "34": 0.014775998750000002,
+    "35": -0.014850499375000001,
+    "36": -0.014850499375000001,
+    "37": -0.014850499375000001,
+    "38": 0.029700998750000002,
+    "39": -0.014850499375000001,
+    "40": -0.014850499375000001,
+    "41": -0.014850499375000001,
+    "42": -0.014850499375000001,
+    "43": -0.014850499375000001,
+    "44": -0.014850499375000001,
+    "45": -0.014850499375000001,
+    "46": -0.014850499375000001,
+    "47": -0.014850499375000001,
+    "48": -0.014850499375000001,
+    "49": -0.014850499375000001,
+    "50": -0.014850499375000001
+  },
+  "adjustments_euro": {
+    "1": -0.014850499375000001,
+    "2": 0.014775998750000002,
+    "3": -0.014850499375000001,
+    "4": -0.014850499375000001,
+    "5": -0.014850499375000001,
+    "6": -0.014850499375000001,
+    "7": -0.014850499375000001,
+    "8": 7.450062499999855e-05,
+    "9": 0.014775998750000002,
+    "10": -0.014850499375000001,
+    "11": -0.014850499375000001,
+    "12": 7.450062499999855e-05
+  },
+  "stats": {
+    "incorrect_main": 135,
+    "correct_main": 15,
+    "incorrect_euro": 30,
+    "correct_euro": 6,
+    "cycles": 3,
+    "last_update": "2026-01-06T21:00:43.269037"
+  },
+  "learning_rate": 0.1,
+  "last_saved": "2026-01-06T21:00:43.269127"
+}