Fix confidence scores loading by using JSON instead of Node.js

BREAKING CHANGE: Switch from parsing JS file to using pure JSON

- Created confidence_scores.json from confidence_scores.js
- Removed Node.js dependency for loading confidence scores
- Added extensive debugging for file path resolution
- Added fallback path handling
- This eliminates the subprocess reliability issues in HF Spaces

The confidence scores should now load reliably without depending on Node.js subprocess execution.

app.py

@@ -216,32 +216,40 @@ if not os.path.exists(CAT_MAPPINGS_SAVE_PATH):
 with open(CAT_MAPPINGS_SAVE_PATH, 'r') as f:
     category_mappings = json.load(f)
 
-# Load confidence scores from confidence_scores.js
+# Load confidence scores directly from JSON file
 def load_confidence_scores():
-    """Load confidence scores from the JavaScript file"""
+    """Load confidence scores from confidence_scores.json"""
     try:
         # Get the directory where this script is located
         script_dir = os.path.dirname(os.path.abspath(__file__))
-        confidence_file = os.path.join(script_dir, 'confidence_scores.js')
+        confidence_file = os.path.join(script_dir, 'confidence_scores.json')
         
         print(f"📂 Script directory: {script_dir}")
         print(f"📂 Looking for confidence file at: {confidence_file}")
         print(f"📂 File exists: {os.path.exists(confidence_file)}")
         
-        result = subprocess.run([
-            'node', '-e', 
-            f'const conf = require("{confidence_file}"); console.log(JSON.stringify(conf.confidenceMapping));'
-        ], capture_output=True, text=True)
+        if not os.path.exists(confidence_file):
+            print(f"⚠️ Confidence file not found, trying fallback location...")
+            # Try current directory as fallback
+            confidence_file = 'confidence_scores.json'
+            print(f"📂 Fallback path: {confidence_file}")
+            print(f"📂 Fallback exists: {os.path.exists(confidence_file)}")
         
-        if result.returncode == 0:
-            confidence_data = json.loads(result.stdout.strip())
+        with open(confidence_file, 'r') as f:
+            confidence_data = json.load(f)
             print(f"✅ Successfully loaded {len(confidence_data)} confidence score combinations")
+            
+            # Print a sample to verify data
+            sample_key = list(confidence_data.keys())[0] if confidence_data else None
+            if sample_key:
+                print(f"📊 Sample entry: {sample_key} = {confidence_data[sample_key]}")
+            
             return confidence_data
-        else:
-            print(f"⚠️ Failed to load confidence scores: {result.stderr}")
-            print(f"⚠️ Return code: {result.returncode}")
-            print(f"⚠️ Stdout: {result.stdout}")
-            return {}
+    except FileNotFoundError as e:
+        print(f"❌ Confidence file not found: {e}")
+        print(f"📂 Current working directory: {os.getcwd()}")
+        print(f"📂 Files in script dir: {os.listdir(script_dir) if os.path.exists(script_dir) else 'N/A'}")
+        return {}
     except Exception as e:
         print(f"⚠️ Error loading confidence scores: {e}")
         import traceback
@@ -250,11 +258,18 @@ def load_confidence_scores():
 
 # Load confidence scores
 try:
+    print("=" * 50)
+    print("🚀 LOADING CONFIDENCE SCORES...")
+    print("=" * 50)
     confidence_scores = load_confidence_scores()
     print(f"✅ Confidence scores loaded successfully: {len(confidence_scores)} combinations")
+    print(f"🔍 confidence_scores is empty: {len(confidence_scores) == 0}")
+    print(f"🔍 confidence_scores type: {type(confidence_scores)}")
+    print("=" * 50)
 except Exception as e:
     print(f"⚠️ Error loading confidence scores: {e}")
     confidence_scores = {}
+    print(f"❌ confidence_scores set to empty dict: {confidence_scores}")
 
 def get_confidence_data(business_model, customer_type, conversion_type, industry, page_type):
     """Get confidence data based on Industry + Page Type combination (more reliable than 5-feature combinations)"""

confidence_scores.json

@@ -0,0 +1,554 @@
+{
+  "Automotive & Transportation|Awareness & Discovery": {
+    "accuracy": 0.6,
+    "count": 15,
+    "training_data_count": 135,
+    "correct_predictions": 9,
+    "actual_wins": 6,
+    "predicted_wins": 2
+  },
+  "Automotive & Transportation|Consideration & Evaluation": {
+    "accuracy": 0.667,
+    "count": 6,
+    "training_data_count": 54,
+    "correct_predictions": 4,
+    "actual_wins": 2,
+    "predicted_wins": 2
+  },
+  "Automotive & Transportation|Conversion": {
+    "accuracy": 1.0,
+    "count": 3,
+    "training_data_count": 27,
+    "correct_predictions": 3,
+    "actual_wins": 0,
+    "predicted_wins": 0
+  },
+  "Automotive & Transportation|Internal & Navigation": {
+    "accuracy": 0.571,
+    "count": 7,
+    "training_data_count": 63,
+    "correct_predictions": 4,
+    "actual_wins": 3,
+    "predicted_wins": 2
+  },
+  "B2B Services|Awareness & Discovery": {
+    "accuracy": 0.698,
+    "count": 483,
+    "training_data_count": 4347,
+    "correct_predictions": 337,
+    "actual_wins": 186,
+    "predicted_wins": 178
+  },
+  "B2B Services|Consideration & Evaluation": {
+    "accuracy": 0.657,
+    "count": 175,
+    "training_data_count": 1575,
+    "correct_predictions": 115,
+    "actual_wins": 82,
+    "predicted_wins": 78
+  },
+  "B2B Services|Conversion": {
+    "accuracy": 0.604,
+    "count": 53,
+    "training_data_count": 477,
+    "correct_predictions": 32,
+    "actual_wins": 26,
+    "predicted_wins": 23
+  },
+  "B2B Services|Internal & Navigation": {
+    "accuracy": 0.719,
+    "count": 139,
+    "training_data_count": 1251,
+    "correct_predictions": 100,
+    "actual_wins": 58,
+    "predicted_wins": 43
+  },
+  "B2B Services|Post-Conversion & Other": {
+    "accuracy": 0.571,
+    "count": 14,
+    "training_data_count": 126,
+    "correct_predictions": 8,
+    "actual_wins": 4,
+    "predicted_wins": 8
+  },
+  "B2B Software & Tech|Awareness & Discovery": {
+    "accuracy": 0.661,
+    "count": 1626,
+    "training_data_count": 14634,
+    "correct_predictions": 1074,
+    "actual_wins": 667,
+    "predicted_wins": 625
+  },
+  "B2B Software & Tech|Consideration & Evaluation": {
+    "accuracy": 0.617,
+    "count": 1046,
+    "training_data_count": 9414,
+    "correct_predictions": 645,
+    "actual_wins": 432,
+    "predicted_wins": 397
+  },
+  "B2B Software & Tech|Conversion": {
+    "accuracy": 0.647,
+    "count": 184,
+    "training_data_count": 1656,
+    "correct_predictions": 119,
+    "actual_wins": 71,
+    "predicted_wins": 74
+  },
+  "B2B Software & Tech|Internal & Navigation": {
+    "accuracy": 0.715,
+    "count": 376,
+    "training_data_count": 3384,
+    "correct_predictions": 269,
+    "actual_wins": 138,
+    "predicted_wins": 117
+  },
+  "B2B Software & Tech|Post-Conversion & Other": {
+    "accuracy": 0.78,
+    "count": 41,
+    "training_data_count": 369,
+    "correct_predictions": 32,
+    "actual_wins": 15,
+    "predicted_wins": 18
+  },
+  "Consumer Services|Awareness & Discovery": {
+    "accuracy": 0.723,
+    "count": 238,
+    "training_data_count": 2142,
+    "correct_predictions": 172,
+    "actual_wins": 97,
+    "predicted_wins": 85
+  },
+  "Consumer Services|Consideration & Evaluation": {
+    "accuracy": 0.592,
+    "count": 103,
+    "training_data_count": 927,
+    "correct_predictions": 61,
+    "actual_wins": 49,
+    "predicted_wins": 41
+  },
+  "Consumer Services|Conversion": {
+    "accuracy": 0.643,
+    "count": 42,
+    "training_data_count": 378,
+    "correct_predictions": 27,
+    "actual_wins": 12,
+    "predicted_wins": 13
+  },
+  "Consumer Services|Internal & Navigation": {
+    "accuracy": 0.607,
+    "count": 56,
+    "training_data_count": 504,
+    "correct_predictions": 34,
+    "actual_wins": 32,
+    "predicted_wins": 22
+  },
+  "Consumer Services|Post-Conversion & Other": {
+    "accuracy": 0.5,
+    "count": 2,
+    "training_data_count": 18,
+    "correct_predictions": 1,
+    "actual_wins": 1,
+    "predicted_wins": 0
+  },
+  "Consumer Software & Apps|Awareness & Discovery": {
+    "accuracy": 0.682,
+    "count": 22,
+    "training_data_count": 198,
+    "correct_predictions": 15,
+    "actual_wins": 5,
+    "predicted_wins": 8
+  },
+  "Consumer Software & Apps|Consideration & Evaluation": {
+    "accuracy": 0.9,
+    "count": 10,
+    "training_data_count": 90,
+    "correct_predictions": 9,
+    "actual_wins": 6,
+    "predicted_wins": 5
+  },
+  "Consumer Software & Apps|Conversion": {
+    "accuracy": 0.667,
+    "count": 15,
+    "training_data_count": 135,
+    "correct_predictions": 10,
+    "actual_wins": 5,
+    "predicted_wins": 6
+  },
+  "Consumer Software & Apps|Internal & Navigation": {
+    "accuracy": 0.2,
+    "count": 5,
+    "training_data_count": 45,
+    "correct_predictions": 1,
+    "actual_wins": 3,
+    "predicted_wins": 3
+  },
+  "Consumer Software & Apps|Post-Conversion & Other": {
+    "accuracy": 0.0,
+    "count": 1,
+    "training_data_count": 9,
+    "correct_predictions": 0,
+    "actual_wins": 1,
+    "predicted_wins": 0
+  },
+  "Education|Awareness & Discovery": {
+    "accuracy": 0.589,
+    "count": 409,
+    "training_data_count": 3681,
+    "correct_predictions": 241,
+    "actual_wins": 180,
+    "predicted_wins": 170
+  },
+  "Education|Consideration & Evaluation": {
+    "accuracy": 0.645,
+    "count": 183,
+    "training_data_count": 1647,
+    "correct_predictions": 118,
+    "actual_wins": 72,
+    "predicted_wins": 77
+  },
+  "Education|Conversion": {
+    "accuracy": 0.605,
+    "count": 43,
+    "training_data_count": 387,
+    "correct_predictions": 26,
+    "actual_wins": 16,
+    "predicted_wins": 17
+  },
+  "Education|Internal & Navigation": {
+    "accuracy": 0.661,
+    "count": 177,
+    "training_data_count": 1593,
+    "correct_predictions": 117,
+    "actual_wins": 70,
+    "predicted_wins": 62
+  },
+  "Education|Post-Conversion & Other": {
+    "accuracy": 0.308,
+    "count": 13,
+    "training_data_count": 117,
+    "correct_predictions": 4,
+    "actual_wins": 9,
+    "predicted_wins": 8
+  },
+  "Finance, Insurance & Real Estate|Awareness & Discovery": {
+    "accuracy": 0.662,
+    "count": 417,
+    "training_data_count": 3753,
+    "correct_predictions": 276,
+    "actual_wins": 172,
+    "predicted_wins": 147
+  },
+  "Finance, Insurance & Real Estate|Consideration & Evaluation": {
+    "accuracy": 0.596,
+    "count": 193,
+    "training_data_count": 1737,
+    "correct_predictions": 115,
+    "actual_wins": 82,
+    "predicted_wins": 78
+  },
+  "Finance, Insurance & Real Estate|Conversion": {
+    "accuracy": 0.615,
+    "count": 52,
+    "training_data_count": 468,
+    "correct_predictions": 32,
+    "actual_wins": 26,
+    "predicted_wins": 22
+  },
+  "Finance, Insurance & Real Estate|Internal & Navigation": {
+    "accuracy": 0.678,
+    "count": 177,
+    "training_data_count": 1593,
+    "correct_predictions": 120,
+    "actual_wins": 65,
+    "predicted_wins": 60
+  },
+  "Finance, Insurance & Real Estate|Post-Conversion & Other": {
+    "accuracy": 0.545,
+    "count": 22,
+    "training_data_count": 198,
+    "correct_predictions": 12,
+    "actual_wins": 13,
+    "predicted_wins": 7
+  },
+  "Food, Hospitality & Travel|Awareness & Discovery": {
+    "accuracy": 0.676,
+    "count": 293,
+    "training_data_count": 2637,
+    "correct_predictions": 198,
+    "actual_wins": 141,
+    "predicted_wins": 136
+  },
+  "Food, Hospitality & Travel|Consideration & Evaluation": {
+    "accuracy": 0.642,
+    "count": 159,
+    "training_data_count": 1431,
+    "correct_predictions": 102,
+    "actual_wins": 70,
+    "predicted_wins": 59
+  },
+  "Food, Hospitality & Travel|Conversion": {
+    "accuracy": 0.6,
+    "count": 60,
+    "training_data_count": 540,
+    "correct_predictions": 36,
+    "actual_wins": 31,
+    "predicted_wins": 27
+  },
+  "Food, Hospitality & Travel|Internal & Navigation": {
+    "accuracy": 0.63,
+    "count": 73,
+    "training_data_count": 657,
+    "correct_predictions": 46,
+    "actual_wins": 32,
+    "predicted_wins": 27
+  },
+  "Food, Hospitality & Travel|Post-Conversion & Other": {
+    "accuracy": 0.286,
+    "count": 7,
+    "training_data_count": 63,
+    "correct_predictions": 2,
+    "actual_wins": 2,
+    "predicted_wins": 5
+  },
+  "Health & Wellness|Awareness & Discovery": {
+    "accuracy": 0.631,
+    "count": 643,
+    "training_data_count": 5787,
+    "correct_predictions": 406,
+    "actual_wins": 262,
+    "predicted_wins": 249
+  },
+  "Health & Wellness|Consideration & Evaluation": {
+    "accuracy": 0.663,
+    "count": 389,
+    "training_data_count": 3501,
+    "correct_predictions": 258,
+    "actual_wins": 175,
+    "predicted_wins": 156
+  },
+  "Health & Wellness|Conversion": {
+    "accuracy": 0.632,
+    "count": 106,
+    "training_data_count": 954,
+    "correct_predictions": 67,
+    "actual_wins": 42,
+    "predicted_wins": 53
+  },
+  "Health & Wellness|Internal & Navigation": {
+    "accuracy": 0.654,
+    "count": 156,
+    "training_data_count": 1404,
+    "correct_predictions": 102,
+    "actual_wins": 72,
+    "predicted_wins": 58
+  },
+  "Health & Wellness|Post-Conversion & Other": {
+    "accuracy": 0.667,
+    "count": 12,
+    "training_data_count": 108,
+    "correct_predictions": 8,
+    "actual_wins": 5,
+    "predicted_wins": 3
+  },
+  "Industrial & Manufacturing|Awareness & Discovery": {
+    "accuracy": 0.573,
+    "count": 171,
+    "training_data_count": 1539,
+    "correct_predictions": 98,
+    "actual_wins": 75,
+    "predicted_wins": 82
+  },
+  "Industrial & Manufacturing|Consideration & Evaluation": {
+    "accuracy": 0.677,
+    "count": 93,
+    "training_data_count": 837,
+    "correct_predictions": 63,
+    "actual_wins": 34,
+    "predicted_wins": 32
+  },
+  "Industrial & Manufacturing|Conversion": {
+    "accuracy": 0.778,
+    "count": 18,
+    "training_data_count": 162,
+    "correct_predictions": 14,
+    "actual_wins": 6,
+    "predicted_wins": 10
+  },
+  "Industrial & Manufacturing|Internal & Navigation": {
+    "accuracy": 0.776,
+    "count": 67,
+    "training_data_count": 603,
+    "correct_predictions": 52,
+    "actual_wins": 25,
+    "predicted_wins": 28
+  },
+  "Industrial & Manufacturing|Post-Conversion & Other": {
+    "accuracy": 0.833,
+    "count": 6,
+    "training_data_count": 54,
+    "correct_predictions": 5,
+    "actual_wins": 4,
+    "predicted_wins": 5
+  },
+  "Media & Entertainment|Awareness & Discovery": {
+    "accuracy": 0.701,
+    "count": 251,
+    "training_data_count": 2259,
+    "correct_predictions": 176,
+    "actual_wins": 99,
+    "predicted_wins": 106
+  },
+  "Media & Entertainment|Consideration & Evaluation": {
+    "accuracy": 0.663,
+    "count": 95,
+    "training_data_count": 855,
+    "correct_predictions": 63,
+    "actual_wins": 28,
+    "predicted_wins": 32
+  },
+  "Media & Entertainment|Conversion": {
+    "accuracy": 0.792,
+    "count": 24,
+    "training_data_count": 216,
+    "correct_predictions": 19,
+    "actual_wins": 10,
+    "predicted_wins": 11
+  },
+  "Media & Entertainment|Internal & Navigation": {
+    "accuracy": 0.676,
+    "count": 68,
+    "training_data_count": 612,
+    "correct_predictions": 46,
+    "actual_wins": 24,
+    "predicted_wins": 18
+  },
+  "Media & Entertainment|Post-Conversion & Other": {
+    "accuracy": 0.6,
+    "count": 5,
+    "training_data_count": 45,
+    "correct_predictions": 3,
+    "actual_wins": 1,
+    "predicted_wins": 1
+  },
+  "Non-Profit & Government|Awareness & Discovery": {
+    "accuracy": 0.692,
+    "count": 107,
+    "training_data_count": 963,
+    "correct_predictions": 74,
+    "actual_wins": 36,
+    "predicted_wins": 37
+  },
+  "Non-Profit & Government|Consideration & Evaluation": {
+    "accuracy": 0.531,
+    "count": 32,
+    "training_data_count": 288,
+    "correct_predictions": 17,
+    "actual_wins": 12,
+    "predicted_wins": 11
+  },
+  "Non-Profit & Government|Conversion": {
+    "accuracy": 0.707,
+    "count": 92,
+    "training_data_count": 828,
+    "correct_predictions": 65,
+    "actual_wins": 29,
+    "predicted_wins": 22
+  },
+  "Non-Profit & Government|Internal & Navigation": {
+    "accuracy": 0.64,
+    "count": 50,
+    "training_data_count": 450,
+    "correct_predictions": 32,
+    "actual_wins": 23,
+    "predicted_wins": 21
+  },
+  "Non-Profit & Government|Post-Conversion & Other": {
+    "accuracy": 0.909,
+    "count": 11,
+    "training_data_count": 99,
+    "correct_predictions": 10,
+    "actual_wins": 4,
+    "predicted_wins": 3
+  },
+  "Other|Awareness & Discovery": {
+    "accuracy": 0.755,
+    "count": 53,
+    "training_data_count": 477,
+    "correct_predictions": 40,
+    "actual_wins": 24,
+    "predicted_wins": 21
+  },
+  "Other|Consideration & Evaluation": {
+    "accuracy": 0.385,
+    "count": 26,
+    "training_data_count": 234,
+    "correct_predictions": 10,
+    "actual_wins": 13,
+    "predicted_wins": 9
+  },
+  "Other|Conversion": {
+    "accuracy": 0.75,
+    "count": 4,
+    "training_data_count": 36,
+    "correct_predictions": 3,
+    "actual_wins": 2,
+    "predicted_wins": 3
+  },
+  "Other|Internal & Navigation": {
+    "accuracy": 0.4,
+    "count": 10,
+    "training_data_count": 90,
+    "correct_predictions": 4,
+    "actual_wins": 5,
+    "predicted_wins": 1
+  },
+  "Other|Post-Conversion & Other": {
+    "accuracy": 1.0,
+    "count": 1,
+    "training_data_count": 9,
+    "correct_predictions": 1,
+    "actual_wins": 1,
+    "predicted_wins": 1
+  },
+  "Retail & E-commerce|Awareness & Discovery": {
+    "accuracy": 0.645,
+    "count": 619,
+    "training_data_count": 5571,
+    "correct_predictions": 399,
+    "actual_wins": 309,
+    "predicted_wins": 239
+  },
+  "Retail & E-commerce|Consideration & Evaluation": {
+    "accuracy": 0.638,
+    "count": 718,
+    "training_data_count": 6462,
+    "correct_predictions": 458,
+    "actual_wins": 345,
+    "predicted_wins": 309
+  },
+  "Retail & E-commerce|Conversion": {
+    "accuracy": 0.661,
+    "count": 112,
+    "training_data_count": 1008,
+    "correct_predictions": 74,
+    "actual_wins": 58,
+    "predicted_wins": 60
+  },
+  "Retail & E-commerce|Internal & Navigation": {
+    "accuracy": 0.636,
+    "count": 154,
+    "training_data_count": 1386,
+    "correct_predictions": 98,
+    "actual_wins": 67,
+    "predicted_wins": 59
+  },
+  "Retail & E-commerce|Post-Conversion & Other": {
+    "accuracy": 1.0,
+    "count": 5,
+    "training_data_count": 45,
+    "correct_predictions": 5,
+    "actual_wins": 2,
+    "predicted_wins": 2
+  }
+}