feat: implement comprehensive land cover classification pipeline with model benchmarking and experiment logging

generate_report_only.py

@@ -26,7 +26,23 @@ if os.path.exists("model_xgboost_info.json"):
 for info_file in glob.glob("model_train/*_info.json"):
     with open(info_file, 'r') as f:
         data = json.load(f)
-        if 'accuracy' not in data and 'f1_score' not in data:
+        # Support both 'accuracy' and 'test_accuracy'
+        acc = data.get('accuracy', data.get('test_accuracy', ''))
+        
+        f1 = data.get('f1_score', '')
+        precision = data.get('precision', '')
+        recall = data.get('recall', '')
+        
+        clf_rep = data.get('classification_report')
+        if isinstance(clf_rep, dict) and 'macro avg' in clf_rep:
+            if not f1:
+                f1 = clf_rep['macro avg'].get('f1-score', '')
+            if not precision:
+                precision = clf_rep['macro avg'].get('precision', '')
+            if not recall:
+                recall = clf_rep['macro avg'].get('recall', '')
+            
+        if not acc and not f1:
             continue
             
         params = data.get('params', {})
@@ -37,10 +53,10 @@ for info_file in glob.glob("model_train/*_info.json"):
             
         land_data.append([
             data.get('model_type', ''),
-            data.get('accuracy', ''),
-            data.get('precision', ''),
-            data.get('recall', ''),
-            data.get('f1_score', ''),
+            acc,
+            precision,
+            recall,
+            f1,
             param_str
         ])