Update script_for_automation.py

script_for_automation.py

@@ -408,20 +408,13 @@ def generate_markdown_output(df):
     for _, row in df.iterrows():
         markdown += f"\n### Recipe ID: {row['Recipe_ID']}\n"
         for key in ["planting", "interactions", "trials"]:
-            # Safely get YAML data
-            gold_yaml = yaml.dump(row['Gold_Standard_YAML'].get(key, {}), default_flow_style=False, sort_keys=True)
-            machine_yaml = yaml.dump(row['Machine_Generated_YAML'].get(key, {}), default_flow_style=False, sort_keys=True)
-    
-            # Add proper line breaks between YAML blocks
-            gold_yaml = "\n".join([line for line in gold_yaml.splitlines()])  # Ensure clean output
-            machine_yaml = "\n".join([line for line in machine_yaml.splitlines()])
-    
-            # Add Markdown table
+            gold = yaml.dumps(row['Gold_Standard_JSON'].get(key, {}), indent=2)
+            machine = yaml.dumps(row['Machine_Generated_JSON'].get(key, {}), indent=2)
             markdown += f"#### {key.capitalize()}\n"
             markdown += "| Type | YAML Content |\n"
             markdown += "|------|--------------|\n"
-            markdown += f"| Gold Standard | ```yaml\n{gold_yaml}\n``` |\n"
-            markdown += f"| Machine Generated | ```yaml\n{machine_yaml}\n``` |\n"
+            markdown += f"| Gold Standard | ```yaml\n{gold}\n``` |\n"
+            markdown += f"| Machine Generated | ```yaml\n{machine}\n``` |\n"
     
     return markdown
 
@@ -506,26 +499,6 @@ def drive_process():
             differences_interactions = list(diff(gold_standard_interactions_json, processed_interactions_json))
             differences_trials = list(diff(gold_standard_trials_json, processed_trials_json))
 
-            print("yaml world")
-            
-            # Convert to yaml
-            completed_gold_standard_planting_json = sanitize_json_for_yaml(gold_standard_planting_json)
-            completed_gold_standard_interactions_json = sanitize_json_for_yaml(gold_standard_interactions_json)
-            completed_gold_standard_trials_json = sanitize_json_for_yaml(gold_standard_trials_json)
-
-            completed_processed_farm_activity_json = sanitize_json_for_yaml(processed_farm_activity_json)
-            completed_processed_interactions_json = sanitize_json_for_yaml(processed_interactions_json)
-            completed_processed_trials_json = sanitize_json_for_yaml(processed_trials_json)
-
-            completed_gold_standard_planting_yaml = yaml.safe_load(completed_gold_standard_planting_json)
-            completed_gold_standard_interactions_yaml = yaml.safe_load(completed_gold_standard_interactions_json)
-            completed_gold_standard_trials_yaml = yaml.safe_load(completed_gold_standard_trials_json)
-
-            completed_comparison_planting_yaml = yaml.safe_load(completed_processed_farm_activity_json)
-            completed_comparison_interactions_yaml = yaml.safe_load(completed_processed_interactions_json)
-            completed_comparison_trials_yaml = yaml.safe_load(completed_processed_trials_json)
-            
-
             json_diff = {
                 "planting": differences_planting,
                 "interactions": differences_interactions,
@@ -571,9 +544,7 @@ def drive_process():
                 "Input_Transcript": input_chunks,  
                 "Gold_Standard_JSON": gold_standard_json,
                 "Machine_Generated_JSON": comparison_json,
-                "Differences": json_diff,
-                "Gold_Standard_YAML": gold_standard_yaml,
-                "Machine_Generated_YAML": comparison_yaml
+                "Differences": json_diff
             })
 
             df = pd.DataFrame(output_rows)