Update script_for_automation.py

script_for_automation.py

@@ -1,4 +1,5 @@
 import requests 
+from jsondiff import diff
 
 # The purpose of this script is to automate running a bunch of tests
 # This script will take an input folder
@@ -23,10 +24,17 @@ import requests
 
 BASEROW_API_KEY = os.getenv("BASEROW_API_KEY")
 
-def get_baserow_data():
+def get_baserow_url(table_id): 
     BASEROW_API_BASE = "https://baserow.f11804a1.federatedcomputer.net/api"
+    return f"{BASEROW_API_BASE}/database/rows/table/{table_id}/?user_field_names=true"
+
+def get_baserow_data():
+    # This is to get the gold standards from baserow
+    # We will also get the input data 
+    
     TABLE_ID = "560"
-    baserow_url = f"{BASEROW_API_BASE}/database/rows/table/{TABLE_ID}/?user_field_names=true"
+
+    BASEROW_URL = get_baserow_url(TABLE_ID)
 
     headers = {
         "Authorization": f"Token {os.environ["BASEROW_API_KEY"]}",
@@ -34,7 +42,7 @@ def get_baserow_data():
     }
     
     try: 
-        response = requests.get(baserow_url, headers=headers)
+        response = requests.get(BASEROW_URL, headers=headers)
         response.raise_for_status()
         rows = response.json()
         results = rows.get("results", [])
@@ -46,26 +54,177 @@ def get_baserow_data():
                 liz_carrot_plantings_gold_standard = row.get("Plantings and Fields - Gold Standard")
                 liz_carrot_interactions_gold_standard = row.get("Interactions - Gold Standard")
                 liz_carrot_trials_gold_standard = row.get("Trials - Gold Standard")
+                
+                liz_carrot_input_data_raw_interview = row.get("Raw Interview")
+                liz_carrot_otter_summary_preprocessing = row.get("Otter Summary")
+                liz_carrot_greg_summary_preprocessing = row.get("Post-Interview Summary")
             elif row.get("id") == 3:
                 ben_soybean_plantings_gold_standard = row.get("Plantings and Fields - Gold Standard")
                 ben_soybean_interactions_gold_standard = row.get("Interactions - Gold Standard")
                 ben_soybean_trials_gold_standard = row.get("Trials - Gold Standard")
+                
+                ben_soybean_input_data_raw_interview = row.get("Raw Interview")
+                ben_soybean_otter_summary_preprocessing = row.get("Otter Summary")
+                ben_soybean_greg_summary_preprocessing = row.get("Post-Interview Summary")
             elif row.get("id") == 5:
                 wally_squash_plantings_gold_standard = row.get("Plantings and Fields - Gold Standard")
                 wally_squash_interactions_gold_standard = row.get("Interactions - Gold Standard")
                 wally_squash_trials_gold_standard = row.get("Trials - Gold Standard")
+                
+                wally_squash_input_data_raw_interview = row.get("Raw Interview")
+                wally_squash_otter_summary_preprocessing = row.get("Otter Summary")
+                wally_squash_greg_summary_preprocessing = row.get("Post-Interview Summary")
+
+        gold_standards = {
+            "planting_gold_standards": {
+                "liz_carrot": liz_carrot_plantings_gold_standard,
+                "ben_soybean": ben_soybean_plantings_gold_standard,
+                "wally_squash": wally_squash_plantings_gold_standard
+            },
+            "interactions_gold_standards": {
+                "liz_carrot": liz_carrot_interactions_gold_standard,
+                "ben_soybean": ben_soybean_interactions_gold_standard,
+                "wally_squash": wally_squash_interactions_gold_standard
+            },
+            "trial_gold_standards": {
+                "liz_carrot": liz_carrot_trials_gold_standard,
+                "ben_soybean": ben_soybean_trials_gold_standard,
+                "wally_squash": wally_squash_trials_gold_standard
+            }
+        }
 
-        result_list = [
-            liz_carrot_plantings_gold_standard, liz_carrot_interactions_gold_standard, liz_carrot_trials_gold_standard,
-            ben_soybean_plantings_gold_standard, ben_soybean_interactions_gold_standard, ben_soybean_trials_gold_standard,
-            wally_squash_plantings_gold_standard, wally_squash_interactions_gold_standard, wally_squash_trials_gold_standard
-        ]
+        # How to retrieve this data
+        # liz_carrot_planting = gold_standards["planting_gold_standards"]["liz_carrot"]
+        # ben_soybean_interactions = gold_standards["interactions_gold_standards"]["ben_soybean"]
+        # wally_squash_trial = gold_standards["trial_gold_standards"]["wally_squash"]
 
-        return result_list
+        input_data = {
+            "raw_interview": {
+                "liz_carrot": liz_carrot_input_data_raw_interview,
+                "ben_soybean": ben_soybean_input_data_raw_interview,
+                "wally_squash": wally_squash_input_data_raw_interview
+            },
+            "otter_summary": {
+                "liz_carrot": liz_carrot_otter_summary_preprocessing,
+                "ben_soybean": ben_soybean_otter_summary_preprocessing,
+                "wally_squash": wally_squash_otter_summary_preprocessing
+            },
+            "summary": {
+                "liz_carrot": liz_carrot_greg_summary_preprocessing,
+                "ben_soybean": ben_soybean_greg_summary_preprocessing,
+                "wally_squash": wally_squash_greg_summary_preprocessing
+            }
+        }
+        
+        return gold_standards, input_data
 
     except requests.exceptions.RequestException as e: 
         print(f"Failed to fetch rows: {e}")
     
+def get_recipes():
+    TABLE_ID = "578"
+
+    BASEROW_URL = get_baserow_url(TABLE_ID)
+
+    headers = {
+        "Authorization": f"Token {os.environ["BASEROW_API_KEY"]}",
+        "Content-Type": "application/json"
+    }
     
+    try: 
+        response = requests.get(BASEROW_URL, headers=headers)
+        response.raise_for_status()
+        rows = response.json()
+        results = rows.get("results", [])
+
+        my_recipes = []
+        for row in results: 
+            print(f"Row ID: {row.get('id')}, Data: {row}")
+            recipe_schema_processing_model = row.get("Schema Processing Model")
+            pre_processing_strategy = row.get("Pre-Processing Strategy")
+            pre_processing_text = row.get("Preprocessing Model")
+            prompting_strategy = row.get("Prompting Strategy")
+            plantings_and_fields_prompt = row.get("Plantings and Fields Prompting Text")
+            interactions_prompt = row.get("Interactions Prompting Text")
+            treatments_prompt = row.get("Treatments Prompting Text")
+
+            recipe_dict = {
+                "schema_processing_model": recipe_schema_processing_model,
+                "pre_processing_strategy": pre_processing_strategy,
+                "pre_processing_text": pre_processing_text,
+                "prompting_strategy": prompting_strategy,
+                "plantings_and_fields_prompt": plantings_and_fields_prompt,
+                "interactions_prompt": interactions_prompt,
+                "treatments_prompt": treatments_prompt
+            }
+            
+            my_recipes.append(recipe_dict)
+
+        return my_recipes    
+
+    except requests.exceptions.RequestException as e: 
+        print(f"Failed to fetch rows: {e}")
+
+def fill_out_survey(recipe_dict, input_data): 
+    survey_id = "673b4994aef86f0533b3546c"
     
+    base_url = "https://app.surveystack.io/api/submissions"
+
+    if recipe_dict.get("pre_processing_text") is None:
+        pre_processing = False
+        pre_process = "no"
+        pre_process_model_version = "None"
 
+    # Set the prompting strategy to be a variable from the list 
+    # Do this here 
+    
+    if pre_processing: 
+        submission_data = {
+            "survey": survey_id, 
+            "data": {
+                "inputstyle": "big-block-input-text",
+                "onelonginputtext": recipe_dict["schema_processing_model"],
+                "schema_prompt": {
+                    "firstschemaprompt": recipe_dict["plantings_and_fields_prompt"],
+                    "secondschemaprompt": recipe_dict["interactions_prompt"],
+                    "thirdschemaprompt": recipe_dict["treatments_prompt"],
+                },
+                "parameters": {
+                    "model_version": recipe_dict["schema_processing_model"],
+                    "pre_process": ["yes"],
+                    "promptstyle": recipe_dict["prompting_strategy"], # replace this one
+                    "preprocessmodelversion": "2.0",
+                    "multiplepreprompts": "no",
+                    "prepromptstyle": recipe_dict["pre_processing_strategy"],
+                    "preprocessingprompt1": recipe_dict["pre_processing_text"],
+                }
+            }
+        }
+        
+    else: 
+        submission_data = {
+            "survey": survey_id, 
+            "data": {
+                "inputstyle": "big-block-input-text",
+                "onelonginputtext": recipe_dict["schema_processing_model"],
+                "schema_prompt": {
+                    "firstschemaprompt": recipe_dict["plantings_and_fields_prompt"],
+                    "secondschemaprompt": recipe_dict["interactions_prompt"],
+                    "thirdschemaprompt": recipe_dict["treatments_prompt"],
+                },
+                "parameters": {
+                    "model_version": recipe_dict["schema_processing_model"],
+                    "pre_process": "no",
+                    "prompt_style": recipe_dict["prompting_strategy"], # replace this one
+                }
+            }
+        }
+        
+    
+    
+    return "pumpkin"
+    
+def drive_process(): 
+    # this is to drive the processing process 
+    return "banana"
+