Upload 2 files

app.py

@@ -8,6 +8,7 @@ import openai
 from openai import OpenAI
 import gradio as gr
 import huggingface_hub
+from datasets import load_dataset
 
 api_key = os.environ.get("API_TOKEN")
 headers = {
@@ -15,17 +16,8 @@ headers = {
     'Content-Type': 'application/json'
 }
 
-DATASET_REPO_URL = "https://huggingface.co/datasets/petcoblue/simulation_data"
-DATA_FILENAME = "user_agents.csv"
-DATA_FILE = os.path.join("data", DATA_FILENAME)
-
-# HF_TOKEN = os.environ.get("HF_TOKEN")
-
-# repo = Repository(
-#     local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
-# )
-
-user_agents = pd.read_csv('./user_agents.csv')
+dataset = load_dataset('csv', data_files='https://huggingface.co/datasets/petcoblue/simulation_data/resolve/main/user_agents.csv')
+user_agents = dataset.to_pandas()
 user_agents = user_agents.iloc[:,1:]
 user_batch = user_agents[:10]
 
@@ -91,14 +83,41 @@ def query_agent(description, question, image0, image1):
         print(f"Failed to analyze {image0} and {image1} after 3 attempts.")
         return None, None
 
-description = "Upload two images of emails and see which is generally preferred by Petco customers!"
+def simulate(user_batch, question, image0, image1):
+    preferences = []
+    reasons = []
+    probs = []
+    for index, user_agent in user_batch.iterrows():
+        description = create_description(user_agent)
+        preference, top_logprobs = query_agent(description, question, image0, image1)
+        prob = np.round(np.exp(top_logprobs[0]['logprob']) * 100, 2)
+
+        split = preference.split("; Characteristics: ")
+        if len(split) == 2:
+            choice, reasoning = split[0], split[1]
+        else:
+            print(preference)
+            choice, reasoning = split[0], ""
+        
+        preferences.append(0 if "0" in choice else 1)    
+        reasons.append(reasoning)
+        probs.append(prob)
+    
+    avg_preference = sum(preferences) / len(preferences)
+    avg_prob = sum(probs) / len(preferences)
+
+    return avg_preference
+
+subtitle = "Upload two images of emails and see which is generally preferred by Petco customers!"
 
-demo = gr.Interface(fn=query_agent, 
-                    inputs=[gr.UploadButton("Click to Upload Email 0", file_types=["image"], file_count="1"), 
+demo = gr.Interface(fn=simulate, 
+                    inputs=[user_batch,
+                            question,
+                            gr.UploadButton("Click to Upload Email 0", file_types=["image"], file_count="1"), 
                             gr.UploadButton("Click to Upload Email 1", file_types=["image"], file_count="1")], 
                     outputs="text",
                     title="Pairwise Simulation of Petco Email Preference",
-                    description=description
+                    description=subtitle
                     )
 
 if __name__ == "__main__":

requirements.txt

@@ -1,4 +1,5 @@
 openai
 https://gradio-builds.s3.amazonaws.com/75ed61524f55e542414d165ed60a976091c24f77/gradio-3.16.2-py3-none-any.whl
 pandas
-numpy
+numpy
+datasets