Update app.py

app.py

@@ -1,57 +1,31 @@
-import gradio as gr
-import openai
-import random
-import time
-import os
+import pandas as pd
 
-# Set up OpenAI API key
-openai.api_key = os.getenv('APICode2')
-system_message = {"role": "system", "content": "You are a helpful assistant."}
+# Define the criteria, alternatives, and weights
+criteria = ['Cost', 'Quality', 'Delivery Time']
+alternatives = ['Option A', 'Option B', 'Option C']
+weights = [0.5, 0.3, 0.2]
 
-with gr.Blocks() as demo:
-    with gr.Row():
-        with gr.Column():
-            msg = gr.Textbox()
-            btn = gr.Button(value="send")
-    with gr.Row():
-        chatbot = gr.Chatbot()
-    with gr.Row():
-        prt = gr.Button("Save in memory")
-        clear = gr.Button("Clear")
-        state = gr.State([])
+# Create a DataFrame to hold the evaluation scores
+evaluation_scores = [
+    [7, 9, 5],
+    [8, 7, 6],
+    [6, 8, 7]
+]
 
-    def user(user_message, history):
-        return "", history + [[user_message, None]]
+decision_matrix = pd.DataFrame(evaluation_scores, columns=criteria, index=alternatives)
 
-    def bot(history, messages_history):
-        user_message = history[-1][0]
-        bot_message, messages_history = ask_gpt(user_message, messages_history)
-        messages_history += [{"role": "assistant", "content": bot_message}]
-        history[-1][1] = bot_message
-        time.sleep(1)
-        return history, messages_history
+# Normalize and weight the scores
+normalized_scores = decision_matrix / decision_matrix.max()
+weighted_scores = normalized_scores * weights
 
-    def ask_gpt(message, messages_history):
-        messages_history += [{"role": "user", "content": message}]
-        response = openai.ChatCompletion.create(
-            model="gpt-4",
-            messages=messages_history
-        )
-        return response['choices'][0]['message']['content'], messages_history
+# Calculate the total score for each alternative
+total_scores = weighted_scores.sum(axis=1)
 
-    def init_history(messages_history):
-        messages_history = []
-        messages_history += [system_message]
-        return messages_history
+# Determine the best alternative
+best_alternative = total_scores.idxmax()
 
-    def printscr(chatbot):
-        print("\n\nYour chat hiatory:\n")
-        for i in range(len(chatbot)):
-            print(f"User input:{chatbot[i][0]}")
-            print(f"Bot output:{chatbot[i][1]}")
-    
-    btn.click(user, [msg, chatbot], [msg, chatbot], queue=False).then(bot, [chatbot, state], [chatbot, state])
-    prt.click(printscr, chatbot, None)
-    clear.click(lambda: None, None, chatbot, queue=False).success(init_history, [state], [state])
-
-demo.launch()
+print("Decision Matrix:\n", decision_matrix)
+print("\nNormalized Scores:\n", normalized_scores)
+print("\nWeighted Scores:\n", weighted_scores)
+print("\nTotal Scores:\n", total_scores)
+print("\nBest Alternative:", best_alternative)