Update app.py

app.py

@@ -296,118 +296,12 @@ elif page == "PS3":
 elif page == "PS2":
     st.header("CLICK ON RUN SCRIPT TO START A TRAFFIC SIMULATION")
     script = st.button("RUN SCRIPT")
-    st.session_state.con = -1
-    if script:
-        st.session_state.con += 1
-        import gymnasium as gym
-        import sumo_rl
-        import os
-        from stable_baselines3 import DQN
-        from stable_baselines3.common.vec_env import DummyVecEnv
-        from stable_baselines3.common.evaluation import evaluate_policy
-        from sumo_rl import SumoEnvironment
-        env = gym.make('sumo-rl-v0',
-                net_file='single-intersection.net.xml',
-                route_file='single-intersection-gen.rou.xml',
-                out_csv_name='output',
-                use_gui=True,
-                single_agent=True,    
-                num_seconds=5000)
-        model1 = DQN.load('DQN_MODEL3.zip',env=env)
-        st.write("The Simulation is currently running for 5000 steps, Results will be shown shortly.....")
-        one,two = evaluate_policy(model1,env = env,n_eval_episodes=5,render=True)
-        st.write("Evaluation Results: \nPer Episode Rewards(Higher the better):",one,"\nPer-episode lengths (in number of steps):",two)
-        import matplotlib.pyplot as plt
-        def eval_plot(path,metric,path_compare = None):
-            data = pd.read_csv(path)
-            if path_compare is not None:
-                data1 = pd.read_csv(path_compare)
-            x = []
-            for i in range(0,len(data)):
-                x.append(i)
-
-            y = data[metric]
-            y_1 = pd.to_numeric(y)
-            y_arr = np.array(y_1)
-            if path_compare is not None:
-                y2 = data1[metric]
-                y_2 = pd.to_numeric(y2)
-                y_arr2 = np.array(y_2)
-
-            x_arr = np.array(x)
-
-            fig = plt.figure()
-            ax1 = fig.add_subplot(2, 1, 1)
-            ax1.set_title(metric)
-            if path_compare is not None:
-                ax2 = fig.add_subplot(2, 1, 2,sharey=ax1)
-                ax2.set_title('compare '+metric)
-
-            ax1.plot(x_arr,y_arr)
-            
-            if path_compare  is not None:
-                ax2.plot(x_arr,y_arr2)
-            
-            return fig
-        for i in range(1,2):
-            st.pyplot(eval_plot(f'output_conn{st.session_state.con}_ep{i}.csv','system_mean_waiting_time'))
-            st.pyplot(eval_plot(f'output_conn{st.session_state.con}_ep{i}.csv','agents_total_accumulated_waiting_time'))  
+    st.alert("This simulation, Unfortunately was not optimized for deployed but still works for locally run version")  
+    st.write("check out this [link](https://github.com/pranavsrinivasa/Traffic-Optimization-Projects)")
 
 elif page == "Chat with Results":
     st.title('Chat with the Results')
     st.write("Please upload the relevant CSV data to get started")
-    reload = st.button('Reload')
-    if 'isran' not in st.session_state or reload == True:
-        st.session_state['isran'] = False
-
-
-    uploaded_file = st.file_uploader('Choose your .csv file', type=["csv"])
-    if uploaded_file is not None and st.session_state['isran'] == False:
-        with open("temp.csv", "wb") as f:
-            f.write(uploaded_file.getvalue())
-        loader = CSVLoader('temp.csv')
-        docs = loader.load()
-        text_splitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)
-        splits = text_splitter.split_documents(docs)
-        
-        embeddings = OllamaEmbeddings(model='mistral')
-        st.session_state.vectorstore = Chroma.from_documents(documents=splits,embedding=embeddings)
-        st.session_state['isran'] = True
-
-    if st.session_state['isran'] == True:
-        st.write("Embedding created")
-
-    def fdocs(docs):
-        return "\n\n".join(doc.page_content for doc in docs)
-
-    def llm(question,context):
-        formatted_prompt = f"Question: {question}\n\nContext:{context}"
-        response = ollama.chat(model='mistral', messages=[
-            {
-                'role': 'user',
-                'content': formatted_prompt
-            },
-            ])
-        return response['message']['content']
-
-
-
-    def rag_chain(question): 
-        retriever = st.session_state.vectorstore.as_retriever()
-        retrieved_docs = retriever.invoke(question)
-        formatted_context = fdocs(retrieved_docs)
-        return llm(question,formatted_context)
-
-    if 'messages' not in st.session_state:
-        st.session_state.messages = []
-
-    for message in st.session_state.messages:
-        st.chat_message(message['role']).markdown(message['content'])
-
-    prompt = st.chat_input("Say something")
-    response = rag_chain(prompt)
-    if prompt:
-        st.chat_message('user').markdown(prompt)
-        st.session_state.messages.append({'role':'user','content':prompt})
-        st.session_state.messages.append({'role':'AI','content':response})
-        st.chat_message('AI').markdown(response)
+    
+    st.alert("This model, Unfortunately was not optimized for deployed but still works for locally run version")  
+    st.write("check out this [link](https://github.com/pranavsrinivasa/Traffic-Optimization-Projects)")