Update app.py

app.py

@@ -17,6 +17,14 @@ from langchain_community.llms import HuggingFaceHub
 from langchain_core.prompts import PromptTemplate
 from langchain.chains import RetrievalQA
 
+# Disclaimer to be dispalyed at the bottom of each tab
+disclaimer = """
+    <div style='background-color:#b43c42; color:#ffffff; padding:8px; border-radius:3px; font-size:12px''>
+        <strong>Disclaimer:</strong> For demo purpose, the tool is currently populated with 10 months (Nov 2020 - Aug 2021) news 
+                and historical data of oil sector from PSX. This data is intended to illustrate the tool's functionality and is not 
+                intended for actual investment decisions.
+    </div>
+    """
 
 # Utils Functions
 def signals_to_plot(selected_indicator, num_signals, signal_column, data):
@@ -73,6 +81,25 @@ def convert_str_to_list(string):
 
 
 # Add Title and Logo
+def get_answer(text):
+  text = response['result']
+  helpful_answer_index = text.find('Helpful Answer:')
+  if helpful_answer_index != -1:
+      helpful_answer = text[helpful_answer_index + len('Helpful Answer:'):].strip()
+      print(helpful_answer)
+  else:
+      print("No helpful answer found.")
+  return helpful_answer
+
+# Streamed response emulator
+def response_generator(answer):
+    response = answer
+    for word in response.split():
+        yield word + " "
+        time.sleep(0.05)
+
+
+# WebApp
 title_container = st.container(border=False)        # Create a container to hold the tile and logo 
 col1, col2 = title_container.columns([0.2, 0.8], gap='medium')        # Create columns to display logo and title side-by-side
 col1.image("logo.png")        # Add logo to the 1st column
@@ -131,27 +158,36 @@ with market_analysis:
         
         # Plot buy/sell signals
         if num_signals != 'None':
-            # get signal values using the signals_to_plot function
+            # get signal values using the signals_to_plot utils function
             strong_buy_dates, strong_sell_dates, strong_hold_dates = signals_to_plot(
                 selected_indicator=selected_indicator, 
                 num_signals=num_signals, 
                 signal_column='EMA9_Signal', 
                 data=data2)
-
-            fig.add_scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['EMA 9'], mode='markers', marker=dict(symbol='triangle-up', size=10, color='green'), name='Strong buy')  
-            fig.add_scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['EMA 9'], mode='markers', marker=dict(symbol='triangle-down', size=10, color='red'), name='Strong sell')
+            
+            # Add Buy signals
+            fig.add_scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['EMA 9'], mode='markers', 
+                            marker=dict(symbol='triangle-up', size=10, color=cs.pos_impacts_color), name='Strong buy')  
+            # Add Sell signals
+            fig.add_scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['EMA 9'], mode='markers', 
+                            marker=dict(symbol='triangle-down', size=10, color=cs.neg_impacts_color), name='Strong sell')
+        
+        # Add date range selection buttons to chart
         fig.update_xaxes(
-        rangeslider_visible=True,
-        rangeselector=dict(
-            buttons=list([
-                dict(count=1, label="1m", step="month", stepmode="backward"),
-                dict(count=6, label="6m", step="month", stepmode="backward"),
-                dict(count=1, label="YTD", step="year", stepmode="todate"),
-                dict(count=1, label="1y", step="year", stepmode="backward"),
-                dict(step="all")
-            ])
+            rangeslider_visible=True,
+            rangeselector=dict(
+                buttons=list([
+                    dict(count=1, label="1m", step="month", stepmode="backward"),
+                    dict(count=6, label="6m", step="month", stepmode="backward"),
+                    dict(count=1, label="YTD", step="year", stepmode="todate"),
+                    dict(count=1, label="1y", step="year", stepmode="backward"),
+                    dict(step="all")
+                ])
+            )
         )
-    )
+        fig.update_yaxes(fixedrange=False)
+        
+        # Show chart on WebApp
         st.plotly_chart(fig)
     
     elif selected_indicator == 'EMA 55':
@@ -159,16 +195,24 @@ with market_analysis:
         fig = px.line(data2, x='Date', y=['Close Price', 'EMA 55'], title='Close Price vs EMA 55',
                     labels={'Date': 'Date', 'value': 'Price in Rs.', 'variable': 'Type'})
         fig.update_traces(selector=dict(type='scatter'))
-        # Plot ‘strong buy’ signals
+        
+        # Plot buy/sell signals
         if num_signals != 'None':
+            # get signal values using the signals_to_plot utils function
             strong_buy_dates, strong_sell_dates, strong_hold_dates = signals_to_plot(
                 selected_indicator=selected_indicator, 
                 num_signals=num_signals, 
                 signal_column='EMA55_Signal', 
                 data=data2)
 
-            fig.add_scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['EMA 55'], mode='markers', marker=dict(symbol='triangle-up', size=10, color='green'), name='Strong buy')
-            fig.add_scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['EMA 55'], mode='markers', marker=dict(symbol='triangle-down', size=10, color='red'), name='Strong sell')
+            # Add Buy signals
+            fig.add_scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['EMA 55'], mode='markers', 
+                            marker=dict(symbol='triangle-up', size=10, color=cs.pos_impacts_color), name='Strong buy')
+            # Add Sell signals
+            fig.add_scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['EMA 55'], mode='markers', 
+                            marker=dict(symbol='triangle-down', size=10, color=cs.neg_impacts_color), name='Strong sell')
+        
+        # Add date range selection buttons to chart
         fig.update_xaxes(
             rangeslider_visible=True,
             rangeselector=dict(
@@ -181,37 +225,51 @@ with market_analysis:
                 ])
             )
         )
+        fig.update_yaxes(fixedrange=False)
+        
+        # Show chart on WebApp
         st.plotly_chart(fig)
 
     elif selected_indicator == 'MACD':
         # Set up the figure and subplots
         fig = make_subplots(rows=2, cols=1)
-        # fig = go.Figure()
+        
         # Add subplot for Close Price and Signals
         fig.add_trace(go.Scatter(x=data2['Date'], y=data2['Close Price'], mode='lines', name='Close Price'),
                         row=1, col=1)
+        
+        # Plot buy/sell signals
         if num_signals != 'None':
+            # get signal values using the signals_to_plot utils function
             strong_buy_dates, strong_sell_dates, strong_hold_dates = signals_to_plot(
                 selected_indicator=selected_indicator, 
                 num_signals=num_signals, 
                 signal_column='MACD_Signals', 
                 data=data2)
-            fig.add_trace(go.Scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['Close Price'], mode='markers', marker=dict(symbol='triangle-up', size=10, color='green'), name='Strong Buy'), row=1, col=1)
-            fig.add_trace(go.Scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['Close Price'], mode='markers', marker=dict(symbol='triangle-down', size=10, color='red'), name='Strong Sell'), row=1, col=1)
-            fig.add_trace(go.Scatter(x=strong_hold_dates['Date'], y=strong_hold_dates['Close Price'], mode='markers', marker=dict(symbol='circle', size=10, color='orange'), name='Hold'), row=1, col=1)
+            
+            # Add Buy signals
+            fig.add_trace(go.Scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['Close Price'], mode='markers', 
+                        marker=dict(symbol='triangle-up', size=10, color=cs.pos_impacts_color), name='Strong Buy'), row=1, col=1)
+            # Add Sell signals
+            fig.add_trace(go.Scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['Close Price'], mode='markers', 
+                        marker=dict(symbol='triangle-down', size=10, color='red'cs.neg_impacts_color), name='Strong Sell'), row=1, col=1)
+            # Add Hold signals
+            fig.add_trace(go.Scatter(x=strong_hold_dates['Date'], y=strong_hold_dates['Close Price'], mode='markers', 
+                        marker=dict(symbol='circle', size=10, color='orange'), name='Hold'), row=1, col=1)
 
         # Add subplot for MACD
         # fig2 = go.Figure()
-        fig.add_trace(go.Scatter(x=data2['Date'], y=data2['MACD_12_26_9'], mode='lines', name='MACD', yaxis='y2'), row=2, col=1)
-        fig.add_trace(go.Scatter(x=data2['Date'], y=data2['MACDs_12_26_9'], mode='lines', name='Signal', yaxis='y2'), row=2, col=1)
-        fig.add_trace(go.Bar(x=data2['Date'], y=data2['MACDh_12_26_9'], name='Histogram', yaxis='y2'), row=2, col=1)
-
-        # # Update layout
-        # fig.update_layout(title='Close Price vs MACD',
-        #                 xaxis=dict(title='Date'),
-        #                 yaxis=dict(title='Close Price', side='left', showgrid=False),
-        #                 yaxis2=dict(title='MACD', side='right', overlaying='y', showgrid=False))
+        fig.add_trace(go.Scatter(x=data2['Date'], y=data2['MACD_12_26_9'], mode='lines', name='MACD', yaxis='y2',
+                                line=dict(dash='solid', color=cs.macd_color, width=2)), row=2, col=1)
+        fig.add_trace(go.Scatter(x=data2['Date'], y=data2['MACDs_12_26_9'], mode='lines', name='Signal', yaxis='y2',
+                                line=dict(dash='solid', color=cs.macd_signal_color, width=2)), row=2, col=1)
+        fig.add_trace(go.Bar(x=data2['Date'], y=data2['MACDh_12_26_9'], name='Histogram', yaxis='y2',
+                            marker=dict(color=cs.macd_hist)), row=2, col=1)
+
+        # Update layout
         fig.update_layout(title='Close Price vs MACD')
+        
+        # Add date range selection buttons to chart
         fig.update_xaxes(
             rangeslider_visible=False,
             rangeselector=dict(
@@ -224,8 +282,11 @@ with market_analysis:
                 ])
             )
         )
+        fig.update_yaxes(fixedrange=False)
+        
+        # Show chart on WebApp
         st.plotly_chart(fig, use_container_width=True)
-        # st.plotly_chart(fig2, use_container_width=True)
+        
 
     elif selected_indicator == 'RSI':
         # Set up the figure
@@ -240,17 +301,26 @@ with market_analysis:
         fig.add_shape(type="line", x0=data2['Date'].min(), y0=overbought_strong, x1=data2['Date'].max(), y1=overbought_strong, line=dict(color="red", width=1, dash="dash"), name="Overbought")
         fig.add_shape(type="line", x0=data2['Date'].min(), y0=oversold_strong, x1=data2['Date'].max(), y1=oversold_strong, line=dict(color="green", width=1, dash="dash"), name="Oversold")
 
+        # Plot buy/sell signals
         if num_signals != 'None':
+            # get signal values using the signals_to_plot utils function
             strong_buy_dates, strong_sell_dates, strong_hold_dates = signals_to_plot(
                 selected_indicator=selected_indicator,
                 num_signals=num_signals, 
                 signal_column='RSI_Signals', 
                 data=data2)
-            fig.add_trace(go.Scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['RSI'], mode='markers', marker=dict(symbol='triangle-up', size=10, color='green'), name='Strong Buy'))
-            fig.add_trace(go.Scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['RSI'], mode='markers', marker=dict(symbol='triangle-down', size=10, color='red'), name='Strong Sell'))
+
+            # Add Buy signals
+            fig.add_trace(go.Scatter(x=strong_buy_dates['Date'], y=strong_buy_dates['RSI'], mode='markers', 
+                                     marker=dict(symbol='triangle-up', size=10, color=cs.pos_impacts_color), name='Strong Buy'))
+            # Add Sell signals
+            fig.add_trace(go.Scatter(x=strong_sell_dates['Date'], y=strong_sell_dates['RSI'], mode='markers', 
+                                     marker=dict(symbol='triangle-down', size=10, color=cs.neg_impacts_color), name='Strong Sell'))
             # fig.add_trace(go.Scatter(x=strong_hold_dates['Date'], y=strong_hold_dates['RSI'], mode='markers', marker=dict(symbol='circle', size=10, color='orange'), name='Hold'))
         
         fig.update_layout(title='RSI Analysis', showlegend=True)
+        
+        # Add date range selection buttons to chart
         fig.update_xaxes(
             rangeslider_visible=True,
             rangeselector=dict(
@@ -263,21 +333,19 @@ with market_analysis:
                 ])
             )
         )
+        fig.update_yaxes(fixedrange=False)
         st.plotly_chart(fig)
     # st.write(data2)
 
-    st.markdown("""
-    <div style='background-color:#b43c42; color:#ffffff; padding:8px; border-radius:3px; font-size:12px''>
-        <strong>Disclaimer:</strong> For demo purpose, the tool is currently populated with 10 months (Nov 2020 - Aug 2021) news and historical data of oil sector from PSX. 
-        This data is intended to illustrate the tool's functionality and is not intended for actual investment decisions.
-    </div>
-    """, unsafe_allow_html=True)
+    
+    # Add discalimer
+    st.markdown(disclaimer, unsafe_allow_html=True)
     
 with news_analysis:
     st.header("News Analysis", help="This module provides news based event impact for the following day based on the current date.")
     # st.write("This module provides news based event impact for the following day based on the current date.")
     
-    # Load data
+    # Load News Events data
     data_file_path = r"Events_SameDay.csv"  # Update this with your file path
     events = pd.read_csv(data_file_path, encoding="ISO-8859-1", lineterminator='\n')
     print(events.columns)
@@ -429,12 +497,8 @@ with news_analysis:
                 st.write(set(features))
                 
 
-    st.markdown("""
-    <div style='background-color:#b43c42; color:#ffffff; padding:8px; border-radius:3px; font-size:12px''>
-        <strong>Disclaimer:</strong> For demo purpose, the tool is currently populated with 10 months (Nov 2020 - Aug 2021) news and historical data of oil sector from PSX. 
-        This data is intended to illustrate the tool's functionality and is not intended for actual investment decisions.
-    </div>
-    """, unsafe_allow_html=True) 
+    # Add Disclaimer
+    st.markdown(disclaimer, unsafe_allow_html=True) 
 
 
 with final_recs:
@@ -571,27 +635,28 @@ with final_recs:
     # Update y-axis to allow vertical scrolling and dragging
     figure.update_yaxes(fixedrange=False)
     st.plotly_chart(figure)
-    
-    st.markdown("""
-    <div style='background-color:#b43c42; color:#ffffff; padding:8px; border-radius:3px; font-size:12px''>
-        <strong>Disclaimer:</strong> For demo purpose, the tool is currently populated with 10 months (Nov 2020 - Aug 2021) news and historical data of oil sector from PSX. 
-        This data is intended to illustrate the tool's functionality and is not intended for actual investment decisions.
-    </div>
-    """, unsafe_allow_html=True)
-    
 
-with chat:
+    # Add Disclaimer
+    st.markdown(disclaimer, unsafe_allow_html=True)
     
 
+with chat:
     st.header("Chat with AI Stock Advisor")
 
-    loader = CSVLoader("Events_SameDay.csv",encoding='iso-8859-1')
+    # loader = CSVLoader("Events_SameDay.csv",encoding='iso-8859-1')
+    
+    # Initialize HuggingFace Instruct Embeddings
     embeddings = HuggingFaceInstructEmbeddings()
+
+    # Load saved Vector Store
     persist_directory = 'FAISS_VectorStore'
-    db2 = FAISS.load_local(persist_directory, embeddings, allow_dangerous_deserialization=True)
+    db = FAISS.load_local(persist_directory, embeddings, allow_dangerous_deserialization=True)
+    
+    # Initialize GenAI LLM Model
     repo_id = "mistralai/Mistral-7B-Instruct-v0.1"
     llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature": 0.1, "max_new_tokens": 1024})
-    
+
+    # Define Prompt Template
     system_prompt = """You are a financial expert for stock market who can perform multiple tasks for the intended user including trading 
     recommendations with reasoning, retrieving articles with their impact in the market, retrieving or enlisting features affecting market 
     trends (could be positive or negative).However, if a user is asking for trading recommendation, then you need to generate trading signal 
@@ -617,14 +682,16 @@ with chat:
                 "\nHelpful Answer: \n"
                 )
     sys_prompt = PromptTemplate(input_variables=["context", "question"], template=template)
-    
+
+    # Create QA Chain
     chain = RetrievalQA.from_chain_type(
-    llm=llm, 
+    llm=llm,    # Add LLM
     chain_type="stuff", 
-    retriever=db2.as_retriever(), 
+    retriever=db.as_retriever(),     # Add Vector Store
     input_key="question",
-    chain_type_kwargs={"prompt": sys_prompt})
+    chain_type_kwargs={"prompt": sys_prompt})    # Add prompt template
 
+    # Add Container to display chat history
     chat_container = st.container(height = 300, border=False)
     with chat_container:
         # Initialize chat history
@@ -636,6 +703,8 @@ with chat:
             with st.chat_message(message["role"]):
                 st.markdown(message["content"])
 
+    
+    st.divider()    # Divider to separate chat history and chat input
     # Accept user input
     if prompt := st.chat_input("Enter your query here.", key='input2'):
         # Add user message to chat history
@@ -644,12 +713,10 @@ with chat:
         with chat_container.chat_message("user"):
             st.markdown(prompt)
 
-        # question = query
-        print(f"User Question: {prompt}")
+        # Get Response to user query from LLM
         response = chain({"question": prompt})
-        print("Answer generated")
+        # Extract the answer from the response
         result = get_answer(response['result'])
-        print("helpful answer extracted")
 
         # Display assistant response in chat message container
         with chat_container.chat_message("assistant"):