Update app.py

app.py

@@ -12,13 +12,8 @@ import base64
 import plotly.express as px
 from datetime import datetime
 
-
-## ............................................... ##
-# Set page configuration (Call this once and make changes as needed)
 st.set_page_config(page_title='Regression Stocks Prediction',  layout='wide', page_icon=':rocket:')
 
-## ............................................... ##
-# Add a dictonary of stock tickers and their company names and make a drop down menu to select the stock to predict
 stock_tickers = {
     "MAPI":"MAPI.JK","MAP Aktif": "MAPA.JK","MAP Boga": "MAPB.JK",
     "Tesla": "TSLA", "Apple": "AAPL", "Microsoft": "MSFT", "Google": "GOOGL", 
@@ -43,54 +38,30 @@ sidebar_css = """
 </style>
 """
 
-# User Input
-#default_index = stock_tickers.keys().index("MAPI.JK") if "MAPI.JK" in stock_tickers.keys() else 0
-#st.markdown(sidebar_css, unsafe_allow_html=True)
-#user_input = st.sidebar.selectbox("Select a Stock", list(stock_tickers.keys()), index=default_index , key="main_selectbox")
-#stock_name = user_input
-#user_input = stock_tickers[user_input]
-
 user_input = st.sidebar.text_input("Select a Stock", "MAPI.JK")
 
-# User input for start and end dates using calendar widget
 start_date = st.sidebar.date_input("Select start date:", datetime(2023, 1, 1))
 end_date = st.sidebar.date_input("Select end date:", datetime(2023, 12, 1))
 
-
-st.sidebar.markdown("----")
-st.sidebar.markdown("© 2023 Stocks Prediction App")
-st.sidebar.markdown("----")
 st.sidebar.markdown("Example Stock Tickers")
 st.sidebar.markdown(stock_tickers)
 
-## ............................................... ##
-# Page Title and Description
-st.title("Stock Price Analysis and Prediction")
-st.write("Created by Bayhaqy")
-st.write("Using Dataset MAPI to Train and Test the Model")
-
-## ............................................... ##
+st.title("IN-Depth Analysis")
 
-# Try to fetch information from Yahoo Finance
 try:
     stock_info = yf.Ticker(user_input).info
 
-    # Check if the 'longName' key exists in stock_info
     if 'longName' in stock_info:
         stock_name = stock_info['longName']
     else:
         stock_name = user_input
 
-    # Fetch the latest news using yfinance
     news_data = yf.Ticker(user_input).news
 
-    # Create a Streamlit app
-    title = f"<h1 style='color: red; font-size: 25px; text-align: center; '>{stock_name}'s Stock Fundamental Analysis</h1>"
+    title = f"<h1 style='color: while; font-size: 25px; text-align: center; '>{stock_name}'s Stock Fundamental Analysis</h1>"
     st.markdown(title, unsafe_allow_html=True)
 
     with st.expander("See Details"):
-        ## ............................................... ##
-        # Display the retrieved stock information
         if 'longName' in stock_info:
             company_name = stock_info['longName']
             st.write(f"Company Name: {company_name}")
@@ -133,8 +104,6 @@ try:
         else:
             st.write("Dividend Yield information not available for this stock.")
 
-        ## ............................................... ##
-        # Display financial metrics
         st.subheader('Financial Metrics')
         if 'trailingEps' in stock_info:
             trailing_eps = stock_info['trailingEps']
@@ -169,8 +138,6 @@ try:
         else:
             st.write("Company Summary information not available for this stock.")
 
-        ## ............................................... ##
-        # Display information about company officers
         st.subheader('Company Officers')
         if 'fullTimeEmployees' in stock_info:
             FullTimeEmployees = stock_info['fullTimeEmployees']
@@ -182,13 +149,8 @@ try:
             officers = stock_info['companyOfficers']
             officer_data = []
 
-            # Create a DataFrame
             df = pd.DataFrame(columns=["Name", "Title", "Age"])
 
-            # Populate the DataFrame with officer information
-            #for officer in officers:
-            #    officer_data.append([officer['name'], officer['title'], officer['age']])
-
             for officer in officers:
                 name = officer.get('name', 'N/A')
                 title = officer.get('title', 'N/A')
@@ -259,39 +221,6 @@ try:
 
             st.plotly_chart(fig, use_container_width=True)
 
-
-            st.markdown(f"<h2 style='text-align: center; color: #264653;'>Data Overview for {stock_name}</h2>", unsafe_allow_html=True)
-            # Get the description of the data
-            description = data.describe()
-
-            # Dictionary of columns and rows to highlight
-            highlight_dict = {
-                "Open": ["mean", "min", "max", "std"],
-                "High": ["mean", "min", "max", "std"],
-                "Low": ["mean", "min", "max", "std"],
-                "Close": ["mean", "min", "max", "std"],
-                "Adj Close": ["mean", "min", "max", "std"]
-            }
-
-            # Colors for specific rows
-            color_dict = {
-                "mean": "lightgreen",
-                "min": "salmon",
-                "max": "lightblue",
-                "std": "lightyellow"
-            }
-
-            # Function to highlight specific columns and rows based on the dictionaries
-            def highlight_specific_cells(val, col_name, row_name):
-                if col_name in highlight_dict and row_name in highlight_dict[col_name]:
-                    return f'background-color: {color_dict[row_name]}'
-                return ''
-
-            styled_description = description.style.apply(lambda row: [highlight_specific_cells(val, col, row.name) for col, val in row.items()], axis=1)
-
-            # Display the styled table in Streamlit
-            st.table(styled_description)
-
             ### ............................................... ##
             # Stock Price Over Time
             g1, g2, g3 = st.columns((1.2,1.2,1))
@@ -425,92 +354,5 @@ try:
             fig15.update_layout(title_text="Historical Volatility (252-day)", title_x=0, margin=dict(l=0, r=10, b=10, t=30), yaxis_title=None, xaxis_title=None)
             g15.plotly_chart(fig15, use_container_width=True)
 
-            ### ............................................... ##
-
-            # Visualizing the data and want to get the data when hovering over the graph
-            st.subheader('Closing Price vs Time Chart')
-            fig1 = go.Figure()
-            fig1.add_trace(go.Scatter(x=data.index, y=data['Close'], mode='lines', name='Close'))
-            fig1.layout.update(hovermode='x')
-            # Display the figure in Streamlit
-            st.plotly_chart(fig1,use_container_width=True)
-
-            st.subheader('Closing Price vs Time Chart with 100MA')
-            ma100 = data['Close'].rolling(100).mean()
-            fig2 = go.Figure()
-            # Add traces for 100MA and Closing Price
-            fig2.add_trace(go.Scatter(x=data.index, y=ma100, mode='lines', name='100MA'))
-            fig2.add_trace(go.Scatter(x=data.index, y=data['Close'], mode='lines', name='Closing Price'))
-            fig2.layout.update(hovermode='x')
-            # Display the figure in Streamlit
-            st.plotly_chart(fig2,use_container_width=True)
-
-            st.subheader('Closing Price vs Time Chart with 100MA and 200MA')
-            ma100 = data['Close'].rolling(100).mean()
-            ma200 = data['Close'].rolling(200).mean()
-            fig3 = go.Figure()
-            # Add traces for 100MA and Closing Price
-            fig3.add_trace(go.Scatter(x=data.index, y=ma100, mode='lines', name='100MA'))
-            fig3.add_trace(go.Scatter(x=data.index, y=ma200, mode='lines', name='200MA'))
-            fig3.add_trace(go.Scatter(x=data.index, y=data['Close'], mode='lines', name='Closing Price'))
-            fig3.layout.update(hovermode='x')
-
-            # Display the figure in Streamlit
-            st.plotly_chart(fig3,use_container_width=True)
-
-    ## ............................................... ##
-    # Enhanced title with larger font size and a different color
-    title = f"<h1 style='color: red; font-size: 25px; text-align: center; '>{stock_name}'s Stock Prediction</h1>"
-    st.markdown(title, unsafe_allow_html=True)
-
-    with st.expander("See Details"):
-        # Define the minimum number of days required for predictions
-        minimum_days_for_predictions = 100
-
-        # Check if the available data is less than the minimum required days
-        if len(data) < minimum_days_for_predictions:
-            st.warning(f"The available data for {stock_name} is less than {minimum_days_for_predictions} days, which is insufficient for predictions.")
-        else:
-            # Splitting the data into training and testing data
-            data_training = pd.DataFrame(data['Close'][0:int(len(data)*0.70)])
-            data_testing = pd.DataFrame(data['Close'][int(len(data)*0.70): int(len(data))])
-
-            # Scaling the data
-            scaler = MinMaxScaler(feature_range=(0,1))
-            data_training_array = scaler.fit_transform(data_training)
-
-            # load the model
-            model = load_model('best_model_MAPI.h5')
-
-            # Testing the model
-            past_100_days = data_training.tail(100)
-            final_df = pd.concat([past_100_days,data_testing], ignore_index=True)
-            input_data = scaler.fit_transform(final_df)
-
-            x_test = []
-            y_test = []
-            for i in range(100, input_data.shape[0]):
-                x_test.append(input_data[i-100:i])
-                y_test.append(input_data[i,0])
-
-            x_test, y_test = np.array(x_test), np.array(y_test)
-
-            y_predicted = model.predict(x_test)
-
-            scaler = scaler.scale_
-            scale_factor = 1/scaler[0]
-            y_predicted = y_predicted * scale_factor
-            y_test = y_test * scale_factor
-
-            # Visualizing the results
-            st.subheader('Predictions vs Actual')
-            fig4 = go.Figure()
-            # Add traces for Actual and Predicted Price
-            fig4.add_trace(go.Scatter(x=data.index[-len(y_test):], y=y_test, mode='lines', name='Actual Price'))
-            fig4.add_trace(go.Scatter(x=data.index[-len(y_predicted):], y=y_predicted[:,0], mode='lines', name='Predicted Price'))
-            fig4.layout.update(hovermode='x')
-            # Display the figure in Streamlit
-            st.plotly_chart(fig4,use_container_width=True)
-
 except Exception as e:
     st.error(f"An error fetching stock information: {str(e)}")