app

Trading_App.py

@@ -0,0 +1,52 @@
+import streamlit as st
+
+# Page configuration
+st.set_page_config(
+    page_title="Trading App",
+    page_icon="📈",
+    layout="wide"
+)
+
+# Title and Header
+st.title("Trading App 📈")
+st.header("Empowering Your Investment Journey")
+
+# Introduction with quotes
+st.subheader("“An investment in knowledge pays the best interest.” – Benjamin Franklin")
+st.write("Welcome to the **Trading App**, your trusted companion in navigating the financial markets. Whether you're a seasoned investor or just starting, our platform offers all the tools and insights you need to make informed decisions.")
+
+# Stock Image
+st.image('stock_image.jpg', use_column_width=True)
+
+# Overview of App Features
+st.markdown("## What We Offer")
+st.write("""
+Our app is designed to cater to every step of your investment process:
+- **Stock Information Page**: Learn about key financial metrics, historical data, and current stock trends.
+- **Stock Analysis Page**: Dive deep into stock fundamentals and explore technical analysis tools.
+- **Stock Prediction Page**: Use advanced machine learning models to predict future stock performance.
+""")
+
+# Add a motivational quote
+st.markdown("### 🌟 Quote of the Day")
+st.info("“The stock market is filled with individuals who know the price of everything but the value of nothing.” – Philip Fisher")
+
+
+st.markdown("### 📊 Did You Know?")
+st.write("""
+The New York Stock Exchange (NYSE) is the largest stock exchange in the world by market capitalization, 
+with a total value exceeding **$25 trillion**! Understanding the markets begins with knowing the incredible scale of global finance.
+""")
+
+# App Navigation Details
+st.markdown("### How to Get Started")
+st.write("""
+1. Navigate to the **Stock Information** page to explore comprehensive stock details.
+2. Move to the **Stock Analysis** page for in-depth analysis of your favorite stocks.
+3. Visit the **Stock Prediction** page to forecast stock prices using cutting-edge technology.
+""")
+
+# Footer
+st.markdown("---")
+st.markdown("### Ready to take charge of your financial future? 🚀")
+st.markdown("“The best time to invest was yesterday. The second-best time is today!”")

pages/Stock_Analysis.py

@@ -0,0 +1,326 @@
+import dateutil.relativedelta
+import streamlit as st 
+import pandas as pd
+import yfinance as yf
+import plotly.graph_objects as go
+import datetime
+import dateutil
+import ta
+import plotly.express as px
+import pandas_ta as pta
+import numpy as np
+npNaN = np.nan
+st.set_page_config(
+    page_title="Stock Analysis",
+    page_icon="page_with_curl",
+    layout='wide'
+)
+
+st.title("Stock Analysis")
+
+col1,col2,col3 =st.columns(3)
+
+today= datetime.date.today()
+
+with col1:
+    ticker =st.text_input("Stocker Ticker","TSLA")
+with col2:
+    start_date = st.date_input("choose Start Date",datetime.date(today.year -1,today.month,today.day))
+with col3:
+    end_date = st.date_input("choose End Date",datetime.date(today.year,today.month,today.day))
+     
+st.subheader(ticker)
+stock = yf.Ticker(ticker)
+try:
+    info = stock.get_info()
+    st.write(stock.info['longBusinessSummary'])
+    st.write("**Sector:**",stock.info['sector'])
+    st.write("**Full Time Employees:**",stock.info['fullTimeEmployees'])
+    st.write("**Website:**",stock.info['website'])
+except Exception as e:
+    print(f"Error: {e}")
+    
+col1= st.columns(1)[0]
+with col1:
+    df = pd.DataFrame({
+    "Metric": ["Market Cap", "Beta", "EPS", "PE Ratio","profitMargins",'revenuePerShare','financialCurrency'],
+    "Value": [
+        stock.info['marketCap'],
+        stock.info['beta'],
+        stock.info['trailingEps'],
+        stock.info['trailingPE'],
+        stock.info['profitMargins'],
+        stock.info['revenuePerShare'],
+        stock.info['financialCurrency']
+        
+        
+     ]
+})
+    st.dataframe(df.style.set_properties(**{'font-size': '20px'}),width=1000)
+
+data = yf.download(ticker,start=start_date,end= end_date)
+
+col1,col2,col3 = st.columns(3)
+daily_change = data['Close'].iloc[-1] - data['Close'].iloc[-2]
+col1.metric("Daily Change",str(round(data['Close'].iloc[-1],2)),str(round(daily_change,2)))
+
+# Display historical data based on start and end date
+filtered_data = data[(data.index >= pd.to_datetime(start_date)) & (data.index <= pd.to_datetime(end_date))]
+
+st.title(f"Historical Data ({start_date} to {end_date})")
+st.dataframe(filtered_data.sort_index(ascending=False).round(3).style.set_properties(**{'font-size': '20px'}), width=1000)
+
+col1,col2,col3,col4,col5,col6,col7=st.columns([1,1,1,1,1,1,1])
+
+num_period=''
+with col1:
+    if st.button("5D"):
+        num_period="5d"
+with col2:
+    if st.button("1M"):
+        num_period="1mo"
+with col3:
+    if st.button("6M"):
+        num_period="6mo"
+with col4:
+    if st.button("YTD"):
+        num_period='ytd'
+with col5:
+    if st.button("1Y"):
+        num_period='1y'
+with col6:
+    if st.button("5Y"):
+        num_period='5y'
+with col7:
+    if st.button("MAX"):
+        num_period= 'max'
+
+##  
+def filter_data(dataframe,num_period):
+    if num_period =='1mo':
+        date = dataframe.index[-1] + dateutil.relativedelta.relativedelta(months=-1)
+    elif num_period == '5d':
+        date =dataframe.index[-1] + dateutil.relativedelta.relativedelta(days=-5)
+    elif num_period == '6mo':
+        date =dataframe.index[-1] + dateutil.relativedelta.relativedelta(months=-6)
+    elif num_period == '1y':
+        date =dataframe.index[-1] + dateutil.relativedelta.relativedelta(years=-1)
+    elif num_period == '5y':
+        date =dataframe.index[-1] + dateutil.relativedelta.relativedelta(years=-5)
+    elif num_period == 'ytd':
+        date = datetime.datetime(dataframe.index[-1].year,1,1).strftime("%Y-%m-%d")
+    else:
+        date = dataframe.index[0]
+    dataframe_reset = dataframe.reset_index()  # Reset index to create a 'Date' column
+    return dataframe_reset[dataframe_reset['Date'] > date]
+
+def close_chart(dataframe,num_period=False):
+    if num_period:
+        dataframe =filter_data(dataframe,num_period)
+    fig =go.Figure()
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],y= dataframe['Open'],
+        mode='lines',
+        name ='Open',line =dict(width=2,color='#5ab7ff')
+    ))
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],y= dataframe['Close'],
+        mode='lines',
+        name ='Close',line =dict(width=2,color='black')
+    ))
+    fig.add_trace(go.Scatter(
+        x=dataframe["Date"],y= dataframe['High'],
+        mode='lines',
+        name ='High',line =dict(width=2,color='#0078ff')
+    ))
+    
+    fig.add_trace(go.Scatter(
+        x=dataframe["Date"],y= dataframe['Low'],
+        mode='lines',
+        name ='Low',line =dict(width=2,color='red')
+    ))
+    fig.update_xaxes(rangeslider_visible = True)
+    fig.update_layout(
+    height=500,
+    margin=dict(l=0, r=20, t=20, b=0),
+    plot_bgcolor='white',
+    paper_bgcolor='#E1EFFF',
+    legend=dict(yanchor='top', xanchor='right'),
+    xaxis_title="Date",  # Add this
+    yaxis_title="Price",  # Add this
+    )
+
+    return fig
+
+
+def candlestick(dataframe,num_period):
+    dataframe = filter_data(dataframe,num_period)
+    fig=go.Figure()
+    fig.add_trace(go.Candlestick(x=dataframe['Date'],
+                   open =dataframe['Open'],high=dataframe['High'],
+                   low = dataframe['Low'],close=dataframe['Close']              
+        ))
+    fig.update_layout(
+    xaxis_title="Date",  # Add this
+    yaxis_title="Price",  # Add this
+    showlegend=False,
+    height=500,
+    margin=dict(l=0, r=20, t=20, b=0),
+    plot_bgcolor='white',
+    paper_bgcolor='#E1EFFF'
+    )
+
+    return fig
+
+def RSI(dataframe,num_period):
+    dataframe['RSI']= pta.rsi(dataframe['Close'])
+    dataframe = filter_data(dataframe,num_period)
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],
+        y=dataframe.RSI,name='RSI',marker_color='orange',line= dict(width=2,color ='orange'),
+        ))
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],
+        y=[70]*len(dataframe),name='Overbought',marker_color='red',line= dict(width=2,color ='red',dash='dash'),
+        ))
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],
+        y=[30]*len(dataframe),fill='tonexty',name='Oversold',marker_color='#79da84',
+        line= dict(width=2,color ='#79da84',dash='dash')
+        ))
+    fig.update_layout(
+        xaxis_title='Date',
+        yaxis_title='RSI',
+        height=500,
+        margin=dict(l=0, r=20, t=20, b=0),
+        plot_bgcolor='white',
+        paper_bgcolor='#E1EFFF'
+    )
+    return fig
+
+
+def Moving_average(dataframe,num_period):
+    dataframe['SMA_50']=pta.sma(dataframe['Close'],50)
+    dataframe = filter_data(dataframe,num_period)
+    if dataframe['SMA_50'].isna().sum() > 0:
+        st.warning("Not enough data to calculate the moving average.")
+    fig=go.Figure()
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],y= dataframe['Open'],
+        mode='lines',
+        name ='Open',line =dict(width=2,color='#5ab7ff')
+    ))
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],y= dataframe['Close'],
+        mode='lines',
+        name ='Open',line =dict(width=2,color='black')
+    ))
+    fig.add_trace(go.Scatter(
+        x=dataframe["Date"],y= dataframe['High'],
+        mode='lines',
+        name ='Open',line =dict(width=2,color='#0078ff')
+    ))
+    
+    fig.add_trace(go.Scatter(
+        x=dataframe["Date"],y= dataframe['Low'],
+        mode='lines',
+        name ='Open',line =dict(width=2,color='red')
+    ))
+    fig.add_traces(go.Scatter(
+        x=dataframe["Date"],y= dataframe['SMA_50'],
+        mode='lines',
+        name ='SMA 50',line =dict(width=2,color='purple')
+    ))
+    fig.update_xaxes(rangeslider_visible = True)
+    fig.update_layout(
+    xaxis_title="Date",  # Add this
+    yaxis_title="Price",  # Add this
+    height=500,
+    margin=dict(l=0, r=20, t=20, b=0),
+    plot_bgcolor='white',
+    paper_bgcolor='#E1EFFF',
+    legend=dict(yanchor='top', xanchor='right')
+    )
+
+    return fig
+
+
+def MACD(dataframe,num_period):
+    macd = pta.macd(dataframe['Close']).iloc[:,0]
+    macd_signal = pta.macd(dataframe['Close']).iloc[:,1]
+    macd_hist =pta.macd(dataframe['Close']).iloc[:,2]
+    dataframe['MACD'] = macd
+    dataframe['MACD-Signal']=macd_signal
+    dataframe['MACD-Hist']=macd_hist
+    dataframe = filter_data(dataframe,num_period)
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],
+        y=dataframe['MACD'],name='RSI',marker_color='orange',line=dict(width=2,color='orange'),
+    ))
+    fig.add_trace(go.Scatter(
+        x=dataframe['Date'],
+        y=dataframe['MACD-Signal'],name='Overbought',marker_color ='red',line =dict(width=2,color='red',dash='dash'),
+    ))
+    c=['red' if cl<0 else 'green' for cl in macd_hist]
+    
+    return fig
+  
+      
+col1,col2,col3 = st.columns([1,1,4])
+
+with col1:
+    char_type =st.selectbox('',('Candle','line'))
+with col2:
+    if char_type == 'Candle':
+        
+        indicators = st.selectbox('',('RSI','MACD'))
+    else:
+        indicators = st.selectbox('',('RSI','Moving Average','MACD'))
+        
+ticker_ = yf.Ticker(ticker)
+new_df1=ticker_.history(period='max')
+data1= ticker_.history(period='max')
+if num_period == '':
+    
+    if char_type == 'Candle' and indicators == 'RSI':
+        st.plotly_chart(candlestick(new_df1,'1y'),use_container_width=True)
+        st.plotly_chart(RSI(new_df1,'1y'),use_container_width=True)
+        
+    if char_type == 'Candle' and indicators == 'MACD':
+        st.plotly_chart(candlestick(new_df1,'1y'),use_container_width=True)
+        st.plotly_chart(MACD(new_df1,'1y'),use_container_width=True)
+        
+    if char_type == 'line' and indicators == 'RSI':
+        st.plotly_chart(close_chart(new_df1,'1y'),use_container_width=True)
+        st.plotly_chart(RSI(new_df1,'1y'),use_container_width=True)
+        
+    if char_type == 'line' and indicators == 'Moving Average':
+        st.plotly_chart(Moving_average(new_df1,'1y'),use_container_width=True)
+        
+    if char_type == 'line' and indicators == 'MACD':
+        st.plotly_chart(close_chart(new_df1,'1y'),use_container_width=True)
+        st.plotly_chart(MACD(new_df1,'1y'),use_container_width=True)
+        
+else:
+    if char_type == 'Candle' and indicators == 'RSI':
+        st.plotly_chart(candlestick(new_df1,num_period),use_container_width=True)
+        st.plotly_chart(RSI(new_df1,num_period),use_container_width=True)
+        
+    if char_type == 'Candle' and indicators == 'MACD':
+        st.plotly_chart(candlestick(new_df1,num_period),use_container_width=True)
+        st.plotly_chart(MACD(new_df1,num_period),use_container_width=True)
+        
+    if char_type == 'line' and indicators == 'RSI':
+        st.plotly_chart(close_chart(new_df1,num_period),use_container_width=True)
+        st.plotly_chart(RSI(new_df1,num_period),use_container_width=True)
+        
+    if char_type == 'line' and indicators == 'Moving Average':
+        st.plotly_chart(Moving_average(new_df1,num_period),use_container_width=True)
+        
+    if char_type == 'line' and indicators == 'MACD':
+        st.plotly_chart(close_chart(new_df1,num_period),use_container_width=True)
+        st.plotly_chart(MACD(new_df1,num_period),use_container_width=True)
+        
+

pages/stock_prediction.py

@@ -0,0 +1,161 @@
+import yfinance as yf
+from statsmodels.tsa.stattools import adfuller
+from sklearn.metrics import mean_squared_error,r2_score
+from statsmodels.tsa.arima.model import ARIMA
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from datetime import datetime, timedelta
+import pandas as pd
+import streamlit as st 
+import plotly.graph_objects as go
+import plotly.express as px
+
+st.set_page_config(
+    page_title="Stock Prediction",
+    page_icon="chart_with_upwords_trend",
+    layout= "wide"
+)
+
+st.title("Stock Prediction")
+col1,clo2,clo3 = st.columns(3)
+
+with col1:
+    ticker = st.text_input('Stock Ticker','AAPL')
+
+def get_data(ticker):
+    stock_data = yf.download(ticker,start='2024-01-01')
+    return stock_data[['Close']]
+
+
+def get_rollng_mean(close_price):
+    rolling_price = close_price.rolling(window=7).mean().dropna()
+    return rolling_price
+
+def stationary_check(close_price):
+    adf_test=adfuller(close_price)
+    p_value=round(adf_test[1],3)
+    return p_value
+
+
+def get_differencing_order(close_price):
+    p_value = stationary_check(close_price)
+    d=0
+    while True:
+        if p_value > 0.05:
+            d=d+1
+            close_price=close_price.diff().dropna()
+            p_value = stationary_check(close_price)
+        else:
+            break
+    return d
+
+
+def scaling(close_price):
+    scaler = StandardScaler()
+    scaled_data = scaler.fit_transform(np.array(close_price).reshape(-1,1))
+    return scaled_data,scaler
+
+rmse =0
+st.subheader('Predicting Next 30 days Close Price for :-'+ticker)
+close_price = get_data(ticker)
+rolling_price = get_rollng_mean(close_price)
+
+differencing_order= get_differencing_order(rolling_price)
+
+def fit_model(data,differencing_order):
+    model =ARIMA(data,order=(7,differencing_order,7))
+    model_fit =model.fit()
+    forcast_steps=30
+    forcast = model_fit.get_forecast(steps=forcast_steps)
+    predictions = forcast.predicted_mean
+    return predictions
+
+def evaluate_model(original_price,differencing_order):
+    train_data, test_data =original_price[:-30], original_price[-30:]
+    predictions = fit_model(train_data,differencing_order)
+    rmse= np.sqrt(mean_squared_error(test_data,predictions))
+    return round(rmse,2)
+
+scaled_data,scaler=scaling(rolling_price)
+rmse = evaluate_model(scaled_data,differencing_order)
+
+def get_forecast(orignal_price,differencing_order):
+    predictions = fit_model(orignal_price,differencing_order)
+    start_date = datetime.now().strftime('%Y-%m-%d')
+    end_date = (datetime.now() + timedelta(days=29)).strftime('%Y-%m-%d')
+    forecast_index = pd.date_range(start=start_date,end=end_date,freq='D')
+    forecast_df= pd.DataFrame(predictions,index=forecast_index,columns= ['Close'])
+    return forecast_df
+
+def inverse_scaling(scaler,scaled_data):
+    close_price = scaler.inverse_transform(np.array(scaled_data).reshape(-1,1))
+    return close_price
+
+
+st.write("**Model RMSE Score**",rmse)
+
+forecast= get_forecast(scaled_data,differencing_order)
+
+forecast['Close']= inverse_scaling(scaler,forecast['Close'])
+
+st.write('#### Forecast Data (Next 30 days)')
+
+df_1=forecast.sort_index(ascending=True).round(3)
+st.dataframe(df_1.style.set_properties(**{'font-size': '20px'}),width=1000)
+
+forecast = pd.concat([rolling_price,forecast])
+
+
+# def Moving_average_forecast(forecast):
+#     # Ensure enough data exists
+#     if len(forecast) <= 30:
+#         return "Not enough data to plot."
+
+#     # Convert index to datetime if needed
+#     if not isinstance(forecast.index, pd.DatetimeIndex):
+#         forecast.index = pd.to_datetime(forecast.index)
+
+#     fig = go.Figure()
+
+#     # First trace: Past close prices
+#     if len(forecast.index[:-30]) > 0:
+#         fig.add_trace(go.Scatter(
+#             x=forecast.index[:-30],
+#             y=forecast['Close'].iloc[:-30],
+#             mode='lines',
+#             name='Close Price',
+#             line=dict(width=2, color='blue')
+#         ))
+#     else:
+#         st.warning("No data available for past close prices.")
+
+#     # Second trace: Future close prices
+#     if len(forecast.index[-31:]) > 0:
+#         fig.add_trace(go.Scatter(
+#             x=forecast.index[-31:],
+#             y=forecast['Close'].iloc[-31:],
+#             mode='lines',
+#             name='Future Close Price',
+#             line=dict(width=2, color='red')
+#         ))
+#     else:
+#         st.warning("No data available for future close prices.")
+
+#     fig.update_layout(
+#         title="Moving Average Forecast",
+#         xaxis_title="Date",
+#         yaxis_title="Close Price",
+#         height=500,
+#         plot_bgcolor='white',
+#         paper_bgcolor='#E1EFFF',
+#         legend=dict(yanchor='top', xanchor='right')
+#     )
+
+#     return fig
+
+# # Plot with debug checks
+# fig = Moving_average_forecast(forecast.iloc[150:])
+# if isinstance(fig, str):
+#     st.warning(fig)
+# else:
+#     st.plotly_chart(fig, use_container_width=True)