Update app.py

app.py

@@ -1,78 +1,101 @@
 import streamlit as st
 import pandas as pd
+import yfinance as yf
 from textblob import TextBlob
 import joblib
 import matplotlib.pyplot as plt
 import datetime
 
-# Load the data
+# Function to load stock data using yfinance
 @st.cache_data
-def load_data():
-    stock_data = pd.read_csv('data/stock_yfinance_data.csv')
-    tweets_data = pd.read_csv('data/stock_tweets.csv')
+def load_yfinance_data():
+    # List of stock tickers
+    tickers = ['TSLA', 'MSFT', 'PG', 'META', 'AMZN', 'GOOG', 'AMD', 'AAPL', 'NFLX', 'TSM',
+               'KO', 'F', 'COST', 'DIS', 'VZ', 'CRM', 'INTC', 'BA', 'BX', 'NOC', 'PYPL', 'ENPH', 'NIO', 'ZS', 'XPEV']
+    
+    # Set the start and end dates for the past 1 year
+    start_date = (datetime.datetime.now() - datetime.timedelta(days=365)).strftime('%Y-%m-%d')
+    end_date = datetime.datetime.today().strftime('%Y-%m-%d')
+
+    # Download the stock data using yfinance
+    data = yf.download(tickers, start=start_date, end=end_date, group_by='ticker')
+
+    # Process and format the data for each ticker
+    all_data = []
+    for ticker in tickers:
+        df = data[ticker].copy()
+        df.reset_index(inplace=True)
+        df['Stock Name'] = ticker
+        all_data.append(df)
+    
+    # Concatenate all the data into a single DataFrame
+    all_stock_data = pd.concat(all_data, ignore_index=True)
+
+    return all_stock_data
 
-    # Convert the Date columns to datetime
-    stock_data['Date'] = pd.to_datetime(stock_data['Date'])
-    tweets_data['Date'] = pd.to_datetime(tweets_data['Date']).dt.date
+# Load the data
+data = load_yfinance_data()
 
-    # Perform sentiment analysis on tweets
-    def get_sentiment(tweet):
-        analysis = TextBlob(tweet)
-        return analysis.sentiment.polarity
+# Perform sentiment analysis on tweets (assuming you still have your tweets data)
+tweets_data = pd.read_csv('data/stock_tweets.csv')
 
-    tweets_data['Sentiment'] = tweets_data['Tweet'].apply(get_sentiment)
+# Convert the Date columns to datetime
+tweets_data['Date'] = pd.to_datetime(tweets_data['Date']).dt.date
 
-    # Aggregate sentiment by date and stock
-    daily_sentiment = tweets_data.groupby(['Date', 'Stock Name']).mean(numeric_only=True).reset_index()
+# Perform sentiment analysis on tweets
+def get_sentiment(tweet):
+    analysis = TextBlob(tweet)
+    return analysis.sentiment.polarity
 
-    # Convert the Date column in daily_sentiment to datetime64[ns]
-    daily_sentiment['Date'] = pd.to_datetime(daily_sentiment['Date'])
+tweets_data['Sentiment'] = tweets_data['Tweet'].apply(get_sentiment)
 
-    # Merge stock data with sentiment data
-    merged_data = pd.merge(stock_data, daily_sentiment, how='left', left_on=['Date', 'Stock Name'], right_on=['Date', 'Stock Name'])
+# Aggregate sentiment by date and stock
+daily_sentiment = tweets_data.groupby(['Date', 'Stock Name']).mean(numeric_only=True).reset_index()
 
-    # Fill missing sentiment values with 0 (neutral sentiment)
-    merged_data['Sentiment'].fillna(0, inplace=True)
+# Convert the Date column in daily_sentiment to datetime64[ns]
+daily_sentiment['Date'] = pd.to_datetime(daily_sentiment['Date'])
 
-    # Sort the data by date
-    merged_data.sort_values(by='Date', inplace=True)
+# Merge stock data with sentiment data
+merged_data = pd.merge(data, daily_sentiment, how='left', on=['Date', 'Stock Name'])
 
-    # Create lagged features
-    merged_data['Prev_Close'] = merged_data.groupby('Stock Name')['Close'].shift(1)
-    merged_data['Prev_Sentiment'] = merged_data.groupby('Stock Name')['Sentiment'].shift(1)
+# Fill missing sentiment values with 0 (neutral sentiment)
+merged_data['Sentiment'].fillna(0, inplace=True)
 
-    # Create moving averages
-    merged_data['MA7'] = merged_data.groupby('Stock Name')['Close'].transform(lambda x: x.rolling(window=7).mean())
-    merged_data['MA14'] = merged_data.groupby('Stock Name')['Close'].transform(lambda x: x.rolling(window=14).mean())
+# Sort the data by date
+merged_data.sort_values(by='Date', inplace=True)
 
-    # Create daily price changes
-    merged_data['Daily_Change'] = merged_data['Close'] - merged_data['Prev_Close']
+# Create lagged features
+merged_data['Prev_Close'] = merged_data.groupby('Stock Name')['Close'].shift(1)
+merged_data['Prev_Sentiment'] = merged_data.groupby('Stock Name')['Sentiment'].shift(1)
 
-    # Create volatility
-    merged_data['Volatility'] = merged_data.groupby('Stock Name')['Close'].transform(lambda x: x.rolling(window=7).std())
+# Create moving averages
+merged_data['MA7'] = merged_data.groupby('Stock Name')['Close'].transform(lambda x: x.rolling(window=7).mean())
+merged_data['MA14'] = merged_data.groupby('Stock Name')['Close'].transform(lambda x: x.rolling(window=14).mean())
 
-    # Drop rows with missing values
-    merged_data.dropna(inplace=True)
+# Create daily price changes
+merged_data['Daily_Change'] = merged_data['Close'] - merged_data['Prev_Close']
 
-    return merged_data
+# Create volatility
+merged_data['Volatility'] = merged_data.groupby('Stock Name')['Close'].transform(lambda x: x.rolling(window=7).std())
 
-data = load_data()
-stock_names = data['Stock Name'].unique()
+# Drop rows with missing values
+merged_data.dropna(inplace=True)
 
 # Load the best model
 model_filename = 'model/best_model.pkl'
 model = joblib.load(model_filename)
 
+# Streamlit application layout
 st.title("Stock Price Prediction Using Sentiment Analysis")
 
 # User input for stock data
 st.header("Input Stock Data")
+stock_names = merged_data['Stock Name'].unique()
 selected_stock = st.selectbox("Select Stock Name", stock_names)
-days_to_predict = st.number_input("Number of Days to Predict",
-min_value=1, max_value=30, value=10)
+days_to_predict = st.number_input("Number of Days to Predict", min_value=1, max_value=30, value=10)
 
 # Get the latest data for the selected stock
-latest_data = data[data['Stock Name'] == selected_stock].iloc[-1]
+latest_data = merged_data[merged_data['Stock Name'] == selected_stock].iloc[-1]
 prev_close = latest_data['Close']
 prev_sentiment = latest_data['Sentiment']
 ma7 = latest_data['MA7']
@@ -113,8 +136,6 @@ if st.button("Predict"):
         ma14 = (ma14 * 13 + next_day_prediction) / 14  # Simplified rolling calculation
         daily_change = next_day_prediction - prev_close
 
-    # st.write(f"Predicted next {days_to_predict} days close prices: {predictions}")
-    # Prepare prediction data for display
     # Prepare prediction data for display
     prediction_dates = pd.date_range(start=latest_date + pd.Timedelta(days=1), periods=days_to_predict)
     prediction_df = pd.DataFrame({
@@ -123,14 +144,51 @@ if st.button("Predict"):
     })
 
     st.subheader("Predicted Prices")
-    st.write(prediction_df)
-
-   # Plotting the results
-    st.subheader("Prediction Chart")
-    plt.figure(figsize=(10, 6))
-    plt.plot(prediction_df['Date'], prediction_df['Predicted Close Price'], marker='o', linestyle='--', label="Predicted Close Price")
-    plt.xlabel("Date")
-    plt.ylabel("Close Price")
-    plt.title(f"{selected_stock} Predicted Close Prices")
-    plt.legend()
-    st.pyplot(plt)
+    # st.write(prediction_df)
+    st.dataframe(prediction_df)
+    # Plot predictions using Plotly
+    import plotly.express as px
+    fig = px.line(prediction_df, x='Date', y='Predicted Close Price',
+                  markers=True, title=f"{selected_stock} Predicted Close Prices")
+    st.plotly_chart(fig, use_container_width=True)
+
+    # ----------------------------------------
+    # Enhanced Visualizations
+    st.header(" Enhanced Stock Analysis")
+    stock_history = data[data['Stock Name'] == selected_stock]
+
+    # Date filter slider
+    min_date = stock_history['Date'].min()
+    max_date = stock_history['Date'].max()
+    date_range = st.slider("Select Date Range for Visualizations",
+                           min_value=min_date, max_value=max_date,
+                           value=(min_date, max_date))
+    filtered_data = stock_history[(stock_history['Date'] >= date_range[0]) & (stock_history['Date'] <= date_range[1])]
+
+    with st.expander(" Price vs Sentiment Trend"):
+        fig1 = px.line(filtered_data, x='Date', y=['Close', 'Sentiment'],
+                       labels={'value': 'Price / Sentiment', 'variable': 'Metric'},
+                       title=f"{selected_stock} - Close Price & Sentiment")
+        st.plotly_chart(fig1, use_container_width=True)
+
+    with st.expander(" Volatility Over Time"):
+        fig2 = px.line(filtered_data, x='Date', y='Volatility',
+                       title=f"{selected_stock} - 7-Day Rolling Volatility")
+        st.plotly_chart(fig2, use_container_width=True)
+
+    with st.expander(" Moving Averages (MA7 vs MA14)"):
+        fig3 = px.line(filtered_data, x='Date',
+                       y=['MA7', 'MA14'],
+                       labels={'value': 'Price', 'variable': 'Moving Average'},
+                       title=f"{selected_stock} - Moving Averages")
+        st.plotly_chart(fig3, use_container_width=True)
+
+    with st.expander(" Daily Price Change"):
+        fig4 = px.line(filtered_data, x='Date', y='Daily_Change',
+                       title=f"{selected_stock} - Daily Price Change")
+        st.plotly_chart(fig4, use_container_width=True)
+
+    with st.expander(" Sentiment Distribution"):
+        fig5 = px.histogram(filtered_data, x='Sentiment', nbins=30,
+                            title=f"{selected_stock} - Sentiment Score Distribution")
+        st.plotly_chart(fig5, use_container_width=True)