Update app.py

app.py

@@ -1,9 +1,10 @@
 import gradio as gr
 import pandas as pd
 import numpy as np
-from prophet import Prophet  # Using updated Prophet library
-import yfinance as yf  # Ensure yfinance is installed
+from sklearn.linear_model import LinearRegression
+import yfinance as yf
 import datetime
+import matplotlib.pyplot as plt
 
 # Function to fetch stock data
 def get_stock_data(ticker, start_date, end_date):
@@ -11,18 +12,21 @@ def get_stock_data(ticker, start_date, end_date):
     stock_data.reset_index(inplace=True)
     return stock_data
 
-# Function to prepare data for Prophet model
+# Function to prepare data for Linear Regression model
 def prepare_data(stock_data):
-    df = stock_data[['Date', 'Close']].rename(columns={'Date': 'ds', 'Close': 'y'})
-    return df
+    stock_data['Date'] = pd.to_datetime(stock_data['Date'])
+    stock_data['Days'] = (stock_data['Date'] - stock_data['Date'].min()).dt.days
+    X = stock_data['Days'].values.reshape(-1, 1)
+    y = stock_data['Close'].values
+    return X, y
 
-# Function to make predictions using Prophet
-def make_predictions(df, periods=90):
-    model = Prophet()
-    model.fit(df)
-    future = model.make_future_dataframe(periods=periods)
-    forecast = model.predict(future)
-    return forecast
+# Function to make predictions using Linear Regression
+def make_predictions(X, y, periods=90):
+    model = LinearRegression()
+    model.fit(X, y)
+    future_days = np.array(range(X[-1][0] + 1, X[-1][0] + 1 + periods)).reshape(-1, 1)
+    predicted_values = model.predict(future_days)
+    return future_days, predicted_values
 
 # Function to calculate percentage change
 def calculate_percentage_change(stock_data):
@@ -37,6 +41,20 @@ def get_stock_stats(stock_data):
     low_value = stock_data['Close'].min()
     return high_value, low_value
 
+# Function to plot stock performance
+def plot_stock_performance(stock_data, predicted_dates, predicted_values):
+    plt.figure(figsize=(10, 5))
+    plt.plot(stock_data['Date'], stock_data['Close'], label="Historical Data", color="blue")
+    plt.plot(predicted_dates, predicted_values, label="Predicted Data", color="orange")
+    plt.xlabel("Date")
+    plt.ylabel("Stock Price")
+    plt.title("Stock Performance (Historical vs Predicted)")
+    plt.legend()
+    plt.grid(True)
+    plt.tight_layout()
+    plt.savefig("stock_performance.png")
+    return "stock_performance.png"
+
 # Main function for UI
 def stock_prediction(ticker, start_date, end_date):
     stock_data = get_stock_data(ticker, start_date, end_date)
@@ -46,21 +64,23 @@ def stock_prediction(ticker, start_date, end_date):
     high_value, low_value = get_stock_stats(stock_data)
     
     # Prepare data for prediction
-    df = prepare_data(stock_data)
-    forecast = make_predictions(df)
+    X, y = prepare_data(stock_data)
+    future_days, predicted_values = make_predictions(X, y)
     
     # Generate buy/sell suggestion (simple rule-based)
     suggestion = "Buy" if percentage_change < 0 else "Sell"
     
-    # Historical stock performance and predicted future trend
-    historical_chart = stock_data[['Date', 'Close']]
-    predicted_chart = forecast[['ds', 'yhat']]
+    # Create prediction dates
+    predicted_dates = pd.date_range(start=stock_data['Date'].max(), periods=len(predicted_values), freq='D')
+    
+    # Plot stock performance
+    plot_file = plot_stock_performance(stock_data, predicted_dates, predicted_values)
     
-    return historical_chart, predicted_chart, percentage_change, high_value, low_value, suggestion
+    return plot_file, percentage_change, high_value, low_value, suggestion
 
 # UI setup
 with gr.Blocks() as app:
-    gr.Markdown("# Stock Prediction App")
+    gr.Markdown("# Stock Prediction App using Linear Regression")
     
     stock_ticker = gr.Dropdown(
         label="Select Stock Ticker", 
@@ -70,8 +90,7 @@ with gr.Blocks() as app:
     start_date = gr.DatePicker(label="Start Date", value=datetime.date(2023, 1, 1))
     end_date = gr.DatePicker(label="End Date", value=datetime.date.today())
     
-    historical_chart_output = gr.LinePlot(label="Historical Stock Performance")
-    predicted_chart_output = gr.LinePlot(label="Predicted Future Stock Performance")
+    plot_output = gr.Image(label="Stock Performance (Historical vs Predicted)")
     percentage_change_output = gr.Textbox(label="Percentage Change")
     high_value_output = gr.Textbox(label="Highest Stock Value")
     low_value_output = gr.Textbox(label="Lowest Stock Value")
@@ -83,7 +102,7 @@ with gr.Blocks() as app:
     predict_button.click(
         stock_prediction, 
         inputs=[stock_ticker, start_date, end_date], 
-        outputs=[historical_chart_output, predicted_chart_output, percentage_change_output, high_value_output, low_value_output, suggestion_output]
+        outputs=[plot_output, percentage_change_output, high_value_output, low_value_output, suggestion_output]
     )
 
 app.launch()