app.py

import yfinance as yf
import pandas as pd
import numpy as np
import gradio as gr
from prophet import Prophet
import plotly.graph_objs as go

# Stock tickers for dropdown
tickers = ["AAPL", "GOOGL", "MSFT", "AMZN", "TSLA", "META", "NFLX", "NVDA", "JPM", "BAC"]

# Function to fetch and process stock data
def get_stock_data(ticker, start_date, end_date):
    data = yf.download(ticker, start=start_date, end=end_date)
    data.reset_index(inplace=True)
    return data

# Train Prophet model
def train_model(data):
    df = data[['Date', 'Close']].rename(columns={"Date": "ds", "Close": "y"})
    model = Prophet()
    model.fit(df)
    return model

# Predict future stock prices
def make_predictions(model, periods=90):
    future = model.make_future_dataframe(periods=periods)
    forecast = model.predict(future)
    return forecast

# Function to generate buy/sell prediction
def predict_stock(ticker, start_date, end_date):
    data = get_stock_data(ticker, start_date, end_date)
    
    # Train the model
    model = train_model(data)
    
    # Make predictions
    forecast = make_predictions(model, periods=90)
    
    # Calculate statistics
    highest_value = data['Close'].max()
    lowest_value = data['Close'].min()
    percentage_change = ((data['Close'].iloc[-1] - data['Close'].iloc[0]) / data['Close'].iloc[0]) * 100
    last_close_price = data['Close'].iloc[-1]
    future_price = forecast['yhat'].iloc[-1]
    
    # Recommendation logic
    recommendation = "Buy" if future_price > last_close_price else "Sell"
    
    # Plotting the historical and predicted prices
    fig = go.Figure()
    fig.add_trace(go.Scatter(x=data['Date'], y=data['Close'], mode='lines', name='Historical Data'))
    fig.add_trace(go.Scatter(x=forecast['ds'], y=forecast['yhat'], mode='lines', name='Forecast Data'))
    fig.update_layout(title=f'Stock Price Prediction for {ticker}',
                      xaxis_title='Date', yaxis_title='Stock Price')
    
    return {
        "Highest Price": highest_value,
        "Lowest Price": lowest_value,
        "Percentage Change": f"{percentage_change:.2f}%",
        "Buy/Sell Recommendation": recommendation,
        "Graph": fig
    }

# Gradio UI Components
def app_ui():
    stock_ticker = gr.Dropdown(choices=tickers, label="Select Stock Ticker")
    start_date = gr.DatePicker(label="Select Start Date")
    end_date = gr.DatePicker(label="Select End Date")
    output = gr.outputs.JSON(label="Stock Prediction Results")
    
    # Define Gradio Interface
    interface = gr.Interface(
        fn=predict_stock,
        inputs=[stock_ticker, start_date, end_date],
        outputs=[output, gr.Plot(label="Stock Performance Graph")],
        live=True
    )
    
    interface.launch()

if __name__ == "__main__":
    app_ui()