Update app.py

app.py

@@ -6,47 +6,51 @@ import plotly.express as px
 import scipy.optimize as sco
 from datetime import datetime, timedelta
 import random
-import yfinance as yf
+import requests
 import time
 
 def fetch_stock_data(tickers):
-    """Fetch real stock data using yfinance with retries"""
-    max_retries = 3
-    retry_delay = 2
-    data_frames = []
+    """Fetch real stock data using Alpha Vantage API"""
+    API_KEY = "Y86RZ52NQ8YVX7F6"  # Should be in environment variable in production
+    BASE_URL = "https://www.alphavantage.co/query"
+    all_data = {}
     
-    for retry in range(max_retries):
+    for ticker in tickers:
         try:
-            # Try to download data for each ticker individually
-            for ticker in tickers:
-                try:
-                    stock = yf.Ticker(ticker)
-                    hist = stock.history(period="1y")
-                    if not hist.empty:
-                        hist.columns = [f"{ticker}_{col}" for col in hist.columns]
-                        data_frames.append(hist[f"{ticker}_Close"])
-                    time.sleep(0.5)  # Add delay between requests
-                except Exception as e:
-                    print(f"Error fetching {ticker}: {str(e)}")
-                    continue
+            # Add delay to respect rate limits (5 API calls per minute for free tier)
+            time.sleep(12)  # 12 second delay between calls
+            
+            params = {
+                "function": "TIME_SERIES_DAILY_ADJUSTED",
+                "symbol": ticker,
+                "outputsize": "full",
+                "apikey": API_KEY
+            }
             
-            if data_frames:
-                # Combine all successful downloads
-                combined_data = pd.concat(data_frames, axis=1)
-                combined_data.columns = [col.replace("_Close", "") for col in combined_data.columns]
-                if not combined_data.empty:
-                    return combined_data
-                    
-            print(f"Retry {retry + 1}/{max_retries} - No data received")
-            time.sleep(retry_delay)
+            response = requests.get(BASE_URL, params=params)
+            data = response.json()
             
+            if "Time Series (Daily)" in data:
+                # Convert the time series data to DataFrame
+                df = pd.DataFrame.from_dict(data["Time Series (Daily)"], orient="index")
+                df = df.astype(float)
+                all_data[ticker] = df["4. close"].iloc[:252]  # Get last year of data
+                print(f"Successfully fetched data for {ticker}")
+            else:
+                print(f"No data found for {ticker}")
+                
         except Exception as e:
-            print(f"Error during retry {retry + 1}: {str(e)}")
-            time.sleep(retry_delay)
+            print(f"Error fetching {ticker}: {str(e)}")
+            continue
     
-    # If we reach here, use backup sample data
-    print("Using backup sample data")
-    return generate_sample_data(tickers)
+    if not all_data:
+        print("No data received, using backup data")
+        return generate_sample_data(tickers)
+        
+    # Combine all data and align dates
+    df = pd.DataFrame(all_data)
+    df = df.sort_index(ascending=True)
+    return df
 
 def generate_sample_data(tickers):
     """Generate sample data as backup"""
@@ -62,8 +66,14 @@ def generate_sample_data(tickers):
         
     return pd.DataFrame(data, index=dates)
 
-# Predefined S&P 500 Stock List (Sample tickers)
-SP500_TICKERS = ['AAPL', 'MSFT', 'GOOGL', 'AMZN', 'TSLA', 'BRK-B', 'NVDA', 'JPM', 'JNJ', 'V']
+# Updated S&P 500 Stock List (reduced number due to API rate limits)
+SP500_TICKERS = [
+    'AAPL',  # Apple
+    'MSFT',  # Microsoft
+    'GOOGL', # Google
+    'AMZN',  # Amazon
+    'TSLA'   # Tesla
+]
 
 def calculate_portfolio_metrics(weights, returns):
     portfolio_return = np.sum(returns.mean() * weights) * 252
@@ -96,8 +106,8 @@ def simulate_investment(weights, mu, years, initial_investment=10000):
 
 def output_results(risk_level):
     try:
-        # Select random tickers
-        selected_tickers = random.sample(SP500_TICKERS, min(len(SP500_TICKERS), 5))
+        # Select random tickers (reduced number due to API rate limits)
+        selected_tickers = random.sample(SP500_TICKERS, min(len(SP500_TICKERS), 3))
         
         # Fetch real stock data
         stocks_df = fetch_stock_data(selected_tickers)