Upload data_fetcher.py

src/data_fetcher.py

@@ -24,40 +24,63 @@ class DataFetcher:
 
     def fetch_market_data(self, days=50):
         """
-        Fetches raw OHLCV and VIX data from Yahoo Finance.
-        Falls back to local CSV in the data/ folder if Yahoo blocks the server IP.
+        Fetches market data using Finnhub (SPY as proxy) with a CSV fallback.
         """
-        print(f"📡 Attempting to fetch last {days} days of {self.ticker} and {self.vix_ticker}...")
+        print(f"📡 Attempting to fetch last {days} days from Finnhub (using SPY proxy)...")
         
         try:
-            # 1. TRY TO FETCH LIVE DATA
-            #df = yf.download(self.ticker, period=f"{days}d", interval="1d", progress=False)
-            #df_vix = yf.download(self.vix_ticker, period=f"{days}d", interval="1d", progress=False)
-
-            # Handle yfinance MultiIndex columns if they exist
-            if isinstance(df.columns, pd.MultiIndex):
-                df.columns = df.columns.get_level_values(0)
-            if isinstance(df_vix.columns, pd.MultiIndex):
-                df_vix.columns = df_vix.columns.get_level_values(0)
-
-            df['VIX'] = df_vix['Close']
-            df = df.ffill() 
+            # 1. Setup Timestamps (Finnhub needs Unix seconds)
+            end_ts = int(time.time())
+            start_ts = int((datetime.now() - timedelta(days=days+10)).timestamp())
+
+            # 2. Fetch SPY (S&P 500 Proxy)
+            # '1' means daily candles
+            res = self.finnhub_client.stock_candles('SPY', 'D', start_ts, end_ts)
+            
+            if res.get('s') != 'ok':
+                raise ValueError(f"Finnhub API returned status: {res.get('s')}")
+
+            # Convert Finnhub response to DataFrame
+            df = pd.DataFrame({
+                'Date': pd.to_datetime(res['t'], unit='s'),
+                'Close': res['c'],
+                'Open': res['o'],
+                'High': res['h'],
+                'Low': res['l'],
+                'Volume': res['v']
+            }).set_index('Date')
+
+            # 3. Handle VIX (Finnhub free tier often blocks ^VIX)
+            # We attempt it, but if it fails, we merge from our backup data
+            try:
+                vix_res = self.finnhub_client.stock_candles('VIX', 'D', start_ts, end_ts)
+                if vix_res.get('s') == 'ok':
+                    df['VIX'] = vix_res['c']
+                else:
+                    raise Exception("VIX not available on API")
+            except:
+                print("⚠️ VIX not available on Finnhub. Pulling VIX from backup...")
+                backup_df = pd.read_csv("data/market_data_backup.csv", index_col=0, parse_dates=True)
+                # Reindex backup to match the dates we just got from the API
+                df['VIX'] = backup_df['VIX'].reindex(df.index, method='ffill')
+
+            # Final cleanup
+            df = df.ffill().dropna()
             
-            # If the dataframe is empty (Yahoo stealth-blocked us), force an error
             if df.empty:
-                raise ValueError("Yahoo Finance returned empty data.")
-                
+                raise ValueError("Resulting DataFrame is empty.")
+
             return df
-            
+
         except Exception as e:
-            # 2. FALLBACK TO LOCAL CSV IF BLOCKED
-            print(f"⚠️ Live fetch failed ({e}). Loading backup data from data/ folder...")
-            
-            # Load the CSV from your new data folder
+            print(f"⚠️ Finnhub fetch failed ({e}). Loading full backup from data/ folder...")
             backup_path = "data/market_data_backup.csv"
-            df_backup = pd.read_csv(backup_path, index_col=0, parse_dates=True)
             
-            # Return only the requested number of days
+            if not os.path.exists(backup_path):
+                print(f"🚨 FATAL: {backup_path} not found!")
+                return pd.DataFrame() # This will trigger your safety check in Processor
+                
+            df_backup = pd.read_csv(backup_path, index_col=0, parse_dates=True)
             return df_backup.tail(days)
 
     # 🛡️ STREAMLIT CACHE: Ignores '_self' so it doesn't try to hash the Finnhub client.