Add in my working data source

Data/datapuller.py

@@ -0,0 +1,49 @@
+import yfinance as yf
+import pandas as pd
+
+# Import the S&P 500 symbols
+symbols = pd.read_excel("./Data/stock_symbols.xlsx")
+symbols.columns = symbols.columns.str.strip()
+tickers = symbols['Symbol'].tolist()
+
+# Scrape the data
+all_data = []
+for i, symbol in enumerate(tickers[:2]): # Try first 20
+    print(f"Processing: {i} of {len(tickers)}")
+    df = yf.download(symbol, period="max")
+    if not df.empty:
+        # Remove the ticker column
+        df.columns = df.columns.get_level_values(0)
+        
+        # Make sure Date is actually a Date Object
+        df = df.reset_index()
+        df['Date'] = pd.to_datetime(df['Date'], format="%Y-%m-%d")
+        df.set_index('Date', inplace=True)
+
+        # Add the Symbol column for tracking
+        df['Symbol'] = symbol
+    
+        # Add feature Spread
+        df['Spread'] = abs( df['High'] - df['Low'] )
+
+        # Add feature for Returns
+        df['Return'] = df['Close'].pct_change()
+
+        # Add feature for volitility last 5
+        df['Volatility_5'] = df['Return'].transform(lambda x: x.rolling(5).std())
+
+        # Add feature for volitility last 20
+        df['Volatility_20'] = df['Return'].transform(lambda x: x.rolling(20).std())
+
+        all_data.append(df)
+
+# Concatinate into a combined list and cache
+print("Processing data")
+final_df = pd.concat(all_data)
+
+# Drop rows with null values
+final_df.dropna(inplace=True)
+
+print("Writing data to file")
+final_df.to_parquet("./Data/stocks.parquet")
+final_df.head(200).to_csv("./Data/stocks_preview.csv")