Change date to number and normalize | 1 hot encode symbol

WebServer/AIPython/datapuller.py

@@ -15,7 +15,7 @@ def pull():
 
     # Scrape the data
     all_data = []
-    for i, symbol in enumerate(tickers): # Try first 20
+    for i, symbol in enumerate(tickers):
         print(f"Processing: {i} of {len(tickers)}")
         df = yf.download(symbol, period="max", auto_adjust=True)
         if not df.empty:
@@ -24,11 +24,10 @@ def pull():
             
             # 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)
+            df['Date'] = pd.to_numeric(pd.to_datetime(df['Date']))
 
-            # Add the Symbol column for tracking
-            df['Symbol'] = symbol
+            # Add the Symbol column for tracking | as an int 1 hot encoded
+            df['Symbol'] = i
         
             # Add feature Spread
             df['Spread'] = abs( df['High'] - df['Low'] )
@@ -48,6 +47,10 @@ def pull():
     print("Processing data")
     final_df = pd.concat(all_data)
 
+    # Nomralize the Date
+    final_df['Date'] = (final_df['Date'] - final_df['Date'].min()) / (final_df['Date'].max() - final_df['Date'].min())
+    final_df.set_index('Date', inplace=True)
+
     # Drop rows with null values
     final_df.dropna(inplace=True)