Switch from volitility to price tomorrow

WebServer/AIPython/ai-predictor.py

@@ -17,7 +17,7 @@ def Predict():
         df = features.CleanDF(df)
 
     # Drop our predictor
-    df.drop('Volatility_5', axis=1, inplace=True)
+    df.drop('Target_Close_Tomorrow', axis=1, inplace=True)
 
     # Lazy load this so it doesnt interfere with yfinance
     from keras.models import load_model
@@ -34,6 +34,6 @@ def Predict():
     # 'predictions' will be a 2D array, flatten it if you want a simple list
     flat_predictions = predictions.flatten()
 
-    print(f"Predicted Volatility: {flat_predictions}")
+    print(f"Predicted Target_Close_Tomorrow: {flat_predictions}")
 
     return flat_predictions

WebServer/AIPython/ai-trainer.py

@@ -16,8 +16,8 @@ def TrainAI():
 
     # Load the dataset
     dataset = pd.read_parquet(os.path.join(DATA_DIR, "stocks.parquet"))
-    X = dataset.drop('Volatility_5', axis=1)
+    X = dataset.drop('Target_Close_Tomorrow', axis=1)
-    Y = dataset['Volatility_5']
+    Y = dataset['Target_Close_Tomorrow']
 
     # Show the datatypes
     print(dataset.dtypes)

WebServer/AIPython/features.py

@@ -23,6 +23,9 @@ def MakeFeatures(df, i):
     # Add feature for volitility last 20
     df['Volatility_20'] = df['Return'].transform(lambda x: x.rolling(20).std())
 
+    # This is our training metric
+    df['Target_Close_Tomorrow'] = df['Close'].shift(-1).pct_change()
+
     # Return new df with new features
     return df