Scale the data before learning to normalize the output

WebServer/AIPython/ai-trainer.py

@@ -2,6 +2,8 @@ import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 import datapuller
+import features
+import joblib
 import os
 os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 from sklearn.model_selection import train_test_split
@@ -20,13 +22,12 @@ def TrainAI(include_pull):
     # Load the dataset
     dataset = pd.read_parquet(os.path.join(DATA_DIR, "stocks.parquet"))
 
-    # Replace Infinity with 0 -> This fixes the AI mental breakdown
-    dataset['Volume_Chg'] = dataset['Volume_Chg'].replace([np.inf, -np.inf], 0)
+    # Create the X, Y vareables
+    X, Y, X_Scaler, Y_Scaler = features.Prepare(dataset)
 
-    # Remove indicators and set the target
-    X = dataset.drop('Target_Close', axis=1)
-    X = dataset.drop('Target_Direction', axis=1)
-    Y = dataset['Target_Close']
+    # Save the scalers for future use
+    joblib.dump(X_Scaler, os.path.join(DATA_DIR, "feature_scaler.pkl"))
+    joblib.dump(Y_Scaler, os.path.join(DATA_DIR, "target_scaler.pkl"))
 
     # Show the datatypes
     print(dataset.dtypes)