Remove the hard coded block for feature count and disable CUDA

WebServer/AIPython/ai-predictor.py

@@ -1,4 +1,5 @@
 import os
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 import yfinance as yf
 import features
 import matplotlib

WebServer/AIPython/ai-trainer.py

@@ -3,6 +3,7 @@ import numpy as np
 import matplotlib.pyplot as plt
 import datapuller
 import os
+os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 from sklearn.model_selection import train_test_split
 from keras import Sequential, layers, optimizers
 
@@ -31,7 +32,7 @@ def TrainAI():
 
     # Start with a linear model
     dnn_linear_model = Sequential([
-        layers.Input(shape=(9,)), # Explicitly tell Keras there are 9 features
+        layers.Input(shape=(train_features.shape[1],)), # Load the feature count dynamically
         normalizer,
         layers.Dense(64, activation='relu'),
         layers.Dense(64, activation='relu'),

dockerfile

@@ -58,8 +58,9 @@ RUN wget https://www.python.org/ftp/python/3.11.0/Python-3.11.0.tgz && \
     ln -s /usr/local/bin/python3.11 /usr/local/bin/python && \
     ln -s /usr/local/bin/pip3.11 /usr/local/bin/pip
 
+# Dont use CUDA for the tensorflow as the CPU is way faster for this smaller workload
 RUN pip install --upgrade pip && \
-    pip install tensorflow[and-cuda] \
+    pip install tensorflow \
     fastparquet \
     openpyxl \
     yfinance \