sthasis100/IIOT-IDS ? reverse-engineered prompt

Build me a Python app for an AI powered intrusion detection system for IIoT network traffic, using the CIC IIoT dataset. It should load the attack and benign CSV files from a data folder, combine and preprocess them, then train and save a few models for detection, including a Random Forest, a deep neural network, a 1D CNN, and an LSTM autoencoder for anomaly detection.

I want one main script that can run the full pipeline, or skip training and just use saved models. Please also make a Streamlit dashboard that shows an overview of the traffic, live detection results, model performance, feature analysis, anomaly scores, network patterns, and a simple project info page.

Add clear logging, save the trained pipeline and metrics, and make it easy to run from the command line. If you need to check current docs for Streamlit or TensorFlow details, look them up online.