yacoubb/stock-trading-ml — reverse-engineered prompt

Build me a Python stock prediction and trading bot project that can download historical stock prices, save them to CSV, train a machine learning model, and then run a simple trading simulation using the trained model.

I want it to support choosing a stock symbol, preparing the dataset, training either a basic model or one that uses technical indicators, and showing how the trading strategy would have performed. Use common Python data science tools like pandas, numpy, scikit learn, keras, tensorflow, and matplotlib.

Please make it easy to run from the command line, with clear scripts for downloading data, training the model, and testing the trading algorithm. Include a requirements file and a simple README that explains setup, how to get stock data, how to change the symbol or history window, how to train, and how to run the simulated trading bot. Look up current docs online if you need to.