Use the RSI signal to drive algorithm buying and selling decisions. When the RSI is over 70, a stock is considered overbought and is sold. On the other hand, when the RSI is below 30, a stock is considered oversold and is bought. Here is additional information from Investorpedia.

Download and install Anaconda

Create a new environment in your conda navidagor or terminal and use Python version 3.5 given dependencies.

$ conda create -n env_zipline python=3.5

Activate the new environment.

$ conda activate env_zipline

Install the Zipline backtesting library from Quantopian.

$ conda install -c Quantopian zipline

Install interactive Python shell and a Jupyter kernel to work with Python code in Jupyter notebooks and other interactive frontends.

$ conda install -c anaconda ipykernel

Install the Python wrapper for TA-Lib

$ pip install TA-Lib

Install Pyfolio, see documentation here for more information.

pip install pyfolio

Obtain a free API key from Quandl

Set an environmental variable in your terminal with your API key.

$ export QUANDL_API_KEY='your API key here'

Ingest the Quandl Wiki Prices data into Zipline

$ zipline ingest -b quandl

Run the below code in your terminal, check the Zipline Documentation for additional information.

$ zipline run -f backtest.py --start 2014-1-1 --end 2018-1-1 -o perf.pickle --no-benchmark --capital-base 20000 --bundle quandl