lib-pybroker 1.0.11

Algorithmic trading with machine learning

Algorithmic Trading in Python with Machine Learning

PyBroker is a Python framework for developing algorithmic trading strategies, especially those that use machine learning. With PyBroker, it is easy to write trading rules, build models, and analyze a strategy's performance.

Key Features

• Fast backtesting engine built in NumPy with Numba acceleration.
• Easily write trading rules and models that execute on multiple instruments.
• Download historical data from Alpaca and Yahoo Finance.
• Train and backtest models using Walkforward Analysis to simulate real trading.
• Includes robust metrics calculated from randomized bootstrapping.
• Caching of downloaded data, indicators, and models for faster development.
• Parallelized computations for faster performance.

Installation

PyBroker supports Python 3.9+ on Windows, Mac, and Linux. You can install PyBroker using pip:

    pip install lib-pybroker

Or you can clone the Git repository with:

    git clone https://github.com/edtechre/pybroker

A Quick Example

Code speaks louder than words! Here is a peek at what backtesting with PyBroker looks like:

   import pybroker
   from pybroker import Alpaca, Strategy

   def train_fn(train_data, test_data, ticker):
      # Train the model using indicators stored in train_data.
      ...
      return trained_model

   # Register the model and its training function with PyBroker.
   my_model = pybroker.model('my_model', train_fn, indicators=[...])

   def exec_fn(ctx):
      preds = ctx.preds('my_model')
      # Open a long position given my_model's latest prediction.
      if not ctx.long_pos() and preds[-1] > threshold:
         ctx.buy_shares = 100
      # Close the long position given my_model's latest prediction.
      elif ctx.long_pos() and preds[-1] < threshold:
         ctx.sell_all_shares()

   alpaca = Alpaca(api_key=..., api_secret=...)
   strategy = Strategy(alpaca, start_date='1/1/2022', end_date='7/1/2022')
   strategy.add_execution(exec_fn, ['AAPL', 'MSFT'], models=my_model)
   # Run Walkforward Analysis on 1 minute data using 5 windows with 50/50 train/test data.
   result = strategy.walkforward(timeframe='1m', windows=5, train_size=0.5)

Online Documentation

To learn how to use PyBroker, head over to the online documentation.

Contact