Skip to content

Library for managing crypto currency assets and allow easy analysis as well as reinforcement learning strategies.

Notifications You must be signed in to change notification settings

guillaume-marion/crypto-invest

Repository files navigation

The cryptoast library provides functionalities for retrieving, storing, and analyzing data. Potenially it also provides functionalities for taking actions based on this data; Either through inferred signals' thresholds or by using a reinforcement learning model on top of it.

 

Optional third-party apis used are:

  • BINANCE for data retrieval and order execution
  • AWS for data storage (optional, local storage can be used)

 

Main prerequisites

  • pandas
  • numpy
  • gym
  • ta
  • s3fs
  • tensorflow
  • scikit-learn
  • python-binance
  • stable-baselines

 

Main functionalities

A number of packages and subsequent modules are available:

 

base.kline.Kline

Object for asset-specific data storage, retrieval, and analysis (through ta indicators and derived signals).

 

base.klines.Klines

Object for regrouping multiple Kline objects, and representing them as a readable list of official asset acronyms.

 

base.klines.KLMngr

Management object for all available assets.

 

model.agents.Backtest

In-house backtester, feedable to a reinforcement-learning agent.

 

model.agents.SingleAssetEnv

Single Asset Environment for reinforcement-learning purposes.

 

Installation

pip install -e cryptoast

 

Minimal example

Local storage update and average signal example.

from binance.client import Client
from cryptoast.base.kline import Kline

client = Client('key', 'secret')
kline = Kline('ETHUSDT')
kline.update(client, store=True)
if kline.signals.iloc[-1, :].eq(1).mean() > .5:
    print('buy')

 

Notebook examples

Examples.ipynb

Notebook showing cryptoast's core functionalities.

 

implementation_rl.ipynb

Testing notebook showing mainly: initialization, data update, dummy buy-sell signal computations and rl implementation tryouts.

 

Exploration.ipynb

Exhaustive testing notebook showing amongst other: initialization, data update, single-asset buy-sell signal computation tryouts, multi-asset buy-sell signal computation tryouts, rl implementation tryouts, categorical modeling tryouts, etc.

 

Disclaimer

No relation whatsoever to http://cryptoast.fr

About

Library for managing crypto currency assets and allow easy analysis as well as reinforcement learning strategies.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages