Skip to main content

Auto Quant

Project description

PypI Versions PyPI - Downloads Python Versions Platform

AutoQuant

AutoQuant is an out-of-the-box quantitative investment platform.

It contains the full ML pipeline of data processing, strategy building(includes AI & traditionals), back-testing, and covers the entire chain of quantitative investment: alpha seeking, risk modeling, portfolio optimization, and order execution.

With AutoQuant, users can easily try ideas to create better Quant investment strategies.

Quick Start

Installation

pip install --upgrade autoquant

Data Preparation

from autoquant.collector import Collector
from autoquant import Market
from datetime import date

collector = Collector.default()

data = collector.daily_prices(
    market=Market.SZ, 
    code='002594', 
    start=date(2021, 11, 1), 
    end=date(2021, 11, 5)
)

data = collector.quarter_statement(
    market=Market.SH, 
    code='601318', 
    quarter=date(2021, 9, 30)
)
    

Backtest

from autoquant.collector import Collector
from autoquant.workflow import Workflow
from autoquant.broker import Broker
from autoquant import Market
from datetime import date

from autoquant.workflow import Workflow
from autoquant.strategy import MA_CrossOver


class SmaCross(MA_CrossOver):
    params = dict(fast=5, slow=20)


collector = Collector.default()
broker = Broker.default(kick_start=100000, commission=0.01)

data = collector.daily_prices(market=Market.SZ, code='002594', start=date(2020, 1, 1), end=date(2021, 11, 1))
w = Workflow().with_broker(broker).with_strategy(SmaCross).backtest(data)

w.visualize()

Advanced Topics

Market

AutoQuant support Shanghai, Shenzhen, HongKong and US markets now. Use Market Enum in codes:

from autoquant import Market

Market.SZ
Market.SH
Market.HK
Market.US

Metrics

  • Gross Rate Of Return
  • CAGR(Compound Annual Growth Rate)

Price Provider

  • BaostockProvider
  • TushareProvider

Financial Statement Provider

  • SnowballProvider

Contribution Guide

Test

Test all

PYTHONPATH=./ pytest

Test specified test

PYTHONPATH=./ pytest tests/<YOUR_DISIRE_FILE>.py -k "<YOUR_DISIRE_TEST_CASE>" -s

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

AutoQuant-0.3.1.tar.gz (9.3 kB view details)

Uploaded Source

Built Distribution

AutoQuant-0.3.1-py3-none-any.whl (12.0 kB view details)

Uploaded Python 3

File details

Details for the file AutoQuant-0.3.1.tar.gz.

File metadata

  • Download URL: AutoQuant-0.3.1.tar.gz
  • Upload date:
  • Size: 9.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.5.0 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.8.8

File hashes

Hashes for AutoQuant-0.3.1.tar.gz
Algorithm Hash digest
SHA256 694d9537e1829ef474d22bb0d40f868075fc82b5d3e7d423ad8328ba045f0748
MD5 d919d52a8db4e9206b872dabad7652e8
BLAKE2b-256 5b95837c09794ecae41411ae6f5e8c89b93378e5d38197cfee2bd8af0598fdbe

See more details on using hashes here.

File details

Details for the file AutoQuant-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: AutoQuant-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 12.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.5.0 importlib_metadata/3.10.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.8.8

File hashes

Hashes for AutoQuant-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 45d5d674134d44c8d542b1fef52734c4095aeb44c8903e32f018c3f87853e0db
MD5 f8d2623d87192d86ea963a0ebeffb1a0
BLAKE2b-256 dfefef4cdc6b0a2f4946efc3b0236116b2db53a4c06c31aaa7dc852fc9710530

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page