frozen-quant 3.2.2

A Quantitative Backtest Framework

📰 What's NEW!   ✨

Recent released features

Feature	Status
Data ETL pipeline	🔨Released on Nov 3, 2024
Parameter tuning by optuna	🔨Released on Oct 23, 2024
Release Frozen v3.0.0	📈Released on Sep 15, 2024
Integrate Qlib machine learning extension	📈Released on Aug 20, 2024
ETF backtest engine	📈Released on Jul 21, 2024
Factor database	🔨Released on Jun 29, 2024
Release Frozen v2.6.0	📈Released on Jun 13, 2024
DuckDB support for data module	📈Released on May 14, 2024
3D-GPlearn factor mining extension	:octocat: Released on Apr 7, 2024
Integrate Qlib factor expression engine	📈Released on Feb 25, 2024
Factor expression engine	🔨Released on Feb 17, 2024
Parallel computation example	🔨Released on Jan 14, 2024
Release Frozen v2.0.0	📈Released on Dec 18, 2023
Release Frozen v1.0.0	📈Released on Apr 24 2023

Frozen is an advanced factor-driven quantitative research platform, powered by a sophisticated event-driven backtesting engine and cutting-edge portfolio optimization engine. The framework aims to seamlessly integrate data processing, research analytics, back-testing, and live-trading into a unified pipeline, while standardizing factor research procedures through a systematic and rigorous approach.

The framework covers the entire chain of quantitative investment: alpha seeking, risk modeling, portfolio optimization, and order execution, enabling researchers and practitioners to efficiently transform their investment hypotheses into implementable strategies. With Frozen's robust architecture and intuitive interface, users can rapidly prototype, validate, and deploy sophisticated quantitative investment strategies with institutional-grade reliability. For more details, please refer to project website

Frameworks, Tutorial, Data & DevOps	Solutions in Auto Quant Research
Plans Framework of Frozen Quick Start Installation Data Preparation Factor Research Workflow Paper Reproduction Factor Mining Investment Strategy Portfolio Optimization Paramemter Tuning Learning Framework Related Reports	Auto Quant Research Workflow Data ETL Pipeline Workflow Orchestration Scheduled Run Automatic Signal Generation Live Trading & Order Execution Algorithms Interactive Visualization Tools Real-Time Monitor Panel Web UI Design Mobile App

Plans

New features under development (order by estimated release time).

Framework of Frozen

Quick Start

This quick start guide tries to demonstrate

1. It's very easy to build a complete Quant research workflow and try your ideas with Frozen.
2. Though with public data and simple models, traditional factors work very well in practical Quant investment.

Here is a quick demo shows how to install Frozen, and run Alpha101 strategy with frun. But, please make sure you have already prepared the data following the instruction.

Installation

This table demonstrates the supported Python version of Frozen:

	install with pip	install from source	Data ETL
Python 3.9	✔️	✔️	❌
Python 3.10	✔️	✔️	✔️
Python 3.11	✔️	✔️	✔️

Note:

1. Conda is suggested for managing your Python environment. In some cases, using Python outside of a conda environment may result in missing header files, causing the installation failure of certain packages.
2. Python introduced match-case expression in version 3.10, which is incorporated in data ETL pipeline. Thus, for python 3.9, users will have to roll back manually to if-else expression.

Install with pip

Users can easily install Qlib by pip according to the following command.

  pip install frozen

Note: pip will install the latest stable frozen. However, the main branch of frozen is in active development. If you want to test the latest scripts or functions in the main branch. Please install frozen with the methods below.

Install from source

Also, users can install the latest dev version Frozen by the source code according to the following steps:

• It is recommended that users create a seperate environment for better management

  # if you prefer to use virtual environment, uncomment the following
  # python -m venv .venv
  # source .venv/bin/activate
  
  # if you prefer to use conda environment, run below
  conda create -n frozen python=3.11
  

• Before installing Frozen from source, users need to install some dependencies:

  pip install numpy
  pip install --upgrade  cython
  

• Download the repository and install Frozen as follows.

  pip install .  # `pip install -e .[dev]` is recommended for development.
  

  Note: You can install Frozen with python setup.py install as well. But it is not the recommended approach. It will skip pip and cause obscure problems. For example, only the command pip install . can overwrite the stable version installed by pip install pyfrozen, while the command python setup.py install can't.

Data Preparation

Factor Research Workflow

Paper reproduction

Factor Mining

Investment Strategy

Portfolio Optimization

Parameter Tuning

Auto Quant Research Workflow

Data ETL Pipeline

Workflow Orchestration

Frozen arrange workflow with Prefect

Scheduled Run

with cron

Automatic Signal Generation

Live Trading & Order Execution Algorithms

Interactive Visualization Tools

Real-Time Monitor Panel

with Grafana

Web UI Design

with Streamlit

Mobile App Design

with Flutter

# if you want to conduct ETL task flow orchestration
prefect config set PREFECT_API_URL="http://127.0.0.1:4200/api"
prefect server start