AlphaPurify - GitLite

KO | EN

gitlite — search

#javascript #python #hacktoberfest #typescript #golang #android #machine-learning #deep-learning #linux #docker #java #awesome-list #vue #open-source

AlphaPurify

(★ 416)

Extremely fast quantitative factor cleaning and backtesting library, based on Polars

파일 탐색기

최종 버전 다운로드 (.zip)

- __init__.py
- AlphaPurifier.py
- APr_utils.py
- Database.py
- Exposures.py
- FactorAnalyzer.py
- logo.jpg
- newplot.png
- newplot1.png
- newplot2.png
- newplot3.png
- newplot4.png
- newplot5.png
- newplot6.png
- newplot7.png
- newplot9.png
- pipeline.jpg
- AlphaPurifier.py
- Database.py
- Exposures.py
- FactorAnalyzer.py
- test_AlphaPurifier.py
- test_Exposures.py
- test_FctorAnalyzer.py
LICENSE
pyproject.toml
README.md
README_CN.md
README_CN2.md
requirements.txt
setup.ini
setup.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/eliasswu/AlphaPurify

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd AlphaPurify

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install alphapurify

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

3. Python

쉬움

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install alphapurify

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

![IC](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/logo.jpg)
<p align="center">
  <a href="https://pypi.python.org/pypi/alphapurify">
    <img src="https://img.shields.io/badge/python-3.10+-blue.svg?style=flat">
  </a>
  <a href="https://pypi.python.org/pypi/alphapurify">
    <img src="https://img.shields.io/pypi/v/alphapurify.svg?maxAge=60">
  </a>
  <a href="https://pypi.python.org/pypi/alphapurify">
    <img src="https://img.shields.io/pypi/status/alphapurify.svg?maxAge=60">
  </a>
  <a href="LICENSE">
    <img src="https://img.shields.io/pypi/l/alphapurify">
  </a>
  <a href="https://pypi.org/project/alphapurify/#files">
    <img src="https://img.shields.io/badge/platform-linux%20%7C%20windows%20%7C%20macos-lightgrey">
  </a>
</p>

<p align="center">
  <a href="README.md">English README</a> | <a href="README_CN.md">简体中文 README</a> | <a href="README_CN2.md">繁体中文 README</a>
</p>

# AlphaPurify: Factor research for quants

**AlphaPurify** Python library for factor construction, preprocessing, backtesting, and factor return attributions to help quants rapidly validate ideas.

---

## 4 Main Modules:

1.**`alphapurify.FactorAnalyzer`** — for IC/ Rank IC testing and Long/ Short/ Long-Short quantile backtests.

2.**`alphapurify.AlphaPurifier`** — for factor preprocessing, including 40+ Winsorization, Neutralization, and Standardization methods (e.g., ridge regression, lasso regression, PCA decomposition, etc.).

3.**`alphapurify.Database`** — for financial data aggregation, factor construction, and factor storage.

4.**`alphapurify.Exposures`** — for factor correlation analysis and factor-based return attribution.

---

## Pipeline Overview
![Pipeline](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/pipeline.jpg)
---

### Full Documents & Examples: **[English Docs](./examples)**

---

## Key Features:

### - Extremely Fast — Processes 4 Millions+ rows (15 years CSI 300) including long/short, long-short, IC backtests and creates 4 interactive reports in under 25 seconds (on a standard i7 CPU).

### - 40+ Preprocessing Methods — Built-in professional factor cleaning tools supporting workflows from ultra high-frequency to low-frequency data.

### - 1:1 Production-Grade Backtesting — Fully vectorized modeling of transaction fees, slippage, rebalancing, and dynamic weight drift to ensure reliable and rigorous backtest results.

### - White-Box Backtesting — Empowering you to visually track weight transitions and asset returns at ANY timestamp, for ANY position direction, and within ANY quantile bin.
---

## AlphaPurify vs Other Quant Libraries
| Feature / Library | AlphaPurify | Qlib | Backtrader | Alphalens | QuantStats | Pyfolio |
|:------------------|:------------|:--------|:------------|:------------|:-------------|:-------------|
| Computation Speed | 🚀 Extremely Fast (Rust vectorized + multiprocessing) | ❌ Slow (heavy infrastructure) | ⚠️ Medium | ✅ Fast | no backtest | no backtest |
| Factor Preprocessing (40+) | ✅ Built-in | ⚠️ Limited | ❌ No | ❌ No | ❌ No | ❌ No |
| OOM Protection | 🟢 High (Zero Copy) | ❌ Low (Heavy DataFrame Cache) | 🟢 High | 🟢 High | no backtest | no backtest |
| Cross-sectional Snapshot | ✅ Native | ❌ No | ❌ No | ❌ No | ❌ No | ❌ No |
| Setup Complexity | 🟢 Low | 🔴 High | 🟡 Medium | 🟢 Low | 🟢 Low | 🟢 Low |
| IC Analysis | ✅ Native | ✅ Yes | ❌ No | ✅Yes | ❌ No | ❌ No |
| Long / Short / Long-Short Rebalancing Quantile Backtest | ✅ Native | ✅ Yes | ⚠️ Indirect | ❌ No | ❌ No | ❌ No |
| Factor Return Attribution | ✅ Native | ⚠️ Indirect | ❌ No | ❌ No | ❌ No | ❌ No |
| Multi-Frequency Support | ✅ Any (microsecond → yearly) | ⚠️ Limited | ⚠️ Mostly daily | ⚠️ Mostly daily | ⚠️ Limited | ⚠️ Limited |
| Coupling | 🟢 Low | 🔴 High | 🟡 Medium | 🟢 Low | 🟢 Low | 🟢 Low |

While ``AlphaPurify`` may look similar to ``Alphalens``, it goes far beyond IC analysis and simple graphs.
It supports long, short, and long-short rebalancing backtests, factor cleaning, atributions and delivers a new generation of interactive visualizations by Plotly.

``AlphaPurify`` is different from libraries like ``QuantStats`` and ``Pyfolio``, which primarily focus on analyzing return curves and portfolio performance, not backtests. Compared to tools like ``Qlib`` and ``Backtrader``, ``AlphaPurify`` directly provides a lightweight, fast factor-driven rebalancing backtesting framework and more useful functions — eliminating the need for users to build custom pipelines or infrastructure in these libraries.

In short, ``AlphaPurify`` provide quants with a whole factor testing pipeline and beautiful interactive reports to rapidly validate ideas.

---

##  Quick Start

### 1.Install with pip
Users can easily install ``AlphaPurify`` by pip according to the following command.

```bash
pip install alphapurify
```
**Note**: pip will install the latest stable ``AlphaPurify``. However, the main branch of AlphaPurify is in active development. If you want to test the latest scripts or functions in the main branch. Please install ``AlphaPurify`` with clone.

---

### 2.Load your DataFrame
| datetime           | symbol | close | volume | alpha_003 | momentum_12_1 | vol_60 | beta_252 |
|:-------------------|:------|------:|------:|------:|--------------:|------:|--------:|
| 2024-01-01 09:30   | AAPL  | 189.9 | 120034 | 0.42 | 0.15 | 0.21 | 1.08 |
| 2024-01-01 09:31   | AAPL  | 190.0 | 98321  | 0.38 | 0.16 | 0.22 | 1.07 |
| 2024-01-01 09:32   | AAPL  | 190.4 | 101245 | 0.41 | 0.17 | 0.23 | 1.06 |
| 2024-01-01 09:30   | MSFT  | 378.5 | 84211  | -0.15 | -0.05 | 0.18 | 0.95 |
| 2024-01-01 09:31   | MSFT  | 378.9 | 90122  | -0.12 | -0.04 | 0.19 | 0.96 |
| 2024-01-01 09:32   | MSFT  | 379.1 | 95433  | -0.08 | -0.03 | 0.20 | 0.97 |

**P.S. Your DataFrame must include a time column, an asset identifier column, a price column, and your factor column to ensure proper usage.**

---

### 3.Creating backtesting reports
```bash
from alphapurify import AlphaPurifier, FactorAnalyzer, PureExposures

# preprocess
df = (
    AlphaPurifier(df, factor_col="alpha_003")
    .winsorize(method="mad")
    .standardize(method="zscore")
    .to_result()
)

#backtest
FA = FactorAnalyzer(base_df=df,
                    trade_date_col='datetime',
                    symbol_col='symbol',
                    price_col='close',
                    factor_name='alpha_003')
FA.run()
FA.create_long_return_sheet()
FA.create_long_short_return_sheet()
FA.create_short_return_sheet()
FA.create_single_fac_ic_sheet()

#contributions of other factors
Ex = PureExposures(
    base_df=df,
    trade_date_col='datetime',
    symbol_col='symbol',
    price_col='close',
    factor_name='alpha_003',
    exposure_cols=['momentum_12_1', 'vol_60', 'beta_252'],
)

Ex.run()
Ex.plot_pure_exposures()
Ex.plot_pure_returns()
Ex.plot_pure_exposures_and_returns()
Ex.plot_correlations()
```

---

## Examples of Backtesting Reports
### Portfolio for long positions only:
![P](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/newplot2.png)
### IC Analysis:
![RankIC](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/newplot6.png)
### Return attributions of other factors:
![IC2](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/newplot3.png)
![IC2](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/newplot4.png)

---
## What's NEW!💖 — FactorAnalyzer.trace( )
### 4.Cross-sectional Snapshot: Empowering you to visually track weight transitions and asset returns at ANY timestamp, for ANY position direction, and within ANY quantile bin!

```bash
#For example, if you want to see the situation of the first bin for quarterly rebalancing of long positions on 2012-09-28

FA.trace("Q",'2012-09-28 00:00:00',position="l",bins=[1])
```
---

![cross](https://raw.githubusercontent.com/eliasswu/AlphaPurify/main/assets/newplot7.png)

## Questions or Feedback?
If you have any questions, run into bugs, or want to suggest new features, feel free to open an issue or start a discussion. I'd love to hear from you!

---

### If you like AlphaPurify, please star & fork this project to support the development!

---

**Elias Wu**