Là một dự án dữ liệu, polakowo/vectorbt đã đạt 9.6k sao trên GitHub, ngôn ngữ Python. The research engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
Tóm tắt dựng từ metadata GitHub của chính dự án — chưa có bài review TopGit. Trang sẽ tự động cập nhật khi bài review đầy đủ được xuất bản.
VÌ SAO CHƯA CÓ REVIEW
TopGit viết bài đầy đủ cho repo có nhiều sao nhất và được yêu cầu nhiều nhất. Trang này là snapshot trong thời gian chờ — xem README gốc ở tab READ ME.
简体中文 / English |
Features ·
Installation ·
Examples ·
Links
Trading research at scale.
VectorBT is a Python toolkit for trading research. Explore market data, build indicators and signals, and compare thousands of ideas across assets and timeframes. NumPy arrays, Numba acceleration, and an optional Rust engine let you run large experiments in a few lines of Python.
Move from exploring price patterns to evaluating strategies in one workflow. Inspect trades, fees, drawdowns, and portfolio performance, then explore the results with interactive charts. Built for traders, researchers, and AI agents, VectorBT brings data analysis, strategy simulation, and visualization together in a composable Python API.
VectorBT is the open-source community edition of VectorBT PRO.
PRO extends the library with parallelization, additional data integrations, portfolio optimization,
pattern recognition, event projections, limit orders, leverage, and over 100 other features,
with new features added weekly.
See VectorBT vs PRO or browse
PRO feature examples.
Features
Fast, vectorized backtesting
Research strategies at scale with pandas, NumPy, and Numba.
Backtesting examples →
Optional Rust engine
Use precompiled kernels for supported operations without JIT compilation.
Rust engine →
Pandas-native API
Work with custom accessors and high-performance operations directly on pandas objects.
Pandas integration →
Flexible broadcasting
Analyze multiple assets and sweep large parameter grids with flexible array broadcasting.
Broadcasting API →
Rich indicator ecosystem
Build custom indicators and use integrations for TA-Lib, Pandas TA, and more.
Indicator features →
Portfolio backtesting
Analyze trades, drawdowns, and performance, with QuantStats integration.
Portfolio analysis →
Signal tooling
Generate, rank, map, and analyze the distribution of trading signals.
Signal features →
Built-in data access
Fetch market data, preprocess it, and generate synthetic time series.
Data features →
Robustness testing
Run walk-forward optimization and generate labels for machine learning workflows.
Robustness testing →
Interactive visualization
Explore results with Plotly charts, Jupyter widgets, and browser dashboards.
Plotting features →
Automation tools
Schedule data updates and send Telegram notifications.
Scheduling and notifications →
Composable Python API
Combine building blocks for rapid experimentation and AI agent-driven workflows.
Python workflows →
Installation
pip install -U vectorbt
To install the optional Rust engine:
pip install -U "vectorbt[rust]"
To install all optional integrations (TA-Lib, Pandas TA, etc.):
pip install -U "vectorbt[full]"
To install all optional integrations together with the Rust engine:
pip install -U "vectorbt[full,rust]"
Examples
Invest $100 in Bitcoin since 2014
import vectorbt as vbt
data = vbt.YFData.download("BTC-USD")
price = data.get("Close")
pf = vbt.Portfolio.from_holding(price, init_cash=100)
print(pf.total_profit())
Use random search to sample a large
parameter grid, or conditional parameters
to exclude combinations such as a fast MA window longer than the slow MA window. The
cross-validation tutorial
shows how to select parameters on training data and evaluate them on later periods.
Inspect any strategy configuration
print(pf[(10, 20, "ETH-USD")].stats())
Output:
Start 2017-11-09 00:00:00+00:00
End 2026-01-03 00:00:00+00:00
Period 2978 days 00:00:00
Start Value 100.0
End Value 1604.093789
Total Return [%] 1504.093789
Benchmark Return [%] 866.094127
Max Gross Exposure [%] 100.0
Total Fees Paid 204.226289
Max Drawdown [%] 70.734951
Max Drawdown Duration 1095 days 00:00:00
Total Trades 81
Total Closed Trades 80
Total Open Trades 1
Open Trade PnL -14.232533
Win Rate [%] 41.25
Best Trade [%] 120.511071
Worst Trade [%] -27.772271
Avg Winning Trade [%] 27.265519
Avg Losing Trade [%] -9.022864
Avg Winning Trade Duration 32 days 20:21:49.090909091
Avg Losing Trade Duration 8 days 16:51:03.829787234
Profit Factor 1.275515
Expectancy 18.979079
Sharpe Ratio 0.861945
Calmar Ratio 0.572758
Omega Ratio 1.20277
Sortino Ratio 1.301377
Name: (10, 20, ETH-USD), dtype: object
Plot any strategy configuration
pf[(10, 20, "ETH-USD")].plot().show()
Output:
Animate Bollinger Bands across multiple symbols
VectorBT goes beyond backtesting, with tools for financial data analysis and visualization:
Visit the website for more examples, documentation, and guides.
Example apps
Candlestick Patterns
Explore candlestick patterns interactively and backtest their signals with VectorBT.
Links
Website
Docker images
Colab notebook
License
This work is fair-code distributed under the Apache 2.0 with Commons Clause license.
The source code is publicly available, and everyone (individuals and organizations) may use it for free. However, you may not sell products or services that are primarily this software.
If you have questions or want to request a license exception, please contact the author.
Installing optional dependencies may be subject to a more restrictive license.
Contributors
Thanks to everyone who has contributed to VectorBT!
Star History
Disclaimer
This software is for educational purposes only. Do not risk money you cannot afford to lose.
Use the software at your own risk. The authors and affiliates assume no responsibility for your trading results.
Trang TopGit này là một snapshot — tab "Readme" hiển thị nguyên văn README của repo (đã bỏ link, giữ ảnh). Repo GitHub ở github.com/polakowo/vectorbt là nguồn chính thức.
polakowo/vectorbt có bao nhiêu sao?
polakowo/vectorbt có 9.6k sao GitHub — tải lại trang để xem số mới nhất, hoặc xem trực tiếp github.com/polakowo/vectorbt. TopGit phản chiếu số sao của GitHub nhưng không cam kết đến từng phút.
polakowo/vectorbt có phải mã nguồn mở không?
TopGit chưa ghi nhận license cho polakowo/vectorbt. Phần lớn repo public trên GitHub là mã nguồn mở, nhưng điều khoản khác nhau từng repo — mở file LICENSE để xác nhận.
polakowo/vectorbt còn đang phát triển không?
Commit gần nhất trên polakowo/vectorbt là 3 tháng trước (theo timestamp GitHub). Repo có 1.2k fork — một chỉ báo về mức độ quan tâm của cộng đồng.
polakowo/vectorbt là gì?
polakowo/vectorbt (polakowo/vectorbt) là dự án Python trên GitHub. Theo mô tả gốc: The research engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
polakowo/vectorbt so với các dự án Data khác thế nào?
polakowo/vectorbt được TopGit xếp vào nhóm Data, với 9.6k sao GitHub và viết bằng Python. Xem trang chủ đề Data trên TopGit để so sánh với các dự án tương tự theo số sao và mức độ hoạt động.
Đọc đầy đủ README ở tab phía trên.
Muốn nghe thêm một ý kiến về vectorbt?
Hỏi một AI đọc được trang này — một cú bấm là có ngay nhận định về vectorbt.
/vectorbt
