Ml4t Book Notebooks

基于《Machine Learning for Trading》第二版配套 notebooks 实现量化交易策略开发与回测，涵盖多市场金融数据的时间序列机器学习分析。

This package appears to be a collection of docs/blueprints for zvt-based quant notebooks and is internally consistent with that purpose. Before you run it: 1) Confirm your environment has Python 3.12+ (the manifest did not declare it) and clarify what the author means by the "uv" package manager (may be a typo or an undocumented requirement). 2) Inspect seed.yaml and the LOCKS.md/PC-* preconditions — the skill expects to run local Python checks, may call pip to install zvt and will create/check ~/.zvt (writes to your home). If you don't want packages installed or dirs created automatically, do not run the automated preconditions; instead manually review and run only the commands you trust. 3) There are no requested credentials, but verify there is no hidden code (this is instruction-only here, but if you later download code or run commands that fetch code, inspect those sources). 4) If you plan to use real brokers or execution paths, audit any later code that performs network or order execution — this skill enforces strong semantic locks (e.g., no look-ahead, T+1 rules) that will affect trading behavior. If any of the above is unclear, treat the skill as untrusted until you can verify the exact runtime commands and dependencies.

Type: OpenClaw Skill Name: ml4t-book-notebooks Version: 0.3.3 The skill bundle is a comprehensive framework for quantitative trading and machine learning based on the 'Machine Learning for Trading' curriculum. It includes robust safety mechanisms, such as 'Semantic Locks' (SL-01 to SL-12) and 'Fatal Constraints' (finance-C-*), specifically designed to prevent common financial modeling errors like look-ahead bias and improper order sequencing. While the bundle utilizes high-risk capabilities including web scraping (Scrapy/Selenium) and shell execution for environment setup, these actions are strictly aligned with the stated purpose of collecting alternative financial data and managing the ZVT trading library. No evidence of malicious intent, data exfiltration, or harmful prompt injection was found; in fact, the configuration explicitly forbids hardcoding credentials (finance-C-004) and enforces physical plausibility checks on trading results (OV-03).