tree
GitHub利用决策树模型分析数据,识别影响目标变量的关键规则。涵盖特征处理、模型训练验证及可视化报告,强调可解释性并避免因果混淆。
触发场景
需要构建决策树模型
进行特征重要性分析
生成可解释的规则报告
安装
npx skills add Zafer-Liu/Data-Analysis-Agent --skill tree -g -y
SKILL.md
Frontmatter
{
"icon": "🌳",
"name": "tree",
"description": "使用决策树识别影响目标变量的关键规则(decision tree 决策树)",
"allowedTools": [
"get_schema",
"query_data",
"run_analysis",
"generate_chart"
]
}
决策树分析
确认目标变量和任务类型,排除泄漏字段,合理处理缺失值与类别变量。执行训练验证并报告性能、重要特征和可解释规则;避免把相关性表述为因果。
Tool routing
- Use
get_schemato identify the target, candidate features, task type, and source table. - Use
query_datato verify field names, target distribution, missingness, and leakage risks. - Use
run_analysiswithanalysis_name="Decision_Tree"for the actual tree computation. - Use
generate_charton tree, feature importance, or validation result tables afterrun_analysissucceeds.
Implementation reference
- Tool entry:
agent/tools/business/data.py::_tool_run_analysis - Analysis registry:
Function/Analyze/registry.py - Analysis implementation:
Function/Analyze/Decision_Tree/analyze.py - Chart implementation:
Function/Charts_generation/chart_generate.py
版本历史
- d6a2c3e 当前 2026-07-24 12:13


