# Responsible Machine Learning
*With Great Power Comes Great Responsibility*.
Voltaire (well, maybe)
How to develop machine learning models in a responsible manner? There are several topics worth considering:
* **Effective**. Is the model good enough? Models with low performance should not be used because they can do more harm than good. Communicate the performance of the model in a language that the user understands. Remember that the models will work on a different dataset than the training one. Make sure to assess the performance on the target dataset.
* **Transparent**. Does the user know what influences model predictions? Interpretability and explainability is important. If the model decisions affect us directly or indirectly, we should know where these decisions come from and how they can be changed.
* **Fair**. Does the model discriminate on the basis of gender, age, race or other sensitive attribute? Direct or indirect? It should not! Discrimination can come in many faces. The model may give lower scores, may have lower performance, or may be based on different variables for the protected population.
* **Secure**. Do not let your model be hacked. Every complex system has its vulnerabilities. Seek them out and fix them. Some users may use various tricks to pull model predictions onto their site.
* **Confidential**. Models are often built on sensitive data. Make sure that the data does not leak, so that sensitive attributes are not shared with unauthorized persons. Also beware of model leaks.
* **Reproducible**. Usually the model development process consists of many steps. Make sure that they are completely reproducible and thus can be verified one by one.
# Collection of tools for Visual Exploration, Explanation and Debugging of Predictive Models
*It takes a village to raise a <del>child</del> model*.
The way how we do predictive modeling is very ineffective. We spend way too much time on manual time-consuming and easy to automate activities like data cleaning and exploration, crisp modeling, model validation. We should be focusing more on model understanding, productisation and communication.
Here are gathered tools that can be used to make out work more efficient through the whole model lifecycle.
The unified grammar beyond DrWhy.AI universe is described in the [Explanatory Model Analysis: Explore, Explain and Examine Predictive Models](https://pbiecek.github.io/ema/) book.
## Lifecycle for Predictive Models
The DrWhy is based on an unified [Model Development Process](https://github.com/ModelOriented/DrWhy/blob/master/images/ModelDevelopmentProcess.pdf) inspired by RUP. Find an overview in the diagram below.
[![images/DALEXverse.png](images/DALEXverse.png)]( https://modeloriented.github.io/ModelDevelopmentProcess/ )
## The DrWhy.AI family
Packages in the `DrWhy.AI` family of models may be divided into four classes.
* **Model adapters**. Predictive models created with different tools have different structures, and different interfaces. Model adapters create uniform wrappers. This way other packages may operate on models in an unified way. `DALEX` is a lightweight package with generic interface. `DALEXtra` is a package with extensions for heavyweight interfaces like `scikitlearn`, `h2o`, `mlr`.
* **Model agnostic explainers**. These packages implement specific methods for model exploration. They can be applied to a single model or they can compare different models. `ingredients` implements variable specific techniques like Ceteris Paribus, Partial Dependency, Permutation based Feature Importance. `iBreakDown` implements techniques for variable attribution, like Break Down or SHAPley values. `auditor` implements techniques for model validation, residual diagnostic and performance diagnostic.
* **Model specific explainers**. These packages implement model specific techniques. `randomForestExplainer` implements techniques for exploration of `randomForest` models. `EIX` implements techniques for exploration of gbm and xgboost models. `cr19` implements techniques for exploration of survival models.
* **Automated exploration**. These packages combine series of model exploration techniques and produce an automated report of website for model exploration. `modelStudio` implements a dashboard generator for local and global interactive model exploration. `modelDown` implements a HTML website generator for global model cross comparison.
[![images/grammar_of_explanations.png](images/grammar_of_explanations.png)]( https://drwhy.ai/ )
Here is a more detailed overview.
--------------------
### [DALEX](http://github.com/ModelOriented/DALEX) <img src="https://modeloriented.github.io/DALEX/reference/figures/logo.png" align="right" width="100"/>
[![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/DALEX)](https://cran.r-project.org/package=DALEX) [![Build Status](https://api.travis-ci.org/ModelOriented/DALEX.png)](https://travis-ci.org/ModelOriented/DALEX) [![Coverage
Status](https://img.shields.io/codecov/c/github/ModelOriented/DALEX/master.svg)](https://codecov.io/github/ModelOriented/DALEX?branch=master)[![DrWhy-eXtrAI](https://img.shields.io/badge/DrWhy-BackBone-373589)](http://drwhy.ai/#BackBone)
The DALEX package (Descriptive mAchine Learning EXplanations) helps to understand how complex models are working. The main function [explain](https://modeloriented.github.io/DALEX/reference/explain.html) creates a wrapper around a predictive model. Wrapped models may then be explored and compared with a collection of local and global explainers. Recent developments from the area of Interpretable Machine Learning/eXplainable Artificial Intelligence.
DALEX wraps methods from other packages, i.e. 'pdp' (Greenwell 2017) <doi:10.32614/RJ-2017-016>, 'ALEPlot' (Apley 2018) <arXiv:1612.08468>, 'factorMerger' (Sitko and Biecek 2017) <arXiv:1709.04412>, 'breakDown' package (Staniak and Biecek 2018) <doi:10.32614/RJ-2018-072>, (Fisher at al. 2018) <arXiv:1801.01489>.
Vignettes:
* [General introduction: Survival on the RMS Titanic](https://modeloriented.github.io/DALEX/articles/vignette_titanic.html)
--------------------
### [DALEXtra](http://github.com/ModelOriented/DALEXtra) <img src="https://github.com/ModelOriented/DALEXtra/blob/master/man/figures/logo.png?raw=true" align="right" width="100"/>
[![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/DALEXtra)](https://cran.r-project.org/package=DALEXtra) [![Build Status](https://api.travis-ci.org/ModelOriented/DALEXtra.png)](https://travis-ci.org/ModelOriented/DALEXtra) [![Coverage
Status](https://img.shields.io/codecov/c/github/ModelOriented/DALEXtra/master.svg)](https://codecov.io/github/ModelOriented/DALEXtra?branch=master) [![DrWhy-eXtrAI](https://img.shields.io/badge/DrWhy-BackBone-373589)](http://drwhy.ai/#BackBone)
The `DALEXtra` package is an extension pack for [DALEX](https://modeloriented.github.io/DALEX) package.
This package provides easy to use connectors for models created with scikitlearn, keras, H2O, mljar and mlr.
Vignettes:
* [General introduction: DALEX with scikitlearn models](https://raw.githack.com/pbiecek/DALEX_docs/master/vignettes/How_to_use_DALEXtra_to_explain_and_visualize_scikitlearn_models.html)
--------------------
### [ingredients](http://github.com/ModelOriented/ingredients) <img src="https://modeloriented.github.io/ingredients/reference/figures/logo.png" align="right" width="100"/>
[![CRAN_Status_Badge](http://www.r-pkg.org/badges/version/ingredients)](https://cran.r-project.org/package=ingredients) [![Build Status](https://api.travis-ci.org/ModelOriented/ingredients.svg?branch=master)](https://travis-ci.org/ModelOriented/ingredients) [![Coverage
Status](https://img.shields.io/codecov/c/github/ModelOriented/ingredients/master.svg)](https://codecov.io/github/ModelOriented/ingredients?branch=master) [![DrWhy-eXtrAI](https://img.shields.io/badge/DrWhy-eXtrAI-4378bf)](http://drwhy.ai/#eXtraAI)
The `ingredients` package is a collec
没有合适的资源?快使用搜索试试~ 我知道了~
DrWhy 是可解释人工智能(XAI)的工具集合_R语言_代码_下载
共101个文件
png:32个
jpg:16个
pdf:13个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 97 浏览量
2022-07-02
23:14:48
上传
评论
收藏 18.51MB ZIP 举报
温馨提示
如何以负责任的方式开发机器学习模型?有几个主题值得考虑: 有效。模型够好吗?不应使用性能低下的模型,因为它们弊大于利。用用户理解的语言传达模型的性能。请记住,模型将在与训练数据集不同的数据集上工作。确保评估目标数据集的性能。 透明的。用户是否知道影响模型预测的因素?可解释性和可解释性很重要。如果模型决策直接或间接影响我们,我们应该知道这些决策来自何处以及如何更改它们。 公平。模型是否基于性别、年龄、种族或其他敏感属性进行区分?直接还是间接?它不应该!歧视可能出现在许多方面。该模型可能给出较低的分数,可能具有较低的性能,或者可能基于受保护人群的不同变量。 安全。不要让您的模型被黑客入侵。每个复杂的系统都有它的弱点。找出并修复它们。一些用户可能会使用各种技巧将模型预测拉到他们的网站上。 机密。模型通常建立在敏感数据之上。确保数据不会泄露,以免敏感属性与未经授权的人员共享。还要注意模型泄漏。 可重现。通常模型开发过程包括许多步骤。确保它们是完全可重现的,因此可以一一验证。 更多详情、使用方法,请下载后阅读README.md文件
资源推荐
资源详情
资源评论
收起资源包目录
DrWhy 是可解释人工智能(XAI)的工具集合_R语言_代码_下载 (101个子文件)
family.ai 777KB
family.ai 777KB
dalexverse.css 171KB
pkgdown.css 5KB
dalexverse-2.css 3KB
DESCRIPTION 947B
.gitignore 40B
index.html 41KB
manifesto.html 6KB
DrWhy_logo.html 6KB
index.html 5KB
index.html 5KB
authors.html 5KB
index.html 5KB
404.html 5KB
local_profile_1.jpg 280KB
misc5.jpg 280KB
local_profile_1.jpg 280KB
misc2.jpg 200KB
local_attributions_1.jpg 200KB
local_attributions_1.jpg 200KB
local_attributions_2.jpg 193KB
local_attributions_2.jpg 193KB
misc3.jpg 193KB
local_interactions_1.jpg 169KB
misc4.jpg 169KB
local_interactions_1.jpg 169KB
drwhy_znak_violet_small.jpg 168KB
drwhy_znak_violet.jpg 168KB
drwhylogo.jpg 168KB
MI2logo.jpg 106KB
pkgdown.js 3KB
jquery.sticky-kit.min.js 3KB
DrWhyAI.key 1.72MB
DrWhyAI.key 1.72MB
README.md 477B
NEWS.md 65B
README.md 33KB
NAMESPACE 67B
ModelDevelopmentProcess.pdf 1.33MB
ModelDevelopmentProcess.pdf 1.33MB
local_attributions_2.pdf 724KB
local_attributions_2.pdf 724KB
DrWhyAI.pdf 443KB
DrWhyAI.pdf 443KB
local_attributions_1.pdf 115KB
local_attributions_1.pdf 115KB
local_interactions_1.pdf 105KB
local_interactions_1.pdf 105KB
DrWhy-RGB-fairmodels.pdf 93KB
local_profile_1.pdf 9KB
local_profile_1.pdf 9KB
family.png 926KB
family.png 926KB
grammar_of_explanations.png 879KB
grammar_of_explanations.png 879KB
DALEXverse.png 745KB
DALEXverse.png 745KB
DALEX_architecture.png 722KB
DrWhy.png 569KB
DrWhy.png 569KB
misc1.png 569KB
DrWhyAI.png 471KB
DrWhyAI.png 471KB
drwhy_hex.png 244KB
diagramMDP.png 239KB
diagramMDP.png 239KB
d2.png 93KB
d1.png 92KB
d3.png 91KB
DrWhy-RGB-fairmodels.png 73KB
d4.png 63KB
DrWhy-RGB-randomForestExplainer.png 22KB
DrWhy-RGB-iBreakDown.png 20KB
DrWhy-RGB-modelStudio.png 20KB
DrWhy-RGB-xspliner.png 19KB
DrWhy-RGB-EloML.png 19KB
DrWhy-RGB-shapper.png 19KB
DrWhy-RGB-auditor.png 18KB
DrWhy-RGB-rSAFE.png 18KB
DrWhy-RGB-vivo.png 18KB
DrWhy-RGB-DALEXtra.png 16KB
DrWhy-RGB-ingredients.png 15KB
DrWhy-RGB-DALEX.png 15KB
toadd.R 9KB
logo.R 387B
zzz.R 330B
test_loaded.R 97B
testthat.R 54B
.Rbuildignore 51B
DrWhy_logo.Rd 260B
manifesto.Rmd 1KB
DrWhy.Rproj 418B
mi2.svg 9KB
mi2.svg 9KB
Hype_Cycle.svg 2KB
Hype_Cycle.svg 2KB
link.svg 810B
tocBullet.svg 693B
_pkgdown.yml 59B
共 101 条
- 1
- 2
资源评论
快撑死的鱼
- 粉丝: 1w+
- 资源: 9154
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功