Model Agnostic Counterfactual Explanations

amirhk, updated 🕥 2022-09-30 18:53:58

General

This repository provides code and examples for generating nearest counterfactual explanations and minimal consequential interventions. The following papers are supported:

Code Pre-requisites

First, console $ git clone https://github.com/amirhk/mace.git $ pip install virtualenv $ cd mace $ virtualenv -p python3 _venv $ source _venv/bin/activate $ pip install -r pip_requirements.txt $ pysmt-install --z3 --confirm-agreement

Then refer to console $ python batchTest.py --help

and run as follows console $ python batchTest.py -d *dataset* -m *model* -n *norm* -a *approach* -b 0 -s *numSamples*

For instance, you may run console $ python batchTest.py -d adult -m lr -n zero_norm -a AR -b 0 -s 1 $ python batchTest.py -d credit -m mlp -n one_norm -a MACE_eps_1e-3 -b 0 -s 1 $ python batchTest.py -d german -m tree -n two_norm -a MINT__eps_1e-3 -b 0 -s 1 $ python batchTest.py -d mortgage -m forest -n infty_norm -a MINT__eps_1e-3 -b 0 -s 1

Finally, view the results under the _experiments folder.

Specific considerations for minimal interventions

For mortgage data, where a causal structure governs the world, AND all variables are actionable and mutable, we should expect to see int_dist <= ? >= cfe_dist, but cfe_dist <= scf_dist. You can assert this by running the following:

console $ python batchTest.py -d mortgage -m lr -n one_norm -a MINT_eps_1e-5 MACE_eps_1e-5 -b 0 -s 10

Then you can compare the distances resulting fron MACE and MINT as outputted in the console. Do make sure to run batchTest.py with loadData.loadDataset(load_from_cache = True) so that MACE and MINT use the same data and the resulting comparison is fair.

Using git-hooks script for sanity checking

There is a pre-push script under _hooks/ which can be used to check MACE under different setups. Specifically, it checks for successfully running of the code and the closeness of the generated CFEs to the previously-saved (approximately) optimal ones. You can either manually call the script from MACE root directory by _hooks/pre-push or place it under your local .git/hooks/ directory to run automatically before every push. In this case, please remember to give it the required permissions:

console $ chmod +x .git/hooks/pre-push

Issues

Model Agnostic MACE

opened on 2022-12-22 11:56:56 by giandos200

Hi @amirhk , I would like to use one of the CF explanation methodologies in the Repo. I'm using MACE, but I see that the CF generation is model-dependent. Exist in the repo a CF generation methodology (AR, MINT) that is model agnostic or is there a way to generate an agnostic "getModelFormula" in MACE?

Bump joblib from 0.14.1 to 1.2.0

opened on 2022-09-30 18:53:58 by dependabot[bot]

Bumps joblib from 0.14.1 to 1.2.0.

Changelog

Sourced from joblib's changelog.

Release 1.2.0

  • Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported. joblib/joblib#1327

  • Make sure that joblib works even when multiprocessing is not available, for instance with Pyodide joblib/joblib#1256

  • Avoid unnecessary warnings when workers and main process delete the temporary memmap folder contents concurrently. joblib/joblib#1263

  • Fix memory alignment bug for pickles containing numpy arrays. This is especially important when loading the pickle with mmap_mode != None as the resulting numpy.memmap object would not be able to correct the misalignment without performing a memory copy. This bug would cause invalid computation and segmentation faults with native code that would directly access the underlying data buffer of a numpy array, for instance C/C++/Cython code compiled with older GCC versions or some old OpenBLAS written in platform specific assembly. joblib/joblib#1254

  • Vendor cloudpickle 2.2.0 which adds support for PyPy 3.8+.

  • Vendor loky 3.3.0 which fixes several bugs including:

    • robustly forcibly terminating worker processes in case of a crash (joblib/joblib#1269);

    • avoiding leaking worker processes in case of nested loky parallel calls;

    • reliability spawn the correct number of reusable workers.

Release 1.1.0

  • Fix byte order inconsistency issue during deserialization using joblib.load in cross-endian environment: the numpy arrays are now always loaded to use the system byte order, independently of the byte order of the system that serialized the pickle. joblib/joblib#1181

  • Fix joblib.Memory bug with the ignore parameter when the cached function is a decorated function.

... (truncated)

Commits
  • 5991350 Release 1.2.0
  • 3fa2188 MAINT cleanup numpy warnings related to np.matrix in tests (#1340)
  • cea26ff CI test the future loky-3.3.0 branch (#1338)
  • 8aca6f4 MAINT: remove pytest.warns(None) warnings in pytest 7 (#1264)
  • 067ed4f XFAIL test_child_raises_parent_exits_cleanly with multiprocessing (#1339)
  • ac4ebd5 MAINT add back pytest warnings plugin (#1337)
  • a23427d Test child raises parent exits cleanly more reliable on macos (#1335)
  • ac09691 [MAINT] various test updates (#1334)
  • 4a314b1 Vendor loky 3.2.0 (#1333)
  • bdf47e9 Make test_parallel_with_interactively_defined_functions_default_backend timeo...
  • Additional commits viewable in compare view


Dependabot compatibility score

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/amirhk/mace/network/alerts).

Bump numpy from 1.18.2 to 1.22.0

opened on 2022-06-21 22:10:42 by dependabot[bot]

Bumps numpy from 1.18.2 to 1.22.0.

Release notes

Sourced from numpy's releases.

v1.22.0

NumPy 1.22.0 Release Notes

NumPy 1.22.0 is a big release featuring the work of 153 contributors spread over 609 pull requests. There have been many improvements, highlights are:

  • Annotations of the main namespace are essentially complete. Upstream is a moving target, so there will likely be further improvements, but the major work is done. This is probably the most user visible enhancement in this release.
  • A preliminary version of the proposed Array-API is provided. This is a step in creating a standard collection of functions that can be used across application such as CuPy and JAX.
  • NumPy now has a DLPack backend. DLPack provides a common interchange format for array (tensor) data.
  • New methods for quantile, percentile, and related functions. The new methods provide a complete set of the methods commonly found in the literature.
  • A new configurable allocator for use by downstream projects.

These are in addition to the ongoing work to provide SIMD support for commonly used functions, improvements to F2PY, and better documentation.

The Python versions supported in this release are 3.8-3.10, Python 3.7 has been dropped. Note that 32 bit wheels are only provided for Python 3.8 and 3.9 on Windows, all other wheels are 64 bits on account of Ubuntu, Fedora, and other Linux distributions dropping 32 bit support. All 64 bit wheels are also linked with 64 bit integer OpenBLAS, which should fix the occasional problems encountered by folks using truly huge arrays.

Expired deprecations

Deprecated numeric style dtype strings have been removed

Using the strings "Bytes0", "Datetime64", "Str0", "Uint32", and "Uint64" as a dtype will now raise a TypeError.

(gh-19539)

Expired deprecations for loads, ndfromtxt, and mafromtxt in npyio

numpy.loads was deprecated in v1.15, with the recommendation that users use pickle.loads instead. ndfromtxt and mafromtxt were both deprecated in v1.17 - users should use numpy.genfromtxt instead with the appropriate value for the usemask parameter.

(gh-19615)

... (truncated)

Commits


Dependabot compatibility score

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/amirhk/mace/network/alerts).

Bump ipython from 7.13.0 to 7.16.3

opened on 2022-01-21 20:14:52 by dependabot[bot]

Bumps ipython from 7.13.0 to 7.16.3.

Commits


Dependabot compatibility score

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/amirhk/mace/network/alerts).

Bump pygments from 2.6.1 to 2.7.4

opened on 2021-03-29 22:16:13 by dependabot[bot]

Bumps pygments from 2.6.1 to 2.7.4.

Release notes

Sourced from pygments's releases.

2.7.4

  • Updated lexers:

    • Apache configurations: Improve handling of malformed tags (#1656)

    • CSS: Add support for variables (#1633, #1666)

    • Crystal (#1650, #1670)

    • Coq (#1648)

    • Fortran: Add missing keywords (#1635, #1665)

    • Ini (#1624)

    • JavaScript and variants (#1647 -- missing regex flags, #1651)

    • Markdown (#1623, #1617)

    • Shell

      • Lex trailing whitespace as part of the prompt (#1645)
      • Add missing in keyword (#1652)

    • SQL - Fix keywords (#1668)

    • Typescript: Fix incorrect punctuation handling (#1510, #1511)

  • Fix infinite loop in SML lexer (#1625)

  • Fix backtracking string regexes in JavaScript/TypeScript, Modula2 and many other lexers (#1637)

  • Limit recursion with nesting Ruby heredocs (#1638)

  • Fix a few inefficient regexes for guessing lexers

  • Fix the raw token lexer handling of Unicode (#1616)

  • Revert a private API change in the HTML formatter (#1655) -- please note that private APIs remain subject to change!

  • Fix several exponential/cubic-complexity regexes found by Ben Caller/Doyensec (#1675)

  • Fix incorrect MATLAB example (#1582)

Thanks to Google's OSS-Fuzz project for finding many of these bugs.

2.7.3

... (truncated)

Changelog

Sourced from pygments's changelog.

Version 2.7.4

(released January 12, 2021)

  • Updated lexers:

    • Apache configurations: Improve handling of malformed tags (#1656)

    • CSS: Add support for variables (#1633, #1666)

    • Crystal (#1650, #1670)

    • Coq (#1648)

    • Fortran: Add missing keywords (#1635, #1665)

    • Ini (#1624)

    • JavaScript and variants (#1647 -- missing regex flags, #1651)

    • Markdown (#1623, #1617)

    • Shell

      • Lex trailing whitespace as part of the prompt (#1645)
      • Add missing in keyword (#1652)

    • SQL - Fix keywords (#1668)

    • Typescript: Fix incorrect punctuation handling (#1510, #1511)

  • Fix infinite loop in SML lexer (#1625)

  • Fix backtracking string regexes in JavaScript/TypeScript, Modula2 and many other lexers (#1637)

  • Limit recursion with nesting Ruby heredocs (#1638)

  • Fix a few inefficient regexes for guessing lexers

  • Fix the raw token lexer handling of Unicode (#1616)

  • Revert a private API change in the HTML formatter (#1655) -- please note that private APIs remain subject to change!

  • Fix several exponential/cubic-complexity regexes found by Ben Caller/Doyensec (#1675)

  • Fix incorrect MATLAB example (#1582)

Thanks to Google's OSS-Fuzz project for finding many of these bugs.

Version 2.7.3

(released December 6, 2020)

... (truncated)

Commits
  • 4d555d0 Bump version to 2.7.4.
  • fc3b05d Update CHANGES.
  • ad21935 Revert "Added dracula theme style (#1636)"
  • e411506 Prepare for 2.7.4 release.
  • 275e34d doc: remove Perl 6 ref
  • 2e7e8c4 Fix several exponential/cubic complexity regexes found by Ben Caller/Doyensec
  • eb39c43 xquery: fix pop from empty stack
  • 2738778 fix coding style in test_analyzer_lexer
  • 02e0f09 Added 'ERROR STOP' to fortran.py keywords. (#1665)
  • c83fe48 support added for css variables (#1633)
  • Additional commits viewable in compare view


Dependabot compatibility score

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) - `@dependabot use these labels` will set the current labels as the default for future PRs for this repo and language - `@dependabot use these reviewers` will set the current reviewers as the default for future PRs for this repo and language - `@dependabot use these assignees` will set the current assignees as the default for future PRs for this repo and language - `@dependabot use this milestone` will set the current milestone as the default for future PRs for this repo and language You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/amirhk/mace/network/alerts).

Issue in running project

opened on 2021-03-05 17:13:18 by HeyItsBethany3

Hi, I am trying to use this library and have followed the README but I'm getting this error when I use the command: python batchTest.py -d credit -m mlp -n one_norm -a MACE_eps_1e-3 -b 0 -s 1 I've attached the error below. Screenshot 2021-03-05 at 17 04 45

Do you have any advice to solve this? Do I need to load the data and model in some way? Also, does your MACE (or MINT) algorithm work well for gradient boosting models? Thanks so much.

Amir-Hossein Karimi
GitHub Repository

counterfactual-explanations explainable-ml explainable-ai xai machine-learning interpretable-machine-learning