SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. SHAP connects game theory with local explanations, uniting several previous methods and representing the only possible consistent and locally accurate additive feature attribution method based on expectations.
1 maintainer
Release files for shap-legacy 0.36.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| shap_legacy-0.36.0-cp37-cp37m-manylinux1_x86_64.whl | CPython 3.7 | CPython 3.7 pymalloc | Linux glibc 2.5+ x86-64 | Details |
| shap_legacy-0.36.0-cp36-cp36m-manylinux1_x86_64.whl | CPython 3.6 | CPython 3.6 pymalloc | Linux glibc 2.5+ x86-64 | Details |
Total release size: 896.4 kB
Release files / shap_legacy-0.36.0-cp37-cp37m-manylinux1_x86_64.whl
| Download URL | shap_legacy-0.36.0-cp37-cp37m-manylinux1_x86_64.whl |
|---|---|
| Size | 448.3 kB |
| Tags | CPython 3.7 CPython 3.7 pymalloc Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
1d088e3ae3991be48d56af4c66d45bbcc8b65df9454338b82659aea9e0290322
|
|
BLAKE2b-256 checksum How to use checksums |
b6fda300a88506ac26354796b88e71ad2e5a3891ef6c09c7c787c75b71da218d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.6.0 requests/2.23.0 setuptools/46.0.0 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.7.9
|
Release files / shap_legacy-0.36.0-cp36-cp36m-manylinux1_x86_64.whl
| Download URL | shap_legacy-0.36.0-cp36-cp36m-manylinux1_x86_64.whl |
|---|---|
| Size | 448.1 kB |
| Tags | CPython 3.6 CPython 3.6 pymalloc Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
5d3d1efd72ed1c1e44864f57a323f4d2ec9077530ce032ba4ee572404ca1ba29
|
|
BLAKE2b-256 checksum How to use checksums |
99b7cee0db31121080f90eacc8dd8130c4aca7c7bd7375d9cc3a619c1e43effa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.6.0 requests/2.23.0 setuptools/46.0.0 requests-toolbelt/0.9.1 tqdm/4.49.0 CPython/3.7.9
|
