Pre-release

This release is a pre-release and may not be stable for production use.

PyPI Conda License Tests Binder Documentation Status Downloads PyPI pyversions

SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions (see papers for details and citations).

Install

SHAP can be installed from either PyPI or conda-forge:

pip install shap
or
conda install -c conda-forge shap

GPU support

To enable GPU-accelerated Tree SHAP, install from source with the CUDA toolkit available and the SHAP_ENABLE_CUDA environment variable set:

SHAP_ENABLE_CUDA=1 pip install .

This requires the CUDA toolkit to be installed on your system.

Supported versions

SHAP follows SPEC 0 for minimum supported dependency versions. We test against the versions specified there and may not fix bugs for older versions.

Contributing

We welcome contributions highly. Feel free to file an issue. Before opening a PR make sure you've read our CONTRIBUTING.md guideline.

Tree ensemble example (XGBoost/LightGBM/CatBoost/scikit-learn/pyspark models)

While SHAP can explain the output of any machine learning model, we have developed a high-speed exact algorithm for tree ensemble methods (see our Nature MI paper). Fast C++ implementations are supported for XGBoost, LightGBM, CatBoost, scikit-learn and pyspark tree models:

import xgboost
import shap

# train an XGBoost model
X, y = shap.datasets.california()
model = xgboost.XGBRegressor().fit(X, y)

# explain the model's predictions using SHAP
# (same syntax works for LightGBM, CatBoost, scikit-learn, transformers, Spark, etc.)
explainer = shap.Explainer(model)
shap_values = explainer(X)

# visualize the first prediction's explanation
shap.plots.waterfall(shap_values[0])

The above explanation shows features each contributing to push the model output from the base value (the average model output over the training dataset we passed) to the model output. Features pushing the prediction higher are shown in red, those pushing the prediction lower are in blue. Another way to visualize the same explanation is to use a force plot (these are introduced in our Nature BME paper):

# visualize the first prediction's explanation with a force plot
shap.plots.force(shap_values[0])

If we take many force plot explanations such as the one shown above, rotate them 90 degrees, and then stack them horizontally, we can see explanations for an entire dataset (in the notebook this plot is interactive):

# visualize all the training set predictions
shap.plots.force(shap_values[:500])

To understand how a single feature effects the output of the model we can plot the SHAP value of that feature vs. the value of the feature for all the examples in a dataset. Since SHAP values represent a feature's responsibility for a change in the model output, the plot below represents the change in predicted house price as the latitude changes. Vertical dispersion at a single value of latitude represents interaction effects with other features. To help reveal these interactions we can color by another feature. If we pass the whole explanation tensor to the color argument the scatter plot will pick the best feature to color by. In this case it picks longitude.

# create a dependence scatter plot to show the effect of a single feature across the whole dataset
shap.plots.scatter(shap_values[:, "Latitude"], color=shap_values)

To get an overview of which features are most important for a model we can plot the SHAP values of every feature for every sample. The plot below sorts features by the sum of SHAP value magnitudes over all samples, and uses SHAP values to show the distribution of the impacts each feature has on the model output. The color represents the feature value (red high, blue low). This reveals for example that higher median incomes increases the predicted home price.

# summarize the effects of all the features
shap.plots.beeswarm(shap_values)

We can also just take the mean absolute value of the SHAP values for each feature to get a standard bar plot (produces stacked bars for multi-class outputs):

shap.plots.bar(shap_values)

Natural language example (transformers)

SHAP has specific support for natural language models like those in the Hugging Face transformers library. By adding coalitional rules to traditional Shapley values we can form games that explain large modern NLP model using very few function evaluations. Using this functionality is as simple as passing a supported transformers pipeline to SHAP:

import transformers
import shap

# load a transformers pipeline model
model = transformers.pipeline('sentiment-analysis', top_k=None)

# explain the model on two sample inputs
explainer = shap.Explainer(model)
shap_values = explainer(["What a great movie! ...if you have no taste."])

# visualize the first prediction's explanation for the POSITIVE output class
shap.plots.text(shap_values[0, :, "POSITIVE"])

Deep learning example with DeepExplainer (TensorFlow/Keras models)

Deep SHAP is a high-speed approximation algorithm for SHAP values in deep learning models that builds on a connection with DeepLIFT described in the SHAP NIPS paper. The implementation here differs from the original DeepLIFT by using a distribution of background samples instead of a single reference value, and using Shapley equations to linearize components such as max, softmax, products, divisions, etc. Note that some of these enhancements have also been since integrated into DeepLIFT. TensorFlow models and Keras models using the TensorFlow backend are supported (there is also preliminary support for PyTorch):

# ...include code from https://github.com/keras-team/keras/blob/master/examples/demo_mnist_convnet.py

import shap
import numpy as np

# select a set of background examples to take an expectation over
background = x_train[np.random.choice(x_train.shape[0], 100, replace=False)]

# explain predictions of the model on four images
e = shap.DeepExplainer(model, background)
# ...or pass tensors directly
# e = shap.DeepExplainer((model.layers[0].input, model.layers[-1].output), background)
shap_values = e.shap_values(x_test[1:5])

# plot the feature attributions
shap.image_plot(shap_values, -x_test[1:5])

The plot above explains ten outputs (digits 0-9) for four different images. Red pixels increase the model's output while blue pixels decrease the output. The input images are shown on the left, and as nearly transparent grayscale backings behind each of the explanations. The sum of the SHAP values equals the difference between the expected model output (averaged over the background dataset) and the current model output. Note that for the 'zero' image the blank middle is important, while for the 'four' image the lack of a connection on top makes it a four instead of a nine.

Deep learning example with GradientExplainer (TensorFlow/Keras/PyTorch models)

Expected gradients combines ideas from Integrated Gradients, SHAP, and SmoothGrad into a single expected value equation. This allows an entire dataset to be used as the background distribution (as opposed to a single reference value) and allows local smoothing. If we approximate the model with a linear function between each background data sample and the current input to be explained, and we assume the input features are independent then expected gradients will compute approximate SHAP values. In the example below we have explained how the 7th intermediate layer of the VGG16 ImageNet model impacts the output probabilities.

from keras.applications.vgg16 import VGG16
from keras.applications.vgg16 import preprocess_input
import keras.backend as K
import numpy as np
import json
import shap

# load pre-trained model and choose two images to explain
model = VGG16(weights='imagenet', include_top=True)
X,y = shap.datasets.imagenet50()
to_explain = X[[39,41]]

# load the ImageNet class names
url = "https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json"
fname = shap.datasets.cache(url)
with open(fname) as f:
    class_names = json.load(f)

# explain how the input to the 7th layer of the model explains the top two classes
def map2layer(x, layer):
    feed_dict = dict(zip([model.layers[0].input], [preprocess_input(x.copy())]))
    return K.get_session().run(model.layers[layer].input, feed_dict)
e = shap.GradientExplainer(
    (model.layers[7].input, model.layers[-1].output),
    map2layer(X, 7),
    local_smoothing=0 # std dev of smoothing noise
)
shap_values,indexes = e.shap_values(map2layer(to_explain, 7), ranked_outputs=2)

# get the names for the classes
index_names = np.vectorize(lambda x: class_names[str(x)][1])(indexes)

# plot the explanations
shap.image_plot(shap_values, to_explain, index_names)

Predictions for two input images are explained in the plot above. Red pixels represent positive SHAP values that increase the probability of the class, while blue pixels represent negative SHAP values the reduce the probability of the class. By using ranked_outputs=2 we explain only the two most likely classes for each input (this spares us from explaining all 1,000 classes).

Model agnostic example with KernelExplainer (explains any function)

Kernel SHAP uses a specially-weighted local linear regression to estimate SHAP values for any model. Below is a simple example for explaining a multi-class SVM on the classic iris dataset.

import sklearn
import shap
from sklearn.model_selection import train_test_split

# print the JS visualization code to the notebook
shap.initjs()

# train a SVM classifier
X_train,X_test,Y_train,Y_test = train_test_split(*shap.datasets.iris(), test_size=0.2, random_state=0)
svm = sklearn.svm.SVC(kernel='rbf', probability=True)
svm.fit(X_train, Y_train)

# use Kernel SHAP to explain test set predictions
explainer = shap.KernelExplainer(svm.predict_proba, X_train, link="logit")
shap_values = explainer.shap_values(X_test, nsamples=100)

# plot the SHAP values for the Setosa output of the first instance
shap.force_plot(explainer.expected_value[0], shap_values[0][0,:], X_test.iloc[0,:], link="logit")

The above explanation shows four features each contributing to push the model output from the base value (the average model output over the training dataset we passed) towards zero. If there were any features pushing the class label higher they would be shown in red.

If we take many explanations such as the one shown above, rotate them 90 degrees, and then stack them horizontally, we can see explanations for an entire dataset. This is exactly what we do below for all the examples in the iris test set:

# plot the SHAP values for the Setosa output of all instances
shap.force_plot(explainer.expected_value[0], shap_values[0], X_test, link="logit")

SHAP Interaction Values

SHAP interaction values are a generalization of SHAP values to higher order interactions. Fast exact computation of pairwise interactions are implemented for tree models with shap.TreeExplainer(model).shap_interaction_values(X). This returns a matrix for every prediction, where the main effects are on the diagonal and the interaction effects are off-diagonal. These values often reveal interesting hidden relationships, such as how the increased risk of death peaks for men at age 60 (see the NHANES notebook for details):

Sample notebooks

The notebooks below demonstrate different use cases for SHAP. Look inside the notebooks directory of the repository if you want to try playing with the original notebooks yourself.

TreeExplainer

An implementation of Tree SHAP, a fast and exact algorithm to compute SHAP values for trees and ensembles of trees.

DeepExplainer

An implementation of Deep SHAP, a faster (but only approximate) algorithm to compute SHAP values for deep learning models that is based on connections between SHAP and the DeepLIFT algorithm.

GradientExplainer

An implementation of expected gradients to approximate SHAP values for deep learning models. It is based on connections between SHAP and the Integrated Gradients algorithm. GradientExplainer is slower than DeepExplainer and makes different approximation assumptions.

LinearExplainer

For a linear model with independent features we can analytically compute the exact SHAP values. We can also account for feature correlation if we are willing to estimate the feature covariance matrix. LinearExplainer supports both of these options.

KernelExplainer

An implementation of Kernel SHAP, a model agnostic method to estimate SHAP values for any model. Because it makes no assumptions about the model type, KernelExplainer is slower than the other model type specific algorithms.

  • Census income classification with scikit-learn - Using the standard adult census income dataset, this notebook trains a k-nearest neighbors classifier using scikit-learn and then explains predictions using shap.

  • ImageNet VGG16 Model with Keras - Explain the classic VGG16 convolutional neural network's predictions for an image. This works by applying the model agnostic Kernel SHAP method to a super-pixel segmented image.

  • Iris classification - A basic demonstration using the popular iris species dataset. It explains predictions from six different models in scikit-learn using shap.

Documentation notebooks

These notebooks comprehensively demonstrate how to use specific functions and objects.

Methods Unified by SHAP

  1. LIME: Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. "Why should i trust you?: Explaining the predictions of any classifier." Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016.

  2. Shapley sampling values: Strumbelj, Erik, and Igor Kononenko. "Explaining prediction models and individual predictions with feature contributions." Knowledge and information systems 41.3 (2014): 647-665.

  3. DeepLIFT: Shrikumar, Avanti, Peyton Greenside, and Anshul Kundaje. "Learning important features through propagating activation differences." arXiv preprint arXiv:1704.02685 (2017).

  4. QII: Datta, Anupam, Shayak Sen, and Yair Zick. "Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems." Security and Privacy (SP), 2016 IEEE Symposium on. IEEE, 2016.

  5. Layer-wise relevance propagation: Bach, Sebastian, et al. "On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation." PloS one 10.7 (2015): e0130140.

  6. Shapley regression values: Lipovetsky, Stan, and Michael Conklin. "Analysis of regression in game theory approach." Applied Stochastic Models in Business and Industry 17.4 (2001): 319-330.

  7. Tree interpreter: Saabas, Ando. Interpreting random forests. http://blog.datadive.net/interpreting-random-forests/

Citations

The algorithms and visualizations used in this package came primarily out of research in Su-In Lee's lab at the University of Washington, and Microsoft Research. If you use SHAP in your research we would appreciate a citation to the appropriate paper(s):

Project links

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Stable release available (0.52.0)

3 maintainers

PyPI data
Data sourced directly from PyPI's database.
Avatar for connortann from gravatar.com connortann Avatar for shap_poster from gravatar.com shap_poster Avatar for slundberg from gravatar.com slundberg

Credits

Author: Scott Lundberg

License

MIT License (MIT License)

Requires

Python >=3.12

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

shap-0.53.0rc0.tar.gz (5.7 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

shap-0.53.0rc0-cp315-cp315t-win_arm64.whl (933.3 kB view details)

Uploaded CPython 3.15tWindows ARM64

shap-0.53.0rc0-cp315-cp315t-win_amd64.whl (760.5 kB view details)

Uploaded CPython 3.15tWindows x86-64

shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_x86_64.whl (2.0 MB view details)

Uploaded CPython 3.15tmusllinux: musl 1.2+ x86-64

shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_aarch64.whl (2.0 MB view details)

Uploaded CPython 3.15tmusllinux: musl 1.2+ ARM64

shap-0.53.0rc0-cp315-cp315t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (555.5 kB view details)

Uploaded CPython 3.15tmanylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

shap-0.53.0rc0-cp315-cp315t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (546.6 kB view details)

Uploaded CPython 3.15tmanylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

shap-0.53.0rc0-cp315-cp315t-macosx_11_0_arm64.whl (542.8 kB view details)

Uploaded CPython 3.15tmacOS 11.0+ ARM64

shap-0.53.0rc0-cp315-cp315t-macosx_10_15_x86_64.whl (549.3 kB view details)

Uploaded CPython 3.15tmacOS 10.15+ x86-64

shap-0.53.0rc0-cp314-cp314t-win_arm64.whl (933.1 kB view details)

Uploaded CPython 3.14tWindows ARM64

shap-0.53.0rc0-cp314-cp314t-win_amd64.whl (760.3 kB view details)

Uploaded CPython 3.14tWindows x86-64

shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_x86_64.whl (2.0 MB view details)

Uploaded CPython 3.14tmusllinux: musl 1.2+ x86-64

shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_aarch64.whl (2.0 MB view details)

Uploaded CPython 3.14tmusllinux: musl 1.2+ ARM64

shap-0.53.0rc0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (555.3 kB view details)

Uploaded CPython 3.14tmanylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

shap-0.53.0rc0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (546.4 kB view details)

Uploaded CPython 3.14tmanylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

shap-0.53.0rc0-cp314-cp314t-macosx_11_0_arm64.whl (542.6 kB view details)

Uploaded CPython 3.14tmacOS 11.0+ ARM64

shap-0.53.0rc0-cp314-cp314t-macosx_10_15_x86_64.whl (549.2 kB view details)

Uploaded CPython 3.14tmacOS 10.15+ x86-64

shap-0.53.0rc0-cp312-abi3-win_arm64.whl (911.4 kB view details)

Uploaded CPython 3.12+Windows ARM64

shap-0.53.0rc0-cp312-abi3-win_amd64.whl (745.9 kB view details)

Uploaded CPython 3.12+Windows x86-64

shap-0.53.0rc0-cp312-abi3-musllinux_1_2_x86_64.whl (2.0 MB view details)

Uploaded CPython 3.12+musllinux: musl 1.2+ x86-64

shap-0.53.0rc0-cp312-abi3-musllinux_1_2_aarch64.whl (2.0 MB view details)

Uploaded CPython 3.12+musllinux: musl 1.2+ ARM64

shap-0.53.0rc0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (550.9 kB view details)

Uploaded CPython 3.12+manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

shap-0.53.0rc0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (541.9 kB view details)

Uploaded CPython 3.12+manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

shap-0.53.0rc0-cp312-abi3-macosx_11_0_arm64.whl (538.3 kB view details)

Uploaded CPython 3.12+macOS 11.0+ ARM64

shap-0.53.0rc0-cp312-abi3-macosx_10_13_x86_64.whl (544.7 kB view details)

Uploaded CPython 3.12+macOS 10.13+ x86-64

File details

Details for the file shap-0.53.0rc0.tar.gz.

File metadata

  • Download URL: shap-0.53.0rc0.tar.gz
  • Upload date:
  • Size: 5.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0.tar.gz
Algorithm Hash digest
SHA256 30c5ebda120cbaa235b21d646f1a65f14436c2a8963884997877b2a931600fa5
MD5 d8c211d3e30490c446218bb53e11edf5
BLAKE2b-256 0d9311db5be7445154388897ae7fdf29224734999c22b1760b86629184112206

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0.tar.gz:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-win_arm64.whl.

File metadata

  • Download URL: shap-0.53.0rc0-cp315-cp315t-win_arm64.whl
  • Upload date:
  • Size: 933.3 kB
  • Tags: CPython 3.15t, Windows ARM64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-win_arm64.whl
Algorithm Hash digest
SHA256 48941b2aefd38cd251590c274b3df61b60a01df47e49a5f8955c09fb624cfe94
MD5 d030e1c1a95390d987b06aad5d4a90cd
BLAKE2b-256 c99c1d4ce46aa934e8b319d8cf58ae0c419870ea8f85f4db2cf59cebf28b285e

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-win_arm64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-win_amd64.whl.

File metadata

  • Download URL: shap-0.53.0rc0-cp315-cp315t-win_amd64.whl
  • Upload date:
  • Size: 760.5 kB
  • Tags: CPython 3.15t, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-win_amd64.whl
Algorithm Hash digest
SHA256 a601a82ea54864bd127ec17e63dc5f644a5e07c7f4dc13adcd0242be229f015b
MD5 a7e01ddc4bc8a15e57ae492e6a915184
BLAKE2b-256 ed0c977e77ed4c5cdf93149806f19b5a324242aea0756b0905ccdd388e2dc836

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-win_amd64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_x86_64.whl
Algorithm Hash digest
SHA256 a0e0f85ec4a88ff90bcd4b5f014d769a4849d0a5992db2470fe5c4bf26ce86b8
MD5 a9e118eab4307639eb02f8bcda8c8cab
BLAKE2b-256 cdf5cc4db5b8f9f55176c312ad2b1869a224269ef7a492033d332036c22435ac

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_aarch64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_aarch64.whl
Algorithm Hash digest
SHA256 dc6adcffa7cfd387eb2cddd6c519724fd365b189addfc2653e1b5f9e7bfa5093
MD5 7f009919292c99edf16cd6489d530159
BLAKE2b-256 ba5bbe9cf724a4f50a3e8a95b5f08883034111d2f38508ad1a5a1ae9c09cdef6

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-musllinux_1_2_aarch64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 78a55af64dc0d77365f7df19c07b6a8205d2dc5ef2772a0cb5b855b23cbbf255
MD5 8d8dfa9221a2e1637e81c6fc433973d6
BLAKE2b-256 1aadd3d25104d11a74d7062f6394b9442b009c367d812efcfd24a3b5d7d2a9e6

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 c75af9bd81c0334039a98422a3ad8dde1d4486090f56839b29182036539e01c0
MD5 a1373678a379def3e7f0cb0530a5a7ae
BLAKE2b-256 a4a6713a2fab47b26ed0216cf99323d655ae9ae7bbf95cf82e7fa905cf9b8752

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 f33e4923d55b847983f81d233cd8d70e2a268251a0a6064b3d48e48205314ada
MD5 8ac60d78505b9171ea5d272eadd88dbc
BLAKE2b-256 ca62cf4f22e7b04b4eaae30446ed23e6f7f21896cbc52ad012ba1a30d9302ad8

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-macosx_11_0_arm64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp315-cp315t-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp315-cp315t-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 12047d54048490841f689d9501216e8c81ca5b6bb0d033f32c3ec446058ddd93
MD5 53b3869eb27dff9212b6c43118f85be7
BLAKE2b-256 f9a6dcc8b1b418c8f0021e3b0342887b170f16ef40f1dfdb7e6dcfa99ec5cf7d

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp315-cp315t-macosx_10_15_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-win_arm64.whl.

File metadata

  • Download URL: shap-0.53.0rc0-cp314-cp314t-win_arm64.whl
  • Upload date:
  • Size: 933.1 kB
  • Tags: CPython 3.14t, Windows ARM64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-win_arm64.whl
Algorithm Hash digest
SHA256 81436f9a597da8b6ac7865a7fcc7507deb10877460c11547a24732abb3f30319
MD5 16314a9dad8f510fea3e6d5c795f4893
BLAKE2b-256 3be96446c32bf4aadaf37e9d5d65ca6102e1d69e42cf7d42fa68e94f4b227e42

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-win_arm64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-win_amd64.whl.

File metadata

  • Download URL: shap-0.53.0rc0-cp314-cp314t-win_amd64.whl
  • Upload date:
  • Size: 760.3 kB
  • Tags: CPython 3.14t, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-win_amd64.whl
Algorithm Hash digest
SHA256 39901d7aa5fd979d1b397993bed70bedfb9c349a3a214987457d21dd5e3d10aa
MD5 6bc6b7494e3b3072637bcf81c2342b72
BLAKE2b-256 1241c42e192279a84c4d3ba45a2597ed558847f4eb1670f63932a43f1b21ad4f

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-win_amd64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_x86_64.whl
Algorithm Hash digest
SHA256 7c4bf06b5fb330ab6b64df5b1c590784a13459f0d1cfcb330b47b09991768226
MD5 071fb8abf0f92a4aa491d81e892282cb
BLAKE2b-256 b11e3e72857f17923448dba2ae0a828c22747af3d796361816ddcdbc84bd3ac6

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_aarch64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_aarch64.whl
Algorithm Hash digest
SHA256 064a349035d6ee0e99ffdbb2679ed3ce84c6eda229ea667679c832432eca9270
MD5 568716501bb96b6597a7e0dcf7eb2867
BLAKE2b-256 0326a495ed7e71fa708c4c9082285bb7e5f1fc2513e3c509f6f780ba562ad0eb

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-musllinux_1_2_aarch64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 1309cc1848ce25f2fca7064cc3f6b68872f7448bb4d7cab9d27c185ffb624892
MD5 64b01c649cad47f6557bd97b8777728a
BLAKE2b-256 58e9051744d5ad859c7b6859c6d42de912956acac81282b66a709ae0c550b689

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 ae3607ae1ca503a705216af3c2d0b90af18c76504ecbb7f532e2e954f281351d
MD5 df0812a77be9ff279e4107d0ce2f9c51
BLAKE2b-256 4533e0b395b301a9c17a7e23eb607971a523246dbbec0e1910bf5eebd6d3718a

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 5e34acbd028edb59f5747de2e381f4dbf7fb29f690628e83cfda5faa44840c3a
MD5 4c54065d95d671a95987228cd89424aa
BLAKE2b-256 cd19a43d3ed51ffdff4dd33cbdb504b59647ab011db7ccae3f0724a72d28c358

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-macosx_11_0_arm64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp314-cp314t-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp314-cp314t-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 6adb9d33015ab1ce3178030656a81384c17edcb9954fe806ecab8506c94e5835
MD5 1883a545c95607ee0666f51b77566da5
BLAKE2b-256 de0abf564ca50bcded51630937ce60aca7c0fe551d9eabef0eb637342f64cd5b

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp314-cp314t-macosx_10_15_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-win_arm64.whl.

File metadata

  • Download URL: shap-0.53.0rc0-cp312-abi3-win_arm64.whl
  • Upload date:
  • Size: 911.4 kB
  • Tags: CPython 3.12+, Windows ARM64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-win_arm64.whl
Algorithm Hash digest
SHA256 6b976a85b8f1f586332507680c3e1fbf15d0dbe632f01553be369c8849570cac
MD5 5b20894e751a4338e094401d14f97bcb
BLAKE2b-256 0353b3577b326da39dc6d928ad4e117c97a2db97644575a2da8f7a145bdd9b31

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-win_arm64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-win_amd64.whl.

File metadata

  • Download URL: shap-0.53.0rc0-cp312-abi3-win_amd64.whl
  • Upload date:
  • Size: 745.9 kB
  • Tags: CPython 3.12+, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 d94c9bb15aae858efa7becb96c596c16ca8d4d57f1471386adaa9a17be237019
MD5 778b219cd2cad61839bfc0c8e14ce84c
BLAKE2b-256 e8d2ef875006b63a5df1480df3140ee40c5b28d93d144b9ef344bf8e9e4967ae

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-win_amd64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-musllinux_1_2_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-musllinux_1_2_x86_64.whl
Algorithm Hash digest
SHA256 84e43077d637b7c230915e073eced45bbf07a890db5ead3b9499c4e6dda589a4
MD5 3045625f9d3e6745ed532fb9c157acc0
BLAKE2b-256 2b5eb00c8053a7083cc0cf7ba2201a613aad7faba58f688e2f942787fc66aeda

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-musllinux_1_2_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-musllinux_1_2_aarch64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-musllinux_1_2_aarch64.whl
Algorithm Hash digest
SHA256 bc615d281a7d85da051cbacc143c96bd471070f374d349e2e25ef964ebb1a53c
MD5 7a76bdc6d56fe3fc99b3416bb5392851
BLAKE2b-256 0c45ad3146b1f1b770951593d82982a1fdedcd4feb4714a413187e87270b9d08

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-musllinux_1_2_aarch64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 bd212d5ddd8e1c64968a80e4ac40fedb5157cb627906dacf9d4acfd83f98db46
MD5 ad4f999baa9de91f3810512a8c45d643
BLAKE2b-256 3c1586a36a2b8e30d8d587ff1e12ffbce53019dd3c97c03a5f5e24a5bf2e8a2c

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 02fd28eef4fa0f49bae51145adcee9443c5feca01c64e9c9c0a93cd399b043b9
MD5 364c774f12f3c6397f912dfdc838f885
BLAKE2b-256 ad183301b1a77113274f0617954a6af06aec23305554226cbee9d3c4daf9a1ca

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 99e58c939623d31ee3b9e23b63d005a236b5dff3f3ccf11eef96094a0a1aee00
MD5 f2ed558c0051810414974e709ed3c69d
BLAKE2b-256 c3a65bfe9956d9e4a7d12236b414f21cd5fd3574fa7976bf2e7bb1c3947e598e

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-macosx_11_0_arm64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file shap-0.53.0rc0-cp312-abi3-macosx_10_13_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.53.0rc0-cp312-abi3-macosx_10_13_x86_64.whl
Algorithm Hash digest
SHA256 9d12892fade8d92178a038a9ed8328348baa4e07b60fc93e61a51a1120c2817a
MD5 6f5a2ae82ece091737fa0d0c390adf33
BLAKE2b-256 f02866a8107c506e2b404fcf619d734dd782b2f75258f9c934fb4f4bf7cde23d

See more details on using hashes here.

Provenance

The following attestation bundles were made for shap-0.53.0rc0-cp312-abi3-macosx_10_13_x86_64.whl:

Publisher: build_wheels.yml on shap/shap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release
Pre-release

0.53.0rc0 This release

25 files

0.52.0

12 files

0.51.0

32 files

0.50.0

32 files

0.49.1

31 files

0.48.0

31 files

0.47.2

25 files

0.47.1

25 files

0.47.0

25 files

0.46.0

25 files

0.45.1

25 files

0.45.0

25 files

0.44.1

24 files

0.44.0

24 files

0.43.0

24 files

0.42.1

25 files

0.42.0

16 files

0.41.0

26 files

0.40.0

21 files

0.39.0

4 files

0.38.1

4 files

0.37.0

4 files

0.36.0

4 files

0.35.0

3 files

0.34.0

4 files

0.33.0

4 files

0.32.1

5 files

0.32.0

4 files

0.31.0

4 files

0.30.2

2 files

0.30.1

4 files

0.30.0

4 files

0.29.3

5 files

0.29.2

3 files

0.29.1

5 files

0.28.6

1 file

0.28.5

4 files

0.28.4

2 files

0.28.3

4 files

0.28.2

4 files

0.28.1

4 files

0.28.0

2 files

0.27.0

4 files

0.26.0

4 files

0.25.2

4 files

0.25.1

4 files

0.25.0

4 files

0.24.0

4 files

0.23.2

2 files

0.23.1

4 files

0.23.0

4 files

0.22.3

4 files

0.22.2

4 files

0.22.1

4 files

0.22.0

4 files

0.21.0

4 files

0.20.2

4 files

0.20.1

4 files

0.19.5

1 file

0.19.4

1 file

0.19.3

1 file

0.19.2

1 file

0.19.1

1 file

0.18.1

1 file

0.18.0

1 file

0.17.1

1 file

0.17.0

1 file

0.16.1

1 file

0.15.0

1 file

0.14.1

1 file

0.14.0

1 file

0.13.7

1 file

0.13.6

1 file

0.13.5

1 file

0.13.3

1 file

0.13.2

1 file

0.13.1

1 file

0.13

1 file

0.12.1

1 file

0.12.0

1 file

0.11.1

1 file

0.11.0

1 file

0.10.3

1 file

0.10.2

1 file

0.10.1

1 file

0.10.0

1 file

0.9.1

1 file

0.8.9

1 file

0.8.8

1 file

0.8.7

1 file

0.8.6

1 file

0.8.5

1 file

0.8.4

1 file

0.8.3

1 file

0.8.2

1 file

0.8.1

1 file

0.8.0

1 file

0.7.0

1 file

0.6.1

1 file

0.6

1 file

0.5

1 file

0.3.3

1 file

0.3.2

1 file

0.3.1

1 file

0.3

1 file

0.2.4

1 file

0.2.3

1 file

0.2.2

1 file

0.2.1

1 file

0.2

1 file

0.1.2

1 file

0.1

1 file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page