diff --git a/README.md b/README.md index 99f9e2c..5b4d998 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,8 @@ - + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/shap/shap) · [上游 README](https://github.com/shap/shap/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。

@@ -15,15 +19,15 @@ [![PyPI pyversions](https://img.shields.io/pypi/pyversions/shap)](https://pypi.org/pypi/shap/) -**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](#citations) for details and citations). +**SHAP (SHapley Additive exPlanations)** 是一种基于博弈论的方法，用于解释任意机器学习模型的输出。它将最优信用分配与局部解释联系起来，采用博弈论中经典的 Shapley 值及其相关扩展（详见 [论文](#citations) 及引用）。 -## Install +## 安装 -SHAP can be installed from either [PyPI](https://pypi.org/project/shap) or [conda-forge](https://anaconda.org/conda-forge/shap): +可从 [PyPI](https://pypi.org/project/shap) 或 [conda-forge](https://anaconda.org/conda-forge/shap): 安装 SHAP： 

 pip install shap
@@ -31,27 +35,27 @@ pip install shap
 conda install -c conda-forge shap
-### GPU support +### GPU 支持 -To enable GPU-accelerated Tree SHAP, install from source with the CUDA toolkit available and the `SHAP_ENABLE_CUDA` environment variable set: +要启用 GPU 加速的 Tree SHAP，请在已安装 CUDA 工具包且设置 `SHAP_ENABLE_CUDA` 环境变量的情况下从源码安装： 
 SHAP_ENABLE_CUDA=1 pip install .
-This requires the [CUDA toolkit](https://developer.nvidia.com/cuda-toolkit) to be installed on your system. +这要求你的系统已安装 [CUDA toolkit](https://developer.nvidia.com/cuda-toolkit)。 -## Supported versions +## 支持的版本 -SHAP follows [SPEC 0](https://scientific-python.org/specs/spec-0000/) for minimum supported dependency versions. We test against the versions specified there and may not fix bugs for older versions. +SHAP 遵循 [SPEC 0](https://scientific-python.org/specs/spec-0000/) 规定的最低依赖版本。我们针对其中指定的版本进行测试，可能不会修复旧版本的 bug。 -## Contributing +## 贡献 -We welcome contributions highly. Feel free to file an issue. Before opening a PR make sure you've read our [CONTRIBUTING.md](CONTRIBUTING.md) guideline. +我们非常欢迎贡献。欢迎随时提交 issue。在发起 PR 之前，请确保已阅读我们的 [CONTRIBUTING.md](CONTRIBUTING.md) 指南。 -## Tree ensemble example (XGBoost/LightGBM/CatBoost/scikit-learn/pyspark models) +## 树集成示例（XGBoost/LightGBM/CatBoost/scikit-learn/pyspark 模型） -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](https://rdcu.be/b0z70)). Fast C++ implementations are supported for *XGBoost*, *LightGBM*, *CatBoost*, *scikit-learn* and *pyspark* tree models: +虽然 SHAP 可以解释任意机器学习模型的输出，但我们为树集成方法开发了高速精确算法（参见我们的 [Nature MI 论文](https://rdcu.be/b0z70)). 已为 *XGBoost*、*LightGBM*、*CatBoost*、*scikit-learn* 和 *pyspark* 树模型提供快速 C++ 实现： ```python import xgboost @@ -74,7 +78,7 @@ 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](https://rdcu.be/baVbR)): +上述解释展示了各特征如何将模型输出从基准值（我们传入的训练数据集上模型输出的平均值）推向当前模型输出。使预测值升高的特征显示为红色，使预测值降低的显示为蓝色。可视化同一解释的另一种方式是使用 force plot（在 [Nature BME 论文](https://rdcu.be/baVbR)): 中介绍）： ```python # visualize the first prediction's explanation with a force plot @@ -85,7 +89,7 @@ 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): +若将许多如上所示的 force plot 解释旋转 90 度后水平堆叠，即可查看整个数据集的解释（在 notebook 中该图可交互）： ```python # visualize all the training set predictions @@ -96,7 +100,7 @@ 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. +要了解单个特征如何影响模型输出，我们可以绘制该特征的 SHAP 值与数据集中所有样本特征值的对比图。由于 SHAP 值表示某特征对模型输出变化的“责任”，下图展示了预测房价随纬度变化的情况。同一纬度值处的纵向分散表示与其他特征的交互效应。为揭示这些交互，可按另一特征着色。若将整个解释张量传给 `color` 参数，散点图会自动选择最佳着色特征；此处它选择了经度。 ```python # create a dependence scatter plot to show the effect of a single feature across the whole dataset @@ -108,7 +112,7 @@ 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. +要概览哪些特征对模型最重要，我们可以绘制每个样本每个特征的 SHAP 值。下图按所有样本上 SHAP 值幅度之和对特征排序，并用 SHAP 值展示各特征对模型输出影响的分布。颜色表示特征值（红色为高，蓝色为低）。例如，这揭示了较高的收入中位数会提高预测房价。 ```python # summarize the effects of all the features @@ -119,7 +123,7 @@ 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): +我们也可以对每个特征 SHAP 值的绝对值取平均，得到标准条形图（多类输出会生成堆叠条形图）： ```python shap.plots.bar(shap_values) @@ -129,9 +133,9 @@ shap.plots.bar(shap_values)

-## Natural language example (transformers) +## 自然语言示例（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: +SHAP 对 Hugging Face transformers 库中的自然语言模型等提供专门支持。通过在传统 Shapley 值上添加联盟规则（coalitional rules），我们可以构造仅需极少函数评估即可解释大型现代 NLP 模型的博弈。使用该功能非常简单，只需将受支持的 transformers pipeline 传给 SHAP： ```python import transformers @@ -152,9 +156,9 @@ shap.plots.text(shap_values[0, :, "POSITIVE"])

-## Deep learning example with DeepExplainer (TensorFlow/Keras models) +## 使用 DeepExplainer 的深度学习示例（TensorFlow/Keras 模型） -Deep SHAP is a high-speed approximation algorithm for SHAP values in deep learning models that builds on a connection with [DeepLIFT](https://arxiv.org/abs/1704.02685) 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): +Deep SHAP 是深度学习模型中 SHAP 值的高速近似算法，建立在 SHAP NIPS 论文中所述与 [DeepLIFT](https://arxiv.org/abs/1704.02685) 的联系之上。此处的实现与原始 DeepLIFT 的不同之处在于：使用背景样本分布而非单一参考值，并使用 Shapley 方程对 max、softmax、乘积、除法等组件进行线性化。请注意，其中一些增强此后也已集成到 DeepLIFT 中。支持 TensorFlow 模型以及使用 TensorFlow 后端的 Keras 模型（对 PyTorch 也有初步支持）： ```python # ...include code from https://github.com/keras-team/keras/blob/master/examples/demo_mnist_convnet.py @@ -179,12 +183,12 @@ 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. +上图解释了四张不同图像对应的十个输出（数字 0-9）。红色像素会提高模型的输出，蓝色像素会降低输出。输入图像显示在左侧，并作为各张解释图背后近乎透明的灰度背景。SHAP 值的总和等于预期模型输出（在背景数据集上取平均）与当前模型输出之间的差值。请注意，对于“零”的图像，中间空白区域很重要；而对于“四”的图像，顶部缺少连接才使它被识别为四而不是九。 -## Deep learning example with GradientExplainer (TensorFlow/Keras/PyTorch models) +## 使用 GradientExplainer 的深度学习示例（TensorFlow/Keras/PyTorch 模型） -Expected gradients combines ideas from [Integrated Gradients](https://arxiv.org/abs/1703.01365), SHAP, and [SmoothGrad](https://arxiv.org/abs/1706.03825) 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. +Expected gradients（预期梯度）将 [Integrated Gradients](https://arxiv.org/abs/1703.01365), SHAP，以及 [SmoothGrad](https://arxiv.org/abs/1706.03825) 融合到一个单一的期望值方程中。这使得可以将整个数据集用作背景分布（而非单个参考值），并支持局部平滑。若我们用每个背景数据样本与当前待解释输入之间的线性函数来近似模型，并假设输入特征相互独立，则 expected gradients 将计算出近似的 SHAP 值。在下面的示例中，我们解释了 VGG16 ImageNet 模型的第 7 个中间层如何影响输出概率。 ```python from keras.applications.vgg16 import VGG16 @@ -227,11 +231,11 @@ 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). +上图解释了两张输入图像的预测结果。红色像素表示正值 SHAP，会提高该类别的概率；蓝色像素表示负值 SHAP，会降低该类别的概率。通过使用 `ranked_outputs=2`，我们仅解释每个输入中最可能的两个类别（这样就不必解释全部 1,000 个类别）。 -## Model agnostic example with KernelExplainer (explains any function) +## 使用 KernelExplainer 的模型无关示例（可解释任意函数） -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. +Kernel SHAP 使用特殊加权的局部线性回归来估计任意模型的 SHAP 值。下面是一个简单示例，用于解释经典 iris 数据集上的多分类 SVM。 ```python import sklearn @@ -257,9 +261,9 @@ shap.force_plot(explainer.expected_value[0], shap_values[0][0,:], X_test.iloc[0,

-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. +上述解释展示了四个特征各自如何将模型输出从基准值（我们传入的训练数据集上的平均模型输出）推向零。若有任何特征将类别标签推高，则会以红色显示。 -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: +若将许多如上所示的解释旋转 90 度，再水平堆叠，便可以看到整个数据集的解释。我们在下面正是这样做的，针对 iris 测试集中的所有样本： ```python # plot the SHAP values for the Setosa output of all instances @@ -269,67 +273,67 @@ shap.force_plot(explainer.expected_value[0], shap_values[0], X_test, link="logit

-## SHAP Interaction Values +## SHAP Interaction Values（SHAP 交互值） -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): +SHAP 交互值是 SHAP 值向高阶交互的推广。对于树模型，已使用 `shap.TreeExplainer(model).shap_interaction_values(X)` 实现了成对交互的快速精确计算。这会为每次预测返回一个矩阵，其中主效应位于对角线，交互效应位于非对角线。这些值常常揭示有趣的隐含关系，例如男性死亡风险在 60 岁时达到峰值（详见 NHANES notebook）：

-## Sample notebooks +## 示例 notebook -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. +下面的 notebook 演示了 SHAP 的不同使用场景。若想亲自尝试原始 notebook，请查看仓库中的 notebooks 目录。 ### TreeExplainer -An implementation of Tree SHAP, a fast and exact algorithm to compute SHAP values for trees and ensembles of trees. +Tree SHAP 的实现，一种为树及树集成快速精确计算 SHAP 值的算法。 -- [**NHANES survival model with XGBoost and SHAP interaction values**](https://shap.github.io/shap/notebooks/NHANES%20I%20Survival%20Model.html) - Using mortality data from 20 years of followup this notebook demonstrates how to use XGBoost and `shap` to uncover complex risk factor relationships. +- [**使用 XGBoost 和 SHAP 交互值的 NHANES 生存模型**](https://shap.github.io/shap/notebooks/NHANES%20I%20Survival%20Model.html) - 使用 20 年随访的死亡率数据，该 notebook 演示如何使用 XGBoost 和 `shap` 揭示复杂的风险因素关系。 -- [**Census income classification with LightGBM**](https://shap.github.io/shap/notebooks/tree_explainer/Census%20income%20classification%20with%20LightGBM.html) - Using the standard adult census income dataset, this notebook trains a gradient boosting tree model with LightGBM and then explains predictions using `shap`. +- [**使用 LightGBM 进行 Census 收入分类**](https://shap.github.io/shap/notebooks/tree_explainer/Census%20income%20classification%20with%20LightGBM.html) - 使用标准的 adult census income 数据集，该 notebook 使用 LightGBM 训练梯度提升树模型，然后使用 `shap` 解释预测结果。 -- [**League of Legends Win Prediction with XGBoost**](https://shap.github.io/shap/notebooks/League%20of%20Legends%20Win%20Prediction%20with%20XGBoost.html) - Using a Kaggle dataset of 180,000 ranked matches from League of Legends we train and explain a gradient boosting tree model with XGBoost to predict if a player will win their match. +- [**使用 XGBoost 进行 League of Legends 胜负预测**](https://shap.github.io/shap/notebooks/League%20of%20Legends%20Win%20Prediction%20with%20XGBoost.html) - 使用 Kaggle 上 18 万场排位赛的 League of Legends 数据集，我们使用 XGBoost 训练并解释梯度提升树模型，以预测玩家是否会赢得比赛。 ### 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. +Deep SHAP 的实现，一种为深度学习模型计算 SHAP 值的更快（但仅为近似）算法，基于 SHAP 与 DeepLIFT 算法之间的联系。 -- [**MNIST Digit classification with Keras**](https://shap.github.io/shap/notebooks/deep_explainer/Front%20Page%20DeepExplainer%20MNIST%20Example.html) - Using the MNIST handwriting recognition dataset, this notebook trains a neural network with Keras and then explains predictions using `shap`. +- [**使用 Keras 进行 MNIST 手写数字分类**](https://shap.github.io/shap/notebooks/deep_explainer/Front%20Page%20DeepExplainer%20MNIST%20Example.html) - 本 notebook 使用 MNIST 手写识别数据集训练 Keras 神经网络，并使用 `shap` 解释预测结果。 -- [**Keras LSTM for IMDB Sentiment Classification**](https://shap.github.io/shap/notebooks/deep_explainer/Keras%20LSTM%20for%20IMDB%20Sentiment%20Classification.html) - This notebook trains an LSTM with Keras on the IMDB text sentiment analysis dataset and then explains predictions using `shap`. +- [**使用 Keras LSTM 进行 IMDB 情感分类**](https://shap.github.io/shap/notebooks/deep_explainer/Keras%20LSTM%20for%20IMDB%20Sentiment%20Classification.html) - 本 notebook 在 IMDB 文本情感分析数据集上使用 Keras 训练 LSTM，并使用 `shap` 解释预测结果。 ### 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. +基于期望梯度（expected gradients）来近似深度学习模型 SHAP 值的实现。它建立在 SHAP 与 Integrated Gradients 算法之间的联系之上。GradientExplainer 比 DeepExplainer 更慢，并采用不同的近似假设。 -- [**Explain an Intermediate Layer of VGG16 on ImageNet**](https://shap.github.io/shap/notebooks/gradient_explainer/Explain%20an%20Intermediate%20Layer%20of%20VGG16%20on%20ImageNet.html) - This notebook demonstrates how to explain the output of a pre-trained VGG16 ImageNet model using an internal convolutional layer. +- [**解释 ImageNet 上 VGG16 的中间层**](https://shap.github.io/shap/notebooks/gradient_explainer/Explain%20an%20Intermediate%20Layer%20of%20VGG16%20on%20ImageNet.html) - 本 notebook 演示如何使用内部卷积层来解释预训练 VGG16 ImageNet 模型的输出。 ### 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. +对于特征相互独立的线性模型，我们可以解析地计算精确的 SHAP 值。若愿意估计特征协方差矩阵，也可以考虑特征相关性。LinearExplainer 同时支持这两种选项。 -- [**Sentiment Analysis with Logistic Regression**](https://shap.github.io/shap/notebooks/linear_explainer/Sentiment%20Analysis%20with%20Logistic%20Regression.html) - This notebook demonstrates how to explain a linear logistic regression sentiment analysis model. +- [**使用逻辑回归进行情感分析**](https://shap.github.io/shap/notebooks/linear_explainer/Sentiment%20Analysis%20with%20Logistic%20Regression.html) - 本 notebook 演示如何解释线性逻辑回归情感分析模型。 ### 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. +Kernel SHAP 的实现，这是一种模型无关（model agnostic）方法，可为任意模型估计 SHAP 值。由于不对模型类型做任何假设，KernelExplainer 比其他针对特定模型类型的算法更慢。 -- [**Census income classification with scikit-learn**](https://shap.github.io/shap/notebooks/Census%20income%20classification%20with%20scikit-learn.html) - Using the standard adult census income dataset, this notebook trains a k-nearest neighbors classifier using scikit-learn and then explains predictions using `shap`. +- [**使用 scikit-learn 进行人口普查收入分类**](https://shap.github.io/shap/notebooks/Census%20income%20classification%20with%20scikit-learn.html) - 本 notebook 使用标准 adult 人口普查收入数据集，通过 scikit-learn 训练 k 近邻分类器，并使用 `shap` 解释预测结果。 -- [**ImageNet VGG16 Model with Keras**](https://shap.github.io/shap/notebooks/ImageNet%20VGG16%20Model%20with%20Keras.html) - 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. +- [**使用 Keras 的 ImageNet VGG16 模型**](https://shap.github.io/shap/notebooks/ImageNet%20VGG16%20Model%20with%20Keras.html) - 解释经典 VGG16 卷积神经网络对某张图像的预测。该方法将模型无关的 Kernel SHAP 应用于超像素（super-pixel）分割后的图像。 -- [**Iris classification**](https://shap.github.io/shap/notebooks/Iris%20classification%20with%20scikit-learn.html) - A basic demonstration using the popular iris species dataset. It explains predictions from six different models in scikit-learn using `shap`. +- [**鸢尾花分类**](https://shap.github.io/shap/notebooks/Iris%20classification%20with%20scikit-learn.html) - 使用广为人知的鸢尾花物种数据集进行基础演示。它使用 `shap` 解释 scikit-learn 中六种不同模型的预测结果。 -## Documentation notebooks +## 文档类 notebook -These notebooks comprehensively demonstrate how to use specific functions and objects. +这些 notebook 全面演示了如何使用特定函数和对象。 -- [`shap.decision_plot` and `shap.multioutput_decision_plot`](https://shap.github.io/shap/notebooks/plots/decision_plot.html) +- [`shap.decision_plot` 与 `shap.multioutput_decision_plot`](https://shap.github.io/shap/notebooks/plots/decision_plot.html) - [`shap.dependence_plot`](https://shap.github.io/shap/notebooks/plots/dependence_plot.html) -## Methods Unified by SHAP +## 由 SHAP 统一的方法 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. @@ -345,13 +349,13 @@ These notebooks comprehensively demonstrate how to use specific functions and ob 7. *Tree interpreter:* Saabas, Ando. Interpreting random forests. http://blog.datadive.net/interpreting-random-forests/ -## Citations +## 引用 -The algorithms and visualizations used in this package came primarily out of research in [Su-In Lee's lab](https://suinlee.cs.washington.edu) 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): +本软件包中使用的算法和可视化主要源自 [Su-In Lee 实验室](https://suinlee.cs.washington.edu) 在华盛顿大学以及 Microsoft Research 开展的研究。若您在研究中使用 SHAP，我们希望能引用相应的论文： -- For general use of SHAP you can read/cite our [NeurIPS paper](http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions) ([bibtex](https://raw.githubusercontent.com/shap/shap/master/docs/references/shap_nips.bib)). -- For TreeExplainer you can read/cite our [Nature Machine Intelligence paper](https://www.nature.com/articles/s42256-019-0138-9) ([bibtex](https://raw.githubusercontent.com/shap/shap/master/docs/references/tree_explainer.bib); [free access](https://rdcu.be/b0z70)). -- For GPUTreeExplainer you can read/cite [this article](https://arxiv.org/abs/2010.13972). -- For `force_plot` visualizations and medical applications you can read/cite our [Nature Biomedical Engineering paper](https://www.nature.com/articles/s41551-018-0304-0) ([bibtex](https://raw.githubusercontent.com/shap/shap/master/docs/references/nature_bme.bib); [free access](https://rdcu.be/baVbR)). +- 对于 SHAP 的一般用途，您可以阅读/引用我们的 [NeurIPS 论文](http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions)（[bibtex](https://raw.githubusercontent.com/shap/shap/master/docs/references/shap_nips.bib)). +- 对于 TreeExplainer，您可以阅读/引用我们的 [Nature Machine Intelligence 论文](https://www.nature.com/articles/s42256-019-0138-9)（[bibtex](https://raw.githubusercontent.com/shap/shap/master/docs/references/tree_explainer.bib); [免费获取](https://rdcu.be/b0z70)). +- 对于 GPUTreeExplainer，您可以阅读/引用[这篇文章](https://arxiv.org/abs/2010.13972). +- 对于 `force_plot` 可视化及医学应用，您可以阅读/引用我们的 [Nature Biomedical Engineering 论文](https://www.nature.com/articles/s41551-018-0304-0)（[bibtex](https://raw.githubusercontent.com/shap/shap/master/docs/references/nature_bme.bib); [免费获取](https://rdcu.be/baVbR)).