Python3.x 如何从形状汇总图中提取实际值

你已经做到了:

from sklearn.datasets import make_classification
from shap import Explainer, waterfall_plot, Explanation
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from shap import summary_plot


# Generate noisy Data
X, y = make_classification(n_samples=1000, 
                          n_features=50, 
                          n_informative=9, 
                          n_redundant=0, 
                          n_repeated=0, 
                          n_classes=10, 
                          n_clusters_per_class=1,
                          class_sep=9,
                          flip_y=0.2,
                          random_state=17)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

model = RandomForestClassifier()
model.fit(X_train, y_train)

explainer = Explainer(model)
sv = explainer.shap_values(X_test)

summary_plot(sv, X_train, plot_type="bar")

请注意，顶部有功能3、29、34等.

如果您这样做了:

np.abs(sv).shape

(10, 250, 50)

您将发现您有10个类，对应于50个特性的250个数据点.

如果你加在一起，你会得到你需要的一切:

aggs = np.abs(sv).mean(1)
aggs.shape

(10, 50)

您可以绘制它:

sv_df = pd.DataFrame(aggs.T)
sv_df.plot(kind="barh",stacked=True)

如果它看起来仍然不熟悉，你可以重新排列和过滤:

sv_df.loc[sv_df.sum(1).sort_values(ascending=True).index[-10:]].plot(kind="barh",stacked=True) 

结论:

sv_df是汇总图形中的聚合Shap值，按每行要素和每列类别排列.

这有帮助吗？