将SHAP摘要图另存为PDF/SVG

Question

我目前正在处理一个分类问题，并希望创建功能重要性的可视化。我使用Python XGBoost包，它已经提供了特性重要性图。然而，我发现了shap (https://github.com/slundberg/shap)，这是一个Python库，它基于树分类器创建了非常好的特征重要性图。一切正常，我也可以将创建的绘图保存为PNG，但是，如果我尝试将其保存为PDF或SVG，我会得到一个异常。下面是我正在做的事情：

首先，我训练XGBoost模型，并得到用bst表示的模型。

train = remove_labels_for_binary_df(dataset_fc_baseline_1[0].train)
test = remove_labels_for_binary_df(dataset_fc_baseline_1[0].test)
results, bst = xgboost_with_bst(*transform_feat_to_num(train, test))

然后我创建形状值，使用这些值创建摘要图并保存创建的可视化效果。如果将绘图另存为plt.savefig('shap.png')，则一切正常。

import shap
import matplotlib.pyplot as plt

shap.initjs()

explainer = shap.TreeExplainer(bst)
shap_values = explainer.shap_values(train)
fig = shap.summary_plot(shap_values, train, show=False)
plt.savefig('shap.png')

然而，我需要的是PDF或SVG图而不是png，因此尝试用plt.savefig('shap.pdf')保存它，它通常工作良好，但产生以下形状图的异常。

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-39-49d17973f438> in <module>()
  1 fig = shap.summary_plot(shap_values, train, show=False)
----> 2 plt.savefig('shap.pdf')

 C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\pyplot.py in 
savefig(*args, **kwargs)
708 def savefig(*args, **kwargs):
709     fig = gcf()
--> 710     res = fig.savefig(*args, **kwargs)
711     fig.canvas.draw_idle()   # need this if 'transparent=True' to reset 
colors
712     return res

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\figure.py in 
savefig(self, fname, **kwargs)
2033             self.set_frameon(frameon)
2034 
-> 2035         self.canvas.print_figure(fname, **kwargs)
2036 
2037         if frameon:

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\backend_bases.py in 
print_figure(self, filename, dpi, facecolor, edgecolor, orientation, format, 
**kwargs)
2261                 orientation=orientation,
2262                 bbox_inches_restore=_bbox_inches_restore,
-> 2263                 **kwargs)
2264         finally:
2265             if bbox_inches and restore_bbox:

C:\Users\Studio\Anaconda3\lib\site- 
packages\matplotlib\backends\backend_pdf.py in print_pdf(self, filename, 
**kwargs)
2584                 RendererPdf(file, image_dpi, height, width),
2585                 bbox_inches_restore=_bbox_inches_restore)
-> 2586             self.figure.draw(renderer)
2587             renderer.finalize()
2588             if not isinstance(filename, PdfPages):

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\artist.py in 
draw_wrapper(artist, renderer, *args, **kwargs)
 53                 renderer.start_filter()
 54 
---> 55             return draw(artist, renderer, *args, **kwargs)
 56         finally:
 57             if artist.get_agg_filter() is not None:

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\figure.py in 
draw(self, renderer)
1473 
1474             mimage._draw_list_compositing_images(
-> 1475                 renderer, self, artists, self.suppressComposite)
1476 
1477             renderer.close_group('figure')

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\image.py in 
_draw_list_compositing_images(renderer, parent, artists, suppress_composite)
139     if not_composite or not has_images:
140         for a in artists:
--> 141             a.draw(renderer)
142     else:
143         # Composite any adjacent images together

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\artist.py in 
draw_wrapper(artist, renderer, *args, **kwargs)
 53                 renderer.start_filter()
 54 
---> 55             return draw(artist, renderer, *args, **kwargs)
 56         finally:
 57             if artist.get_agg_filter() is not None:

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in 
draw(self, renderer, inframe)
2605             renderer.stop_rasterizing()
2606 
-> 2607         mimage._draw_list_compositing_images(renderer, self, 
 artists)
2608 
2609         renderer.close_group('axes')

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\image.py in 
_draw_list_compositing_images(renderer, parent, artists, suppress_composite)
139     if not_composite or not has_images:
140         for a in artists:
--> 141             a.draw(renderer)
142     else:
143         # Composite any adjacent images together

C:\Users\Studio\Anaconda3\lib\site-packages\matplotlib\artist.py in 
draw_wrapper(artist, renderer, *args, **kwargs)
 58                 renderer.stop_filter(artist.get_agg_filter())
 59             if artist.get_rasterized():
---> 60                 renderer.stop_rasterizing()
 61 
 62     draw_wrapper._supports_rasterization = True

C:\Users\Studio\Anaconda3\lib\site- 
packages\matplotlib\backends\backend_mixed.py in stop_rasterizing(self)
128 
129             height = self._height * self.dpi
--> 130             buffer, bounds = 
self._raster_renderer.tostring_rgba_minimized()
131             l, b, w, h = bounds
132             if w > 0 and h > 0:

C:\Users\Studio\Anaconda3\lib\site- 
packages\matplotlib\backends\backend_agg.py in tostring_rgba_minimized(self)
138                 [extents[0] + extents[2], self.height - extents[1]]]
139         region = self.copy_from_bbox(bbox)
--> 140         return np.array(region), extents
141 
142     def draw_path(self, gc, path, transform, rgbFace=None):

ValueError: negative dimensions are not allowed

你知道怎么解决这个问题吗？提前感谢！

Answer 1

在保存绘图时，必须附加matplotlib=True,show=False

def heart_disease_risk_factors(model, patient):

    explainer = shap.TreeExplainer(model)
    shap_values = explainer.shap_values(patient)
    shap.initjs()

    return shap.force_plot(explainer.expected_value[1],shap_values[1],\
        patient,matplotlib=True,show=False)


plt.clf()
data_for_prediction = X_test.iloc[2,:].astype(float)
heart_disease_risk_factors(model, data_for_prediction)
plt.savefig("gg.png",dpi=150, bbox_inches='tight')

Answer 2

这是在使用rasterized=True ( shap does if there are more than 500 datapoints)绘制时导致的an issue between NumPy and matplotlib，已在最新版本的matplotlib中解决。

Answer 3

也许你可以试试这个：

shap.plots.force(shape_values[0], show=False, matplotlib=True).savefig('shap.pdf')