Explain features from my keras object with lime R package

Question

After obtaining accuracy metric from my keras binary classification model, I need know what the model made the predictions. So, I'm interested in variable importance. I use lime package.

library(lime)

explainer <- lime (
  x  = x_train, 
  model  = model_keras, 
  bin_continuous  = FALSE)

explanation <- explain (
    x_test[1:20,], # Show first 20 samples
    explainer    = explainer, 
    n_labels     = 1, 
    n_features   = 5)

Explain function gives me the following error in py_get_attr_impl function: AttributeError: 'function' object has no attribute 'func_name'.

I have compiled keras model with R, but this Issue seems to be that error comes from Python version. Problems with Reticulate package?

You need to define appropriate `lime::model_type()` and `lime::predict_model()` methods for your `keras` model. Can you share a [reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example)? — Mikael Poul Johannesson, May 17 '18 at 17:42
Lime v0.4 is supposed to have native support for keras [https://tensorflow.rstudio.com/blog/lime-v0.4-the-kitten-picture-edition.html] — Scott Worland, May 22 '18 at 19:25

score 1 · Accepted Answer · answered Jul 31 '18 at 22:02

It works with python 2.7 but generates error with python 3+.

Actually function attribute func_name was renamed in python 3+ to __name__.

lime package (models.R) has a line:

if (keras::get_layer(x, index = -1)$activation$func_name == 'linear')

I removed $func_name and the code worked for me. I suppose this is not the best workaround, however the possible solution that comes to mind:

if (keras::get_layer(x, index = -1)$activation$__name__ == 'linear')

did not work with R.

The full code was taken from here: http://www.business-science.io/business/2017/11/28/customer_churn_analysis_keras.html — Sergey Volkov, Jul 31 '18 at 22:16

Explain features from my keras object with lime R package

1 Answers1