Ramaravind K M

Hey, did you get a chance to try with `posthoc_sparsity_algorithm="binary"` in `generate_counterfactuals()`? I have tried with features taking very small values and this option was several orders of magnitude faster....

Hey, you can specify box constraints using `permitted_range` parameter while initiating data object `d`. For instance, you can do `d = dice_ml.Data(dataframe=dataset, continuous_features=['age', 'hours_per_week'], outcome_name='income', permitted_range={'hours_per_week':[40,60]})` https://github.com/interpretml/DiCE/blob/master/dice_ml/data_interfaces/public_data_interface.py#L21

Currently, we don't support that, but it will be really good to have that option! Most likely a small tweak in https://github.com/interpretml/DiCE/blob/master/dice_ml/data_interfaces/public_data_interface.py#L242 method should work. I will have a look...

Currently, DiCE supports classifiers based on TensorFlow or PyTorch frameworks only. If you want to use something like XGBoost, perhaps you can try [BoostedTreeClassifier](https://www.tensorflow.org/api_docs/python/tf/estimator/BoostedTreesClassifier) in TensorFlow and [here](https://www.tensorflow.org/tutorials/estimator/boosted_trees) is a...

Hmm, okay. I will check and let you know.

Hey, sorry for the late response. You are right, DiCE currently doesn't support TF's BoostedTreeClassifier. I checked and it seems like the TF's estimator API is too abstract for the...

So to differentiate the model wrt input variables, we do model(x) in both PyTorch and TensorFlow. So any model that is callable in these libraries should work such as a...

I think it depends on your model and how it is trained to handle unknown categories. Your suggestion to use OneHotEncoder to handle unknown categories will also work. However, if...

DiCE internally selects a version of the explainer implementation based on the `backend` parameter to `dice_ml.Model`. The default version is TensorFlow 1.x so you need to set it manually if...

yeah okay, so did you try using the backend parameter as mentioned in the previous comment?