Paul Glad Mihai

I'm not sure my problem fits here, but I get the following error for a kraken import: `ledgers.csv row 7: Parameters for refid QYTM757-VSJIHJ-JGLBQP (Deposit) do not agree: coin.` The...

Just to clarify, I do indeed have two lines with the same transaction and this is what it looks like 1. [missing txid] QYTM757-VSJIHJ-JGLBQP date deposit currency ZEUR 11 0.1...

It ran through successfully! Thanks for the tip! You can add it to the `kraken_asset_map`. Or I can add it and do a PR.

There's a bug in deeptable.py at line 660 where the model is saved. Please change `os.makedirs` to `os.makedir`.

I'm not really seeing any embedding of the continuous features. They also don't enter the CIN or the AutoInt models.

I'm also interested in computing explanations using i[ntegrated gradients](https://github.com/ankurtaly/Integrated-Gradients) working ([Here's a nice Keras tutorial](https://keras.io/examples/vision/integrated_gradients/)). Unfortunately, the embedding layers are not differentiable and gradient calculations are then impossible. A solution...

I've got the SHAP values working with DT. You need a helper function in order to get the feature names back into a dataframe. SHAP takes a pandas dataframe but...

@kcetskcaz did you add the function to the MAE class? If so, how did you cal lit? If not, how did you implement it? I'm a bit confused over the...

Thanks for your answer. I tried SHAP but kept running into trouble with the inputs, and unfortunately I haven't been abel to figure it out. I would really appreciate a...

I've found the following solution. SHAP loses the feature names and tb.transform needs them to differentiate categorical from numerical features: ``` feature_names=X_train.columns.to_list() def model_predict(data_asarray): data_asframe = pd.DataFrame(data_asarray, columns=feature_names) x =...