urllib.parse.quote: improper usage?

[kdrobnyh]

I got a problem running the model:
ValueError: feature_names mismatch

The problem is that df_inputs in predict.py:253 has columns with wrong names, like

Diagnosis%20of%20Nephritis_%20nephrosis_%20renal%20sclerosis%20in%20the%20previous%2012%20months

This is because of use urllib.parse.quote here:
df_inputs.columns = [urllib.parse.quote(col) for col in df_inputs.columns]

Python 3.7.7 and 3.8.1, Windows 10.

[DaveDeCaprio]

I think I might know what this is. Are you using the "xgboost" model rather than "xgboost_all_ages"?

We'd suggest using the "xgboost_all_ages" model as a workaround until we can get that addressed. The all ages model generally has better performance anyway.

[kdrobnyh]

Yes, I wanted to use different models. So you use different feature names?

[DaveDeCaprio]

I just pushed an update that fixes this issue for the xgboost model. It is the same columns. The all ages model uses a newer version of our platform that urlencodes the columns.

[kdrobnyh]

Great, thank you!