Open chriseal opened 5 years ago
Just had this bug, but was able to resolve by removing nan values.
I can't see any nans in the array you posted above, but maybe try a quick variable clean?
I've checked the data, and as far as I can tell, as long as the feature doesn't include any null values in the array, it is not drawing this error. Since I used XGBoost, I had to mask the feature set for non-null values in the column of choice.
So it seems, I was unable to recreate the error. Though, I'm not entirely sure which dataset I was using when I posted this, so can't entirely attribute it to a variable clean. I'll repost if I find it again.
Ran into this issue as well. Any plans for supporting NaN? (since xgboost and other boosting libraries do)
My data has no NaN but still runs to this issue...btw I'm using XGBoost
I've got pdp_isolate to work on other features, but it throws an exception "ValueError: No objects to concatenate" when plotted for column "f66". Does this mean there isn't enough information to make a plot of this feature?
Code that draws the error is:
Error printout is:
The array of data is: