Output exceeds the size limit. Open the full output data in a text editor about featurewiz HOT 5 CLOSED

hello @eromoe
I figured out the problem in the first statement. 👍

You must send in the entire train dataframe in the statement below and the target refers to the name of your target column in the train dataframe - instead you sent in X and y. That's the issue!

import featurewiz as FW
outputs = FW.featurewiz(dataname=X.reset_index(drop=True), target=y.reset_index(drop=True), corr_limit=0.70, verbose=2, sep=',', 
          header=0, test_data='',feature_engg='', category_encoders='',
          dask_xgboost_flag=False, nrows=None)

Also I noticed that this is a big dataframe. So you might want to set nrows to be 10000 or something small so that your dataframe is handled in pandas without blowing up.
Hope this finally solves it.
AutoVimal

from featurewiz.

Hi @eromoe 👍
There is something wrong with the input. I would suggest you avoid the y.reset_index(drop=True) statement. Instead, just send X and y as is. Featurewiz doesn't mind if you send dataframes with index in them. Can you try that and report back to me?

Thanks
Autovimal

from featurewiz.

@AutoViML The index is string, so I droped, without drop got same error .
PS: The new style feature selection works well with same input .

from featurewiz.

Oh , that's my mistake , thank you for point it out !

from featurewiz.

help me

from featurewiz.