UserWarning: The y_pred values do not sum to one. Starting from 1.5 thiswill result in an error.

[pplonski]

When training AutoML on iris dataset I got warning:

[/home/piotr/sandbox/extensions/extenv/lib/python3.11/site-packages/sklearn/metrics/_scorer.py:548](http://localhost:8888/lab/tree/extenv/lib/python3.11/site-packages/sklearn/metrics/_scorer.py#line=547): FutureWarning: The `needs_threshold` and `needs_proba` parameter are deprecated in version 1.4 and will be removed in 1.6. You can either let `response_method` be `None` or set it to `predict` to preserve the same behaviour.
  warnings.warn(
[/home/piotr/sandbox/extensions/extenv/lib/python3.11/site-packages/sklearn/metrics/_classification.py:2981](http://localhost:8888/lab/tree/extenv/lib/python3.11/site-packages/sklearn/metrics/_classification.py#line=2980): UserWarning: The y_pred values do not sum to one. Starting from 1.5 thiswill result in an error.

[/home/piotr/sandbox/extensions/extenv/lib/python3.11/site-packages/supervised/preprocessing/scale.py:33](http://localhost:8888/lab/workspaces/auto-O/tree/extenv/lib/python3.11/site-packages/supervised/preprocessing/scale.py#line=32): FutureWarning: Setting an item of incompatible dtype is deprecated and will raise in a future error of pandas. Value '[-0.75189103 -0.5221718   1.66016084  1.66016084  1.66016084 -0.40731219
 -0.40731219  1.66016084 -0.63703141 -0.5221718   1.66016084 -0.63703141
 -0.63703141 -0.63703141 -0.29245258 -0.5221718   1.66016084 -0.63703141
  1.66016084  1.66016084 -0.75189103 -0.63703141  1.66016084 -0.5221718
 -0.63703141 -0.17759296  1.66016084 -0.63703141 -0.98161025 -0.86675064
 -0.5221718  -0.63703141 -0.63703141  1.66016084 -0.63703141  1.66016084
 -0.5221718  -0.63703141  1.66016084  1.66016084  1.66016084 -0.63703141
 -0.5221718  -0.29245258  1.66016084 -0.29245258 -0.63703141 -0.5221718
 -0.63703141 -0.98161025  1.66016084 -0.29245258 -0.5221718  -0.63703141
  1.66016084 -0.5221718   1.66016084 -0.98161025 -0.5221718   1.66016084
 -0.75189103  1.66016084 -0.40731219 -0.5221718   1.66016084 -0.63703141
 -0.5221718  -0.63703141 -0.5221718  -0.17759296 -0.5221718  -0.5221718
  1.66016084 -0.5221718  -0.63703141  1.66016084 -0.17759296 -0.63703141
 -0.86675064 -0.63703141 -0.17759296 -0.5221718  -0.5221718  -0.63703141
 -0.75189103  1.66016084 -0.63703141 -0.29245258 -0.63703141 -0.75189103
 -0.63703141 -0.63703141 -0.86675064 -0.40731219 -0.5221718  -0.17759296
  1.66016084 -0.98161025 -0.5221718  -0.40731219 -0.5221718  -0.5221718
 -0.17759296  1.66016084  1.66016084 -0.5221718   1.66016084  1.66016084
 -0.98161025 -0.63703141  1.66016084 -0.98161025  1.66016084 -0.98161025
 -0.5221718  -0.63703141 -0.5221718  -0.63703141 -0.63703141 -0.86675064
 -0.5221718   1.66016084 -0.63703141 -0.5221718  -0.5221718  -0.29245258
 -0.75189103]' has dtype incompatible with int64, please explicitly cast to a compatible dtype first.

`sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.

The behavior of Series.argmax/argmin with skipna=False and NAs, or with all-NAs is deprecated. In a future version this will raise ValueError.