SequentialFeatureSelector is not working with ColumnTransformer #25711
Description
Describe the bug
Please see the code.
Steps/Code to Reproduce
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.compose import ColumnTransformer
import pandas as pd
import numpy as np
# dummy data
N = 100
dummy_x = pd.DataFrame(
np.random.randn(N,3),
columns = list('abc'),
)
dummy_y = pd.DataFrame(
np.random.choice([0,1], size= (N,1)),
columns = ['label'],
)
num_pipeline = Pipeline([
('imputer', SimpleImputer(strategy="median")),
('std_scaler', StandardScaler()),
])
ct_parts = [
('num', num_pipeline, [0,1,2]),
]
data_preparation_pipe = ColumnTransformer(ct_parts, remainder='passthrough')
from sklearn.feature_selection import SequentialFeatureSelector
from sklearn.ensemble import GradientBoostingClassifier
model = Pipeline(
[
# ('data_prep', num_pipeline),
('data_prep', data_preparation_pipe),
('ML', GradientBoostingClassifier()),
]
)
sfs = SequentialFeatureSelector(
model,
)
sfs.fit(dummy_x, dummy_y)Expected Results
No error
Actual Results
Traceback (most recent call last):
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/IPython/core/interactiveshell.py", line 3460, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "/tmp/ipykernel_3433582/3663298101.py", line 1, in <module>
sfs.fit(dummy_x, dummy_y)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/feature_selection/_sequential.py", line 268, in fit
new_feature_idx, new_score = self._get_best_new_feature_score(
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/feature_selection/_sequential.py", line 299, in _get_best_new_feature_score
scores[feature_idx] = cross_val_score(
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 515, in cross_val_score
cv_results = cross_validate(
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 285, in cross_validate
_warn_or_raise_about_fit_failures(results, error_score)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 367, in _warn_or_raise_about_fit_failures
raise ValueError(all_fits_failed_message)
ValueError:
All the 5 fits failed.
It is very likely that your model is misconfigured.
You can try to debug the error by setting error_score='raise'.
Below are more details about the failures:
--------------------------------------------------------------------------------
5 fits failed with the following error:
Traceback (most recent call last):
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/utils/__init__.py", line 416, in _get_column_indices
idx = _safe_indexing(np.arange(n_columns), key)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/utils/__init__.py", line 356, in _safe_indexing
return _array_indexing(X, indices, indices_dtype, axis=axis)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/utils/__init__.py", line 185, in _array_indexing
return array[key] if axis == 0 else array[:, key]
IndexError: index 1 is out of bounds for axis 0 with size 1
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/model_selection/_validation.py", line 686, in _fit_and_score
estimator.fit(X_train, y_train, **fit_params)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/pipeline.py", line 401, in fit
Xt = self._fit(X, y, **fit_params_steps)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/pipeline.py", line 359, in _fit
X, fitted_transformer = fit_transform_one_cached(
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/joblib/memory.py", line 349, in __call__
return self.func(*args, **kwargs)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/pipeline.py", line 893, in _fit_transform_one
res = transformer.fit_transform(X, y, **fit_params)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/utils/_set_output.py", line 142, in wrapped
data_to_wrap = f(self, X, *args, **kwargs)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/compose/_column_transformer.py", line 724, in fit_transform
self._validate_column_callables(X)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/compose/_column_transformer.py", line 426, in _validate_column_callables
transformer_to_input_indices[name] = _get_column_indices(X, columns)
File "/software/anaconda3/envs/TOSC_ML/lib/python3.10/site-packages/sklearn/utils/__init__.py", line 418, in _get_column_indices
raise ValueError(
ValueError: all features must be in [0, 0] or [-1, 0]Versions
System:
python: 3.10.9 | packaged by conda-forge | (main, Feb 2 2023, 20:20:04) [GCC 11.3.0]
executable: /software/anaconda3/envs/TOSC_ML/bin/python
machine: Linux-4.18.0-305.3.1.el8.x86_64-x86_64-with-glibc2.28
Python dependencies:
sklearn: 1.2.1
pip: 23.0
setuptools: 67.3.2
numpy: 1.23.5
scipy: 1.10.0
Cython: None
pandas: 1.5.3
matplotlib: 3.7.0
joblib: 1.2.0
threadpoolctl: 3.1.0
Built with OpenMP: True
threadpoolctl info:
user_api: blas
internal_api: openblas
prefix: libopenblas
filepath: /software/anaconda3/envs/TOSC_ML/lib/libopenblasp-r0.3.21.so
version: 0.3.21
threading_layer: pthreads
architecture: Zen
num_threads: 128
user_api: openmp
internal_api: openmp
prefix: libgomp
filepath: /software/anaconda3/envs/TOSC_ML/lib/libgomp.so.1.0.0
version: None
num_threads: 128