• StackOverflow Question: https://stackoverflow.com/questions/42151921/array-like-input-for-sklearn-logisticregressioncv/42152550#42152550

Description

TypeError: Expected sequence or array-like, got estimator

Steps/Code to Reproduce

Example:

import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegressionCV

X=np.random.rand(50,5)
y=np.random.randint(2, size=50)
logmodel = LogisticRegressionCV(Cs =1, dual=False , scoring = accuracy_score, penalty = 'l2')
logmodel.fit(X, y)

Expected Results

No error is thrown.

Actual Results

TypeError: Expected sequence or array-like, got estimator

Observation:

Passing 'accuracy' or make_scorer(accuracy_score) works correctly. If this is the intended behaviour it should be mentioned in documentation.
Documentation says "Scoring function to use as cross-validation criteria. For a list of scoring functions that can be used, look at sklearn.metrics. The default scoring option used is accuracy_score.". So user may be tempted to pass accuracy_score as argument which throws the error.

Suggestion

If it is the intended behaviour, then please make the documentation same as GridSearchCV, so that the confusion may be avoided
"A string (see model evaluation documentation) or a scorer callable object / function with signature scorer(estimator, X, y). If None, the score method of the estimator is used"

Versions

Linux-3.16.0-77-generic-x86_64-with-Ubuntu-14.04-trusty
('Python', '2.7.6 (default, Oct 26 2016, 20:30:19) \n[GCC 4.8.4]')
('NumPy', '1.12.0')
('SciPy', '0.18.1')
('Scikit-Learn', '0.18.1')