Closed
Description
Description
MultiOutputClassifier has predict_proba attribute when even when base classifier does not have predict_proba.
Improvement from PR #12222
Steps/Code to Reproduce
from sklearn.linear_model import SGDClassifier
from sklearn.multioutput import MultiOutputClassifier
from sklearn import datasets
from sklearn.utils import shuffle
import numpy as np
iris = datasets.load_iris()
X = iris.data
y1 = iris.target
y2 = shuffle(y1, random_state=1)
y3 = shuffle(y1, random_state=2)
y = np.column_stack((y1, y2, y3))
sgd_linear_clf = SGDClassifier(random_state=1, max_iter=5)
multi_target_linear = MultiOutputClassifier(sgd_linear_clf)
hasattr(multi_target_linear, "predict_proba") # returns True
multi_target_linear.fit(X, y)
hasattr(multi_target_linear, "predict_proba") # returns True
multi_target_linear.predict_proba(X) # raises ValueErrorExpected Results
hasattr(multi_target_linear, "predict_proba") returns False before fit and ValueError after fit.
Actual Results
hasattr(multi_target_linear, "predict_proba") returns True before and after fit.
Versions
System:
python: 3.7.5 (default, Oct 25 2019, 10:52:18) [Clang 4.0.1 (tags/RELEASE_401/final)]
executable: /usr/local/anaconda3/envs/sklearndev/bin/python3
machine: Darwin-19.0.0-x86_64-i386-64bit
Python deps:
pip: 19.3.1
setuptools: 41.6.0.post20191030
sklearn: 0.22.dev0
numpy: 1.17.2
scipy: 1.3.1
Cython: 0.29.13
pandas: None
matplotlib: 3.1.1
joblib: 0.14.0
Metadata
Metadata
Assignees
Labels
No labels