Unhelpful error message when running a classifier on a regression outcome #26270
Description
Describe the bug
When running a classifier on a regression outcome, we get a really unhelpful error message:
Steps/Code to Reproduce
In [2]: from sklearn import linear_model, datasets
In [3]: X, y = datasets.make_regression()
In [4]: model = linear_model.LogisticRegression()
In [5]: model.fit(X, y)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-5-6d10fe8973eb> in <module>
----> 1 model.fit(X, y)
~/.local/lib/python3.10/site-packages/sklearn/linear_model/_logistic.py in fit(self, X, y, sample_weight)
1202 accept_large_sparse=solver not in ["liblinear", "sag", "saga"],
1203 )
-> 1204 check_classification_targets(y)
1205 self.classes_ = np.unique(y)
1206
~/.local/lib/python3.10/site-packages/sklearn/utils/multiclass.py in check_classification_targets(y)
205 "multilabel-sequences",
206 ]:
--> 207 raise ValueError("Unknown label type: %r" % y_type)
208
209
ValueError: Unknown label type: 'continuous'Expected Results
An error message that puts the user on the right track.
Actual Results
We could add the following sentence to the error message "Maybe you are trying to fit a classifier (discrete classes) on a regression target (continuous values)".
Versions
Present on main.
In [6]: import sklearn; sklearn.show_versions()
System:
python: 3.10.7 (main, Mar 10 2023, 10:47:39) [GCC 12.2.0]
executable: /usr/bin/python3
machine: Linux-5.19.0-38-generic-x86_64-with-glibc2.36
Python dependencies:
sklearn: 1.3.dev0
pip: 22.2
setuptools: 59.6.0
numpy: 1.21.5
scipy: 1.8.1
Cython: 0.29.34
pandas: 1.3.5
matplotlib: 3.5.2
joblib: 1.1.0
threadpoolctl: 3.1.0
Built with OpenMP: True
threadpoolctl info:
user_api: blas
internal_api: openblas
prefix: libopenblas
filepath: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.20.so
version: 0.3.20
threading_layer: pthreads
architecture: Haswell
num_threads: 8
user_api: openmp
internal_api: openmp
prefix: libgomp
filepath: /usr/lib/x86_64-linux-gnu/libgomp.so.1.0.0
version: None
num_threads: 8