scikit-learn__scikit-learn-11578

For probabilistic scorers, LogisticRegressionCV(multi_class='multinomial') uses OvR to calculate scores

Verdict: the fix is stated in the issue (Tier A).

It seems like altering L922 to read `log_reg = LogisticRegression(fit_intercept=fit_intercept, multi_class=multi_class)` so that the `LogisticRegression()` instance supplied to the scoring function at line 955 inherits the `multi_class` option specified in `LogisticRegressionCV()` would be a fix, but I am not a coder and would appreciate some expert insight!

The text states the fix: “It seems like altering L922 to read `log_reg = LogisticRegression(fit_intercept=fit_intercept, multi_class=multi_class)` so that the `LogisticRegression()` instance supp…”

All SWE-bench Verified tasks · more scikit-learn/scikit-learn tasks · How the check works