LogisticRegression
E97070
LogisticRegression is a scikit-learn machine learning estimator that models the probability of class membership using a linear decision boundary with logistic (sigmoid) or related link functions.
All labels observed (1)
| Label | Occurrences |
|---|---|
| LogisticRegression canonical | 1 |
Statements (60)
| Predicate | Object |
|---|---|
| instanceOf |
Python class
ⓘ
classification algorithm ⓘ linear model ⓘ scikit-learn estimator ⓘ |
| assumesRelationship | log-odds linear in features ⓘ |
| defaultMultiClass | auto ⓘ |
| defaultPenalty | l2 ⓘ |
| defaultSolver | lbfgs ⓘ |
| hasAttribute |
classes_
ⓘ
coef_ ⓘ intercept_ ⓘ |
| hasMethod |
decision_function
ⓘ
fit ⓘ predict ⓘ predict_proba ⓘ score ⓘ |
| linkFunctionFamily | logit link ⓘ |
| models | probability of class membership ⓘ |
| module |
scikit-learn
ⓘ
surface form:
sklearn.linear_model
|
| optimizationObjective | logistic loss minimization with regularization ⓘ |
| parameter |
C
ⓘ
class_weight ⓘ dual ⓘ fit_intercept ⓘ intercept_scaling ⓘ l1_ratio ⓘ max_iter ⓘ multi_class ⓘ n_jobs ⓘ penalty ⓘ random_state ⓘ solver ⓘ tol ⓘ verbose ⓘ warm_start ⓘ |
| providedBy | scikit-learn ⓘ |
| regularizationControlledBy | C ⓘ |
| requiresFeatureScaling | often beneficial ⓘ |
| supportsPenalty |
elasticnet
ⓘ
l1 ⓘ l2 ⓘ none ⓘ |
| supportsProbabilityEstimates | True ⓘ |
| supportsSolver |
lbfgs
ⓘ
liblinear ⓘ newton-cg ⓘ sag ⓘ saga ⓘ |
| supportsTask |
L1-regularized logistic regression
ⓘ
L2-regularized logistic regression ⓘ binary classification ⓘ elastic-net regularized logistic regression ⓘ multiclass classification ⓘ multinomial logistic regression ⓘ one-vs-one classification (via wrappers) ⓘ one-vs-rest classification ⓘ probability estimation ⓘ |
| usesDecisionBoundaryType | linear decision boundary ⓘ |
| usesLinkFunction |
logistic
ⓘ
sigmoid ⓘ |
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.