Linear models

Least squares, regularized, robust, Bayesian and generalized linear models.

ARDRegression	Bayesian ARD (automatic relevance determination) regression.
BayesianRidge	Bayesian ridge regression.
ElasticNet	Linear regression with a combined l1 and l2 penalty, fitted by coordinate descent.
ElasticNetCV	Elastic net with l1_ratio and alpha chosen by K-fold cross-validation.
GammaRegressor	Generalized linear model with a Gamma distribution and a log link.
HuberRegressor	Linear regression with the Huber loss, robust to outliers.
IsotonicRegression	Isotonic regression: the best monotone fit of one feature.
Lars	Least angle regression (LARS).
Lasso	Linear regression with an l1 penalty, fitted by coordinate descent.
LassoCV	Lasso with alpha chosen by K-fold cross-validation along a path.
LassoLars	Lasso fitted by least angle regression.
LinearRegression	Ordinary least squares linear regression.
LogisticRegression	Logistic regression classifier, solved by a quasi-Newton method.
LogisticRegressionCV	Logistic regression with C chosen by stratified K-fold cross-validation.
PassiveAggressiveClassifier	Passive-aggressive classifier (PA-I or PA-II).
PassiveAggressiveRegressor	Passive-aggressive regressor (PA-I or PA-II).
Perceptron	Perceptron classifier.
PoissonRegressor	Generalized linear model with a Poisson distribution and a log link.
QNRegressor	Linear regression on the squared or absolute loss, solved by a quasi-Newton method.
QuantileRegressor	Linear regression that predicts a conditional quantile.
Ridge	Linear least squares with l2 regularization.
RidgeClassifier	Classifier using ridge regression on -1/+1 targets.
RidgeCV	Ridge regression with built-in selection of alpha.
SGDClassifier	Linear classifier trained by stochastic gradient descent.
SGDOneClassSVM	Linear one-class SVM trained by stochastic gradient descent.
SGDRegressor	Linear regression trained by stochastic gradient descent.
TweedieRegressor	Generalized linear model with a Tweedie distribution.