Package parsimony :: Module estimators
[hide private]
[frames] | no frames]

Module estimators

source code

Estimators encapsulates an algorithm with (possibly) a corresponding loss function and penalties.

Created on Sat Nov 2 15:19:17 2013

Copyright (c) 2013-2014, CEA/DSV/I2BM/Neurospin. All rights reserved.


Author: Tommy Löfstedt, Edouard Duchesnay

License: BSD 3-clause.

Classes [hide private]
  BaseEstimator
Base class for estimators.
  RegressionEstimator
Base estimator for regression estimation.
  LogisticRegressionEstimator
Base estimator for logistic regression estimation
  LinearRegression
Linear regression:
  RidgeRegression
Linear regression with an L2 penalty.
  Lasso
Linear regression with an L1 penalty:
  ElasticNet
Linear regression with L1 and L2 penalties.
  LinearRegressionL1L2TV
Linear regression with L1, L2 and TV penalties:
  LinearRegressionL1L2GL
Linear regression with L1, L2 and Group lasso penalties:
  LogisticRegression
Logistic regression (re-weighted log-likelihood aka.
  RidgeLogisticRegression
Logistic regression (re-weighted log-likelihood aka.
  ElasticNetLogisticRegression
Logistic regression (re-weighted log-likelihood aka.
  LogisticRegressionL1L2TV
Logistic regression (re-weighted log-likelihood aka.
  LogisticRegressionL1L2GL
Logistic regression (re-weighted log-likelihood aka.
  LinearRegressionL2SmoothedL1TV
Linear regression with L2 and simultaneously smoothed L1 and TV penalties:
  PLSRegression
Estimator for PLS regression
  SparsePLSRegression
Estimator for sparse PLS regression
  Clustering
Estimator for the clustering problem, i.e.
Variables [hide private]
  __package__ = 'parsimony'