This shows you the differences between two versions of the page.
code:ridge_regression [2013/09/18 14:38] asa created |
code:ridge_regression [2016/08/09 10:25] |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | === Ridge Regression === | ||
- | |||
- | <file python ridge_regression.py> | ||
- | |||
- | import numpy as np | ||
- | from PyML.classifiers.baseClassifiers import Classifier | ||
- | from PyML.evaluators import resultsObjects | ||
- | |||
- | """ | ||
- | An implementation of ridge regression. | ||
- | This is a simpler version than the one in PyML (see classifiers/ridgeRegression). | ||
- | It works with the PyVectorDataSet container | ||
- | """ | ||
- | |||
- | class RidgeRegression (Classifier) : | ||
- | |||
- | """ | ||
- | An implementation of ridge regression | ||
- | |||
- | :Keywords: | ||
- | - `ridge` -- the ridge parameter [default: 10.0] | ||
- | - `kernel` -- a kernel object [default: Linear] | ||
- | - `regression` -- whether to use the object for regression [default: False] | ||
- | in its default (False), it is used as a classifier | ||
- | - `fit_bias` -- whether to incorporate a bias term [default: True] | ||
- | |||
- | """ | ||
- | |||
- | attributes = {'ridge': 10, | ||
- | 'regression' : False, | ||
- | 'fit_bias' : True} | ||
- | |||
- | def __init__(self, arg=None, **args) : | ||
- | |||
- | Classifier.__init__(self, arg, **args) | ||
- | if self.regression : | ||
- | self.resultsObject = resultsObjects.RegressionResults | ||
- | self.classify = self.decisionFunc | ||
- | |||
- | |||
- | def train(self, data, **args) : | ||
- | |||
- | Classifier.train(self, data, **args) | ||
- | |||
- | if not self.regression and data.labels.numClasses != 2 : | ||
- | raise ValueError, "not a binary classification problem" | ||
- | |||
- | if self.fit_bias : | ||
- | data.addFeature('bias', [1.0 for i in range(len(data))]) | ||
- | |||
- | self.w = np.zeros(data.numFeatures) | ||
- | self.bias = 0.0 | ||
- | |||
- | Y = np.array(data.labels.Y) | ||
- | if not (self.regression) : | ||
- | Y = Y * 2 - 1 | ||
- | self.w = np.linalg.solve(data.X.T.dot(data.X) + self.ridge * np.eye(data.numFeatures), data.X.T.dot(Y)) | ||
- | # there are alternative ways of computing the weight vector which are not | ||
- | # as computationally efficient: | ||
- | #self.w = np.dot(np.linalg.inv(data.X.T.dot(data.X)), X.T.dot(Y)) | ||
- | #self.w = np.dot(np.linalg.pinv(data.X), Y) | ||
- | if self.fit_bias : | ||
- | data.eliminateFeatures([data.numFeatures -1]) | ||
- | self.bias = self.w[-1] | ||
- | self.w = self.w[:-1] | ||
- | |||
- | # this should be the last command in the train function | ||
- | self.log.trainingTime = self.getTrainingTime() | ||
- | |||
- | |||
- | def decisionFunc(self, data, i) : | ||
- | |||
- | return np.dot(self.w, data.X[i]) + self.bias | ||
- | |||
- | def classify(self, data, i) : | ||
- | |||
- | score = self.decisionFunc(data, i) | ||
- | classification = 1 if score > 0 else 0 | ||
- | return (classification, score) | ||
- | |||
- | </file> |