import numpy as np import evaluation from sklearn.cross_validation import KFold from sklearn.feature_selection import RFE from sklearn.feature_selection import SelectKBest from datahandler import DataHandler def f_regression(X, Y): import sklearn return sklearn.feature_selection.f_regression(X, Y, center=False) # center=True (the default) would not work ("ValueError: center=True only allowed for dense data") but should presumably work in general if __name__ == '__main__': [X, y] = DataHandler.getTrainingData() X = DataHandler.getFeatures(X) yCasual = y[0] yRegistered = y[1] kf = KFold(len(X), n_folds=10) scoresCasualExtraTreesRegression = [] scoresRegisteredExtraTreesRegression = [] scoresTotalExtraTreesRegression = [] scoresCasualABR = [] scoresRegisteredABR = [] scoresTotalABR = [] mdlExtraTreesRegressorCasual = None mdlExtraTreesRegressorRegistered = None
from sklearn.feature_selection import RFE from sklearn.feature_selection import SelectKBest from datahandler import DataHandler def f_regression(X, Y): import sklearn return sklearn.feature_selection.f_regression( X, Y, center=False ) # center=True (the default) would not work ("ValueError: center=True only allowed for dense data") but should presumably work in general if __name__ == '__main__': [X, y] = DataHandler.getTrainingData() X = DataHandler.getFeatures(X) yCasual = y[0] yRegistered = y[1] kf = KFold(len(X), n_folds=10) scoresCasualExtraTreesRegression = [] scoresRegisteredExtraTreesRegression = [] scoresTotalExtraTreesRegression = [] scoresCasualABR = [] scoresRegisteredABR = [] scoresTotalABR = [] mdlExtraTreesRegressorCasual = None mdlExtraTreesRegressorRegistered = None