def do_Lasso_Kfold(y,yname,files,X): subject_num = y.shape[0] output = Outputsclass(subject_num,y,yname) output.prepare_kfold() data, idx, img = load_data(files) for train, test in cv.StratifiedKFold(np.zeros(subject_num), k = 4): # PCA pca, data_red = do_PCA(data[train]) output.pca.append(pca) data_red_test = pca.transform(data[test]) # Build design matrix & test vector desmat_cv = np.hstack((data_red,X[train])) desmat_cv = np.array(desmat_cv) y_cv = y[train] test_vec = np.hstack((data_red_test,X[test])) test_vec = np.array(test_vec) #Lasso lasso = do_LASSO(y_cv,desmat_cv) output.lasso.append(lasso) output.rsq[test] = lasso.score(desmat_cv,y_cv) output.adjrsq[test] = 1 - (1 - output.rsq[test])*(subject_num-1-1)/(subject_num-1 - lasso.coef_.shape[0] -1) # Prediction output.prediction[test] = lasso.predict(test_vec) output.pred_errors[test] = y[test] - output.prediction[test] print "did prediction, error = ", output.pred_errors[test] output.append_kfold(train,test) return output
def do_R_Crossval(y,yname,files,X,gr = 0): from LassoPCR_test import load_data from LassoPCR_test import do_PCA subject_num = y.shape[0] output = Outputsclass(subject_num,y,yname) data, idx, img = load_data(files) for train, test in cv.LeaveOneOut(subject_num): pca, data_red = do_PCA(data[train]) output.pca.append(pca) data_red_test = pca.transform(data[test]) desmat_cv = np.hstack((data_red,X[train])) desmat_cv = np.array(desmat_cv) y_cv = y[train] if type(gr) == type(y): gr_cv = gr[train] else: gr_cv = 0 test_vec = np.hstack((data_red_test,X[test])) test_vec = np.array(test_vec) mult_lm = do_Regression(y_cv,desmat_cv,gr_cv) output.mult_lm.append(mult_lm) output.rsq[test] = np.array(base.summary(mult_lm).rx("r.squared")[0]) output.adjrsq[test] = np.array(base.summary(mult_lm).rx("adj.r.squared")[0]) # Prediction predd = dict() for i, vec in enumerate(test_vec[0]): name = "roi%02d"%i predd[name] = vec if type(gr) == type(y): predd["group"] = FV([gr[test]]) preddataf = rob.DataFrame(predd) output.prediction[test] = stats.predict(mult_lm, preddataf)[0] output.pred_errors[test] = y[test] - output.prediction[test] #print "did prediction, error = ", output.pred_errors[test] return output