acc = np.mean(accs) print "CV accuracy %0.4f (std %0.4f)" % \ (acc, np.std(accs)) d['cv_acc'].append(acc) aucs = sklearn.cross_validation.cross_val_score( ensemble, X, Y, cv = 5, scoring='roc_auc') auc = np.mean(aucs) print "CV AUC %0.4f (std %0.4f)" % \ (auc, np.std(aucs)) d['cv_auc'].append(auc) ensemble.fit(X, Y) X_pos_test = vectorizer.transform(cancer_peptides) Y_pos_pred = ensemble.predict(X_pos_test) pos_acc = np.mean(Y_pos_pred) print "Tumor antigen accuracy %0.4f" % (pos_acc,) d['pos_acc'].append(pos_acc) X_neg_test = vectorizer.transform( non_immunogenic_hiv_peptides) Y_neg_pred = ensemble.predict(X_neg_test) neg_acc = 1.0 - np.mean(Y_neg_pred) print "Non-immunogenic accuracy %0.4f" % (neg_acc,) d['neg_acc'].append(neg_acc) n_pos_pred = np.sum(Y_pos_pred) n_neg_pred = np.sum(Y_neg_pred) precision = n_pos_pred / float(n_pos_pred + n_neg_pred) recall = pos_acc
(np.mean(accs), np.std(accs)) d['acc'].append(np.mean(accs)) aucs = sklearn.cross_validation.cross_val_score( ensemble, X, Y, cv = 5, scoring='roc_auc') print "CV AUC %0.4f (std %0.4f)" % \ (np.mean(aucs), np.std(aucs)) d['auc'].append(np.mean(aucs)) ensemble.fit(X, Y) #X_self = vectorizer.transform(self_peptides) #Y_pred = ensemble.predict(X_self) #print "Self epitope accuracy %0.4f" % \ # (1.0 - np.mean(Y_pred)) X_test = vectorizer.transform(cancer_peptides) Y_pred = ensemble.predict(X_test) recall = np.mean(Y_pred) print "Tumor antigen accuracy %0.4f" % (recall,) d['recall'].append(recall) print "---" print combined = (np.mean(aucs) + recall) / 2.0 d['combined'].append(combined) df = pd.DataFrame(d) print df.sort('combined', ascending=False)