def gcf(X_train, X_test, y_train, y_test, cnames): clf = gcForest(shape_1X=(1, 18988), window=[1000, 2000], stride=10) clf.fit(X_train, y_train) y_pred = clf.predict(X_test) print(y_pred)
y_test_cna = y_cna.iloc[folds_cna[j]] X_train_cna = x_cna.iloc[ list(set(range(x.shape[0])).difference(set(folds_cna[j]))), :] y_train_cna = y_cna.iloc[list( set(range(x.shape[0])).difference(set(folds_cna[j])))] X_test_cna.to_csv("four/" + str(j) + str(drug) + "_X_test_cna.csv") y_test_cna.to_csv("four/" + str(j) + str(drug) + "_y_test_cna.csv") ######################mgs expr part################ levels = np.unique(np.array(y_train)) print("levels:", levels) File = open("four/" + str(j) + str(drug) + ".txt", "w") File.write("levels:" + str(levels) + "\n") clf = gcForest(shape_1X=(1, 400), window=[100, 200], stride=2, levels=levels, f=File) if np.shape(X_train)[0] != len(y_train): raise ValueError('Sizes of y and X do not match.') expr_mgs_X = clf.mg_scanning(np.array(X_train), np.array(y_train)) pd.DataFrame(expr_mgs_X).to_csv("four/expr_mgs_X.csv") expr_window1 = expr_mgs_X[0] print("expr_window1:", expr_window1) expr_window2 = expr_mgs_X[1] expr_mgs_X_test = clf.mg_scanning(np.array(X_test)) pd.DataFrame(expr_mgs_X_test).to_csv("four/expr_mgs_X_test.csv") expr_window1_test = expr_mgs_X_test[0] expr_window2_test = expr_mgs_X_test[1] ######################mgs cna part################