class LassoImpl(): def __init__(self, alpha=1.0, fit_intercept=True, normalize=False, precompute=False, copy_X=True, max_iter=1000, tol=0.0001, warm_start=False, positive=False, random_state=None, selection='cyclic'): self._hyperparams = { 'alpha': alpha, 'fit_intercept': fit_intercept, 'normalize': normalize, 'precompute': precompute, 'copy_X': copy_X, 'max_iter': max_iter, 'tol': tol, 'warm_start': warm_start, 'positive': positive, 'random_state': random_state, 'selection': selection} self._wrapped_model = SKLModel(**self._hyperparams) def fit(self, X, y=None): if (y is not None): self._wrapped_model.fit(X, y) else: self._wrapped_model.fit(X) return self def predict(self, X): return self._wrapped_model.predict(X)
def test_fit_simple_backupsklearn(backend='auto'): df = pd.read_csv("./open_data/simple.txt", delim_whitespace=True) X = np.array(df.iloc[:, :df.shape[1] - 1], dtype='float32', order='C') y = np.array(df.iloc[:, df.shape[1] - 1], dtype='float32', order='C') Solver = h2o4gpu.Lasso enet = Solver(glm_stop_early=False, backend=backend) print("h2o4gpu fit()") enet.fit(X, y) print("h2o4gpu predict()") print(enet.predict(X)) print("h2o4gpu score()") print(enet.score(X, y)) enet_wrapper = Solver(positive=True, random_state=1234, backend=backend) print("h2o4gpu scikit wrapper fit()") enet_wrapper.fit(X, y) print("h2o4gpu scikit wrapper predict()") print(enet_wrapper.predict(X)) print("h2o4gpu scikit wrapper score()") print(enet_wrapper.score(X, y)) from sklearn.linear_model.coordinate_descent import Lasso enet_sk = Lasso(positive=True, random_state=1234) print("Scikit fit()") enet_sk.fit(X, y) print("Scikit predict()") print(enet_sk.predict(X)) print("Scikit score()") print(enet_sk.score(X, y)) enet_sk_coef = csr_matrix(enet_sk.coef_, dtype=np.float32).toarray() enet_sk_sparse_coef = csr_matrix(enet_sk.sparse_coef_, dtype=np.float32).toarray() if backend != 'h2o4gpu': print(enet_sk.coef_) print(enet_sk.sparse_coef_) print(enet_sk_coef) print(enet_sk_sparse_coef) print(enet_wrapper.coef_) print(enet_wrapper.sparse_coef_) print(enet_sk.intercept_) print(enet_wrapper.intercept_) print(enet_sk.n_iter_) print(enet_wrapper.n_iter_) print(enet_wrapper.time_prepare) print(enet_wrapper.time_upload_data) print(enet_wrapper.time_fitonly) assert np.allclose(enet_wrapper.coef_, enet_sk_coef) assert np.allclose(enet_wrapper.intercept_, enet_sk.intercept_) assert np.allclose(enet_wrapper.n_iter_, enet_sk.n_iter_)
def test_lasso_zero(): # Check that the lasso can handle zero data without crashing X = [[0], [0], [0]] y = [0, 0, 0] clf = Lasso(alpha=0.1).fit(X, y) pred = clf.predict([[1], [2], [3]]) assert_array_almost_equal(clf.coef_, [0]) assert_array_almost_equal(pred, [0, 0, 0]) assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_zero(): """Check that the sparse lasso can handle zero data without crashing""" X = sp.csc_matrix((3, 1)) y = [0, 0, 0] T = np.array([[1], [2], [3]]) clf = Lasso().fit(X, y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [0]) assert_array_almost_equal(pred, [0, 0, 0]) assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_readonly_data(): X = np.array([[-1], [0], [1]]) Y = np.array([-1, 0, 1]) # just a straight line T = np.array([[2], [3], [4]]) # test sample with TempMemmap((X, Y)) as (X, Y): clf = Lasso(alpha=0.5) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [.25]) assert_array_almost_equal(pred, [0.5, 0.75, 1.]) assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_toy(): """ Test Lasso on a toy example for various values of alpha. When validating this against glmnet notice that glmnet divides it against nobs. """ X = [[-1], [0], [1]] Y = [-1, 0, 1] # just a straight line T = [[2], [3], [4]] # test sample clf = Lasso(alpha=1e-8) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [1]) assert_array_almost_equal(pred, [2, 3, 4]) assert_almost_equal(clf.dual_gap_, 0) clf = Lasso(alpha=0.1) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [0.85]) assert_array_almost_equal(pred, [1.7, 2.55, 3.4]) assert_almost_equal(clf.dual_gap_, 0) clf = Lasso(alpha=0.5) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [0.25]) assert_array_almost_equal(pred, [0.5, 0.75, 1.0]) assert_almost_equal(clf.dual_gap_, 0) clf = Lasso(alpha=1) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [0.0]) assert_array_almost_equal(pred, [0, 0, 0]) assert_almost_equal(clf.dual_gap_, 0)
def test_lasso_toy(): """ Test Lasso on a toy example for various values of alpha. When validating this against glmnet notice that glmnet divides it against nobs. """ X = [[-1], [0], [1]] Y = [-1, 0, 1] # just a straight line T = [[2], [3], [4]] # test sample clf = Lasso(alpha=1e-8) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [1]) assert_array_almost_equal(pred, [2, 3, 4]) assert_almost_equal(clf.dual_gap_, 0) clf = Lasso(alpha=0.1) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [.85]) assert_array_almost_equal(pred, [1.7, 2.55, 3.4]) assert_almost_equal(clf.dual_gap_, 0) clf = Lasso(alpha=0.5) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [.25]) assert_array_almost_equal(pred, [0.5, 0.75, 1.]) assert_almost_equal(clf.dual_gap_, 0) clf = Lasso(alpha=1) clf.fit(X, Y) pred = clf.predict(T) assert_array_almost_equal(clf.coef_, [.0]) assert_array_almost_equal(pred, [0, 0, 0]) assert_almost_equal(clf.dual_gap_, 0)
print X_train[123, :] ''' norm1 = np.linalg.norm(y_train) if norm1 != 0: y_train, y_test = y_train/norm1, y_test/norm1 print norm1 ''' print y_train.shape model = SVR(C=1.0, gamma=1.0) model = LinearRegression() lasso = Lasso(alpha=0.1).fit(X_train, y_train) enet = ElasticNet(alpha=0.1, l1_ratio=0.7).fit(X_train, y_train) y_pred = lasso.predict(X_test) print "MSE", mean_squared_error(y_test, y_pred) m = np.mean(y_test) print "MSE (Mean)", mean_squared_error(y_test, m * np.ones(len(y_test))) print "r^2 on test data", r2_score(y_test, y_pred) plt.plot(enet.coef_, label='Elastic net coefficients') plt.plot(lasso.coef_, label='Lasso coefficients') plt.legend(loc='best') plt.title("Lasso R^2: %f, Elastic Net R^2: %f" % (r2_score( y_test, lasso.predict(X_test)), r2_score(y_test, enet.predict(X_test)))) plt.show()
''' norm1 = np.linalg.norm(y_train) if norm1 != 0: y_train, y_test = y_train/norm1, y_test/norm1 print norm1 ''' print y_train.shape model = SVR(C=1.0, gamma=1.0) model = LinearRegression() lasso = Lasso(alpha=0.1).fit(X_train, y_train) enet = ElasticNet(alpha=0.1, l1_ratio=0.7).fit(X_train, y_train) y_pred = lasso.predict(X_test) print "MSE", mean_squared_error(y_test, y_pred) m = np.mean(y_test) print "MSE (Mean)",mean_squared_error(y_test, m*np.ones(len(y_test))) print "r^2 on test data", r2_score(y_test, y_pred) plt.plot(enet.coef_, label='Elastic net coefficients') plt.plot(lasso.coef_, label='Lasso coefficients') plt.legend(loc='best') plt.title("Lasso R^2: %f, Elastic Net R^2: %f" % (r2_score(y_test, lasso.predict(X_test)), r2_score(y_test, enet.predict(X_test)))) plt.show()