def test_write_parameters():
# Test that we can write to coef_ and intercept_
clf = LogisticRegression(random_state=0)
clf.fit(X, Y1)
clf.coef_[:] = 0
clf.intercept_[:] = 0
assert_array_almost_equal(clf.decision_function(X), 0)
def test_write_parameters():
# Test that we can write to coef_ and intercept_
clf = LogisticRegression(random_state=0)
clf.fit(X, Y1)
clf.coef_[:] = 0
clf.intercept_[:] = 0
assert_array_almost_equal(clf.decision_function(X), 0)
class LogisticRegressionImpl():
def __init__(self, penalty='l2', dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight='balanced', random_state=None, solver='liblinear', max_iter=100, multi_class='ovr', verbose=0, warm_start=False, n_jobs=None):
self._hyperparams = {
'penalty': penalty,
'dual': dual,
'tol': tol,
'C': C,
'fit_intercept': fit_intercept,
'intercept_scaling': intercept_scaling,
'class_weight': class_weight,
'random_state': random_state,
'solver': solver,
'max_iter': max_iter,
'multi_class': multi_class,
'verbose': verbose,
'warm_start': warm_start,
'n_jobs': n_jobs}
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 predict_proba(self, X):
return self._wrapped_model.predict_proba(X)
def decision_function(self, X):
return self._wrapped_model.decision_function(X)
def test_sparsify():
# Test sparsify and densify members.
n_samples, n_features = iris.data.shape
target = iris.target_names[iris.target]
clf = LogisticRegression(random_state=0).fit(iris.data, target)
pred_d_d = clf.decision_function(iris.data)
clf.sparsify()
assert_true(sp.issparse(clf.coef_))
pred_s_d = clf.decision_function(iris.data)
sp_data = sp.coo_matrix(iris.data)
pred_s_s = clf.decision_function(sp_data)
clf.densify()
pred_d_s = clf.decision_function(sp_data)
assert_array_almost_equal(pred_d_d, pred_s_d)
assert_array_almost_equal(pred_d_d, pred_s_s)
assert_array_almost_equal(pred_d_d, pred_d_s)
def test_sparsify():
# Test sparsify and densify members.
n_samples, n_features = iris.data.shape
target = iris.target_names[iris.target]
clf = LogisticRegression(random_state=0).fit(iris.data, target)
pred_d_d = clf.decision_function(iris.data)
clf.sparsify()
assert_true(sp.issparse(clf.coef_))
pred_s_d = clf.decision_function(iris.data)
sp_data = sp.coo_matrix(iris.data)
pred_s_s = clf.decision_function(sp_data)
clf.densify()
pred_d_s = clf.decision_function(sp_data)
assert_array_almost_equal(pred_d_d, pred_s_d)
assert_array_almost_equal(pred_d_d, pred_s_s)
assert_array_almost_equal(pred_d_d, pred_d_s)
def test_multinomial_binary_probabilities():
# Test multinomial LR gives expected probabilities based on the
# decision function, for a binary problem.
X, y = make_classification()
clf = LogisticRegression(multi_class='multinomial', solver='saga')
clf.fit(X, y)
decision = clf.decision_function(X)
proba = clf.predict_proba(X)
expected_proba_class_1 = (np.exp(decision) /
(np.exp(decision) + np.exp(-decision)))
expected_proba = np.c_[1-expected_proba_class_1, expected_proba_class_1]
assert_almost_equal(proba, expected_proba)
def test_fit_credit_backupsklearn():
df = pd.read_csv("./open_data/creditcard.csv")
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.LogisticRegression
enet_h2o4gpu = Solver(glm_stop_early=False)
print("h2o4gpu fit()")
enet_h2o4gpu.fit(X, y)
print("h2o4gpu predict()")
print(enet_h2o4gpu.predict(X))
print("h2o4gpu score()")
print(enet_h2o4gpu.score(X, y))
enet = Solver(dual=True, max_iter=100, tol=1E-4, random_state=1234)
print("h2o4gpu scikit wrapper fit()")
enet.fit(X, y)
print("h2o4gpu scikit wrapper predict()")
print(enet.predict(X))
print("h2o4gpu scikit wrapper predict_proba()")
print(enet.predict_proba(X))
print("h2o4gpu scikit wrapper predict_log_proba()")
print(enet.predict_log_proba(X))
print("h2o4gpu scikit wrapper score()")
print(enet.score(X, y))
print("h2o4gpu scikit wrapper decision_function()")
print(enet.decision_function(X))
print("h2o4gpu scikit wrapper densify()")
print(enet.densify())
print("h2o4gpu scikit wrapper sparsify")
print(enet.sparsify())
from sklearn.linear_model.logistic import LogisticRegression
enet_sk = LogisticRegression(dual=True,
max_iter=100,
tol=1E-4,
random_state=1234)
print("Scikit fit()")
enet_sk.fit(X, y)
print("Scikit predict()")
print(enet_sk.predict(X))
print("Scikit predict_proba()")
print(enet_sk.predict_proba(X))
print("Scikit predict_log_proba()")
print(enet_sk.predict_log_proba(X))
print("Scikit score()")
print(enet_sk.score(X, y))
print("Scikit decision_function()")
print(enet_sk.decision_function(X))
print("Scikit densify()")
print(enet_sk.densify())
print("Sciki sparsify")
print(enet_sk.sparsify())
enet_sk_coef = csr_matrix(enet_sk.coef_, dtype=np.float32).toarray()
print(enet_sk.coef_)
print(enet_sk_coef)
print(enet.coef_)
print(enet_sk.intercept_)
print("Coeffs, intercept, and n_iters should match")
assert np.allclose(enet.coef_, enet_sk_coef)
assert np.allclose(enet.intercept_, enet_sk.intercept_)
assert np.allclose(enet.n_iter_, enet_sk.n_iter_)
print("Preds should match")
assert np.allclose(enet.predict_proba(X), enet_sk.predict_proba(X))
assert np.allclose(enet.predict(X), enet_sk.predict(X))
assert np.allclose(enet.predict_log_proba(X), enet_sk.predict_log_proba(X))
def test_fit_credit_backupsklearn():
df = pd.read_csv("./open_data/creditcard.csv")
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.LogisticRegression
enet_h2o4gpu = Solver(glm_stop_early=False)
print("h2o4gpu fit()")
enet_h2o4gpu.fit(X, y)
print("h2o4gpu predict()")
print(enet_h2o4gpu.predict(X))
print("h2o4gpu score()")
print(enet_h2o4gpu.score(X,y))
enet = Solver(dual=True, max_iter=100, tol=1E-4, intercept_scaling=0.99, random_state=1234)
print("h2o4gpu scikit wrapper fit()")
enet.fit(X, y)
print("h2o4gpu scikit wrapper predict()")
print(enet.predict(X))
print("h2o4gpu scikit wrapper predict_proba()")
print(enet.predict_proba(X))
print("h2o4gpu scikit wrapper predict_log_proba()")
print(enet.predict_log_proba(X))
print("h2o4gpu scikit wrapper score()")
print(enet.score(X,y))
print("h2o4gpu scikit wrapper decision_function()")
print(enet.decision_function(X))
print("h2o4gpu scikit wrapper densify()")
print(enet.densify())
print("h2o4gpu scikit wrapper sparsify")
print(enet.sparsify())
from sklearn.linear_model.logistic import LogisticRegression
enet_sk = LogisticRegression(dual=True, max_iter=100, tol=1E-4, intercept_scaling=0.99, random_state=1234)
print("Scikit fit()")
enet_sk.fit(X, y)
print("Scikit predict()")
print(enet_sk.predict(X))
print("Scikit predict_proba()")
print(enet_sk.predict_proba(X))
print("Scikit predict_log_proba()")
print(enet_sk.predict_log_proba(X))
print("Scikit score()")
print(enet_sk.score(X,y))
print("Scikit decision_function()")
print(enet_sk.decision_function(X))
print("Scikit densify()")
print(enet_sk.densify())
print("Sciki sparsify")
print(enet_sk.sparsify())
enet_sk_coef = csr_matrix(enet_sk.coef_, dtype=np.float32).toarray()
print(enet_sk.coef_)
print(enet_sk_coef)
print(enet.coef_)
print(enet_sk.intercept_)
print("Coeffs, intercept, and n_iters should match")
assert np.allclose(enet.coef_, enet_sk_coef)
assert np.allclose(enet.intercept_, enet_sk.intercept_)
assert np.allclose(enet.n_iter_, enet_sk.n_iter_)
print("Preds should match")
assert np.allclose(enet.predict_proba(X), enet_sk.predict_proba(X))
assert np.allclose(enet.predict(X), enet_sk.predict(X))
assert np.allclose(enet.predict_log_proba(X), enet_sk.predict_log_proba(X))
