def test_mbsgd_regressor_default(datatype, nrows,
column_info):
ncols, n_info = column_info
X, y = make_regression(n_samples=nrows, n_features=ncols,
n_informative=n_info, random_state=0)
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8,
random_state=0)
cu_mbsgd_regressor = cumlMBSGRegressor()
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test).to_array()
skl_sgd_regressor = SGDRegressor()
skl_sgd_regressor.fit(X_train, y_train)
skl_pred = skl_sgd_regressor.predict(X_test)
cu_r2 = r2_score(cu_pred, y_test, convert_dtype=datatype)
skl_r2 = r2_score(skl_pred, y_test, convert_dtype=datatype)
try:
assert abs(cu_r2 - skl_r2) <= 0.02
except AssertionError:
pytest.xfail("failed due to AssertionError error, "
"fix will be merged soon")
def test_mbsgd_regressor_vs_skl(lrate, penalty, make_dataset):
nrows, datatype, X_train, X_test, y_train, y_test = make_dataset
if nrows < 500000:
cu_mbsgd_regressor = cumlMBSGRegressor(learning_rate=lrate,
eta0=0.005,
epochs=100,
fit_intercept=True,
batch_size=2,
tol=0.0,
penalty=penalty)
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test)
cu_r2 = r2_score(cp.asnumpy(cu_pred),
cp.asnumpy(y_test),
convert_dtype=datatype)
skl_sgd_regressor = SGDRegressor(learning_rate=lrate,
eta0=0.005,
max_iter=100,
fit_intercept=True,
tol=0.0,
penalty=penalty,
random_state=0)
skl_sgd_regressor.fit(cp.asnumpy(X_train), cp.asnumpy(y_train).ravel())
skl_pred = skl_sgd_regressor.predict(cp.asnumpy(X_test))
skl_r2 = r2_score(skl_pred, cp.asnumpy(y_test), convert_dtype=datatype)
assert abs(cu_r2 - skl_r2) <= 0.02
def test_mbsgd_regressor(datatype, lrate, input_type, penalty,
nrows, column_info):
ncols, n_info = column_info
X, y = make_regression(n_samples=nrows, n_features=ncols,
n_informative=n_info, random_state=0)
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8,
random_state=0)
cu_mbsgd_regressor = cumlMBSGRegressor(learning_rate=lrate, eta0=0.005,
epochs=100, fit_intercept=True,
batch_size=2, tol=0.0,
penalty=penalty)
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test).to_array()
skl_sgd_regressor = SGDRegressor(learning_rate=lrate, eta0=0.005,
max_iter=100, fit_intercept=True,
tol=0.0, penalty=penalty,
random_state=0)
skl_sgd_regressor.fit(X_train, y_train)
skl_pred = skl_sgd_regressor.predict(X_test)
cu_r2 = r2_score(cu_pred, y_test, convert_dtype=datatype)
skl_r2 = r2_score(skl_pred, y_test, convert_dtype=datatype)
assert abs(cu_r2 - skl_r2) <= 0.02
def test_mbsgd_regressor(datatype, lrate, input_type, penalty, nrows, ncols):
train_rows = int(nrows * 0.8)
X, y = make_regression(n_samples=nrows, n_features=ncols, random_state=0)
X_test = np.array(X[train_rows:, :], dtype=datatype)
X_train = np.array(X[:train_rows, :], dtype=datatype)
y_train = np.array(y[:train_rows, ], dtype=datatype)
y_test = np.array(y[train_rows:, ], dtype=datatype)
cu_mbsgd_regressor = cumlMBSGRegressor(learning_rate=lrate,
eta0=0.005,
epochs=100,
fit_intercept=True,
batch_size=2,
tol=0.0,
penalty=penalty)
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test).to_array()
skl_sgd_regressor = SGDRegressor(learning_rate=lrate,
eta0=0.005,
max_iter=100,
fit_intercept=True,
tol=0.0,
penalty=penalty,
random_state=0)
skl_sgd_regressor.fit(X_train, y_train)
skl_pred = skl_sgd_regressor.predict(X_test)
cu_r2 = r2_score(cu_pred, y_test)
skl_r2 = r2_score(skl_pred, y_test)
assert (cu_r2 - skl_r2 <= 0.02)
def test_mbsgd_regressor_set_params():
x = np.linspace(0, 1, 50)
y = x * 2
model = cumlMBSGRegressor()
model.fit(x, y)
coef_before = model.coef_
model = cumlMBSGRegressor(eta0=0.1, fit_intercept=False)
model.fit(x, y)
coef_after = model.coef_
model = cumlMBSGRegressor()
model.set_params(**{'eta0': 0.1, 'fit_intercept': False})
model.fit(x, y)
coef_test = model.coef_
assert coef_before != coef_after
assert coef_after == coef_test
def test_mbsgd_regressor_attributes():
X, y = make_blobs()
clf = cumlMBSGRegressor()
clf.fit(X, y)
attrs = ["dtype", "solver_model", "coef_", "intercept_",
"l1_ratio", "n_cols", "loss", "eta0", "batch_size",
"epochs"]
for attr in attrs:
assert hasattr(clf, attr)
def test_mbsgd_regressor_default(make_dataset):
nrows, datatype, X_train, X_test, y_train, y_test = make_dataset
cu_mbsgd_regressor = cumlMBSGRegressor(batch_size=nrows / 100)
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test)
cu_r2 = r2_score(cp.asnumpy(cu_pred),
cp.asnumpy(y_test),
convert_dtype=datatype)
assert cu_r2 > 0.9
def test_mbsgd_regressor_default(make_dataset):
nrows, datatype, X_train, X_test, y_train, y_test = make_dataset
cu_mbsgd_regressor = cumlMBSGRegressor()
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test)
cu_r2 = r2_score(cu_pred, y_test, convert_dtype=datatype)
if nrows < 500000:
skl_sgd_regressor = SGDRegressor()
skl_sgd_regressor.fit(X_train, y_train)
skl_pred = skl_sgd_regressor.predict(X_test)
skl_r2 = r2_score(skl_pred, y_test, convert_dtype=datatype)
assert abs(cu_r2 - skl_r2) <= 0.02
def test_mbsgd_regressor(lrate, penalty, make_dataset):
nrows, datatype, X_train, X_test, y_train, y_test = make_dataset
cu_mbsgd_regressor = cumlMBSGRegressor(learning_rate=lrate,
eta0=0.005,
epochs=100,
fit_intercept=True,
batch_size=nrows / 100,
tol=0.0,
penalty=penalty)
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test)
cu_r2 = r2_score(cu_pred, y_test, convert_dtype=datatype)
assert cu_r2 >= 0.9
def test_mbsgd_regressor_default(datatype, nrows,
column_info):
ncols, n_info = column_info
X, y = make_regression(n_samples=nrows, n_features=ncols,
n_informative=n_info, random_state=0)
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8,
random_state=0)
cu_mbsgd_regressor = cumlMBSGRegressor()
cu_mbsgd_regressor.fit(X_train, y_train)
cu_pred = cu_mbsgd_regressor.predict(X_test).to_array()
cu_r2 = r2_score(cu_pred, y_test, convert_dtype=datatype)
if nrows < 500000:
skl_sgd_regressor = SGDRegressor()
skl_sgd_regressor.fit(X_train, y_train)
skl_pred = skl_sgd_regressor.predict(X_test)
skl_r2 = r2_score(skl_pred, y_test, convert_dtype=datatype)
assert abs(cu_r2 - skl_r2) <= 0.02
