def test_lasso_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_lasso = cuLasso()
cu_lasso.fit(X_train, y_train)
assert cu_lasso.coef_ is not None
cu_predict = cu_lasso.predict(X_test)
cu_r2 = r2_score(y_test, cu_predict)
sk_lasso = Lasso()
sk_lasso.fit(X_train, y_train)
sk_predict = sk_lasso.predict(X_test)
sk_r2 = r2_score(y_test, sk_predict)
assert cu_r2 >= sk_r2 - 0.07
def test_lasso(datatype, X_type, alpha, algorithm,
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_lasso = cuLasso(alpha=np.array([alpha]), fit_intercept=True,
normalize=False, max_iter=1000,
selection=algorithm, tol=1e-10)
cu_lasso.fit(X_train, y_train)
assert cu_lasso.coef_ is not None
cu_predict = cu_lasso.predict(X_test)
cu_r2 = r2_score(y_test, cu_predict)
if nrows < 500000:
sk_lasso = Lasso(alpha=np.array([alpha]), fit_intercept=True,
normalize=False, max_iter=1000,
selection=algorithm, tol=1e-10)
sk_lasso.fit(X_train, y_train)
sk_predict = sk_lasso.predict(X_test)
sk_r2 = r2_score(y_test, sk_predict)
assert cu_r2 >= sk_r2 - 0.07
def test_lasso_predict_convert_dtype(train_dtype, test_dtype):
X, y = make_regression(n_samples=50, n_features=10,
n_informative=5, random_state=0)
X = X.astype(train_dtype)
y = y.astype(train_dtype)
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8,
random_state=0)
clf = cuLasso()
clf.fit(X_train, y_train)
clf.predict(X_test.astype(test_dtype))
def test_lasso(datatype, X_type, alpha, algorithm, nrows, ncols, n_info):
train_rows = np.int32(nrows * 0.8)
X, y = make_regression(n_samples=nrows,
n_features=ncols,
n_informative=n_info,
random_state=0)
X_test = np.asarray(X[train_rows:, 0:], dtype=datatype)
X_train = np.asarray(X[0:train_rows, :], dtype=datatype)
y_train = np.asarray(y[0:train_rows, ], dtype=datatype)
cu_lasso = cuLasso(alpha=np.array([alpha]),
fit_intercept=True,
normalize=False,
max_iter=1000,
selection=algorithm,
tol=1e-10)
if X_type == 'dataframe':
y_train = pd.DataFrame({'fea0': y_train[0:, ]})
X_train = pd.DataFrame(
{'fea%d' % i: X_train[0:, i]
for i in range(X_train.shape[1])})
X_test = pd.DataFrame(
{'fea%d' % i: X_test[0:, i]
for i in range(X_test.shape[1])})
X_cudf = cudf.DataFrame.from_pandas(X_train)
X_cudf_test = cudf.DataFrame.from_pandas(X_test)
y_cudf = y_train.values
y_cudf = y_cudf[:, 0]
y_cudf = cudf.Series(y_cudf)
cu_lasso.fit(X_cudf, y_cudf)
cu_predict = cu_lasso.predict(X_cudf_test)
elif X_type == 'ndarray':
cu_lasso.fit(X_train, y_train)
cu_predict = cu_lasso.predict(X_test)
if nrows < 500000:
sk_lasso = Lasso(alpha=np.array([alpha]),
fit_intercept=True,
normalize=False,
max_iter=1000,
selection=algorithm,
tol=1e-10)
sk_lasso.fit(X_train, y_train)
sk_predict = sk_lasso.predict(X_test)
assert array_equal(sk_predict, cu_predict, 1e-1, with_sign=True)
X_train_np = X_train.toarray()
else:
X_train_np = X_train
if args.densify_all:
X_train = X_train_np
if args.test == 'ridge':
sk = Ridge(fit_intercept=False,
alpha=regularizer,
max_iter=1000000,
tol=1e-06)
cu = cuRidge(fit_intercept=False, alpha=regularizer, solver='eig')
elif args.test == 'lasso':
sk = Lasso(fit_intercept=False, alpha=regularizer / X_train.shape[0])
cu = cuLasso(fit_intercept=False, alpha=regularizer / X_train.shape[0])
elif args.test == 'logistic':
sk = Logistic(fit_intercept=False,
C=regularizer,
dual=True,
solver='liblinear')
cu = cuLogistic(fit_intercept=False,
C=regularizer * X_train.shape[0],
max_iter=100000,
tol=1e-8)
else:
raise ("Invalid test")
if args.densify_sk:
X_train_sk = X_train_np
else:
