def test_pca_fit(datatype, input_type):
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]],
dtype=datatype)
skpca = skPCA(n_components=2)
skpca.fit(X)
cupca = cuPCA(n_components=2)
if input_type == 'dataframe':
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([-1, -2, -3, 1, 2, 3], dtype=datatype)
gdf['1'] = np.asarray([-1, -1, -2, 1, 1, 2], dtype=datatype)
cupca.fit(gdf)
else:
cupca.fit(X)
for attr in [
'singular_values_', 'components_', 'explained_variance_',
'explained_variance_ratio_', 'noise_variance_'
]:
with_sign = False if attr in ['components_'] else True
print(attr)
print(getattr(cupca, attr))
print(getattr(skpca, attr))
cuml_res = (getattr(cupca, attr))
if isinstance(cuml_res, cudf.Series):
cuml_res = cuml_res.to_array()
else:
cuml_res = cuml_res.as_matrix()
skl_res = getattr(skpca, attr)
assert array_equal(cuml_res, skl_res, 1e-3, with_sign=with_sign)
def test_ridge(datatype, X_type, y_type, algorithm):
X = np.array([[2.0, 5.0], [6.0, 9.0], [2.0, 2.0], [2.0, 3.0]],
dtype=datatype)
y = np.dot(X, np.array([5.0, 10.0]).astype(datatype))
pred_data = np.array([[3.0, 5.0], [2.0, 5.0]]).astype(datatype)
skridge = skRidge(fit_intercept=False, normalize=False)
skridge.fit(X, y)
curidge = cuRidge(fit_intercept=False, normalize=False, solver=algorithm)
if X_type == 'dataframe':
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([2, 6, 2, 2], dtype=datatype)
gdf['1'] = np.asarray([5, 9, 2, 3], dtype=datatype)
curidge.fit(gdf, y)
elif X_type == 'ndarray':
curidge.fit(X, y)
sk_predict = skridge.predict(pred_data)
cu_predict = curidge.predict(pred_data).to_array()
assert array_equal(sk_predict, cu_predict, 1e-3, with_sign=True)
def test_ols(datatype, X_type, y_type, algorithm):
X = np.array([[2.0, 5.0], [6.0, 9.0], [2.0, 2.0], [2.0, 3.0]],
dtype=datatype)
y = np.dot(X, np.array([5.0, 10.0]).astype(datatype))
pred_data = np.array([[3.0, 5.0], [2.0, 5.0]]).astype(datatype)
skols = skLinearRegression(fit_intercept=True, normalize=False)
skols.fit(X, y)
cuols = cuLinearRegression(fit_intercept=True,
normalize=False,
algorithm=algorithm)
if X_type == 'dataframe':
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([2, 6, 2, 2], dtype=datatype)
gdf['1'] = np.asarray([5, 9, 2, 3], dtype=datatype)
cuols.fit(gdf, y)
elif X_type == 'ndarray':
cuols.fit(X, y)
sk_predict = skols.predict(pred_data)
cu_predict = cuols.predict(pred_data).to_array()
print(sk_predict)
print(cu_predict)
# print(skols.coef_)
print(cuols.gdf_datatype)
print(y.dtype)
assert array_equal(sk_predict, cu_predict, 1e-3, with_sign=True)
def check_table(table_name):
original_rows = get_table(table_name,
database_settings["original_db_name"])
new_rows = get_table(table_name, database_settings["new_db_name"])
for k in original_rows.keys():
original = original_rows[k]
new = new_rows[k]
if original[k] != new[k] and (not utils.array_equal(original, new)):
print("Change in row {rowid}: was {old}, now {new}".format(
rowid=k, old=original_rows[k], new=new_rows[k]))
def test_tsvd_inverse_transform(datatype, input_type):
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([-1, -2, -3, 1, 2, 3], dtype=datatype)
gdf['1'] = np.asarray([-1, -1, -2, 1, 1, 2], dtype=datatype)
cutsvd = cuTSVD(n_components=1)
if input_type == 'dataframe':
Xcutsvd = cutsvd.fit_transform(gdf)
else:
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]],
dtype=datatype)
Xcutsvd = cutsvd.fit_transform(X)
input_gdf = cutsvd.inverse_transform(Xcutsvd)
assert array_equal(input_gdf, gdf, 0.4, with_sign=True)
def test_pca_inverse_transform(datatype, input_type):
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([-1, -2, -3, 1, 2, 3], dtype=datatype)
gdf['1'] = np.asarray([-1, -1, -2, 1, 1, 2], dtype=datatype)
cupca = cuPCA(n_components=2)
if input_type == 'dataframe':
Xcupca = cupca.fit_transform(gdf)
else:
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]],
dtype=datatype)
Xcupca = cupca.fit_transform(X)
input_gdf = cupca.inverse_transform(Xcupca)
assert array_equal(input_gdf, gdf, 1e-3, with_sign=True)
def test_tsvd_fit_transform(datatype, input_type):
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]],
dtype=datatype)
skpca = skTSVD(n_components=1)
Xsktsvd = skpca.fit_transform(X)
cutsvd = cuTSVD(n_components=1)
if input_type == 'dataframe':
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([-1, -2, -3, 1, 2, 3], dtype=datatype)
gdf['1'] = np.asarray([-1, -1, -2, 1, 1, 2], dtype=datatype)
Xcutsvd = cutsvd.fit_transform(gdf)
else:
Xcutsvd = cutsvd.fit_transform(X)
assert array_equal(Xcutsvd, Xsktsvd, 1e-3, with_sign=True)
def test_tsvd_fit(datatype, input_type):
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]],
dtype=datatype)
sktsvd = skTSVD(n_components=1)
sktsvd.fit(X)
cutsvd = cuTSVD(n_components=1)
if input_type == 'dataframe':
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([-1, -2, -3, 1, 2, 3], dtype=datatype)
gdf['1'] = np.asarray([-1, -1, -2, 1, 1, 2], dtype=datatype)
cutsvd.fit(gdf)
else:
cutsvd.fit(X)
for attr in ['singular_values_', 'components_',
'explained_variance_ratio_']:
with_sign = False if attr in ['components_'] else True
assert array_equal(getattr(cutsvd, attr), getattr(sktsvd, attr),
0.4, with_sign=with_sign)
