def test_random_projection_fit_transform(datatype, method):
if has_scipy():
from scipy.spatial.distance import pdist
else:
pytest.skip('Skipping test_random_projection_fit_transform because ' +
'Scipy is missing')
eps = 0.2
# dataset generation
data, target = make_blobs(n_samples=800, centers=400, n_features=3000)
# conversion to input_type
data = data.astype(datatype)
target = target.astype(datatype)
# creation of model
if method == 'gaussian':
model = GaussianRandomProjection(eps=eps)
else:
model = SparseRandomProjection(eps=eps)
# fitting the model
model.fit(data)
# applying transformation
transformed_data = model.transform(data)
original_pdist = pdist(data)
embedded_pdist = pdist(transformed_data)
# check JL lemma
assert (np.all(((1.0 - eps) * original_pdist) <= embedded_pdist)
and np.all(embedded_pdist <= ((1.0 + eps) * original_pdist)))
def test_random_projection_fit_transform_default(datatype, method):
eps = 0.8
# dataset generation
data, target = make_blobs(n_samples=30, centers=4, n_features=5000)
# conversion to input_type
data = data.astype(datatype)
target = target.astype(datatype)
# creation of model
if method == 'gaussian':
model = GaussianRandomProjection()
else:
model = SparseRandomProjection()
# fitting the model
model.fit(data)
transformed_data = model.transform(data)
original_pdist = pdist(data)
embedded_pdist = pdist(transformed_data)
# check JL lemma
assert (np.all(((1.0 - eps) * original_pdist) <= embedded_pdist)
and np.all(embedded_pdist <= ((1.0 + eps) * original_pdist)))
def test_random_projection_fit(datatype, method):
# dataset generation
data, target = make_blobs(n_samples=800, centers=400, n_features=3000)
# conversion to input_type
data = data.astype(datatype)
target = target.astype(datatype)
# creation of model
if method == 'gaussian':
model = GaussianRandomProjection(eps=0.2)
else:
model = SparseRandomProjection(eps=0.2)
# fitting the model
model.fit(data)
assert True # Did not crash
def test_random_projection_fit_transform(datatype, input_type, method):
eps = 0.2
# dataset generation
data, target = make_blobs(n_samples=800, centers=400, n_features=3000)
# conversion to input_type
data = data.astype(datatype)
target = target.astype(datatype)
# creation of model
if method == 'gaussian':
model = GaussianRandomProjection(eps=eps)
else:
model = SparseRandomProjection(eps=eps)
# fitting the model
if input_type == 'dataframe':
gdf = cudf.DataFrame()
for i in range(data.shape[1]):
gdf[str(i)] = np.asarray(data[:, i], dtype=datatype)
model.fit(gdf)
else:
model.fit(data)
# applying transformation
if input_type == 'dataframe':
transformed_data = model.transform(gdf).as_matrix()
else:
transformed_data = model.transform(data)
original_pdist = pdist(data)
embedded_pdist = pdist(transformed_data)
# check JL lemma
assert (np.all(((1.0 - eps) * original_pdist) <= embedded_pdist)
and np.all(embedded_pdist <= ((1.0 + eps) * original_pdist)))
def test_random_projection_fit(datatype, input_type, method):
# dataset generation
data, target = make_blobs(n_samples=800, centers=400, n_features=3000)
# conversion to input_type
data = data.astype(datatype)
target = target.astype(datatype)
# creation of model
if method == 'gaussian':
model = GaussianRandomProjection(eps=0.2)
else:
model = SparseRandomProjection(eps=0.2)
# fitting the model
if input_type == 'dataframe':
gdf = cudf.DataFrame()
for i in range(data.shape[1]):
gdf[str(i)] = np.asarray(data[:, i], dtype=datatype)
model.fit(gdf)
else:
model.fit(data)
assert True # Did not crash