def test_normalizer_l1():
rng = np.random.RandomState(0)
X_dense = rng.randn(4, 5)
X_sparse_unpruned = sparse.csr_matrix(X_dense)
# set the row number 3 to zero
X_dense[3, :] = 0.0
# set the row number 3 to zero without pruning (can happen in real life)
indptr_3 = X_sparse_unpruned.indptr[3]
indptr_4 = X_sparse_unpruned.indptr[4]
X_sparse_unpruned.data[indptr_3:indptr_4] = 0.0
# build the pruned variant using the regular constructor
X_sparse_pruned = sparse.csr_matrix(X_dense)
# check inputs that support the no-copy optim
for X in (X_dense, X_sparse_pruned, X_sparse_unpruned):
normalizer = Normalizer(norm='l1', copy=True)
X_norm = normalizer.transform(X)
assert_true(X_norm is not X)
X_norm1 = toarray(X_norm)
normalizer = Normalizer(norm='l1', copy=False)
X_norm = normalizer.transform(X)
assert_true(X_norm is X)
X_norm2 = toarray(X_norm)
for X_norm in (X_norm1, X_norm2):
row_sums = np.abs(X_norm).sum(axis=1)
for i in range(3):
assert_almost_equal(row_sums[i], 1.0)
assert_almost_equal(row_sums[3], 0.0)
# check input for which copy=False won't prevent a copy
for init in (sparse.coo_matrix, sparse.csc_matrix, sparse.lil_matrix):
X = init(X_dense)
X_norm = normalizer = Normalizer(norm='l2', copy=False).transform(X)
assert_true(X_norm is not X)
assert_true(isinstance(X_norm, sparse.csr_matrix))
X_norm = toarray(X_norm)
for i in range(3):
assert_almost_equal(row_sums[i], 1.0)
assert_almost_equal(la.norm(X_norm[3]), 0.0)
def test_normalizer_l1():
rng = np.random.RandomState(0)
X_dense = rng.randn(4, 5)
X_sparse_unpruned = sparse.csr_matrix(X_dense)
# set the row number 3 to zero
X_dense[3, :] = 0.0
# set the row number 3 to zero without pruning (can happen in real life)
indptr_3 = X_sparse_unpruned.indptr[3]
indptr_4 = X_sparse_unpruned.indptr[4]
X_sparse_unpruned.data[indptr_3:indptr_4] = 0.0
# build the pruned variant using the regular constructor
X_sparse_pruned = sparse.csr_matrix(X_dense)
# check inputs that support the no-copy optim
for X in (X_dense, X_sparse_pruned, X_sparse_unpruned):
normalizer = Normalizer(norm='l1', copy=True)
X_norm = normalizer.transform(X)
assert_true(X_norm is not X)
X_norm1 = toarray(X_norm)
normalizer = Normalizer(norm='l1', copy=False)
X_norm = normalizer.transform(X)
assert_true(X_norm is X)
X_norm2 = toarray(X_norm)
for X_norm in (X_norm1, X_norm2):
row_sums = np.abs(X_norm).sum(axis=1)
for i in range(3):
assert_almost_equal(row_sums[i], 1.0)
assert_almost_equal(row_sums[3], 0.0)
# check input for which copy=False won't prevent a copy
for init in (sparse.coo_matrix, sparse.csc_matrix, sparse.lil_matrix):
X = init(X_dense)
X_norm = normalizer = Normalizer(norm='l2', copy=False).transform(X)
assert_true(X_norm is not X)
assert_true(isinstance(X_norm, sparse.csr_matrix))
X_norm = toarray(X_norm)
for i in range(3):
assert_almost_equal(row_sums[i], 1.0)
assert_almost_equal(la.norm(X_norm[3]), 0.0)
class NormalizerImpl():
def __init__(self, norm='l2', copy=True):
self._hyperparams = {'norm': norm, 'copy': copy}
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 transform(self, X):
return self._wrapped_model.transform(X)
class DFNormalizer(TransformerMixin):
# Row wise transformer? - Can be removed if so
def __init__(self, norm='l2', copy=True):
self.norm = norm
self.copy = copy
self.ss_ = None
def fit(self, X, y=None):
return self
def transform(self, X):
# assumes X is a DataFrame
self.ss_ = Normalizer()
Xss = self.ss_.transform(X)
Xscaled = pd.DataFrame(Xss, index=X.index, columns=X.columns)
return Xscaled
class CreateNormalizer(CreateModel):
def fit(self, data, args):
self.model = Normalizer(norm="l2")
with Timer() as t:
self.model.fit(data.X_train, data.y_train)
return t.interval
def test(self, data):
assert self.model is not None
return self.model.transform(data.X_test)
def predict(self, data):
with Timer() as t:
self.predictions = self.test(data)
data.learning_task = LearningTask.REGRESSION
return t.interval