8000 [MRG] Pass the dtype consistency & accuracy tests for ridge by ncordier · Pull Request #4 · massich/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[MRG] Pass the dtype consistency & accuracy tests for ridge #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 10 commits into from
Jun 8, 2017
Merged

[MRG] Pass the dtype consistency & accuracy tests for ridge #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
3833817
Allows 32-bit dtype consistency if solver is svd
ncordier Jun 8, 2017
28a2cff
Pass the consistency test for ridge with 32-bit dtype input
ncordier Jun 8, 2017
87a4a91
Typo fixed
ncordier Jun 8, 2017
1f2a9c0
Add sparse_cg to the list of solvers to test for dtype consistency
ncordier Jun 8, 2017
daf695e
Allows 32-bit dtype consistency if solver is sparse_cg
ncordier Jun 8, 2017
6c924dc
Add cholesky to the list of solvers to test for dtype consistency
ncordier Jun 8, 2017
2b93657
Add lsqr to the list of solvers to test for dtype consistency
ncordier Jun 8, 2017
6004808
Allows 32-bit dtype consistency if solver is lsqr
ncordier Jun 8, 2017
8899064
Make sure dtype consistency is ensured if solver is cholesky_kernel (…
ncordier Jun 8, 2017
3b10043
Updated list of solvers which have been tested
ncordier Jun 8, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions sklearn/linear_model/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ def _preprocess_data(X, y, fit_intercept, normalize=False, copy=True,
if sp.issparse(X):
X_offset, X_var = mean_variance_axis(X, axis=0)
if not return_mean:
X_offset = np.zeros(X.shape[1])
X_offset = np.zeros(X.shape[1], dtype=X.dtype)

if normalize:

Expand All @@ -186,7 +186,7 @@ def _preprocess_data(X, y, fit_intercept, normalize=False, copy=True,
X_scale[X_scale == 0] = 1
inplace_column_scale(X, 1. / X_scale)
else:
X_scale = np.ones(X.shape[1])
X_scale = np.ones(X.shape[1], dtype=X.dtype)

else:
X_offset = np.average(X, axis=0, weights=sample_weight)
Expand All @@ -195,12 +195,12 @@ def _preprocess_data(X, y, fit_intercept, normalize=False, copy=True,
X, X_scale = f_normalize(X, axis=0, copy=False,
return_norm=True)
else:
X_scale = np.ones(X.shape[1])
X_scale = np.ones(X.shape[1], dtype=X.dtype)
y_offset = np.average(y, axis=0, weights=sample_weight)
y = y - y_offset
else:
X_offset = np.zeros(X.shape[1])
X_scale = np.ones(X.shape[1])
X_offset = np.zeros(X.shape[1], dtype=X.dtype)
X_scale = np.ones(X.shape[1], dtype=X.dtype)
y_offset = 0. if y.ndim == 1 else np.zeros(y.shape[1], dtype=X.dtype)

return X, y, X_offset, y_offset, X_scale
Expand Down
20 changes: 13 additions & 7 deletions sklearn/linear_model/ridge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@
def _solve_sparse_cg(X, y, alpha, max_iter=None, tol=1e-3, verbose=0):
n_samples, n_features = X.shape
X1 = sp_linalg.aslinearoperator(X)
coefs = np.empty((y.shape[1], n_featu 10000 res))
coefs = np.empty((y.shape[1], n_features), dtype=X.dtype)

if n_features > n_samples:
def create_mv(curr_alpha):
Expand Down Expand Up @@ -80,7 +80,7 @@ def _mv(x):

def _solve_lsqr(X, y, alpha, max_iter=None, tol=1e-3):
n_samples, n_features = X.shape
coefs = np.empty((y.shape[1], n_features))
coefs = np.empty((y.shape[1], n_features), dtype=X.dtype)
n_iter = np.empty(y.shape[1], dtype=np.int32)

# According to the lsqr documentation, alpha = damp^2.
Expand Down Expand Up @@ -111,7 +111,7 @@ def _solve_cholesky(X, y, alpha):
return linalg.solve(A, Xy, sym_pos=True,
overwrite_a=True).T
else:
coefs = np.empty([n_targets, n_features])
coefs = np.empty([n_targets, n_features], dtype=X.dtype)
for coef, target, current_alpha in zip(coefs, Xy.T, alpha):
A.flat[::n_features + 1] += current_alpha
coef[:] = linalg.solve(A, target, sym_pos=True,
Expand Down Expand Up @@ -186,7 +186,7 @@ def _solve_svd(X, y, alpha):
idx = s > 1e-15 # same default value as scipy.linalg.pinv
s_nnz = s[idx][:, np.newaxis]
UTy = np.dot(U.T, y)
d = np.zeros((s.size, alpha.size))
d = np.zeros((s.size, alpha.size), dtype=X.dtype)
d[idx] = s_nnz / (s_nnz ** 2 + alpha)
d_UT_y = d * UTy
return np.dot(Vt.T, d_UT_y).T
Expand Down Expand Up @@ -327,7 +327,7 @@ def ridge_regression(X, y, alpha, sample_weight=None, solver='auto',
y = check_array(y, dtype=np.float64, ensure_2d=False, order='F')
else:
X = check_array(X, accept_sparse=['csr', 'csc', 'coo'],
dtype=np.float64)
dtype='numeric')
y = check_array(y, dtype='numeric', ensure_2d=False)
check_consistent_length(X, y)

Expand Down Expand Up @@ -371,7 +371,7 @@ def ridge_regression(X, y, alpha, sample_weight=None, solver='auto',
X, y = _rescale_data(X, y, sample_weight)

# There should be either 1 or n_targets penalties
alpha = np.asarray(alpha).ravel()
alpha = np.asarray(alpha, dtype=X.dtype).ravel()
if alpha.size not in [1, n_targets]:
raise ValueError("Number of targets and number of penalties "
"do not correspond: %d != %d"
Expand Down Expand Up @@ -469,7 +469,13 @@ def __init__(self, alpha=1.0, fit_intercept=True, normalize=False,
self.random_state = random_state

def fit(self, X, y, sample_weight=None):
X, y = check_X_y(X, y, ['csr', 'csc', 'coo'], dtype=np.float64,

if self.solver in ['svd', 'sparse_cg', 'cholesky', 'lsqr']:
_dtype = [np.float64, np.float32]
else:
_dtype = np.float64

X, y = check_X_y(X, y, ['csr', 'csc', 'coo'], dtype=_dtype,
multi_output=True, y_numeric=True)

if ((sample_weight is not None) and
Expand Down
4 changes: 2 additions & 2 deletions sklearn/linear_model/tests/test_ridge.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -801,7 +801,7 @@ def test_dtype_match():
y_32 = y_64.astype(np.float32)

# solvers = ("svd", "sparse_cg", "cholesky", "lsqr", "sag")
solvers = ["svd"]
solvers = ["svd", "sparse_cg", "cholesky", "lsqr"]
for solver in solvers:

# Check type consistency 32bits
Expand All @@ -815,4 +815,4 @@ def test_dtype_match():
assert_equal(ridge_64.coef_.dtype, X_64.dtype)

# Check accuracy consistency
assert_almost_equal(ridge_32.coefs_, ridge_64.coefs_.astype(np.float32))
assert_almost_equal(ridge_32.coef_, ridge_64.coef_.astype(np.float32))
0