8000 MAINT remove -Wsign-compare when compiling `sklearn.utils.sparsefuncs_fast` by Vincent-Maladiere · Pull Request #25244 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

MAINT remove -Wsign-compare when compiling sklearn.utils.sparsefuncs_fast #25244

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 8 commits into from
Jan 5, 2023
Merged

MAINT remove -Wsign-compare when compiling sklearn.utils.sparsefuncs_fast #25244

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
a19f0e2
remove warnings
Vincent-Maladiere Dec 28, 2022
b059f8e
reverse a spurious change
Vincent-Maladiere Dec 28, 2022
ac82aa3
reverse a spurious change
Vincent-Maladiere Dec 28, 2022
e231a92
Merge branch 'main' into remove_wsign_compare
Vincent-Maladiere Dec 28, 2022
36fc10d
apply suggestions
Vincent-Maladiere Dec 31, 2022
30473d6
Merge branch 'main' into remove_wsign_compare
Vincent-Maladiere Dec 31, 2022
895be87
Merge branch 'main' into remove_wsign_compare
Vincent-Maladiere Jan 3, 2023
c4658d3
Merge branch 'main' into remove_wsign_compare
Vincent-Maladiere Jan 4, 2023
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
100 changes: 57 additions & 43 deletions sklearn/utils/sparsefuncs_fast.pyx
View file
Open in desktop
8000
Original file line number Diff line number Diff line change
Expand Up @@ -106,9 +106,9 @@ def _csr_mean_variance_axis0(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
# Implement the function here since variables using fused types
# cannot be declared directly and can only be passed as function arguments
cdef:
cnp.npy_intp i
unsigned long long row_ind
integral col_ind
cnp.intp_t row_ind
unsigned long long feature_idx
integral i, col_ind
cnp.float64_t diff
# means[j] contains the mean of feature j
cnp.ndarray[cnp.float64_t, ndim=1] means = np.zeros(n_features)
Expand Down Expand Up @@ -142,8 +142,8 @@ def _csr_mean_variance_axis0(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
# number of non nan elements of X[:, col_ind]
counts[col_ind] -= 1

for i in range(n_features):
means[i] /= sum_weights[i]
for feature_idx in range(n_features):
means[feature_idx] /= sum_weights[feature_idx]

for row_ind in range(len(X_indptr) - 1):
for i in range(X_indptr[row_ind], X_indptr[row_ind + 1]):
Expand All @@ -156,15 +156,22 @@ def _csr_mean_variance_axis0(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
correction[col_ind] += diff * weights[row_ind]
variances[col_ind] += diff * diff * weights[row_ind]

for i in range(n_features):
if counts[i] != counts_nz[i]:
correction[i] -= (sum_weights[i] - sum_weights_nz[i]) * means[i]
correction[i] = correction[i]**2 / sum_weights[i]
if counts[i] != counts_nz[i]:
for feature_idx in range(n_features):
if counts[feature_idx] != counts_nz[feature_idx]:
correction[feature_idx] -= (
sum_weights[feature_idx] - sum_weights_nz[feature_idx]
) * means[feature_idx]
correction[feature_idx] = correction[feature_idx]**2 / sum_weights[feature_idx]
if counts[feature_idx] != counts_nz[feature_idx]:
# only compute it when it's guaranteed to be non-zero to avoid
# catastrophic cancellation.
variances[i] += (sum_weights[i] - sum_weights_nz[i]) * means[i]**2
variances[i] = (variances[i] - correction[i]) / sum_weights[i]
variances[feature_idx] += (
sum_weights[feature_idx] - sum_weights_nz[feature_idx]
) * means[feature_idx]**2
variances[feature_idx] = (
(variances[feature_idx] - correction[feature_idx]) /
sum_weights[feature_idx]
)

if floating is float:
return (np.array(means, dtype=np.float32),
Expand Down Expand Up @@ -228,9 +235,8 @@ def _csc_mean_variance_axis0(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
# Implement the function here since variables using fused types
# cannot be declared directly and can only be passed as function arguments
cdef:
cnp.npy_intp i
unsigned long long col_ind
integral row_ind
integral i, row_ind
unsigned long long feature_idx, col_ind
cnp.float64_t diff
# means[j] contains the mean of feature j
cnp.ndarray[cnp.float64_t, ndim=1] means = np.zeros(n_features)
Expand Down Expand Up @@ -264,8 +270,8 @@ def _csc_mean_variance_axis0(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
# number of non nan elements of X[:, col_ind]
counts[col_ind] -= 1

for i in range(n_features):
means[i] /= sum_weights[i]
for feature_idx in range(n_features):
means[feature_idx] /= sum_weights[feature_idx]

for col_ind in range(n_features):
for i in range(X_indptr[col_ind], X_indptr[col_ind + 1]):
Expand All @@ -278,15 +284,21 @@ def _csc_mean_variance_axis0(cnp.ndarray[floating, ndim=1, mode="c"] X_data,
correction[col_ind] += diff * weights[row_ind]
variances[col_ind] += diff * diff * weights[row_ind]

for i in range(n_features):
if counts[i] != counts_nz[i]:
correction[i] -= (sum_weights[i] - sum_weights_nz[i]) * means[i]
correction[i] = correction[i]**2 / sum_weights[i]
if counts[i] != counts_nz[i]:
for feature_idx in range(n_features):
if counts[feature_idx] != counts_nz[feature_idx]:
correction[feature_idx] -= (
sum_weights[feature_idx] - sum_weights_nz[feature_idx]
) * means[feature_idx]
correction[feature_idx] = correction[feature_idx]**2 / sum_weights[feature_idx]
if counts[feature_idx] != counts_nz[feature_idx]:
# only compute it when it's guaranteed to be non-zero to avoid
# catastrophic cancellation.
variances[i] += (sum_weights[i] - sum_weights_nz[i]) * means[i]**2
variances[i] = (variances[i] - correction[i]) / sum_weights[i]
variances[feature_idx] += (
sum_weights[feature_idx] - sum_weights_nz[feature_idx]
) * means[feature_idx]**2
variances[feature_idx] = (
(variances[feature_idx] - correction[feature_idx])
) / sum_weights[feature_idx]

if floating is float:
return (np.array(means, dtype=np.float32),
Expand Down Expand Up @@ -383,13 +395,12 @@ def _incr_mean_variance_axis0(cnp.ndarray[floating, ndim=1] X_data,
# Implement the function here since variables using fused types
# cannot be declared directly and can only be passed as function arguments
cdef:
cnp.npy_intp i
unsigned long long i

# last = stats until now
# new = the current increment
# updated = the aggregated stats
# when arrays, they are indexed by i per-feature
cdef:
# last = stats until now
# new = the current increment
# updated = the aggregated stats
# when arrays, they are indexed by i per-feature
cnp.ndarray[floating, ndim=1] new_mean
cnp.ndarray[floating, ndim=1] new_var
cnp.ndarray[floating, ndim=1] updated_mean
Expand Down Expand Up @@ -469,15 +480,17 @@ def _inplace_csr_row_normalize_l1(cnp.ndarray[floating, ndim=1] X_data,
shape,
cnp.ndarray[integral, ndim=1] X_indices,
cnp.ndarray[integral, ndim=1] X_indptr):
cdef unsigned long long n_samples = shape[0]
cdef unsigned long long n_features = shape[1]
cdef:
unsigned long long n_samples = shape[0]
unsigned long long n_features = shape[1]

# the column indices for row i are stored in:
# indices[indptr[i]:indices[i+1]]
# and their corresponding values are stored in:
# data[indptr[i]:indptr[i+1]]
cdef cnp.npy_intp i, j
cdef double sum_
# the column indices for row i are stored in:
# indices[indptr[i]:indices[i+1]]
# and their corresponding values are stored in:
# data[indptr[i]:indptr[i+1]]
unsigned long long i
integral j
double sum_

for i in range(n_samples):
sum_ = 0.0
Expand All @@ -503,11 +516,12 @@ def _inplace_csr_row_normalize_l2(cnp.ndarray[floating, ndim=1] X_data,
shape,
cnp.ndarray[integral, ndim=1] X_indices,
cnp.ndarray[integral, ndim=1] X_indptr):
cdef integral n_samples = shape[0]
cdef integral n_features = shape[1]

cdef cnp.npy_intp i, j
cdef double sum_
cdef:
unsigned long long n_samples = shape[0]
unsigned long long n_features = shape[1]
unsigned long long i
integral j
double sum_

for i in range(n_samples):
sum_ = 0.0
Expand Down
0