77 lines
2.5 KiB
Plaintext
77 lines
2.5 KiB
Plaintext
|
{{py:
|
||
|
|
||
|
"""
|
||
|
Dataset abstractions for sequential data access.
|
||
|
|
||
|
Template file for easily generate fused types consistent code using Tempita
|
||
|
(https://github.com/cython/cython/blob/master/Cython/Tempita/_tempita.py).
|
||
|
|
||
|
Generated file: _seq_dataset.pxd
|
||
|
|
||
|
Each class is duplicated for all dtypes (float and double). The keywords
|
||
|
between double braces are substituted in setup.py.
|
||
|
"""
|
||
|
|
||
|
# name_suffix, c_type
|
||
|
dtypes = [('64', 'float64_t'),
|
||
|
('32', 'float32_t')]
|
||
|
|
||
|
}}
|
||
|
"""Dataset abstractions for sequential data access."""
|
||
|
|
||
|
from ._typedefs cimport float32_t, float64_t, intp_t, uint32_t
|
||
|
|
||
|
# SequentialDataset and its two concrete subclasses are (optionally randomized)
|
||
|
# iterators over the rows of a matrix X and corresponding target values y.
|
||
|
|
||
|
{{for name_suffix, c_type in dtypes}}
|
||
|
|
||
|
#------------------------------------------------------------------------------
|
||
|
|
||
|
cdef class SequentialDataset{{name_suffix}}:
|
||
|
cdef int current_index
|
||
|
cdef int[::1] index
|
||
|
cdef int *index_data_ptr
|
||
|
cdef Py_ssize_t n_samples
|
||
|
cdef uint32_t seed
|
||
|
|
||
|
cdef void shuffle(self, uint32_t seed) noexcept nogil
|
||
|
cdef int _get_next_index(self) noexcept nogil
|
||
|
cdef int _get_random_index(self) noexcept nogil
|
||
|
|
||
|
cdef void _sample(self, {{c_type}} **x_data_ptr, int **x_ind_ptr,
|
||
|
int *nnz, {{c_type}} *y, {{c_type}} *sample_weight,
|
||
|
int current_index) noexcept nogil
|
||
|
cdef void next(self, {{c_type}} **x_data_ptr, int **x_ind_ptr,
|
||
|
int *nnz, {{c_type}} *y, {{c_type}} *sample_weight) noexcept nogil
|
||
|
cdef int random(self, {{c_type}} **x_data_ptr, int **x_ind_ptr,
|
||
|
int *nnz, {{c_type}} *y, {{c_type}} *sample_weight) noexcept nogil
|
||
|
|
||
|
|
||
|
cdef class ArrayDataset{{name_suffix}}(SequentialDataset{{name_suffix}}):
|
||
|
cdef const {{c_type}}[:, ::1] X
|
||
|
cdef const {{c_type}}[::1] Y
|
||
|
cdef const {{c_type}}[::1] sample_weights
|
||
|
cdef Py_ssize_t n_features
|
||
|
cdef intp_t X_stride
|
||
|
cdef {{c_type}} *X_data_ptr
|
||
|
cdef {{c_type}} *Y_data_ptr
|
||
|
cdef const int[::1] feature_indices
|
||
|
cdef int *feature_indices_ptr
|
||
|
cdef {{c_type}} *sample_weight_data
|
||
|
|
||
|
|
||
|
cdef class CSRDataset{{name_suffix}}(SequentialDataset{{name_suffix}}):
|
||
|
cdef const {{c_type}}[::1] X_data
|
||
|
cdef const int[::1] X_indptr
|
||
|
cdef const int[::1] X_indices
|
||
|
cdef const {{c_type}}[::1] Y
|
||
|
cdef const {{c_type}}[::1] sample_weights
|
||
|
cdef {{c_type}} *X_data_ptr
|
||
|
cdef int *X_indptr_ptr
|
||
|
cdef int *X_indices_ptr
|
||
|
cdef {{c_type}} *Y_data_ptr
|
||
|
cdef {{c_type}} *sample_weight_data
|
||
|
|
||
|
{{endfor}}
|