explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-07-11 16:52:21 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Make .pxd file for huffman codec

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-13 13:54:51 +02:00
parent 0628e0e2a8
commit 77385d5580
2 changed files with 23 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
spacy/serialize.pxd Normal file
View File

@ -0,0 +1,23 @@
from libcpp.vector cimport vector
from libc.stdint cimport uint32_t
from libc.stdint cimport int64_t
from libc.stdint cimport int32_t
from libc.stdint cimport uint64_t
cdef struct Node:
float prob
int32_t left
int32_t right
cdef struct Code:
uint64_t bits
char length
cdef class HuffmanCodec:
cdef vector[Node] nodes
cdef vector[Code] codes
cdef uint32_t eol

14
spacy/serialize.pyx
View File

@ -19,17 +19,6 @@ cimport cython
# combo. ? bits per word. 40 * 80 * 40 * 12 = 1.5m symbol vocab # combo. ? bits per word. 40 * 80 * 40 * 12 = 1.5m symbol vocab
cdef struct Node:
float prob
int32_t left
int32_t right
cdef struct Code:
uint64_t bits
char length
# Note that we're setting the most significant bits here first, when in practice # Note that we're setting the most significant bits here first, when in practice
# we're actually wanting the last bit to be most significant (for Huffman coding, # we're actually wanting the last bit to be most significant (for Huffman coding,
# anyway). # anyway).
@ -90,9 +79,6 @@ cdef class HuffmanCodec:
eol (uint32_t): The index of the weight of the EOL symbol. eol (uint32_t): The index of the weight of the EOL symbol.
""" """
cdef vector[Node] nodes
cdef vector[Code] codes
cdef uint32_t eol
def __init__(self, float[:] probs, uint32_t eol): def __init__(self, float[:] probs, uint32_t eol):
self.eol = eol self.eol = eol
self.codes.resize(len(probs)) self.codes.resize(len(probs))