比較的メモリを節約する疎行列 Python ストレージ ソリューション

'''
Sparse Matrix
'''
import struct
import numpy as np
import bsddb
from cStringIO import StringIO
  
class DictMatrix():
    def __init__(self, container = {}, dft = 0.0):
        self._data  = container
        self._dft   = dft
        self._nums  = 0
  
    def __setitem__(self, index, value):
        try:
            i, j = index
        except:
            raise IndexError('invalid index')
  
        ik = ('i%d' % i)
        # 为了节省内存，我们把j, value打包成字二进制字符串
        ib = struct.pack('if', j, value)
        jk = ('j%d' % j)
        jb = struct.pack('if', i, value)
  
        try:
            self._data[ik] += ib
        except:
            self._data[ik] = ib
        try:
            self._data[jk] += jb
        except:
            self._data[jk] = jb
        self._nums += 1
  
    def __getitem__(self, index):
        try:
            i, j = index
        except:
            raise IndexError('invalid index')
  
        if (isinstance(i, int)):
            ik = ('i%d' % i)
            if not self._data.has_key(ik): return self._dft
            ret = dict(np.fromstring(self._data[ik], dtype = 'i4,f4'))
            if (isinstance(j, int)): return ret.get(j, self._dft)
  
        if (isinstance(j, int)):
            jk = ('j%d' % j)
            if not self._data.has_key(jk): return self._dft
            ret = dict(np.fromstring(self._data[jk], dtype = 'i4,f4'))
  
        return ret
  
    def __len__(self):
        return self._nums
  
    def __iter__(self):
        pass
  
    '''
    从文件中生成matrix
    考虑到dbm读写的性能不如内存，我们做了一些缓存，每1000W次批量写入一次
    考虑到字符串拼接性能不太好，我们直接用StringIO来做拼接
    '''
    def from_file(self, fp, sep = 't'):
        cnt = 0
        cache = {}
        for l in fp:
            if 10000000 == cnt:
                self._flush(cache)
                cnt = 0
                cache = {}
            i, j, v = [float(i) for i in l.split(sep)]
  
            ik = ('i%d' % i)
            ib = struct.pack('if', j, v)
            jk = ('j%d' % j)
            jb = struct.pack('if', i, v)
  
            try:
                cache[ik].write(ib)
            except:
                cache[ik] = StringIO()
                cache[ik].write(ib)
  
            try:
                cache[jk].write(jb)
            except:
                cache[jk] = StringIO()
                cache[jk].write(jb)
  
            cnt += 1
            self._nums += 1
  
        self._flush(cache)
        return self._nums
  
    def _flush(self, cache):
        for k,v in cache.items():
            v.seek(0)
            s = v.read()
            try:
                self._data[k] += s
            except:
                self._data[k] = s
  
if __name__ == '__main__':
    db = bsddb.btopen(None, cachesize = 268435456)
    data = DictMatrix(db)
    data.from_file(open('/path/to/log.txt', 'r'), ',')

import timeit
timeit.Timer('foo = __main__.data[9527, ...]', 'import __main__').timeit(number = 1000)