Python scipy.sparse 模块,data() 实例源码

我们从Python开源项目中,提取了以下15个代码示例,用于说明如何使用scipy.sparse.data()

项目:paragraph2vec    作者:thunlp    | 项目源码 | 文件源码
def chunkize_serial(iterable, chunksize, as_numpy=False):
    """
    Return elements from the iterable in `chunksize`-ed lists. The last returned
    element may be smaller (if length of collection is not divisible by `chunksize`).

    >>> print(list(grouper(range(10), 3)))
    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]

    """
    import numpy
    it = iter(iterable)
    while True:
        if as_numpy:
            # convert each document to a 2d numpy array (~6x faster when transmitting
            # chunk data over the wire, in Pyro)
            wrapped_chunk = [[numpy.array(doc) for doc in itertools.islice(it, int(chunksize))]]
        else:
            wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
        if not wrapped_chunk[0]:
            break
        # memory opt: wrap the chunk and then pop(), to avoid leaving behind a dangling reference
        yield wrapped_chunk.pop()
项目:topical_word_embeddings    作者:thunlp    | 项目源码 | 文件源码
def chunkize_serial(iterable, chunksize, as_numpy=False):
    """
    Return elements from the iterable in `chunksize`-ed lists. The last returned
    element may be smaller (if length of collection is not divisible by `chunksize`).

    >>> print(list(grouper(range(10), 3)))
    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]

    """
    import numpy
    it = iter(iterable)
    while True:
        if as_numpy:
            # convert each document to a 2d numpy array (~6x faster when transmitting
            # chunk data over the wire, in Pyro)
            wrapped_chunk = [[numpy.array(doc) for doc in itertools.islice(it, int(chunksize))]]
        else:
            wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
        if not wrapped_chunk[0]:
            break
        # memory opt: wrap the chunk and then pop(), to avoid leaving behind a dangling reference
        yield wrapped_chunk.pop()
项目:topical_word_embeddings    作者:thunlp    | 项目源码 | 文件源码
def chunkize_serial(iterable, chunksize, as_numpy=False):
    """
    Return elements from the iterable in `chunksize`-ed lists. The last returned
    element may be smaller (if length of collection is not divisible by `chunksize`).

    >>> print(list(grouper(range(10), 3)))
    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]

    """
    import numpy
    it = iter(iterable)
    while True:
        if as_numpy:
            # convert each document to a 2d numpy array (~6x faster when transmitting
            # chunk data over the wire, in Pyro)
            wrapped_chunk = [[numpy.array(doc) for doc in itertools.islice(it, int(chunksize))]]
        else:
            wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
        if not wrapped_chunk[0]:
            break
        # memory opt: wrap the chunk and then pop(), to avoid leaving behind a dangling reference
        yield wrapped_chunk.pop()
项目:nonce2vec    作者:minimalparts    | 项目源码 | 文件源码
def chunkize_serial(iterable, chunksize, as_numpy=False):
    """
    Return elements from the iterable in `chunksize`-ed lists. The last returned
    element may be smaller (if length of collection is not divisible by `chunksize`).

    >>> print(list(grouper(range(10), 3)))
    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]

    """
    it = iter(iterable)
    while True:
        if as_numpy:
            # convert each document to a 2d numpy array (~6x faster when transmitting
            # chunk data over the wire, in Pyro)
            wrapped_chunk = [[np.array(doc) for doc in itertools.islice(it, int(chunksize))]]
        else:
            wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
        if not wrapped_chunk[0]:
            break
        # memory opt: wrap the chunk and then pop(), to avoid leaving behind a dangling reference
        yield wrapped_chunk.pop()
项目:ohmnet    作者:marinkaz    | 项目源码 | 文件源码
def chunkize_serial(iterable, chunksize, as_numpy=False):
    """
    Return elements from the iterable in `chunksize`-ed lists. The last returned
    element may be smaller (if length of collection is not divisible by `chunksize`).

    >>> print(list(grouper(range(10), 3)))
    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]

    """
    import numpy
    it = iter(iterable)
    while True:
        if as_numpy:
            # convert each document to a 2d numpy array (~6x faster when transmitting
            # chunk data over the wire, in Pyro)
            wrapped_chunk = [[numpy.array(doc) for doc in itertools.islice(it, int(chunksize))]]
        else:
            wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
        if not wrapped_chunk[0]:
            break
        # memory opt: wrap the chunk and then pop(), to avoid leaving behind a dangling reference
        yield wrapped_chunk.pop()
项目:doc2vec    作者:stanlee5    | 项目源码 | 文件源码
def chunkize_serial(iterable, chunksize, as_numpy=False):
    """
    Return elements from the iterable in `chunksize`-ed lists. The last returned
    element may be smaller (if length of collection is not divisible by `chunksize`).

    >>> print(list(grouper(range(10), 3)))
    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]

    """
    import numpy
    it = iter(iterable)
    while True:
        if as_numpy:
            # convert each document to a 2d numpy array (~6x faster when transmitting
            # chunk data over the wire, in Pyro)
            wrapped_chunk = [[numpy.array(doc) for doc in itertools.islice(it, int(chunksize))]]
        else:
            wrapped_chunk = [list(itertools.islice(it, int(chunksize)))]
        if not wrapped_chunk[0]:
            break
        # memory opt: wrap the chunk and then pop(), to avoid leaving behind a dangling reference
        yield wrapped_chunk.pop()
项目:paragraph2vec    作者:thunlp    | 项目源码 | 文件源码
def load(cls, fname, mmap=None):
        """
        Load a previously saved object from file (also see `save`).

        If the object was saved with large arrays stored separately, you can load
        these arrays via mmap (shared memory) using `mmap='r'`. Default: don't use
        mmap, load large arrays as normal objects.

        """
        logger.info("loading %s object from %s" % (cls.__name__, fname))
        subname = lambda suffix: fname + '.' + suffix + '.npy'
        obj = unpickle(fname)
        for attrib in getattr(obj, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            setattr(obj, attrib, numpy.load(subname(attrib), mmap_mode=mmap))
        for attrib in getattr(obj, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            sparse = unpickle(subname(attrib))
            sparse.data = numpy.load(subname(attrib) + '.data.npy', mmap_mode=mmap)
            sparse.indptr = numpy.load(subname(attrib) + '.indptr.npy', mmap_mode=mmap)
            sparse.indices = numpy.load(subname(attrib) + '.indices.npy', mmap_mode=mmap)
            setattr(obj, attrib, sparse)
        for attrib in getattr(obj, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(obj, attrib, None)
        return obj
项目:topical_word_embeddings    作者:thunlp    | 项目源码 | 文件源码
def load(cls, fname, mmap=None):
        """
        Load a previously saved object from file (also see `save`).

        If the object was saved with large arrays stored separately, you can load
        these arrays via mmap (shared memory) using `mmap='r'`. Default: don't use
        mmap, load large arrays as normal objects.

        """
        logger.info("loading %s object from %s" % (cls.__name__, fname))
        subname = lambda suffix: fname + '.' + suffix + '.npy'
        obj = unpickle(fname)
        for attrib in getattr(obj, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            setattr(obj, attrib, numpy.load(subname(attrib), mmap_mode=mmap))
        for attrib in getattr(obj, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            sparse = unpickle(subname(attrib))
            sparse.data = numpy.load(subname(attrib) + '.data.npy', mmap_mode=mmap)
            sparse.indptr = numpy.load(subname(attrib) + '.indptr.npy', mmap_mode=mmap)
            sparse.indices = numpy.load(subname(attrib) + '.indices.npy', mmap_mode=mmap)
            setattr(obj, attrib, sparse)
        for attrib in getattr(obj, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(obj, attrib, None)
        return obj
项目:topical_word_embeddings    作者:thunlp    | 项目源码 | 文件源码
def load(cls, fname, mmap=None):
        """
        Load a previously saved object from file (also see `save`).

        If the object was saved with large arrays stored separately, you can load
        these arrays via mmap (shared memory) using `mmap='r'`. Default: don't use
        mmap, load large arrays as normal objects.

        """
        logger.info("loading %s object from %s" % (cls.__name__, fname))
        subname = lambda suffix: fname + '.' + suffix + '.npy'
        obj = unpickle(fname)
        for attrib in getattr(obj, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            setattr(obj, attrib, numpy.load(subname(attrib), mmap_mode=mmap))
        for attrib in getattr(obj, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            sparse = unpickle(subname(attrib))
            sparse.data = numpy.load(subname(attrib) + '.data.npy', mmap_mode=mmap)
            sparse.indptr = numpy.load(subname(attrib) + '.indptr.npy', mmap_mode=mmap)
            sparse.indices = numpy.load(subname(attrib) + '.indices.npy', mmap_mode=mmap)
            setattr(obj, attrib, sparse)
        for attrib in getattr(obj, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(obj, attrib, None)
        return obj
项目:topical_word_embeddings    作者:thunlp    | 项目源码 | 文件源码
def load(cls, fname, mmap=None):
        """
        Load a previously saved object from file (also see `save`).

        If the object was saved with large arrays stored separately, you can load
        these arrays via mmap (shared memory) using `mmap='r'`. Default: don't use
        mmap, load large arrays as normal objects.

        """
        logger.info("loading %s object from %s" % (cls.__name__, fname))
        subname = lambda suffix: fname + '.' + suffix + '.npy'
        obj = unpickle(fname)
        for attrib in getattr(obj, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            setattr(obj, attrib, numpy.load(subname(attrib), mmap_mode=mmap))
        for attrib in getattr(obj, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            sparse = unpickle(subname(attrib))
            sparse.data = numpy.load(subname(attrib) + '.data.npy', mmap_mode=mmap)
            sparse.indptr = numpy.load(subname(attrib) + '.indptr.npy', mmap_mode=mmap)
            sparse.indices = numpy.load(subname(attrib) + '.indices.npy', mmap_mode=mmap)
            setattr(obj, attrib, sparse)
        for attrib in getattr(obj, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(obj, attrib, None)
        return obj
项目:nonce2vec    作者:minimalparts    | 项目源码 | 文件源码
def mock_data_row(dim=1000, prob_nnz=0.5, lam=1.0):
    """
    Create a random gensim sparse vector. Each coordinate is nonzero with
    probability `prob_nnz`, each non-zero coordinate value is drawn from
    a Poisson distribution with parameter lambda equal to `lam`.

    """
    nnz = np.random.uniform(size=(dim,))
    data = [(i, float(np.random.poisson(lam=lam) + 1.0))
            for i in xrange(dim) if nnz[i] < prob_nnz]
    return data
项目:nonce2vec    作者:minimalparts    | 项目源码 | 文件源码
def mock_data(n_items=1000, dim=1000, prob_nnz=0.5, lam=1.0):
    """
    Create a random gensim-style corpus, as a list of lists of (int, float) tuples,
    to be used as a mock corpus.

    """
    data = [mock_data_row(dim=dim, prob_nnz=prob_nnz, lam=lam)
            for _ in xrange(n_items)]
    return data
项目:doc2vec    作者:stanlee5    | 项目源码 | 文件源码
def load(cls, fname, mmap=None):
        """
        Load a previously saved object from file (also see `save`).

        If the object was saved with large arrays stored separately, you can load
        these arrays via mmap (shared memory) using `mmap='r'`. Default: don't use
        mmap, load large arrays as normal objects.

        """
        logger.info("loading %s object from %s" % (cls.__name__, fname))
        subname = lambda suffix: fname + '.' + suffix + '.npy'
        obj = unpickle(fname)
        for attrib in getattr(obj, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            setattr(obj, attrib, numpy.load(subname(attrib), mmap_mode=mmap))
        for attrib in getattr(obj, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (attrib, subname(attrib), mmap))
            sparse = unpickle(subname(attrib))
            sparse.data = numpy.load(subname(attrib) + '.data.npy', mmap_mode=mmap)
            sparse.indptr = numpy.load(subname(attrib) + '.indptr.npy', mmap_mode=mmap)
            sparse.indices = numpy.load(subname(attrib) + '.indices.npy', mmap_mode=mmap)
            setattr(obj, attrib, sparse)
        for attrib in getattr(obj, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(obj, attrib, None)
        return obj
项目:nonce2vec    作者:minimalparts    | 项目源码 | 文件源码
def _load_specials(self, fname, mmap, compress, subname):
        """
        Loads any attributes that were stored specially, and gives the same
        opportunity to recursively included SaveLoad instances.

        """
        mmap_error = lambda x, y: IOError(
            'Cannot mmap compressed object %s in file %s. ' % (x, y) +
            'Use `load(fname, mmap=None)` or uncompress files manually.')

        for attrib in getattr(self, '__recursive_saveloads', []):
            cfname = '.'.join((fname, attrib))
            logger.info("loading %s recursively from %s.* with mmap=%s" % (
                attrib, cfname, mmap))
            getattr(self, attrib)._load_specials(cfname, mmap, compress, subname)

        for attrib in getattr(self, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (
                attrib, subname(fname, attrib), mmap))

            if compress:
                if mmap:
                    raise mmap_error(attrib, subname(fname, attrib))

                val = np.load(subname(fname, attrib))['val']
            else:
                val = np.load(subname(fname, attrib), mmap_mode=mmap)

            setattr(self, attrib, val)

        for attrib in getattr(self, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (
                attrib, subname(fname, attrib), mmap))
            sparse = unpickle(subname(fname, attrib))
            if compress:
                if mmap:
                    raise mmap_error(attrib, subname(fname, attrib))

                with np.load(subname(fname, attrib, 'sparse')) as f:
                    sparse.data = f['data']
                    sparse.indptr = f['indptr']
                    sparse.indices = f['indices']
            else:
                sparse.data = np.load(subname(fname, attrib, 'data'), mmap_mode=mmap)
                sparse.indptr = np.load(subname(fname, attrib, 'indptr'), mmap_mode=mmap)
                sparse.indices = np.load(subname(fname, attrib, 'indices'), mmap_mode=mmap)

            setattr(self, attrib, sparse)

        for attrib in getattr(self, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(self, attrib, None)
项目:ohmnet    作者:marinkaz    | 项目源码 | 文件源码
def _load_specials(self, fname, mmap, compress, subname):
        """
        Loads any attributes that were stored specially, and gives the same
        opportunity to recursively included SaveLoad instances.

        """

        mmap_error = lambda x, y: IOError(
            'Cannot mmap compressed object %s in file %s. ' % (x, y) +
            'Use `load(fname, mmap=None)` or uncompress files manually.')

        for attrib in getattr(self, '__recursive_saveloads', []):
            cfname = '.'.join((fname, attrib))
            logger.info("loading %s recursively from %s.* with mmap=%s" % (
                attrib, cfname, mmap))
            getattr(self, attrib)._load_specials(cfname, mmap, compress, subname)

        for attrib in getattr(self, '__numpys', []):
            logger.info("loading %s from %s with mmap=%s" % (
                attrib, subname(fname, attrib), mmap))

            if compress:
                if mmap:
                    raise mmap_error(attrib, subname(fname, attrib))

                val = numpy.load(subname(fname, attrib))['val']
            else:
                val = numpy.load(subname(fname, attrib), mmap_mode=mmap)

            setattr(self, attrib, val)

        for attrib in getattr(self, '__scipys', []):
            logger.info("loading %s from %s with mmap=%s" % (
                attrib, subname(fname, attrib), mmap))
            sparse = unpickle(subname(fname, attrib))
            if compress:
                if mmap:
                    raise mmap_error(attrib, subname(fname, attrib))

                with numpy.load(subname(fname, attrib, 'sparse')) as f:
                    sparse.data = f['data']
                    sparse.indptr = f['indptr']
                    sparse.indices = f['indices']
            else:
                sparse.data = numpy.load(subname(fname, attrib, 'data'), mmap_mode=mmap)
                sparse.indptr = numpy.load(subname(fname, attrib, 'indptr'), mmap_mode=mmap)
                sparse.indices = numpy.load(subname(fname, attrib, 'indices'), mmap_mode=mmap)

            setattr(self, attrib, sparse)

        for attrib in getattr(self, '__ignoreds', []):
            logger.info("setting ignored attribute %s to None" % (attrib))
            setattr(self, attrib, None)