Python sparse.tocsr方法代码示例

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def scipy2sparse(vec, eps=1e-9):
    """Convert a scipy.sparse vector into gensim document format (=list of 2-tuples)."""
    vec = vec.tocsr()
    assert vec.shape[0] == 1
    return [(int(pos), float(val)) for pos, val in zip(vec.indices, vec.data) if numpy.abs(val) > eps] 

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def __init__(self, sparse, documents_columns=True):
        if documents_columns:
            self.sparse = sparse.tocsc()
        else:
            self.sparse = sparse.tocsr().T # make sure shape[1]=number of docs (needed in len()) 

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def unitvec(vec):
    """
    Scale a vector to unit length. The only exception is the zero vector, which
    is returned back unchanged.

    Output will be in the same format as input (i.e., gensim vector=>gensim vector,
    or numpy array=>numpy array, scipy.sparse=>scipy.sparse).
    """
    if scipy.sparse.issparse(vec): # convert scipy.sparse to standard numpy array
        vec = vec.tocsr()
        veclen = numpy.sqrt(numpy.sum(vec.data ** 2))
        if veclen > 0.0:
            return vec / veclen
        else:
            return vec

    if isinstance(vec, numpy.ndarray):
        vec = numpy.asarray(vec, dtype=float)
        veclen = blas_nrm2(vec)
        if veclen > 0.0:
            return blas_scal(1.0 / veclen, vec)
        else:
            return vec

    try:
        first = next(iter(vec))     # is there at least one element?
    except:
        return vec

    if isinstance(first, (tuple, list)) and len(first) == 2: # gensim sparse format?
        length = 1.0 * math.sqrt(sum(val ** 2 for _, val in vec))
        assert length > 0.0, "sparse documents must not contain any explicit zero entries"
        if length != 1.0:
            return [(termid, val / length) for termid, val in vec]
        else:
            return list(vec)
    else:
        raise ValueError("unknown input type") 

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def __init__(self, sparse, documents_columns=True):
        if documents_columns:
            self.sparse = sparse.tocsc()
        else:
            self.sparse = sparse.tocsr().T  # make sure shape[1]=number of docs (needed in len()) 

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def unitvec(vec):
    """
    Scale a vector to unit length. The only exception is the zero vector, which
    is returned back unchanged.

    Output will be in the same format as input (i.e., gensim vector=>gensim vector,
    or numpy array=>numpy array, scipy.sparse=>scipy.sparse).
    """
    if scipy.sparse.issparse(vec):  # convert scipy.sparse to standard numpy array
        vec = vec.tocsr()
        veclen = numpy.sqrt(numpy.sum(vec.data ** 2))
        if veclen > 0.0:
            return vec / veclen
        else:
            return vec

    if isinstance(vec, numpy.ndarray):
        vec = numpy.asarray(vec, dtype=float)
        veclen = blas_nrm2(vec)
        if veclen > 0.0:
            return blas_scal(1.0 / veclen, vec)
        else:
            return vec

    try:
        first = next(iter(vec))  # is there at least one element?
    except:
        return vec

    if isinstance(first, (tuple, list)) and len(first) == 2:  # gensim sparse format?
        length = 1.0 * math.sqrt(sum(val ** 2 for _, val in vec))
        assert length > 0.0, "sparse documents must not contain any explicit zero entries"
        if length != 1.0:
            return [(termid, val / length) for termid, val in vec]
        else:
            return list(vec)
    else:
        raise ValueError("unknown input type") 

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def scipy2sparse(vec, eps=1e-9):
    """Convert a scipy.sparse vector into document format (=list of 2-tuples)."""
    vec = vec.tocsr()
    assert vec.shape[0] == 1
    return [(int(pos), float(val)) for pos, val in zip(vec.indices, vec.data) if numpy.abs(val) > eps] 

# 需要导入模块: from scipy import sparse [as 别名]
# 或者: from scipy.sparse import tocsr [as 别名]
def unitvec(vec, norm='l2'):
    """
    Scale a vector to unit length. The only exception is the zero vector, which
    is returned back unchanged.

    Output will be in the same format as input.
    """
    if norm not in ('l1', 'l2'):
        raise ValueError("'%s' is not a supported norm. Currently supported norms are 'l1' and 'l2'." % norm)
    if scipy.sparse.issparse(vec):
        vec = vec.tocsr()
        if norm == 'l1':
            veclen = numpy.sum(numpy.abs(vec.data))
        if norm == 'l2':
            veclen = numpy.sqrt(numpy.sum(vec.data ** 2))
        if veclen > 0.0:
            return vec / veclen
        else:
            return vec

    if isinstance(vec, numpy.ndarray):
        vec = numpy.asarray(vec, dtype=float)
        if norm == 'l1':
            veclen = numpy.sum(numpy.abs(vec))
        if norm == 'l2':
            veclen = blas_nrm2(vec)
        if veclen > 0.0:
            return blas_scal(1.0 / veclen, vec)
        else:
            return vec

    try:
        first = next(iter(vec))     # is there at least one element?
    except:
        return vec

    if isinstance(first, (tuple, list)) and len(first) == 2:
        if norm == 'l1':
            length = float(sum(abs(val) for _, val in vec))
        if norm == 'l2':
            length = 1.0 * math.sqrt(sum(val ** 2 for _, val in vec))
        assert length > 0.0, "sparse documents must not contain any explicit zero entries"
        return ret_normalized_vec(vec, length)
    else:
        raise ValueError("unknown input type")