def main():
from optparse import OptionParser
from mrec import load_sparse_matrix, save_sparse_matrix
parser = OptionParser()
parser.add_option('--input_format',dest='input_format',help='format of input dataset tsv | csv | mm (matrixmarket) | csr (scipy.sparse.csr_matrix) | fsm (mrec.sparse.fast_sparse_matrix)')
parser.add_option('--input',dest='input',help='filepath to input')
parser.add_option('--output_format',dest='output_format',help='format of output dataset(s) tsv | csv | mm (matrixmarket) | csr (scipy.sparse.csr_matrix) | fsm (mrec.sparse.fast_sparse_matrix)')
parser.add_option('--output',dest='output',help='filepath for output')
(opts,args) = parser.parse_args()
if not opts.input or not opts.output or not opts.input_format or not opts.output_format:
parser.print_help()
raise SystemExit
if opts.output_format == opts.input_format:
raise SystemExit('input and output format are the same, not doing anything')
if opts.input_format == 'tsv' and opts.output_format == 'mm':
# we can do this without loading the data
tsv2mtx(opts.input,opts.output)
else:
data = load_sparse_matrix(opts.input_format,opts.input)
save_sparse_matrix(data,opts.output_format,opts.output)
def test_save_load_sparse_matrix():
X = get_random_coo_matrix()
for fmt in ["tsv", "csv", "npz", "mm", "fsm"]:
if fmt == "mm":
suffix = ".mtx"
elif fmt == "npz" or fmt == "fsm":
suffix = ".npz"
else:
suffix = ""
f, path = tempfile.mkstemp(suffix=suffix)
save_sparse_matrix(X, fmt, path)
Y = load_sparse_matrix(fmt, path)
assert_sparse_matrix_equal(X, Y)
os.remove(path)
def test_save_load_sparse_matrix():
X = get_random_coo_matrix()
for fmt in ['tsv','csv','npz','mm','fsm']:
if fmt == 'mm':
suffix = '.mtx'
elif fmt == 'npz' or fmt == 'fsm':
suffix = '.npz'
else:
suffix = ''
f,path = tempfile.mkstemp(suffix=suffix)
save_sparse_matrix(X,fmt,path)
Y = load_sparse_matrix(fmt,path)
assert_sparse_matrix_equal(X,Y)
os.remove(path)
def main():
from optparse import OptionParser
from mrec import load_sparse_matrix, save_sparse_matrix
parser = OptionParser()
parser.add_option(
'--input_format',
dest='input_format',
help=
'format of input dataset tsv | csv | mm (matrixmarket) | csr (scipy.sparse.csr_matrix) | fsm (mrec.sparse.fast_sparse_matrix)'
)
parser.add_option('--input', dest='input', help='filepath to input')
parser.add_option(
'--output_format',
dest='output_format',
help=
'format of output dataset(s) tsv | csv | mm (matrixmarket) | csr (scipy.sparse.csr_matrix) | fsm (mrec.sparse.fast_sparse_matrix)'
)
parser.add_option('--output', dest='output', help='filepath for output')
(opts, args) = parser.parse_args()
if not opts.input or not opts.output or not opts.input_format or not opts.output_format:
parser.print_help()
raise SystemExit
if opts.output_format == opts.input_format:
raise SystemExit(
'input and output format are the same, not doing anything')
if opts.input_format == 'tsv' and opts.output_format == 'mm':
# we can do this without loading the data
tsv2mtx(opts.input, opts.output)
else:
data = load_sparse_matrix(opts.input_format, opts.input)
save_sparse_matrix(data, opts.output_format, opts.output)
