def test_c_reader_npz(self):
distreader = DistNpz(self.currentFolder + "/../examples/toydata10.dist.npz")
distdata = distreader.read(order='F',force_python_only=False)
snp_c = distdata.val
self.assertEqual(np.float64, snp_c.dtype)
self.assertTrue(np.allclose(self.dist_values[:,:10], snp_c, rtol=1e-05, atol=1e-05))
distreader1 = DistNpz(self.currentFolder + "/../examples/toydata10.dist.npz")
distreader2 = DistNpz(self.currentFolder + "/../examples/toydata.dist.npz")[:,:10]
self.assertTrue(np.allclose(distreader1.read().val, distreader2.read().val, rtol=1e-05, atol=1e-05))
distdata.val[1,2] = np.NaN # Inject a missing value to test writing and reading missing values
output = "tempdir/distreader/toydata10.dist.npz"
create_directory_if_necessary(output)
DistNpz.write(output,distdata)
snpdata2 = DistNpz(output).read()
np.testing.assert_array_almost_equal(distdata.val, snpdata2.val, decimal=10)
snpdata3 = distdata[:,0:0].read() #create distdata with no sids
output = "tempdir/distreader/toydata0.dist.npz"
DistNpz.write(output,snpdata3)
snpdata4 = DistNpz(output).read()
assert snpdata3 == snpdata4
def test_write_x_x_cpp(self):
distreader = DistNpz(self.currentFolder + "/../examples/toydata.dist.npz")
for order in ['C','F']:
for dtype in [np.float32,np.float64]:
distdata = distreader.read(order=order,dtype=dtype)
distdata.val[-1,0] = float("NAN")
output = "tempdir/toydata.{0}{1}.cpp.dist.npz".format(order,"32" if dtype==np.float32 else "64")
create_directory_if_necessary(output)
DistNpz.write(output, distdata)
snpdata2 = DistNpz(output).read()
np.testing.assert_array_almost_equal(distdata.val, snpdata2.val, decimal=10)
def test_write_distnpz_f64cpp_0(self):
distreader = DistNpz(self.currentFolder + "/../examples/toydata.dist.npz")
iid_index = 0
logging.info("iid={0}".format(iid_index))
#if distreader.iid_count % 4 == 0: # divisible by 4 isn't a good test
# distreader = distreader[0:-1,:]
#assert distreader.iid_count % 4 != 0
distdata = distreader[0:iid_index,:].read(order='F',dtype=np.float64)
if distdata.iid_count > 0:
distdata.val[-1,0] = float("NAN")
output = "tempdir/toydata.F64cpp.{0}.dist.npz".format(iid_index)
create_directory_if_necessary(output)
DistNpz.write(output, distdata )
snpdata2 = DistNpz(output).read()
np.testing.assert_array_almost_equal(distdata.val, snpdata2.val, decimal=10)
if __name__ == '__main__':
logging.basicConfig(level=logging.WARN)
if False:
from pysnptools.snpreader import Bed
from pysnptools.distreader import DistData, DistNpz
# Create toydata.dist.npz
currentFolder = os.path.dirname(os.path.realpath(__file__))
if True:
snpreader = Bed(currentFolder + "/../examples/toydata.5chrom.bed",count_A1=True)[:25,:]
np.random.seed(392)
val = np.random.random((snpreader.iid_count,snpreader.sid_count,3))
val /= val.sum(axis=2,keepdims=True) #make probabilities sum to 1
distdata = DistData(iid=snpreader.iid,sid=snpreader.sid,pos=snpreader.pos,val=val)
DistNpz.write(currentFolder + "/../examples/toydata.dist.npz",distdata)
if True:
distdata = DistNpz(currentFolder + "/../examples/toydata.dist.npz").read()
for sid_major,name_bit in [(False,'iidmajor'),(True,'snpmajor')]:
DistHdf5.write(currentFolder + "/../examples/toydata.{0}.dist.hdf5".format(name_bit),distdata,sid_major=sid_major)
if True:
distdata = DistNpz(currentFolder + "/../examples/toydata.dist.npz")[:,:10].read()
DistNpz.write(currentFolder + "/../examples/toydata10.dist.npz",distdata)
if True:
distdata = DistNpz(currentFolder + "/../examples/toydata.dist.npz")[:,:10].read()
DistMemMap.write(currentFolder + "/../examples/tiny.dist.memmap",distdata)
print('done')
suites = getTestSuite()
r = unittest.TextTestRunner(failfast=False)
ret = r.run(suites)