def test_parser_get_physical_coordinates(data_path, parse_lib):
parser = ImzMLParser(data_path, parse_lib=parse_lib)
x, y = parser.get_physical_coordinates(0)
assert x == 100.0
assert y == 100.0
def write_msi_to_hdf(self, h5f_fname_w_path, imzml_fname_w_path, norm=''):
"""
Converts imzML data to HDF5 format. Iterates through imzML and, one
spectrum at a time, reads and writes spectral data to h5 as new raw
dataset. Spectra are stored to HDF5 dataset in the order in which
they are read from imzML file.
"""
imzml = ImzMLParser(imzml_fname_w_path)
#Infer dataset dimensions from first spectrum in imzML
samp_mz, samp_int = imzml.getspectrum(0)
length = len(samp_mz)
self.mzsaxis = np.asarray(samp_mz)
height = len(imzml.mzOffsets)
del samp_int, samp_mz
#Create and open hdf5 file
hf = h5py.File(h5f_fname_w_path, 'w')
print('\n%i spectra x %i mz data points'%(height, length))
print()
print('Importing...')
print('')
grp = hf.create_group('MALDI_001')
dset1 = grp.create_dataset('Intensities', shape=(height, length),
chunks=(1, 1024), dtype='float64')
grp.create_dataset('m_over_z', data=self.mzsaxis)
dset3 = grp.create_dataset('Coordinates', shape=(height,2))
grp.create_group('Normalization Factors')
# Iterates through spectra contained in .ibd binary using getspectrum()
# For each spectrum, writes mz axis and intensity list as line in
# appropriate datasets in group "MALDI_001"
summed_ints = np.zeros(length)
max_int = 0
for i in range(height):
mz, intensity = imzml.getspectrum(i)
try:
coordinates = imzml.get_physical_coordinates(i)
except KeyError:
imzml.imzmldict['pixel size y'] = imzml.imzmldict['pixel size x']
coordinates = imzml.get_physical_coordinates(i)
point = np.asarray([coordinates[0], coordinates[1]])
dset1[i] = intensity
dset3[i] = point
if max(intensity) > max_int:
max_int = max(intensity)
summed_ints = summed_ints + intensity
if self.log and i > 0:
if i % 1000 == 0:
print('%i / %i'%((i, height)))
average_spectrum = summed_ints / height
grp.create_dataset('Average spectrum', data=(average_spectrum), dtype='float64')
del summed_ints, mz, intensity, coordinates, point, max_int
#Revert Numpy error handling to default setting (print)
np.seterr(all = 'print')
# Clean up, flush buffer, close file
print('Finished importing!')
if norm=='' or norm.upper()=='NONE':
pass
else:
self._calculate_new_normalization_(norm, hf)
hf.flush()
hf.close()
return
