def main(path_to_file):
print(f"Reading opus file from path" f"{path_to_file}")
opus_data = read_file(path_to_file)
print(f"Data fields: " f"{list(opus_data.keys())}")
ab_x = opus_data.get_range("AB")
# the "AB" data can contain more null values at the end (at least 1)
# so the getting useful data requires slicing the array:
abs = opus_data["AB"][0:len(ab_x)]
print(f"Absorption spectrum range: " f"{ab_x[0]} {ab_x[-1]}")
print(f"Absorption elements num: " f'{len(abs)}')
try:
import matplotlib.pyplot as plt
print("Plotting AB")
plt.plot(opus_data.get_range("AB"), abs)
plt.show()
print("Plotting interpolated AB")
plt.plot(*opus_data.interpolate(ab_x[0], ab_x[-1], 100))
plt.show()
except ImportError:
print(f"Install matplotlib to plot spectra")
def load_spectra_df(SPECTRA_DIR, AFSIS_PATH):
names = []
spectra = []
for path in tqdm(AFSIS_PATH.glob(SPECTRA_DIR)):
if path.is_file():
spect_data = read_file(path)
spectra.append(spect_data["AB"])
names.append(path.stem)
wave_nums = spect_data.get_range()
column_names = ['{:.3f}'.format(x) for x in wave_nums]
spectra_df = pd.DataFrame(spectra, index=names, columns=column_names)
return spectra_df
def main(path_to_file):
print(f'Reading opus file from path' f'{path_to_file}')
opus_data = read_file(path_to_file)
print(f'Dimension of data: ' f'{len(opus_data.wave_nums)}')
print(f'Spectrum range: ['
f'{min(opus_data.spectrum)}; '
f'{max(opus_data.spectrum)}]')
print(f'Metadata: ' f'{opus_data.meta}')
plt.plot(opus_data.wave_nums, opus_data.spectrum)
plt.title(f'Spectrum {path_to_file}')
plt.show()
def load_spectra(path=DATA_SPECTRA):
"""Returns DRIFT/MIRs spectra, Petra's data, Vietnam, 2007-2008"""
path = Path(path)
df_list = []
for i, f in enumerate(path.glob('*.*')):
if f.suffix != '.xls':
file = brukeropusreader.read_file(f)
spectrum = pd.Series(file['AB'])
spectrum_name = _clean_column_name(f.name)
if i == 0:
wavelength = pd.Series(file.get_range("AB"))
data = {'wavenumber': wavelength, spectrum_name: spectrum}
else:
data = {spectrum_name: spectrum}
df_list.append(pd.DataFrame(data))
return pd.concat(df_list, axis=1, ignore_index=False, sort=False).set_index('wavenumber')
def parse_values(self, filenames):
'''parse values of .0 files from bruker opus'''
if not hasattr(self, 'file_error'):
self.file_error = []
values = {}
for filename in filenames:
if filename[0][-2:] == '.0':
try:
bruker_object = read_file(filename[0])
except ValueError:
print(f'ValueError {filename}')
self.file_error.append(f'ValueError {filename}')
continue
wave = pd.DataFrame(
bruker_object.spectrum,
1 / np.array(bruker_object.wave_nums) * 1e7)
wave.columns = ['intensity(relative)']
wave.index.name = 'wavelength(nm)'
values[filename[1]] = wave
return values
def load_spectra_rep(path=DATA_SPECTRA_REP):
"""Returns DRIFT/MIRs spectra and their replicates, Petra's data, Vietnam, 2007-2008"""
path = Path(path)
df_list = []
_ids = []
for i, f in enumerate(path.glob('*.0')):
_id = int(re.search(r'(.*?)_', f.name).group(1))
if (_id in range(3179, 4922)) and (_id not in _ids):
file = brukeropusreader.read_file(f)
if 'AB' in file:
_ids.append(_id)
spectrum = pd.Series(file['AB'])
spectrum_name = _id
if len(df_list) == 0:
wavelength = pd.Series(file.get_range('AB'))
data = {'wavenumber': wavelength, spectrum_name: spectrum}
else:
data = {spectrum_name: spectrum}
df_list.append(pd.DataFrame(data))
df = pd.concat(df_list, axis=1, ignore_index=False, sort=False).set_index('wavenumber')
return df.reindex(sorted(df.columns), axis=1)
def main(path_to_file):
print(f"Reading opus file from path" f"{path_to_file}")
opus_data = read_file(path_to_file)
print(f"Data fields: " f"{list(opus_data.keys())}")
ab_x = opus_data.get_range("AB")
print(f"Absorption spectrum range: " f"{ab_x[0]} {ab_x[-1]}")
print(f"Absorption elements num: " f'{len(opus_data["AB"])}')
try:
import matplotlib.pyplot as plt
print("Plotting AB")
plt.plot(opus_data.get_range("AB"), opus_data["AB"])
plt.show()
print("Plotting interpolated AB")
plt.plot(*opus_data.interpolate(ab_x[0], ab_x[-1], 100))
plt.show()
except ImportError:
print(f"Install matplotlib to plot spectra")
print(Z2)
# %% [markdown]
# Note above that a warning was issued because the `irdata/OPUS` contains a background file
# (single beam) which is not read by SpectroChemPy.
#
# Finally, supplementary information can be obtained by the direct use of
# `brukeropusreader`.
#
# For instance:
# %%
from brukeropusreader import read_file # noqa: E402
opusfile = scp.DATADIR / "irdata" / "OPUS" / "test.0000" # the full path of the file
Z3 = read_file(
opusfile) # returns a dictionary of the data and metadata extracted
for key in Z3:
print(key)
Z3["Optik"] # looks what is the Optik block:
# %% [markdown]
# ## Import/Export of JCAMP-DX files
#
# [JCAMP-DX](http://www.jcamp-dx.org/) is an open format initially developed for IR data and extended to
# other spectroscopies. At present, the JCAMP-DX reader implemented in Spectrochempy is limited to IR data and
# AFFN encoding (see R. S. McDonald and Paul A. Wilks, JCAMP-DX: A Standard Form for Exchange of Infrared Spectra in
# Readable Form, Appl. Spec., 1988, 1, 151–162. doi:10.1366/0003702884428734 for details).
#
# The JCAMP-DX reader of spectrochempy has been essentially written to read again the jcamp-dx files exported by
# spectrochempy `write_jdx()` writer.
def __init__(self, filename):
"""Load a binary Bruker Opus file into a dictionary."""
import brukeropusreader
self.filename = filename
self.data = brukeropusreader.read_file(expand_path(filename))
shutil.rmtree("converted_data")
except:
print("could not remove /converted_data, directory not does exist")
# Calculate files and directories that need to be created
targetDirs = list(
map(lambda dir: dir.replace("raw_data", "converted_data", 1), dirs))
targetFiles = list(
map(lambda file: file.replace("raw_data", "converted_data", 1), files))
targetDirs.append("converted_data")
# Create all target directories
for dir in targetDirs:
try:
Path(dir).mkdir(parents=True, exist_ok=True)
except:
print("Could not create directory: " + dir)
# Read binary OPUS files and extract ScSm data, lining up each value with it's
# corresponding X-Axis value, and save each row as an X-Axis,Y-Axis pair
for fileIndex, binaryFile in enumerate(files):
opus_data = read_file(binaryFile)
newFileName = targetFiles[fileIndex] + ".dpt"
with open(newFileName, "w") as newFile:
for index, yValue in enumerate(opus_data["ScSm"]):
newFile.write(
str(xValues[index]) + "," + str(
Decimal(str(yValue)).quantize(
Decimal('.00001'), rounding=ROUND_HALF_EVEN)) + "\n")
print("Created file: " + newFileName)
