def test_fetch_hitemp_OH(verbose=True, *args, **kwargs):
"""Test proper download of HITEMP OH database.
Good to test fetch_hitemp.
``13_HITEMP2020.par.bz2`` is only 900 kb so it can be run on online
tests without burning the planet ЁЯМ│
тЪая╕П if using the default `chunksize=100000`, it uncompresses in one pass
(only 57k lines for OH) and we cannot test that appending to the same HDF5
works. So here we use a smaller chunksize of 20,000.
.
"""
df = fetch_hitemp("OH",
cache="regen",
chunksize=20000,
verbose=3 * verbose)
assert "HITEMP-OH" in getDatabankList()
assert len(df) == 57019
# Load again and make sure it works (ex: metadata properly loaded etc.):
fetch_hitemp("OH")
def test_partial_loading(*args, **kwargs):
""" Assert that using partial loading of the database works """
wmin, wmax = 2500, 4500
# First ensures that the database is wider than this (else test is irrelevant) :
df = fetch_hitemp("OH")
assert df.wav.min() < wmin
assert df.wav.max() > wmax
# Now fetch with partial loading
df = fetch_hitemp("OH", load_wavenum_min=wmin, load_wavenum_max=wmax)
assert df.wav.min() >= wmin
assert df.wav.max() <= wmax
def test_fetch_hitemp_all_molecules(molecule, verbose=False, *args, **kwargs):
"""Test fetch HITEMP for all molecules whose download URL is available.
..warning::
this downloads gigabytes of data. It is unselected by default by Pytest
(see radis/setup.cfg)
The bz2 compression factor gives about 17 MB / million lines :
- OH (57 k lines) is only 900 kb
- CO (0.7 M lines) is only ~14 Mb
- CH4 (114 M lines) is 435 MB
If it fails, check the databases downloaded in ~/.radisdb
Notes
-----
Performance tests of chunksize tested on CO :
- chunksize=1000000 > 22s , 1 iteration ~ 22s
- chunksize=100000 > 18s, , 1 iteration ~ 4s
- chunksize=50000 > 19s ,1 iteration ~ 2s
- chunksize=1000 --> 90s , 1 iteration << 1s
"""
df = fetch_hitemp(molecule, verbose=verbose)
assert f"HITEMP-{molecule}" in getDatabankList()
assert len(df) == INFO_HITEMP_LINE_COUNT[molecule]
def test_local_hdf5_lines_loading(*args, **kwargs):
"""
We use the OH HITEMP line database to test :py:func:`~radis.io.hitemp.fetch_hitemp`
and :py:func:`~radis.io.hdf5.hdf2df`
- Partial loading (only specific wavenumbers)
- Only certain isotopes
- Only certain columns
"""
fetch_hitemp("OH") # to initialize the database
path = getDatabankEntries("HITEMP-OH")["path"]
# Initialize the database
fetch_hitemp("OH")
path = getDatabankEntries("HITEMP-OH")["path"][0]
df = hdf2df(path)
wmin, wmax = df.wav.min(), df.wav.max()
assert wmin < 2300 # needed for next test to be valid
assert wmax > 2500 # needed for next test to be valid
assert len(df.columns) > 5 # many columns loaded by default
assert len(df.iso.unique()) > 1
# Test loading only certain columns
df = hdf2df(path, columns=["wav", "int"])
assert len(df.columns) == 2 and "wav" in df.columns and "int" in df.columns
# Test loading only certain isotopes
df = hdf2df(path, isotope="2")
assert df.iso.unique() == 2
# Test partial loading of wavenumbers
df = hdf2df(path, load_wavenum_min=2300, load_wavenum_max=2500)
assert df.wav.min() >= 2300
assert df.wav.max() <= 2500
# Test with only one
assert hdf2df(path, load_wavenum_min=2300).wav.min() >= 2300
# Test with the other
assert hdf2df(path, load_wavenum_max=2500).wav.max() <= 2500
# -*- coding: utf-8 -*-
"""
Download HITEMP H2O database, parse & cache them, to make sure the example notebooks run fast
"""
from radis.test.utils import setup_test_line_databases
from radis.io.hitemp import fetch_hitemp
setup_test_line_databases() # init radis.json etc if needed
for (wmin, wmax) in [(0, 50), (50, 150), (150, 250), (250, 350), (350, 500),
(500, 600), (600, 700), (700, 800), (800, 900),
(900, 1000), (1000, 1150), (1150, 1300), (1300, 1500),
(1500, 1750), (1750, 2000), (2000, 2250), (2250, 2500),
(2500, 2750), (2750, 3000), (3000, 3250), (3250, 3500),
(3500, 4150), (4150, 4500), (4500, 5000), (5000, 5500),
(5500, 6000), (6000, 6500), (6500, 7000), (7000, 7500),
(7500, 8000), (8000, 8500), (8500, 9000), (9000, 11000),
(11000, 30000)]:
fetch_hitemp(
"H2O",
isotope='1', # only 1 HITEMP file so all isotopes are downloaded anyway
load_wavenum_min=wmin,
load_wavenum_max=wmax,
verbose=3)
# -*- coding: utf-8 -*-
"""
Download HITEMP database, parse & cache them, to make sure the example notebooks run fast
"""
from radis.test.utils import setup_test_line_databases
from radis.io.hitemp import fetch_hitemp
setup_test_line_databases() # init radis.json etc if needed
# Download other species
for molecule in ["OH", "CO", "NO", "NO2"]:
print("Downloading and caching ", molecule)
fetch_hitemp(molecule, isotope='1', # only 1 HITEMP file so all isotopes are downloaded anyway
load_wavenum_min=2000, # keep memory usage low. only 1 HITEMP file so everything is downloaded anyway
load_wavenum_max=5000,
verbose=3)
# Not downloaded because to big for Binder / GESIS : CH4, N2O (we could actually try N2O)
# Downloaded and computed separately: CO2, H2O
