def main():
# Parse command-line arguments.
parser = argparse.ArgumentParser(description='Build a Pandas dataset from local ThermoML Archive mirror.')
parser.add_argument('--journalprefix', dest='journalprefix', metavar='JOURNALPREFIX', action='store', type=str, default=None,
help='journal prefix to use in globbing *.xml files')
parser.add_argument('--path', dest='path', metavar='path', action='store', type=str, default=None,
help='path to local ThermoML Archive mirror')
args = parser.parse_args()
# Get location of local ThermoML Archive mirror.
XML_PATH = os.path.join(os.environ["HOME"], '.thermoml') # DEFAULT LOCATION
if args.path != None:
XML_PATH = args['path']
elif 'THERMOML_PATH' in os.environ:
XML_PATH = os.environ["THERMOML_PATH"]
# Get path for XML files.
if args.journalprefix != None:
filenames = glob.glob("%s/%s*.xml" % (XML_PATH, args.journalprefix))
else:
filenames = glob.glob("%s/*.xml" % XML_PATH)
# Process data.
from thermopyl.utils import build_pandas_dataframe
[data, compound_dict] = build_pandas_dataframe(filenames)
data.to_hdf("%s/data.h5" % XML_PATH, 'data')
compound_dict.to_hdf("%s/compound_name_to_formula.h5" % XML_PATH, 'data')
return
def test_build_pandas_dataframe():
tmpdir = tempfile.mkdtemp()
from thermopyl.utils import build_pandas_dataframe, pandas_dataframe
# Generate dataframe
filenames = [get_fn("je8006138.xml")]
[data, compounds] = build_pandas_dataframe(filenames)
# Write as HDF5
data.to_hdf(os.path.join(tmpdir, 'data.h5'), 'data')
compounds.to_hdf(os.path.join(tmpdir, 'compound_name_to_formula.h5'), 'data')
# Read dataframe
df = pandas_dataframe(thermoml_path=tmpdir)
# Clean up tmpdir
import shutil
shutil.rmtree(tmpdir)
def main():
# Parse command-line arguments.
parser = argparse.ArgumentParser(
description='Build a Pandas dataset from local ThermoML Archive mirror.'
)
parser.add_argument('--journalprefix',
dest='journalprefix',
metavar='JOURNALPREFIX',
action='store',
type=str,
default=None,
help='journal prefix to use in globbing *.xml files')
parser.add_argument('--path',
dest='path',
metavar='path',
action='store',
type=str,
default=None,
help='path to local ThermoML Archive mirror')
args = parser.parse_args()
# Get location of local ThermoML Archive mirror.
XML_PATH = os.path.join(os.environ["HOME"],
'.thermoml') # DEFAULT LOCATION
if args.path != None:
XML_PATH = args['path']
elif 'THERMOML_PATH' in os.environ:
XML_PATH = os.environ["THERMOML_PATH"]
# Get path for XML files.
if args.journalprefix != None:
filenames = glob.glob("%s/%s*.xml" % (XML_PATH, args.journalprefix))
else:
filenames = glob.glob("%s/*.xml" % XML_PATH)
# Process data.
from thermopyl.utils import build_pandas_dataframe
[data, compound_dict] = build_pandas_dataframe(filenames)
data.to_hdf("%s/data.h5" % XML_PATH, 'data')
compound_dict.to_hdf("%s/compound_name_to_formula.h5" % XML_PATH, 'data')
return
