def test_extract_values(self):
matchups = [
Matchup([0, 0, 0, 0], [1261440000, 0.001, 55.2, 5.3], ReferenceRecord(0, 55.21, 5.31, 1261440250, 0.0012)),
Matchup([0, 0, 0, 1], [1261440000, 0.001, 55.2, 5.8], ReferenceRecord(1, 55.8, 5.72, 1261440300, 0.0013))
]
class DataMock(object):
def get_reference_dimensions(self, ignored):
return "recordNum"
def read_reference(self, ignored_1, ignored_2):
if hasattr(self, 'second_time_ref'):
return 0.2
else:
self.second_time_ref = True
return np.nan
def read_model(self, ignored_1, ignored_2):
if hasattr(self, 'second_time_mod'):
return 0.2111
else:
self.second_time_mod = True
return 0.1111
ref, model = utils.extract_values(matchups, DataMock(), 'chl_ref', 'chl')
test.assert_almost_equal(ref, np.ma.array([np.nan, 0.2], mask=[True, False]))
test.assert_almost_equal(model, np.ma.array([0.1111, 0.2111], mask=[False, False]))
def test_extract_values(self):
matchups = [
Matchup([0, 0, 0, 0], [1261440000, 0.001, 55.2, 5.3], ReferenceRecord(0, 55.21, 5.31, 1261440250, 0.0012)),
Matchup([0, 0, 0, 1], [1261440000, 0.001, 55.2, 5.8], ReferenceRecord(1, 55.8, 5.72, 1261440300, 0.0013)),
]
class DataMock(object):
def get_reference_dimensions(self, ignored):
return "recordNum"
def read_reference(self, ignored_1, ignored_2):
if hasattr(self, "second_time_ref"):
return 0.2
else:
self.second_time_ref = True
return np.nan
def read_model(self, ignored_1, ignored_2):
if hasattr(self, "second_time_mod"):
return 0.2111
else:
self.second_time_mod = True
return 0.1111
ref, model = utils.extract_values(matchups, DataMock(), "chl_ref", "chl")
test.assert_almost_equal(ref, np.ma.array([np.nan, 0.2], mask=[True, False]))
test.assert_almost_equal(model, np.ma.array([0.1111, 0.2111], mask=[False, False]))
def extract_values_from_matchups(matchups, data, model_name, ref_name):
"""
Returns the reference values and the model values for the given variables in the given matchups.
@param matchups: the matchups from which to extract the data.
@param model_name: the name of the model variable.
@param ref_name: the name of the reference variable.
@return: two numpy arrays: reference_values, model_values
"""
return utils.extract_values(matchups, data, ref_name, model_name)
def extract_values_from_matchups(matchups, data, model_name, ref_name):
"""
Returns the reference values and the model values for the given variables in the given matchups.
@param matchups: the matchups from which to extract the data.
@param model_name: the name of the model variable.
@param ref_name: the name of the reference variable.
@return: two numpy arrays: reference_values, model_values
"""
return utils.extract_values(matchups, data, ref_name, model_name)
def main():
parsed_args = parse_arguments(sys.argv[1:])
config = Configuration(properties_file_name=parsed_args.config, target_dir=parsed_args.output_dir,
target_prefix=parsed_args.prefix)
file_handler = setup_logging(config)
if parsed_args.reference_file is not None:
data = Data(parsed_args.path, parsed_args.reference_file, config.max_cache_size)
else:
data = Data(parsed_args.path, max_cache_size=config.max_cache_size)
output = Output(config=config)
matchups = None
if data.has_one_dim_ref_var():
me = MatchupEngine(data, config)
matchups = me.find_all_matchups()
if not matchups:
logging.warning('No matchups found. System will exit.')
exit(0)
if config.remove_empty_matchups:
matchups = me.remove_empty_matchups(matchups)
if not os.name == 'nt':
logging.debug('Memory after matchups have been found: %s' % resource.getrusage(resource.RUSAGE_SELF).ru_maxrss)
matchup_count = 0 if matchups is None else len(matchups)
collected_statistics = {}
density_plot_files = []
target_files = []
density_plots = {}
for (model_name, ref_name) in parsed_args.variable_mappings:
unit = data.unit(model_name)
is_gridded = len(data.get_reference_dimensions(ref_name)) > 1
if is_gridded:
reference_values, model_values = data.get_values(ref_name, model_name)
matchup_count += ma.count(reference_values)
else:
reference_values, model_values = utils.extract_values(matchups, data, ref_name, model_name)
reference_values, model_values = utils.harmonise(reference_values, model_values)
logging.debug('Compressing ref-variable %s' % ref_name)
reference_values = reference_values.compressed()
logging.debug('Compressing model-variable %s' % model_name)
model_values = model_values.compressed()
logging.info('Calculating statistics for \'%s\' with \'%s\'' % (model_name, ref_name))
stats = processor.calculate_statistics(model_values, reference_values, model_name, ref_name, unit, config)
collected_statistics[(model_name, ref_name)] = stats
if config.write_density_plots:
axis_min = min(stats['min'], stats['ref_min'])
axis_max = max(stats['p90'], stats['ref_p90'])
logging.info('Creating density plot for \'%s\' and \'%s\'' % (model_name, ref_name))
density_plots[model_name + ref_name] = output.density_plot(model_name, ref_name, model_values,
reference_values, config.density_plot_log_scaled,
None, axis_min, axis_max, data.unit(model_name))
if not os.name == 'nt':
logging.debug(
'Memory after statistics have been computed: %s' % resource.getrusage(resource.RUSAGE_SELF).ru_maxrss)
if config.write_csv:
csv_target_file = '%s/%sstatistics.csv' % (parsed_args.output_dir, config.target_prefix)
target_files.append(csv_target_file)
output.csv(data, parsed_args.variable_mappings, collected_statistics, matchup_count, matchups=matchups, source_file=parsed_args.path, target_file=csv_target_file)
logging.info('CSV output written to \'%s\'' % csv_target_file)
if matchups is not None:
matchup_filename = '%s_matchups.csv' % os.path.splitext(csv_target_file)[0]
logging.info('Matchups written to \'%s\'' % matchup_filename)
target_files.append(matchup_filename)
taylor_target_files = []
if config.write_taylor_diagrams:
taylor_target_file = '%s/%staylor.png' % (parsed_args.output_dir, config.target_prefix)
written_taylor_diagrams, d = output.taylor(list(collected_statistics.values()), taylor_target_file)
del d
if written_taylor_diagrams:
for written_taylor_diagram in written_taylor_diagrams:
logging.info('Taylor diagram written to \'%s\'' % written_taylor_diagram)
target_files.append(written_taylor_diagram)
taylor_target_files.append(written_taylor_diagram)
if config.write_density_plots:
for (model_name, ref_name) in parsed_args.variable_mappings:
density_target = '%s/density-%s-%s.png' % (parsed_args.output_dir, model_name, ref_name)
density_plot_files.append(density_target)
target_files.append(density_target)
output.write_density_plot(density_plots[model_name + ref_name], density_target)
logging.info('Density plot written to \'%s\'' % density_target)
target_diagram_file = None
if config.write_target_diagram:
target_diagram_file = '%s/%starget.png' % (parsed_args.output_dir, config.target_prefix)
output.target_diagram(list(collected_statistics.values()), target_diagram_file)
logging.info('Target diagram written to \'%s\'' % target_diagram_file)
target_files.append(target_diagram_file)
if config.write_xhtml:
xml_target_file = '%s/%sreport.xml' % (parsed_args.output_dir, config.target_prefix)
path = str(os.path.dirname(os.path.realpath(__file__))) + '/../resources/'
xsl = path + 'analysis-summary.xsl'
css = path + 'styleset.css'
xsl_target = '%s/%s' % (parsed_args.output_dir, os.path.basename(xsl))
css_target = '%s/%s' % (parsed_args.output_dir, os.path.basename(css))
output.xhtml(list(collected_statistics.values()), matchup_count, matchups, data, xml_target_file, taylor_target_files,
target_diagram_file, density_plot_files)
logging.info('XHTML report written to \'%s\'' % xml_target_file)
shutil.copy(xsl, parsed_args.output_dir)
logging.info('XHTML support file written to \'%s/%s\'' % (parsed_args.output_dir, 'analysis-summary.xsl'))
shutil.copy(css, parsed_args.output_dir)
logging.info('XHTML support file written to \'%s/%s\'' % (parsed_args.output_dir, 'styleset.xsl'))
target_files.append(xml_target_file)
target_files.append(xsl_target)
target_files.append(css_target)
if config.zip:
create_zip(target_files, config, file_handler, parsed_args)
logging.info('End of process')
