def density_plot(model_name,
ref_name,
model_values,
ref_values,
axis_min=None,
axis_max=None,
target_file=None,
unit=None,
log_scaled=None,
config=None):
"""
Creates the density plot for the given matchups and variables and possible writes it to the given target file.
@param model_name: the name of the model variable.
@param ref_name: the name of the reference variable.
@param model_name: the name of the model variable.
@param ref_name: the name of the reference variable.
@param target_file: the optional target diagram file. If None, nothing will be written.
@param config: the optional configuration.
@return: the density plot.
"""
op = Output(config=config)
if log_scaled is None and config is not None:
log_scaled = config.density_plot_log_scaled
elif log_scaled is None:
log_scaled = False
return op.density_plot(model_name, ref_name, model_values, ref_values,
log_scaled, target_file, axis_min, axis_max, unit)
def target_diagram(statistics, target_file=None, config=None):
"""
Creates the target diagram derived from the statistics and possibly writes it to the given target file.
@param statistics: An iterable of statistics to write the target diagram for.
@param target_file: the name of the target diagram file. If None, nothing will be written.
@param config: the optional configuration.
@return: the target diagram.
"""
op = Output(config=config)
return op.target_diagram(statistics, target_file)
def target_diagram(statistics, target_file=None, config=None):
"""
Creates the target diagram derived from the statistics and possibly writes it to the given target file.
@param statistics: An iterable of statistics to write the target diagram for.
@param target_file: the name of the target diagram file. If None, nothing will be written.
@param config: the optional configuration.
@return: the target diagram.
"""
op = Output(config=config)
return op.target_diagram(statistics, target_file)
def taylor_diagrams(statistics, target_file=None, config=None):
"""
Creates the taylor diagrams derived from the statistics and possibly writes them to the given target file.
@param statistics: an iterable of statistics to write taylor diagrams for.
@param target_file: the basename for the file where to write the taylor diagrams. If None, nothing will be written.
@param config: the optional configuration.
@return: a list of the taylor diagrams.
"""
op = Output(config=config)
t, diagrams = op.taylor(statistics, target_file)
return diagrams
def taylor_diagrams(statistics, target_file=None, config=None):
"""
Creates the taylor diagrams derived from the statistics and possibly writes them to the given target file.
@param statistics: an iterable of statistics to write taylor diagrams for.
@param target_file: the basename for the file where to write the taylor diagrams. If None, nothing will be written.
@param config: the optional configuration.
@return: a list of the taylor diagrams.
"""
op = Output(config=config)
t, diagrams = op.taylor(statistics, target_file)
return diagrams
def write_xhtml_report(statistics_list, matchups, data, target_file, taylor_target_files=None, target_diagram_file=None, density_plot_files=None, config=None):
"""
Writes the xhtml report to the given target file.
@param statistics_list: the list of statistics to mention in the report.
@param matchups: the matchups the statistics have been calculated for.
@param target_file: the target xhtml file.
@param taylor_target_files: the optional paths to the taylor diagrams.
@param target_diagram_file: the optional paths to the target diagram.
@param density_plot_files: the optional paths to the density plots.
@param config: the optional configuration.
@return: None.
"""
op = Output(config=config)
op.xhtml(statistics_list, len(matchups), matchups, data, target_file, taylor_target_files, target_diagram_file, density_plot_files)
def write_csv(statistics, model_name, ref_name, matchups, data, target_file=None, config=None):
"""
Returns the given statistics as CSV string; writes this string if target_file is provided.
@param model_name: the model variable name.
@param ref_name: the reference variable name.
@param statistics: a dictionary containing all statistics.
@param matchups: the matchups.
@param data: the input data file.
@param target_file: the optional target file; if not None, result string will be written to that file.
@param config: the optional configuration.
@return: the given statistics as CSV string.
"""
op = Output(config=config)
op.csv(data, [(model_name, ref_name)], {(model_name, ref_name): statistics}, len(matchups), matchups=matchups, target_file=target_file)
def test_output_csv(self):
chl_ref_chl = ('chl', 'Ref_chl')
chl_ref2_chl = ('chl', 'Ref2_chl')
sst_ref_sst = ('sst', 'sst_reference')
sst_sst = ('sst', 'sst')
mappings = [chl_ref_chl, chl_ref2_chl, sst_ref_sst, sst_sst]
statistics = {}
statistics[chl_ref_chl] = processor.calculate_statistics(np.array([11, 9, 11.2, 10.5]), np.array([10, 10, 10, 10]), 'chl', 'Ref_chl')
statistics[chl_ref2_chl] = processor.calculate_statistics(np.array([12, 2, 3, 5]), np.array([2, 3, 4, 6]), 'chl', 'Ref2_chl')
statistics[sst_ref_sst] = processor.calculate_statistics(np.array([8, 9, 15, 4]), np.array([6, 8, 2, 1]), 'sst', 'Ref_sst')
statistics[sst_sst] = processor.calculate_statistics(np.array([8, 10, 2, 55]), np.array([99, 5, 5, 23]), 'sst', 'sst')
output = Output()
output.csv(mappings, statistics, 10957, matchups=None, target_file='c:\\temp\\output\\benchmark\\test.csv')
def density_plot(model_name, ref_name, model_values, ref_values, axis_min=None, axis_max=None, target_file=None, unit=None, log_scaled=None, config=None):
"""
Creates the density plot for the given matchups and variables and possible writes it to the given target file.
@param model_name: the name of the model variable.
@param ref_name: the name of the reference variable.
@param model_name: the name of the model variable.
@param ref_name: the name of the reference variable.
@param target_file: the optional target diagram file. If None, nothing will be written.
@param config: the optional configuration.
@return: the density plot.
"""
op = Output(config=config)
if log_scaled is None and config is not None:
log_scaled = config.density_plot_log_scaled
elif log_scaled is None:
log_scaled = False
return op.density_plot(model_name, ref_name, model_values, ref_values, log_scaled, target_file, axis_min, axis_max, unit)
def write_xhtml_report(statistics_list,
matchups,
data,
target_file,
taylor_target_files=None,
target_diagram_file=None,
density_plot_files=None,
config=None):
"""
Writes the xhtml report to the given target file.
@param statistics_list: the list of statistics to mention in the report.
@param matchups: the matchups the statistics have been calculated for.
@param target_file: the target xhtml file.
@param taylor_target_files: the optional paths to the taylor diagrams.
@param target_diagram_file: the optional paths to the target diagram.
@param density_plot_files: the optional paths to the density plots.
@param config: the optional configuration.
@return: None.
"""
op = Output(config=config)
op.xhtml(statistics_list, len(matchups), matchups, data, target_file,
taylor_target_files, target_diagram_file, density_plot_files)
def test_output_csv(self):
chl_ref_chl = ('chl', 'Ref_chl')
chl_ref2_chl = ('chl', 'Ref2_chl')
sst_ref_sst = ('sst', 'sst_reference')
sst_sst = ('sst', 'sst')
mappings = [chl_ref_chl, chl_ref2_chl, sst_ref_sst, sst_sst]
statistics = {}
statistics[chl_ref_chl] = processor.calculate_statistics(
np.array([11, 9, 11.2, 10.5]), np.array([10, 10, 10, 10]), 'chl',
'Ref_chl')
statistics[chl_ref2_chl] = processor.calculate_statistics(
np.array([12, 2, 3, 5]), np.array([2, 3, 4, 6]), 'chl', 'Ref2_chl')
statistics[sst_ref_sst] = processor.calculate_statistics(
np.array([8, 9, 15, 4]), np.array([6, 8, 2, 1]), 'sst', 'Ref_sst')
statistics[sst_sst] = processor.calculate_statistics(
np.array([8, 10, 2, 55]), np.array([99, 5, 5, 23]), 'sst', 'sst')
output = Output()
output.csv(mappings,
statistics,
10957,
matchups=None,
target_file='c:\\temp\\output\\benchmark\\test.csv')
def write_csv(statistics,
model_name,
ref_name,
matchups,
data,
target_file=None,
config=None):
"""
Returns the given statistics as CSV string; writes this string if target_file is provided.
@param model_name: the model variable name.
@param ref_name: the reference variable name.
@param statistics: a dictionary containing all statistics.
@param matchups: the matchups.
@param data: the input data file.
@param target_file: the optional target file; if not None, result string will be written to that file.
@param config: the optional configuration.
@return: the given statistics as CSV string.
"""
op = Output(config=config)
op.csv(data, [(model_name, ref_name)],
{(model_name, ref_name): statistics},
len(matchups),
matchups=matchups,
target_file=target_file)
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')