def get_weights(_dict, _ky, _d):
#set all objects equal weight, unless defined
if pval.key_not_none(_dict, _ky) is False:
#print ("you have not set any weights for this test")
#print ("continuing with weights=1")
weights = np.ones(len(_d))
else:
weights = _d[tst['weights']]
return weights / np.sum(weights)
#poplate the lists of files for point predictions, and pdf predictions
files = {'point': [], 'pdf': []}
#load the files we will use
for arg in args:
# are these standard .fits and .hdf5 files?
files = fileType(arg, files)
#do we also have a yaml configuration file?
if '.yaml' in arg:
config = load_yaml(arg)
if 'filePaths' in config:
if pval.key_not_none(config, 'filePaths'):
for i in config['filePaths']:
f = glob.glob(i)
for ii in f:
files = fileType(ii, files)
if len(files['point']) + len(files['pdf']) < 1:
print "DES photoz validation code"
print "usage like"
print "photoz_metrics.py data/PointPredictions1.fits data/PointPredictions*.fits"
print "or"
print "photoz_metrics.py data/pdfPredictions*.hdf5"
print "or a mix of the two"
print "photoz_metrics.py data/pdfPredictions*.hdf5 data/PointPredictions*.fits"
print "or you can make more fine tuned validations using a configuration yaml file"
def perform_tests_fast(d, tst):
"""perform_tests_fast performs a fast set of tests without boot strap resampling, or any error resampling """
#results dictionary
res = {}
#get all the columns we are gonna test on
reqcols = tst['metrics'].keys()
for i in reqcols:
if i not in d.keys():
print "missing column ", i
sys.exit()
#which redshift do we need for this metric test?
for photoz in tst['metrics']:
res[photoz] = {}
z_truth = np.array(d[tst['truths']])
z_pred = np.array(d[photoz])
#what is the metric test?
for metric in tst['metrics'][photoz]:
res[photoz][metric] = {}
#convert metric name to metric function
metric_function = pval.get_function(metric)
#do I have to pass any additional arguments to this function?
extra_params = pval.get_extra_params(tst, metric)
#what weighting scheme shall we apply?
for wght in tst['weights']:
res[photoz][metric][wght] = {}
#get the data weights
weights = np.array(d[wght], dtype=float)
res[photoz][metric][wght]['value'] = vlfn.process_function(
metric_function,
z_truth,
z_pred,
weights=weights,
extra_params=extra_params)
#shall we calculate binning statiscs?
if pval.key_not_none(tst, 'bins'):
binning = tst['bins']
res[photoz][metric][wght]['bins'] = {}
for ky in binning:
bin_vals = binning[ky]
res[photoz][metric][wght]['bins'][ky] = {}
res[photoz][metric][wght]['bins'][ky]['bin_center'] = []
res[photoz][metric][wght]['bins'][ky]['value'] = []
for bbn in range(len(bin_vals) - 1):
ind_bn = (d[ky] <= bin_vals[bbn + 1]) * (d[ky] >
bin_vals[bbn])
if np.sum(ind_bn) > 1 and np.sum(weights[ind_bn]) > 0:
res[photoz][metric][wght]['bins'][ky][
'bin_center'].append(np.mean(d[ky][ind_bn]))
res[photoz][metric][wght]['bins'][ky][
'value'].append(
vlfn.process_function(
metric_function,
z_truth[ind_bn],
z_pred[ind_bn],
weights=weights[ind_bn],
extra_params=extra_params))
return res
files = fileType(arg, files)
if len(files['point']) + len(files['pdf']) < 1:
help()
#which sets of metrics + tests shall we perform
testProperties = {'point': [], 'pdf': []}
import string
import random
#nothing is specified, using the standard tests
test_path = path + '/testConfig/' + SCIENCE_SAMPLE + '.yaml'
p = load_yaml(test_path)
for ptype in testProperties:
if pval.key_not_none(p, ptype):
testProperties[ptype] = p[ptype]
#First point predictions
ptype = 'point'
#do we have any files of this type to work with?
if len(files[ptype]) > 0:
#results dictionary
res = {'test_config': testProperties[ptype]}
#obtain the tests and required cols
tst = testProperties[ptype]
#get all the columns we are gonna test on