def test_qp_file_writing():
locs = np.array([1.0, 1.0, 2.0])
locs2 = np.array([1.2, 1.9, 1.8])
scales = np.array([0.1, 0.2, 0.5])
ens = qp.Ensemble(qp.stats.norm, data=dict(loc=locs, scale=scales))
ens2 = qp.Ensemble(qp.stats.norm, data=dict(loc=locs2, scale=scales))
outfile = "./fin_qp.hdf5"
tmpfile = "./tmp_qp.hdf5"
metafile = "./fin_qp_meta.hdf5"
_ = initialize_qp_output(outfile)
write_qp_output_chunk(tmpfile, outfile, ens, 0)
write_qp_output_chunk(tmpfile, outfile, ens2, 1)
num_chunks = 2
qp_reformat_output(tmpfile, outfile, num_chunks)
assert os.path.exists(outfile)
assert os.path.exists(metafile)
os.remove(outfile)
os.remove(metafile)
def estimate(self, test_data):
color_data = make_color_data(test_data)
pdfs, z_grid = self.model.predict(color_data, n_grid=self.nzbins)
self.zgrid = np.array(z_grid).flatten()
if self.output_format == 'qp':
qp_dstn = qp.Ensemble(qp.interp,
data=dict(xvals=self.zgrid, yvals=pdfs))
return qp_dstn
else:
zmode = np.array([self.zgrid[np.argmax(pdf)]
for pdf in pdfs]).flatten()
pz_dict = {'zmode': zmode, 'pz_pdf': pdfs}
return pz_dict
def estimate(self, test_data):
test_size = len(test_data['id'])
zmode = np.repeat(self.zmode, test_size)
if self.output_format == 'qp':
qp_d = qp.Ensemble(qp.interp,
data=dict(xvals=self.zgrid,
yvals=np.tile(self.train_pdf,
(test_size, 1))))
return qp_d
else:
pz_dict = {
'zmode': zmode,
'pz_pdf': np.tile(self.train_pdf, (test_size, 1))
}
return pz_dict
def estimate(self, test_data):
color_data = make_color_data(test_data)
input_data = regularize_data(color_data)
zmode = np.round(self.model.predict(input_data), 3)
pdfs = []
widths = self.width * (1.0+zmode)
if self.output_format == 'qp':
qp_dstn = qp.Ensemble(qp.stats.norm, data=dict(loc=zmode,
scale=widths))
return qp_dstn
else:
self.zgrid = np.linspace(self.zmin, self.zmax, self.nzbins)
for i, zb in enumerate(zmode):
pdfs.append(norm.pdf(self.zgrid, zb, widths[i]))
pz_dict = {'zmode': zmode, 'pz_pdf': pdfs}
return pz_dict
def main(argv):
starttime = time.time()
currenttime = time.time()
outfile = "CDE_STATS.out"
outfp = open(outfile,"w")
z_array,ID,szs,mags,pzs = ingdata.ingestflexzdata()
print "making Ensemble..."
approx_pdf = qp.Ensemble(pzs.shape[0],gridded=(z_array,pzs),procs=3)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds"%(currenttime-oldtime)
print "making EvaluateMetric Object"
bpzobj = inmet.EvaluateMetric(approx_pdf,szs)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds"%(currenttime-oldtime)
#print "calculating PIT vals..."
#bpzPIT = bpzobj.PIT()
#oldtime = currenttime
#currenttime = time.time()
#print "took %g seconds"%(currenttime-oldtime)
#print "PIT!"
#print bpzPIT
#write to file
oldtime = currenttime
currenttime = time.time()
print "took %g seconds"%(currenttime-oldtime)
print "calculating cdeloss..."
tmpxgrid = np.linspace(0.0,10.0,1000)
cde_loss = bpzobj.cde_loss(tmpxgrid)
print "CDE loss: %g\n"%cde_loss
outfp.write("CDE LOSS:\n%.6g\n"%(cde_loss))
outfp.close()
oldtime = currenttime
currenttime = time.time()
print "took %g seconds"%(currenttime-oldtime)
print "finished\n"
def load_gridded(catalog_file_name, pz_file_name, z_spec_col,
z_min, z_max, z_step):
""" Load a files that are sampled on a reqular grid.
Load data files that come from codes such as LePHARE and BPZ which
sample their PDFs at regular grid points.
Parameters
----------
catalog_file_name : str
Name of the catalog file to load containing z_estimated and z_spec
pz_file_name : str
Name of file containing gridded PDF information
z_min : float
Minimum redshift of PDFs
z_max : float
Maximum redshift of PDFs. z_max is defined as inclusive in this calse
z_step : float
Step size in redshift for PDFs
z_spec_col : int
Column number of spectroscopic redshift.
Returns
-------
A tubple gontaining a list of qp.PDF objects for each estimated pdf
in the file and a qp.PDF of the true N(z) created from samples of the
distribution.
"""
# Load our data and create a the array of redshifts used in the grid.
z_array = np.arange(z_min, z_max + z_step / 2., z_step)
z_trues = np.loadtxt(catalog_file_name, usecols=z_spec_col)
gridded_pdfs = np.loadtxt(pz_file_name)
# Create our "true" PDF using the samples from the inputed data file.
true_pdf = qp.PDF(samples=z_trues)
# Create a qp.Ensamble objecct for each of the estimated pdfs.
estimated_pdfs = qp.Ensemble(gridded_pdfs.shape[0],
gridded=(z_array, gridded_pdfs))
return (estimated_pdfs, true_pdf)
def estimate(self, test_data):
pdf = []
# allow for either format for now
try:
d = test_data['i_mag']
except Exception:
d = test_data['mag_i_lsst']
numzs = len(d)
zmode = np.round(np.random.uniform(0.0, self.zmax, numzs), 3)
widths = self.width * (1.0 + zmode)
self.zgrid = np.linspace(0., self.zmax, self.nzbins)
for i in range(numzs):
pdf.append(norm.pdf(self.zgrid, zmode[i], widths[i]))
if self.output_format == 'qp':
qp_d = qp.Ensemble(qp.stats.norm,
data=dict(loc=zmode, scale=widths))
return qp_d
else:
pz_dict = {'zmode': zmode, 'pz_pdf': pdf}
return pz_dict
def main(argv):
starttime = time.time()
currenttime = time.time()
z_array, ID, szs, mags, pzs = ingdata.ingestflexzdata()
print "making Ensemble..."
approx_pdf = qp.Ensemble(pzs.shape[0], gridded=(z_array, pzs), procs=3)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
print "making EvaluateMetric Object"
bpzobj = inmet.EvaluateMetric(approx_pdf, szs)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
print "calculating PIT vals..."
bpzPIT = bpzobj.PIT()
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
#print "PIT!"
#print bpzPIT
#write to file
outfp = open("TESTPITVALS.out", "w")
outfp.write("#ID PIT\n")
for i in range(len(ID)):
outfp.write("%d %0.5f\n" % (ID[i], bpzobj.pitarray[i]))
outfp.close()
#QQplot
print "making QQ plot..."
qq_qtheory, qq_qdata = bpzobj.QQvectors(using='gridded',
dx=0.0001,
Nquants=1001)
outfp = open("TESTQQvectors.out", "w")
outfp.write("#qtheory qdata\n")
for i in range(len(qq_qtheory)):
outfp.write("%0.6f %0.6f\n" % (qq_qtheory[i], qq_qdata[i]))
outfp.close()
###all stats
outfp = open("TEST_STATS_KSCVMAD.out", "w")
ksstat, kspval = bpzobj.KS(using='gridded', dx=0.0001)
outfp.write("KSval: %.6g\n" % (ksstat))
outfp.write("KSpval: %.6g\n" % (kspval))
cvmstat, cvmpval = bpzobj.CvM(using='gridded', dx=0.0001)
outfp.write("CvMval: %.6g\n" % (cvmstat))
outfp.write("Cvmpval: %.6g\n" % (cvmpval))
vmn = 0.05
vmx = 0.95
adstat, adpval = bpzobj.AD(using='gridded', dx=0.0001, vmin=vmn, vmax=vmx)
outfp.write("ADval for vmin/vmax=%.3f %.3f: %.6g\n" % (vmn, vmx, adstat))
outfp.write("ADpval: %.6g\n" % (adpval))
vmn = 0.1
vmx = 0.9
adstat, adpval = bpzobj.AD(using='gridded', dx=0.0001, vmin=vmn, vmax=vmx)
outfp.write("ADval for vmin/vmax=%.3f %.3f: %.6g\n" % (vmn, vmx, adstat))
outfp.write("ADpval: %.6g\n" % (adpval))
vmn = 0.01
vmx = 0.99
adstat, adpval = bpzobj.AD(using='gridded', dx=0.0001, vmin=vmn, vmax=vmx)
outfp.write("ADval for vmin/vmax=%.3f %.3f: %.6g\n" % (vmn, vmx, adstat))
outfp.write("ADpval: %.6g\n" % (adpval))
print "finished\n"
def main(argv):
starttime = time.time()
currenttime = time.time()
#
z_array, ID, szs, mags, pzs = ingdata.ingestflexzdata()
print "making Ensemble..."
approx_pdf = qp.Ensemble(pzs.shape[0], gridded=(z_array, pzs), procs=3)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
print "making NzSumEvaluateMetric Object, with stacking..."
nzobj = inmet.NzSumEvaluateMetric(approx_pdf,
szs,
eval_grid=z_array,
using='gridded',
dx=0.0001)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
print "calculating Nz sum vectors..."
newgrid = np.arange(0.0, 2.0001, 0.001)
#create qp object of samples from the spec-z sample
szsamplepdf = qp.PDF(samples=szs)
specznz = szsamplepdf.evaluate(
newgrid, using='samples', vb=True,
norm=False)[1] #only grab the 2nd part of the tuples!
photznz = nzobj.stackpz.evaluate(
newgrid, using='gridded', vb=True,
norm=False)[1] #only grab the 2nd part of the tuples!
outfp = open("NZPLOT_vectors.out", "w")
outfp.write("#z_array speczNz photzNz\n")
for i in range(len(newgrid)):
outfp.write("%f %g %g\n" % (newgrid[i], specznz[i], photznz[i]))
outfp.close()
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
print "calculating KS stat..."
ks_stat, ks_pval = nzobj.NZKS()
print "ks_stat: %g\nks_pval: %g\n" % (ks_stat, ks_pval)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
cvm_stat, cvm_pval = nzobj.NZCVM()
print "cvm_stat: %g\cvm_pval: %g\n" % (cvm_stat, cvm_pval)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
zmin = min(szs)
zmax = max(szs)
delv = (zmax - zmin) / 200.
ad_stat, ad_pval = nzobj.NZAD(vmin=zmin, vmax=zmax, delv=delv)
print "ad_stat: %g\ad_pval: %g\n" % (ad_stat, ad_pval)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
ad_statx, ad_pvalx = nzobj.NZAD(vmin=0.0, vmax=2.0, delv=0.01)
print "ad_stat full range: %g\ad_pval: %g\n" % (ad_statx, ad_pvalx)
oldtime = currenttime
currenttime = time.time()
print "took %g seconds" % (currenttime - oldtime)
###all stats
outfp = open("NZ_STATS_KSCVMAD.out", "w")
outfp.write("KSval: %.6g\n" % (ks_stat))
outfp.write("KSpval: %.6g\n" % (ks_pval))
outfp.write("CvMval: %.6g\n" % (cvm_stat))
outfp.write("Cvmpval: %.6g\n" % (cvm_pval))
outfp.write("ADval for vmin/vmax=%.3f %.3f: %.6g\n" %
(zmin, zmax, ad_stat))
outfp.write("ADpval: %.6g\n" % (ad_pval))
outfp.write("ADval for vmin/vmax=0.0/2.0: %.6g\n" % (ad_statx))
outfp.write("ADpval: %.6g\n" % (ad_pvalx))
outfp.close()
print "finished\n"
