def fetch_and_shift_spectra(n_spectra,
outfile,
primtarget=TARGET_GALAXY,
zlim=(0, 0.7),
loglam_start=3.5,
loglam_end=3.9,
Nlam=1000):
"""
This function queries CAS for matching spectra, and then downloads
them and shifts them to a common redshift binning
"""
# First query for the list of spectra to download
plate, mjd, fiber = query_plate_mjd_fiber(n_spectra, primtarget, zlim[0],
zlim[1])
# Set up arrays to hold information gathered from the spectra
spec_cln = np.zeros(n_spectra, dtype=np.int32)
lineindex_cln = np.zeros(n_spectra, dtype=np.int32)
log_NII_Ha = np.zeros(n_spectra, dtype=np.float32)
log_OIII_Hb = np.zeros(n_spectra, dtype=np.float32)
z = np.zeros(n_spectra, dtype=np.float32)
zerr = np.zeros(n_spectra, dtype=np.float32)
spectra = np.zeros((n_spectra, Nlam), dtype=np.float32)
mask = np.zeros((n_spectra, Nlam), dtype=np.bool)
# Calculate new wavelength coefficients
new_coeff0 = loglam_start
new_coeff1 = (loglam_end - loglam_start) / Nlam
# Now download all the needed spectra, and resample to a common
# wavelength bin.
n_spectra = len(plate)
num_skipped = 0
i = 0
while i < n_spectra:
sys.stdout.write(' %i / %i spectra\r' % (i + 1, n_spectra))
sys.stdout.flush()
try:
spec = fetch_sdss_spectrum(plate[i], mjd[i], fiber[i])
except HTTPError:
num_skipped += 1
print("%i, %i, %i not found" % (plate[i], mjd[i], fiber[i]))
i += 1
continue
spec_rebin = spec.restframe().rebin(new_coeff0, new_coeff1, Nlam)
if np.all(spec_rebin.spectrum == 0):
num_skipped += 1
print("%i, %i, %i is all zero" % (plate[i], mjd[i], fiber[i]))
i += 1
continue
spec_cln[i] = spec.spec_cln
lineindex_cln[i], (log_NII_Ha[i], log_OIII_Hb[i])\
= spec.lineratio_index()
z[i] = spec.z
zerr[i] = spec.zerr
spectra[i] = spec_rebin.spectrum
mask[i] = spec_rebin.compute_mask(0.5, 5)
i += 1
sys.stdout.write('\n')
N = i
print(" %i spectra skipped" % num_skipped)
print(" %i spectra processed" % N)
print("saving to %s" % outfile)
np.savez(outfile,
spectra=spectra[:N],
mask=mask[:N],
coeff0=new_coeff0,
coeff1=new_coeff1,
spec_cln=spec_cln[:N],
lineindex_cln=lineindex_cln[:N],
log_NII_Ha=log_NII_Ha[:N],
log_OIII_Hb=log_OIII_Hb[:N],
z=z[:N],
zerr=zerr[:N])
import sys
import numpy as np
import matplotlib.pyplot as plt
from astroML.datasets import fetch_sdss_spectrum
from astroML.datasets.tools import query_plate_mjd_fiber, TARGET_GALAXY_RED
from specanalysis import SpecMeanAggregator
primtarget=TARGET_GALAXY_RED
zlim=(0.2, 0.6)
plate, mjd, fiber = query_plate_mjd_fiber(100, primtarget, zlim[0], zlim[1])
agg = SpecMeanAggregator()
lam = agg.lam
zdist = []
for plate_n, mjd_n, fiber_n in zip(plate, mjd, fiber):
sys.stdout.write("{0}.{1}.{2} \r".format(plate_n, mjd_n, fiber_n))
sys.stdout.flush()
spec = fetch_sdss_spectrum(plate_n, mjd_n, fiber_n)
zdist.append(spec.z)
agg.add_spec(spec)
sys.stdout.write('\n')
spec, dspec = agg.reduce()
def fetch_and_shift_spectra(n_spectra,
outfile,
primtarget=TARGET_GALAXY,
zlim=(0, 0.7),
loglam_start=3.5,
loglam_end=3.9,
Nlam=1000):
"""
This function queries CAS for matching spectra, and then downloads
them and shifts them to a common redshift binning
"""
# First query for the list of spectra to download
plate, mjd, fiber = query_plate_mjd_fiber(n_spectra, primtarget,
zlim[0], zlim[1])
# Set up arrays to hold information gathered from the spectra
spec_cln = np.zeros(n_spectra, dtype=np.int32)
lineindex_cln = np.zeros(n_spectra, dtype=np.int32)
log_NII_Ha = np.zeros(n_spectra, dtype=np.float32)
log_OIII_Hb = np.zeros(n_spectra, dtype=np.float32)
z = np.zeros(n_spectra, dtype=np.float32)
zerr = np.zeros(n_spectra, dtype=np.float32)
spectra = np.zeros((n_spectra, Nlam), dtype=np.float32)
mask = np.zeros((n_spectra, Nlam), dtype=np.bool)
# Calculate new wavelength coefficients
new_coeff0 = loglam_start
new_coeff1 = (loglam_end - loglam_start) / Nlam
# Now download all the needed spectra, and resample to a common
# wavelength bin.
n_spectra = len(plate)
num_skipped = 0
i = 0
while i < n_spectra:
sys.stdout.write(' %i / %i spectra\r' % (i + 1, n_spectra))
sys.stdout.flush()
try:
spec = fetch_sdss_spectrum(plate[i], mjd[i], fiber[i])
except HTTPError:
num_skipped += 1
print("%i, %i, %i not found" % (plate[i], mjd[i], fiber[i]))
i += 1
continue
spec_rebin = spec.restframe().rebin(new_coeff0, new_coeff1, Nlam)
if np.all(spec_rebin.spectrum == 0):
num_skipped += 1
print("%i, %i, %i is all zero" % (plate[i], mjd[i], fiber[i]))
continue
spec_cln[i] = spec.spec_cln
lineindex_cln[i], (log_NII_Ha[i], log_OIII_Hb[i])\
= spec.lineratio_index()
z[i] = spec.z
zerr[i] = spec.zerr
spectra[i] = spec_rebin.spectrum
mask[i] = spec_rebin.compute_mask(0.5, 5)
i += 1
sys.stdout.write('\n')
N = i
print(" %i spectra skipped" % num_skipped)
print(" %i spectra processed" % N)
print("saving to %s" % outfile)
np.savez(outfile,
spectra=spectra[:N],
mask=mask[:N],
coeff0=new_coeff0,
coeff1=new_coeff1,
spec_cln=spec_cln[:N],
lineindex_cln=lineindex_cln[:N],
log_NII_Ha=log_NII_Ha[:N],
log_OIII_Hb=log_OIII_Hb[:N],
z=z[:N],
zerr=zerr[:N])
def fetch_and_shift_spectra(n_spectra,
outfile,
primtarget=TARGET_GALAXY,
zlim=(0, 0.7),
loglam_start=3.5,
loglam_end=3.9,
Nlam=1000):
"""
This function queries CAS for matching spectra, and then downloads
them and shifts them to a common redshift binning
"""
# First query for the list of spectra to download
plate, mjd, fiber = query_plate_mjd_fiber(n_spectra, primtarget,
zlim[0], zlim[1])
# Set up arrays to hold information gathered from the spectra
spec_cln = np.zeros(n_spectra, dtype=np.int32)
lineindex_cln = np.zeros(n_spectra, dtype=np.int32)
log_NII_Ha = np.zeros(n_spectra, dtype=np.float32)
log_OIII_Hb = np.zeros(n_spectra, dtype=np.float32)
z = np.zeros(n_spectra, dtype=np.float32)
zerr = np.zeros(n_spectra, dtype=np.float32)
spectra = np.zeros((n_spectra, Nlam), dtype=np.float32)
mask = np.zeros((n_spectra, Nlam), dtype=np.bool)
specerr = np.zeros((n_spectra, Nlam), dtype=np.float32)
# also save plate, mjd, fiber to allow reference to SDSS data
plates = np.zeros(n_spectra, dtype=np.int32)
mjds = np.zeros(n_spectra, dtype=np.int32)
fibers = np.zeros(n_spectra, dtype=np.int32)
# Calculate new wavelength coefficients
new_coeff0 = loglam_start
new_coeff1 = (loglam_end - loglam_start) / Nlam
# Now download all the needed spectra, and resample to a common
# wavelength bin.
n_spectra = len(plate)
num_skipped = 0
# changed counter and loop so that skipped spectra do not create gaps in arrays
j = 0
for i in range(n_spectra):
sys.stdout.write(' %i / %i spectra\r' % (i + 1, n_spectra))
sys.stdout.flush()
try:
spec = fetch_sdss_spectrum(plate[i], mjd[i], fiber[i], data_home='/epyc/users/sportill/specAE/cache')
except HTTPError:
num_skipped += 1
print("%i, %i, %i not found" % (plate[i], mjd[i], fiber[i]))
continue
spec_rebin = spec.restframe().rebin(new_coeff0, new_coeff1, Nlam)
if spec.z < zlim[0] or spec.z > zlim[1]:
num_skipped += 1
print("%i, %i, %i outside redshift range" % (plate[i], mjd[i], fiber[i]))
continue
if np.all(spec_rebin.spectrum == 0):
num_skipped += 1
print("%i, %i, %i is all zero" % (plate[i], mjd[i], fiber[i]))
continue
#if spec.spec_cln < 2 or spec.spec_cln > 3:
# num_skipped += 1
# print("%i, %i, %i is not a galaxy spectrum" % (plate[i], mjd[i], fiber[i]))
# continue
spec_cln[j] = spec.spec_cln
lineindex_cln[j], (log_NII_Ha[j], log_OIII_Hb[j])\
= spec.lineratio_index()
z[j] = spec.z
zerr[j] = spec.zerr
spectra[j] = spec_rebin.spectrum
mask[j] = spec_rebin.compute_mask(0.5, 5)
assert((mask[j] == 0).any())
specerr[j] = spec_rebin.error
plates[j] = plate[i]
mjds[j] = mjd[i]
fibers[j] = fiber[i]
j += 1
sys.stdout.write('\n')
N = j
print(" %i spectra skipped" % num_skipped)
print(" %i spectra processed" % N)
print("saving to %s" % outfile)
np.savez(outfile,
spectra=spectra[:N],
mask=mask[:N],
spec_err=specerr[:N],
coeff0=new_coeff0,
coeff1=new_coeff1,
spec_cln=spec_cln[:N],
lineindex_cln=lineindex_cln[:N],
log_NII_Ha=log_NII_Ha[:N],
log_OIII_Hb=log_OIII_Hb[:N],
z=z[:N],
zerr=zerr[:N],
plate=plates[:N],
mjd=mjds[:N],
fiber=fibers[:N])