Comparing G16 vs ML for the Referee

In [17]:

    

# imports
import numpy as np
import os, sys

from linetools.utils import dv_from_z

from dla_cnn.io import load_ml_dr7, load_ml_dr12, load_garnett16
from dla_cnn.catalogs import match_boss_catalogs

sys.path.append(os.path.abspath("../Analysis/py"))
import defs as analy_defs


    

In [2]:

    

g16_pcut = analy_defs.g16_pcut
dztoler = 0.015
g16_pcut


    

    
Out[2]:





0.95

In [3]:

    

# Load BOSS ML
_, dr12_abs = load_ml_dr12()
# Cut on DLA
dlas = dr12_abs['NHI'] >= 20.3
no_bals = dr12_abs['flg_BAL'] == 0
high_conf = dr12_abs['conf'] > 0.9
#
zem = (dr12_abs['zem'] > dr12_abs['zabs']) & (dr12_abs['zem'] > 2.15)  # G16 cut on zem
zcut = dr12_abs['zabs'] > 2.15
zprox = dr12_abs['zabs'] < (dr12_abs['zem'] - 3000./3e5)
# cut
dr12_cut = dlas & no_bals & high_conf & zem & zcut  & zprox
dr12_dla = dr12_abs[dr12_cut]
len(dr12_dla)


    

    
Out[3]:





15922

In [4]:

    

g16_abs = load_garnett16()
g_dlas = g16_abs['log.NHI'] >= 20.3
g_conf = g16_abs['pDLAD'] >= g16_pcut
# Cut
g_cut = g_dlas & g_conf
g16_dlas = g16_abs[g_cut]
len(g16_dlas)


    

    




/home/xavier/.pyenv/versions/anaconda3-4.3.1/lib/python3.6/site-packages/ipykernel_launcher.py:2: RuntimeWarning: invalid value encountered in greater_equal
  
/home/xavier/.pyenv/versions/anaconda3-4.3.1/lib/python3.6/site-packages/ipykernel_launcher.py:3: RuntimeWarning: invalid value encountered in greater_equal
  This is separate from the ipykernel package so we can avoid doing imports until






    
Out[4]:





18173

In [5]:

    

dr12_to_g16 = match_boss_catalogs(dr12_dla, g16_dlas, dztoler=dztoler)
matched = dr12_to_g16 >= 0
g16_idx = dr12_to_g16[matched]
print("We matched {:d} of {:d} DLAs between high quality ML and G16 within dz={:g}".format(
    np.sum(matched), np.sum(dr12_cut), dztoler))

high_conf = (dr12_dla['conf'][matched] > 0.9) & (g16_dlas['pDLAD'][g16_idx] > analy_defs.g16_pcut)
print("Of these, {:d} are high confidence in both".format(np.sum(high_conf)))


    

    




We matched 10205 of 15922 DLAs between high quality ML and G16 within dz=0.015
Of these, 10205 are high confidence in both

In [6]:

    

NHI = dr12_dla['NHI'][matched]
dNHI = dr12_dla['NHI'][matched] - g16_dlas['log.NHI'][g16_idx]


    

In [7]:

    

large_dNHI = np.abs(dNHI) > 0.5
np.sum(large_dNHI)


    

    
Out[7]:





133

In [27]:

    

not_matched = dr12_to_g16 < 0
np.sum(not_matched)
#
not_idx = np.where(not_matched)[0]


    

In [29]:

    

jj = not_idx[0]
dr12_dla[jj]


    

    
Out[29]:




<Row index=1>

Plate
Fiber
MJD
RA
DEC
zem
zabs
NHI
sigNHI
conf
flg_BAL
SNR
int64
int64
int64
float64
float64
float64
float64
float64
float64
float64
int64
float64
3587
617
55182
8.0754
0.1354
3.78847770165
2.95625578063
20.6791075122
0.0624429993331
0.9625
0
1.3497

In [30]:

    

jj


    

    
Out[30]:





1

In [33]:

    

jj1 = match_boss_catalogs(dr12_dla[jj:jj+2], g16_abs, dztoler=1.)  # Needed 2 for the code to run
jj1


    

    
Out[33]:





array([ 9039, 11200])

In [34]:

    

g16_abs[9039]


    

    
Out[34]:




<Row index=9039 masked=True>

THINGID
SDSS
Plate
MJD
Fiber
RAdeg
DEdeg
z_QSO
SNR
flg_BAL
zmin
zmax
log.pnDLA
log.pDLA
log.pDnDLA
log.pDDLA
pnDLAD
pDLAD
z_DLA
log.NHI
int64
str18
int64
int64
int64
float64
float64
float64
float64
int64
float64
float64
float64
float64
float64
float64
float64
float64
float64
float64
96897814
003218.09+000807.3
3587
55182
617
8.0753961
0.1353659
3.7994
1.3497
0
2.6096
3.7894
-0.10889
-2.2714
-1237.94
-1228.96
0.0010918
0.998908
2.8347
20.301

In [19]:

    

dv_from_z(2.956255, 2.8347)


    

    
Out[19]:





$9352.4873 \; \mathrm{\frac{km}{s}}$

In [16]:

    

g16_to_dr12 = match_boss_catalogs(g16_dlas, dr12_dla, dztoler=dztoler, reverse=True)
matched2 = g16_to_dr12 >= 0
dr12_idx = g16_to_dr12[matched2]
print("We matched {:d} of {:d} DLAs between high quality ML and G16 within dz={:g}".format(
    np.sum(matched2), np.sum(g_cut), dztoler))


    

    




We matched 10205 of 18173 DLAs between high quality ML and G16 within dz=0.015

In [15]:

    

matched2


    

    
Out[15]:





array([ True,  True,  True, ...,  True,  True,  True], dtype=bool)

In [ ]: