def variable_set(name, value):
"""
Set a persistent variable.
@param name
The name of the variable to set.
@param value
The value to set. This can be any PHP data type; these functions take care
of serialization as necessary.
"""
lib_database.merge("variable").key({"name": name}).fields({"value": php.serialize(value)}).execute()
cache_clear_all("variables", "cache")
settings.conf[name] = value
def variable_set(name, value):
"""
Set a persistent variable.
@param name
The name of the variable to set.
@param value
The value to set. This can be any PHP data type; these functions take care
of serialization as necessary.
"""
lib_database.merge('variable').key({'name' : name}).fields(\
{'value' : php.serialize(value)}).execute()
cache_clear_all('variables', 'cache')
settings.conf[name] = value
def find_channels():
'''
Function to determine the channel range needed for input during extraction.
Requires the file energy_conversion_table.txt to determine the initial
channel selection.
'''
purpose = 'Finding the correct channels for later extraction'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from collections import defaultdict
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
d = defaultdict(list)
for obsid, group in db.groupby(['obsids']):
group = group.drop_duplicates('paths_data')
print obsid
for mode, path, time, bit in zip(group.modes, group.paths_data,
group.times, group.bitsize):
if mode == 'std1':
d['paths_data'].append(path)
d['energy_channels'].append('INDEF')
continue
# Determine channels according to epoch
abs_channels = calculated_energy_range(time, MIN_E, MAX_E, bit)
final_channels = abs_channels
# Check in which fashion the channels are binned, and return these
if mode == 'event' or mode == 'binned':
bin_channels = get_channel_range(mode, abs_channels, path, bit)
final_channels = bin_channels
print ' ', mode, '-->', final_channels
d['paths_data'].append(path)
d['energy_channels'].append(final_channels)
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db, df, ['energy_channels'])
database.save(db)
logs.stop_logging()
def create_power_colours():
'''
Function to generate power spectral density based on RXTE lightcurves.
'''
# Let the user know what's going to happen
purpose = 'Creating Power Colours'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from collections import defaultdict
from math import isnan
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
# Get database
os.chdir(paths.data)
db = pd.read_csv(paths.database)
d = defaultdict(list)
for ps, group in db.groupby('power_spectra'):
# Determine parameters
obsid = group.obsids.values[0]
path_obsid = group.paths_obsid.values[0]
mode = group.modes.values[0]
res = group.resolutions.values[0]
print obsid, mode, res
# Calculate power colour
output = power_colour(ps)
if output:
pc1, pc1err, pc2, pc2err, constraint = output
d['power_spectra'].append(ps)
d['pc1'].append(pc1)
d['pc1_err'].append(pc1err)
d['pc2'].append(pc2)
d['pc2_err'].append(pc2err)
d['lt3sigma'].append(constraint)
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db, df,
['pc1', 'pc1_err', 'pc2', 'pc2_err', 'lt3sigma'])
print 'DBNUNIQUE\n', db.apply(pd.Series.nunique)
database.save(db)
logs.stop_logging()
def cut_xray_flares():
'''
Function to find X-ray flares in a light curve by finding when the rate
exceeds more than 7sigma, and then cut around it. Write output to a file
in an obsid-folder with the name corrected_rate_minus_xray_flare_
<timingresolution>.dat if an X-ray flare was detected
'''
# Let the user know what's going to happen
purpose = 'Determining X-ray flares'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from collections import defaultdict
from math import isnan
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
d = defaultdict(list)
for path_lc, group in db.groupby('bkg_corrected_lc'):
# Set parameters
obsid = group.obsids.values[0]
path_bkg = group.rebinned_bkg.values[0]
res = group.resolutions.values[0]
mode = group.modes.values[0]
path_obsid = group.paths_obsid.values[0]
print obsid, mode, res
# Calculate whether flare present
result = cut_flare(path_obsid, path_lc, path_bkg, res, mode)
if result:
print 'Flare between:', result[2]
d['bkg_corrected_lc'].append(path_lc)
d['lc_no_flare'].append(result[0])
d['bkg_no_flare'].append(result[1])
d['flare_times'].append(result[2])
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db, df, ['lc_no_flare', 'bkg_no_flare', 'flare_times'])
database.save(db)
logs.stop_logging()
def analyze(self, x):
if isinstance(x, list):
return [self.analyze(y) for y in x]
if isinstance(x, AudioData):
return self.process(x)
if isinstance(x, tuple):
return self.analyze(*x)
log.info("Grabbing stream...", uid=x.id)
laf = LocalAudioStream(self.get_stream(x))
setattr(laf, "_metadata", x)
Database().ensure(merge(x, laf.analysis))
return self.process(laf)
def analyze(self, x):
if isinstance(x, list):
return [self.analyze(y) for y in x]
if isinstance(x, AudioData):
return self.process(x)
if isinstance(x, tuple):
return self.analyze(*x)
log.info("Grabbing stream...", uid=x.id)
laf = LocalAudioStream(self.get_stream(x))
# To ensure that we have output,
try:
# Read a single sample from the output to ensure
# FFMPEG can read *any* audio for us.
laf[0:1]
except (IOError, ValueError):
raise ValueError("Could not read any samples from FFMPEG!")
setattr(laf, "_metadata", x)
Database().ensure(merge(x, laf.analysis))
return self.process(laf)
def analyze(self, x):
if isinstance(x, list):
return [self.analyze(y) for y in x]
if isinstance(x, AudioData):
return self.process(x)
if isinstance(x, tuple):
return self.analyze(*x)
log.info("Grabbing stream...", uid=x.id)
laf = LocalAudioStream(self.get_stream(x))
# To ensure that we have output,
try:
# Read a single sample from the output to ensure
# FFMPEG can read *any* audio for us.
laf[0:1]
except (IOError, ValueError):
raise ValueError("Could not read any samples from FFMPEG!")
setattr(laf, "_metadata", x)
Database().ensure(merge(x, laf.analysis))
return self.process(laf)
def spacecraft_filters():
'''
Function to run the ftool maketime over all filter files (.xfl.gz files).
Creates time_filter.gti files and updates database with path to gti files
'''
purpose = 'Create time filters'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
from astropy.io import fits
import os
import pandas as pd
import glob
import numpy as np
from collections import defaultdict
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
# Run maketime for each obsid
d = defaultdict(list)
for obsid, group in db.groupby(['obsids']):
print obsid
# Check whether an observation has high count rates
lc = group.paths_obsid.values[0] + 'stdprod/xp' + obsid.replace(
'-', '') + '_n1.lc.gz'
try:
hdulist = fits.open(lc)
data = hdulist[1].data
_, rate, _, _, _ = zip(*data)
mean = np.nanmean(rate)
except IOError:
mean = 0.
f = group.paths_obsid.values[0] + 'stdprod/x' + obsid.replace(
'-', '') + '.xfl.gz'
gti = group.paths_obsid.values[0] + 'time_filter.gti'
# Remove previous version (maketime doesn't like them)
try:
os.remove(gti)
except OSError:
pass
# Selection expression for maketime
sel = (
'elv.gt.10.and.' + 'offset.lt.0.02.and.' + 'num_pcu_on.ge.1.and.' +
'(time_since_saa.gt.10.or.' + #South Atlantic Anomality
'time_since_saa.lt.0.0)')
if mean <= 500:
sel += '.and.electron2.lt.0.1'
command = [
'maketime',
f, # Name of FITS file
gti, # Name of output FITS file
sel, # Selection expression
'compact=no', # Flag yes, if HK format is compact
'time="TIME"'
] # Column containing HK parameter times
if os.path.exists(f):
shell.execute(command)
# Check if gti file is empty (exclude if so)
hdulist = fits.open(gti)
data = hdulist[1].data
if len(data) == 0:
gti = float('nan')
else:
git = float('nan')
d['obsids'].append(obsid)
d['filters'].append(f)
d['gti'].append(gti)
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db, df, ['filters', 'gti'])
database.save(db)
logs.stop_logging()
def set(cid, data, table = 'cache', expire = None, headers = None):
"""
Store data in the persistent cache.
The persistent cache is split up into four database
tables. Contributed plugins can add additional tables.
'cache_page': This table stores generated pages for anonymous
users. This is the only table affected by the page cache setting on
the administrator panel.
'cache_menu': Stores the cachable part of the users' menus.
'cache_filter': Stores filtered pieces of content. This table is
periodically cleared of stale entries by cron.
'cache': Generic cache storage table.
The reasons for having several tables are as follows:
- smaller tables allow for faster selects and inserts
- we try to put fast changing cache items and rather static
ones into different tables. The effect is that only the fast
changing tables will need a lot of writes to disk. The more
static tables will also be better cachable with MySQL's query cache
@param cid
The cache ID of the data to store.
@param data
The data to store in the cache. Complex data types will be
automatically serialized before insertion.
Strings will be stored as plain text and not serialized.
@param table
The table table to store the data in. Valid core values are 'cache_filter',
'cache_menu', 'cache_page', or 'cache'.
@param expire
One of the following values:
- CACHE_PERMANENT: Indicates that the item should never be removed unless
explicitly told to using cache_clear_all() with a cache ID.
- CACHE_TEMPORARY: Indicates that the item should be removed at the next
general cache wipe.
- A Unix timestamp: Indicates that the item should be kept at least until
the given time, after which it behaves like CACHE_TEMPORARY.
@param headers
A string containing HTTP php.header information for cached pages.
"""
if expire is None:
expire = lib_bootstrap.CACHE_PERMANENT
fields = {
'serialized' : 0,
'created' : REQUEST_TIME,
'expire' : expire,
'headers' : headers
}
if (not php.is_string(data)):
fields['data'] = php.serialize(data)
fields['serialized'] = 1
else:
fields['data'] = data
fields['serialized'] = 0
lib_database.merge(table).key({'cid' : cid}).fields(fields).execute()
def determine_info():
'''
Function to split out the files created by Phil's script in find_data_files
over each obsid folder, allowing code to be executed per obsid. Also
creates a file with information on each observation
'''
purpose = 'Finding information on data files'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from collections import defaultdict
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
with open(paths.obsid_list, 'r') as f:
obsids = [l.strip() for l in f.readlines()]
db = pd.read_csv(paths.database)
db['P'] = ['P' + o.split('-')[0] for o in db['obsids']]
db['paths_obsid'] = paths.data + db['P'] + '/' + db['obsids'] + '/'
# Find all files created by Phil's xtescan2 script
all_files = []
for f in db['P'].unique():
p = os.path.join(paths.data, f, paths.selection + '*.list*')
all_files.extend(glob.glob(p))
# Remove all 500us event files
# See above Table 1 on heasarc.gsfc.nasa.gov/docs/xte/recipes/bitmasks.html
all_files = [a for a in all_files if '500us' not in a]
d = defaultdict(list)
# Split out values per obsid per mode
for a in all_files:
mode = a.split('.')[-2]
if 'E_' in mode:
with open(a) as e:
for line in e:
obsid = line.split('/')[0]
path = os.getcwd() + '/P' + obsid.split(
'-')[0] + '/' + line.split(' ')[0]
time = line.split(' ')[2]
resolution = line.split(' ')[1].split('_')[1]
d['obsids'].append(obsid)
d['paths_data'].append(path)
d['times'].append(time)
d['resolutions'].append(resolution)
d['modes'].append('event')
d['bitsize'].append(float('NaN'))
if 'Standard2f' in mode:
with open(a) as s:
for i, line in enumerate(s):
obsid = line.split('/')[0]
path = os.getcwd() + '/P' + obsid.split(
'-')[0] + '/' + line.split(' ')[0].split('.')[0]
time = line.split(' ')[2]
d['obsids'].append(obsid)
d['paths_data'].append(path)
d['times'].append(time)
d['resolutions'].append('16s')
d['modes'].append('std2')
d['bitsize'].append(float('NaN'))
if 'Standard1b' in mode:
with open(a) as s:
for i, line in enumerate(s):
obsid = line.split('/')[0]
path = os.getcwd() + '/P' + obsid.split(
'-')[0] + '/' + line.split(' ')[0].split('.')[0]
time = line.split(' ')[2]
d['obsids'].append(obsid)
d['paths_data'].append(path)
d['times'].append(time)
d['resolutions'].append('125ms')
d['modes'].append('std1')
d['bitsize'].append(float('NaN'))
if 'GoodXenon1' in mode:
with open(a) as g:
for line in g:
obsid = line.split('/')[0]
path = os.getcwd() + '/P' + obsid.split(
'-')[0] + '/' + line.split(' ')[0].split('.')[0]
time = line.split(' ')[2]
resolution = line.split(' ')[1].split('_')[1]
d['obsids'].append(obsid)
d['paths_data'].append(path)
d['times'].append(time)
d['resolutions'].append(resolution)
d['modes'].append('gx1')
d['bitsize'].append(float('NaN'))
if 'GoodXenon2' in mode:
with open(a) as g:
for line in g:
obsid = line.split('/')[0]
path = os.getcwd() + '/P' + obsid.split(
'-')[0] + '/' + line.split(' ')[0].split('.')[0]
time = line.split(' ')[2]
resolution = line.split(' ')[1].split('_')[1]
d['obsids'].append(obsid)
d['paths_data'].append(path)
d['times'].append(time)
d['resolutions'].append(resolution)
d['modes'].append('gx2')
d['bitsize'].append(float('NaN'))
if mode.startswith('B_'):
with open(a) as e:
for line in e:
obsid = line.split('/')[0]
path = os.getcwd() + '/P' + obsid.split(
'-')[0] + '/' + line.split(' ')[0]
time = line.split(' ')[2]
resolution = line.split(' ')[1].split('_')[1]
bitsize = mode.split('_')[-1]
d['obsids'].append(obsid)
d['paths_data'].append(path)
d['times'].append(time)
d['resolutions'].append(resolution)
d['modes'].append('binned')
d['bitsize'].append(bitsize)
# Add information to database
new_data = pd.DataFrame(d)
new_c = ['paths_data', 'times', 'resolutions', 'modes', 'bitsize']
db = database.merge(db, new_data, new_c)
d = defaultdict(list)
# List all data files per obsid, per mode, per res
for obsid in db.obsids.unique():
print obsid
condo = (db.obsids == obsid)
for mode in db[condo].modes.unique():
condm = condo & (db.modes == mode)
for res in db[condm].resolutions.unique():
condr = condm & (db.resolutions == res)
sf = mode
# Ensure goodxenon files are listed together
if mode[:2] == 'gx':
condr = condo & (
(db.modes == 'gx1') |
(db.modes == 'gx2')) & (db.resolutions == res)
sf = 'gx'
# Create subdatabase of values
sdb = db[condr]
sdb.drop_duplicates('paths_data')
# Write paths to file per obsid per mode per resolution
filename = 'paths_' + sf + '_' + res
path_to_output = sdb.paths_obsid.values[0] + filename
# Remove previous versions
data = list(set(sdb.paths_data))
with open(path_to_output, 'w') as text:
text.write('\n'.join(data) + '\n')
d['obsids'].append(obsid)
d['modes'].append(mode)
d['resolutions'].append(res)
d['paths_po_pm_pr'].append(path_to_output)
#Add to database
new_data = pd.DataFrame(d)
db = database.merge(db, new_data, ['paths_po_pm_pr'])
unfound_obsids = db[db.modes.isnull()].obsids.values
if len(unfound_obsids) > 0:
print 'ERROR: NO DATA FOR THESE OBSIDS', unfound_obsids
db = db[db.modes.notnull()]
database.save(db)
logs.stop_logging()
def create_response():
'''
Function to create responses for spectra
'''
purpose = 'Creating responses'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from astropy.io import fits
from collections import defaultdict
from math import isnan
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
# Only want std2 data
d = defaultdict(list)
for sp, group in db[(db.modes == 'std2')].groupby('spectra'):
# Determine variables
obsid = group.obsids.values[0]
path_obsid = group.paths_obsid.values[0]
bkg_sp = group.spectra_bkg.values[0]
fltr = group.filters.values[0]
# Check whether extracting per layer
layers = False
if sp.endswith('_per_layer.pha'):
layers = True
# Setup names
# Must be short, otherwise it can't be written in the header of the
# spectrum file
out = path_obsid + 'sp.rsp'
print obsid
# Set up the command for pcarsp
pcarsp = [
'pcarsp',
'-f' + sp, #Input
'-a' + fltr, #Filter file
'-n' + out, #Output file
'-s'
] #Use smart std2 mode
# Create responses
shell.execute(pcarsp)
#shell.execute(bkgpcarsp)
# pcarsp doesn't allow for long file name to be written in the header
# of the spectrum, so have to manually do it
# Must have astropy version >1.0. Trust me.
hdulist = fits.open(sp, mode='update')
hdu = hdulist[1]
hdu.header['RESPFILE'] = out
hdulist.flush() #.writeto(sp, clobber=True)
d['spectra'].append(sp)
d['rsp'].append(out)
#d['rsp_bkg'].append(out_bkg)
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db, df, ['rsp'])
database.save(db)
logs.stop_logging()
def create_power_spectra():
'''
Function to generate power spectral density based on RXTE lightcurves.
'''
# Let the user know what's going to happen
purpose = 'Creating Power Spectra'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from collections import defaultdict
from math import isnan
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
# Get database
os.chdir(paths.data)
db = pd.read_csv(paths.database)
d = defaultdict(list)
for path_lc, group in db.groupby('bkg_corrected_lc'):
# Check whether x-ray flare was present
path_bkg = group.rebinned_bkg.values[0]
flare = False
if 'lc_no_flare' in group:
if pd.notnull(group.lc_no_flare.values[0]):
flare = True
former_lc = path_lc
path_lc = group.lc_no_flare.values[0]
path_bkg = group.bkg_no_flare.values[0]
# Determine parameters
obsid = group.obsids.values[0]
path_obsid = group.paths_obsid.values[0]
mode = group.modes.values[0]
res = group.resolutions.values[0]
if mode == 'gx2':
mode = 'gx'
print obsid, mode, res
# Find std1 path
try:
std1 = db[((db.obsids == obsid) &
(db.modes == 'std1'))].paths_data.iloc[0]
path_std1 = glob.glob(std1 + '*')[0]
except IndexError:
print(
'ERROR: No std1 file for this obsid. Aborting power spectrum.')
continue
# Determine the maximum number of pcus on during the observation
npcu = group.npcu.values[0]
# Calculate power spectrum
output = power_spectrum(path_lc, path_bkg, path_std1, npcu)
if output:
ps, ps_er, ps_sq, num_seg, freq, freq_er = output
path_ps = path_obsid + mode + '_' + res + '.ps'
# Create file within obsid folder
with open(path_ps, 'w') as f:
# For each value in a power spectrum
for i, value in enumerate(ps):
line = (repr(value) + ' ' + repr(ps_er[i]) + ' ' +
repr(freq[i]) + ' ' + repr(freq_er[i]) + ' ' +
repr(ps_sq[i]) + ' ' + repr(num_seg) + '\n')
f.write(line)
if not flare:
d['bkg_corrected_lc'].append(path_lc)
d['lc_no_flare'].append(float('NaN'))
d['power_spectra'].append(path_ps)
else:
d['bkg_corrected_lc'].append(former_lc)
d['lc_no_flare'].append(path_lc)
d['power_spectra'].append(path_ps)
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db, df, ['power_spectra'])
database.save(db)
logs.stop_logging()
def pcu_filters():
'''
Function to determine if pcu changes have take place, and if so cut 32s
around them. Used the times scripts to save the times of pcu changes to
a database
'''
purpose = 'Determine if number of PCUs has changed'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from astropy.io import fits
from collections import defaultdict
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
d = defaultdict(list)
for obsid, group in db.groupby(['obsids']):
filt = group.filters.values[0]
# Import data
try:
hdulist = fits.open(filt)
except IOError:
print 'ERROR: File not found for obsid ', obsid
continue
tstart = hdulist[0].header['TSTART']
timezero = hdulist[0].header['TIMEZERO']
num_pcu_on = hdulist[1].data.field('NUM_PCU_ON')
time = hdulist[1].data.field('Time')
# Remember time has an offset due to spacecraft time
#time -= time[0]
time += timezero
# Counter to determine when the number of pcus changes
pcu = num_pcu_on[0]
# The acceptable time range
t_range = repr(time[0]) + '-'
for i, n in enumerate(num_pcu_on):
# Check if the number of pcus has changed
if n != pcu:
pcu = n
# Cut 32s around it
low_t = time[i] - 16
high_t = time[i] + 16
previous_t = float(t_range.split('-')[-2].split(',')[-1])
# Check whether there's any overlap
if low_t <= previous_t:
# Replace the previous upper time if there is
t_range = t_range.replace(
t_range.split('-')[-2].split(',')[-1], repr(high_t))
continue
else:
t_range += repr(low_t) + ','
# Check whether you've reached the end
if high_t > time[-1]:
t_range = t_range[:-1]
break
else:
t_range += repr(high_t) + '-'
if t_range[-1] == '-':
t_range += repr(time[-1])
print obsid, '-->', t_range
filename = group.paths_obsid.values[0] + 'times_pcu.dat'
with open(filename, 'w') as f:
text = t_range.replace(',', '\n').replace('-', ' ')
f.write(text + '\n')
# Note that I'm only saving the maximum pcu number
nupcu = max(num_pcu_on[1:])
d['npcu'].append(nupcu)
d['obsids'].append(obsid)
d['times_obsid'].append(str(tstart + timezero) + '-' + str(time[-1]))
d['times_pcu'].append(filename)
# Add starting times of each obsid to database
df = pd.DataFrame(d)
db = database.merge(db, df, ['times_obsid', 'times_pcu', 'npcu'])
database.save(db)
logs.stop_logging()
def correct_for_background():
'''
Function to intrapolate background files to correct various mode files for
the corresponding background count rate
'''
purpose = 'Accounting for backgrounds'
print len(purpose)*'=' + '\n' + purpose + '\n' + len(purpose)*'='
import os
import pandas as pd
import glob
from collections import defaultdict
from math import isnan
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
d = defaultdict(list)
for path_lc, group in db.groupby('lightcurves'):
# Layer background subtraction is done in xspec, so skip these
if path_lc.endswith('per_layer.lc'):
continue
obsid = group.obsids.values[0]
path_obsid = group.paths_obsid.values[0]
path_bkg = group.lightcurves_bkg.values[0]
res = group.resolutions.values[0]
mode = group.modes.values[0]
# Std2 files won't have a high enough time resolution to create
# power colours in the high band
if mode == 'std2' or mode == 'std1':
continue
if (mode == 'gx1' or mode == 'gx2'):
mode = 'gx'
print obsid, mode, res
# Rebin, and create a corrected version
paths = rebin(path_obsid, path_lc, path_bkg, mode, res)
rebinned_bkg = paths[0]
bkg_corrected_lc = paths[1]
d['lightcurves'].append(path_lc)
d['rebinned_bkg'].append(rebinned_bkg)
d['bkg_corrected_lc'].append(bkg_corrected_lc)
# Update database and save
df = pd.DataFrame(d)
db = database.merge(db,df,['rebinned_bkg','bkg_corrected_lc'])
database.save(db)
logs.stop_logging()
def goodxenon_to_fits():
'''
Function to convert GoodXenon files to fitsfiles using make_se. Subsequently
groups the paths to the produced files into a file
path_gxfits_<resolution> and updates db.
'''
purpose = 'Converting GoodXenon files to fits files'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
import os
import pandas as pd
import glob
from collections import defaultdict
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
os.chdir(paths.data)
db = pd.read_csv(paths.database)
# Running it over gx1 or gx2 will give same result, but only needs to be
# run once
if 'gx1' not in db.modes.unique():
print 'No GoodXenon files found'
return
# Run maketime for each obsid
sdb = db[db.modes == 'gx1']
sdb['gxfits'] = sdb.paths_obsid + 'gxfits_' + sdb.resolutions
# Create a list of the gxfits files
d = defaultdict(list)
for i, row in sdb.iterrows():
# Create goodxenon fits files
command = [
'make_se',
'-i', #Input file with list to gx1 and gx2 files
row.paths_po_pm_pr,
'-p', #Output the prefix for the goodxenon files
row.gxfits
]
shell.execute(command)
gxfiles = row.paths_obsid + 'gxfits_' + row.resolutions + '*'
paths_gx = glob.glob(gxfiles)
d['obsids'].append(row.obsids)
d['modes'].append(row.modes)
d['resolutions'].append(row.resolutions)
path_gx = row.paths_obsid + 'paths_gxfits_' + row.resolutions
d['paths_gx'].append(path_gx)
with open(path_gx, 'w') as text:
text.write('\n'.join(paths_gx) + '\n')
# Ensure gx2 has the same data as gx1
for k in d:
if k != 'modes':
d[k].extend(d[k])
else:
d[k].extend(['gx2' for g in d[k]])
df = pd.DataFrame(d)
# Ensure that the column paths_gx is updated
db = database.merge(db, df, ['paths_gx'])
database.save(db)
logs.stop_logging()
def set(cid, data, table='cache', expire=None, headers=None):
"""
Store data in the persistent cache.
The persistent cache is split up into four database
tables. Contributed plugins can add additional tables.
'cache_page': This table stores generated pages for anonymous
users. This is the only table affected by the page cache setting on
the administrator panel.
'cache_menu': Stores the cachable part of the users' menus.
'cache_filter': Stores filtered pieces of content. This table is
periodically cleared of stale entries by cron.
'cache': Generic cache storage table.
The reasons for having several tables are as follows:
- smaller tables allow for faster selects and inserts
- we try to put fast changing cache items and rather static
ones into different tables. The effect is that only the fast
changing tables will need a lot of writes to disk. The more
static tables will also be better cachable with MySQL's query cache
@param cid
The cache ID of the data to store.
@param data
The data to store in the cache. Complex data types will be
automatically serialized before insertion.
Strings will be stored as plain text and not serialized.
@param table
The table table to store the data in. Valid core values are 'cache_filter',
'cache_menu', 'cache_page', or 'cache'.
@param expire
One of the following values:
- CACHE_PERMANENT: Indicates that the item should never be removed unless
explicitly told to using cache_clear_all() with a cache ID.
- CACHE_TEMPORARY: Indicates that the item should be removed at the next
general cache wipe.
- A Unix timestamp: Indicates that the item should be kept at least until
the given time, after which it behaves like CACHE_TEMPORARY.
@param headers
A string containing HTTP php.header information for cached pages.
"""
if expire is None:
expire = lib_bootstrap.CACHE_PERMANENT
fields = {
'serialized': 0,
'created': REQUEST_TIME,
'expire': expire,
'headers': headers
}
if (not php.is_string(data)):
fields['data'] = php.serialize(data)
fields['serialized'] = 1
else:
fields['data'] = data
fields['serialized'] = 0
lib_database.merge(table).key({'cid': cid}).fields(fields).execute()
def calculate_hi(low_e=3.0, high_e=16.0, soft=(6.4, 9.7), hard=(9.7, 16.)):
'''
Function to calculate hardness & intensity values.
Arguments:
Energy ranges in keV
- low_e (float): Lower energy boundary for selection
- high_e (float): Higher energy boundary for selection
- soft (tuple of floats): Energy range between which to integrate
the soft range
- hard (tuple of floats): Energy range between which to integrate
the hard range
'''
purpose = 'Calculating hardness & intensity values'
print len(purpose) * '=' + '\n' + purpose + '\n' + len(purpose) * '='
print 'Soft:', soft, 'Hard:', hard, '\n' + len(purpose) * '-'
import os
import pandas as pd
import glob
import xspec
from collections import defaultdict
from math import isnan
from numpy import genfromtxt
import paths
import logs
import execute_shell_commands as shell
import database
# Set log file
filename = __file__.split('/')[-1].split('.')[0]
logs.output(filename)
# Import data
os.chdir(paths.data)
db = pd.read_csv(paths.database)
# Compile Fortran code for later use
cmpl = [
'gfortran', paths.subscripts + 'integflux.f', '-o',
paths.subscripts + 'integflux.xf'
]
shell.execute(cmpl)
# Only want spectra from std2
d = defaultdict(list)
for sp, group in db[(db.modes == 'std2')].groupby('spectra'):
# Determine variables
obsid = group.obsids.values[0]
path_obsid = group.paths_obsid.values[0]
bkg_sp = group.spectra_bkg.values[0]
rsp = group.rsp.values[0]
fltr = group.filters.values[0]
print obsid
# Check whether response file is there
if not os.path.isfile(rsp):
print 'ERROR: No response file'
continue
# XSPEC Commands to unfold spectrum around flat powerlaw
# Reason as per Heil et al. (see doi:10.1093/mnras/stv240):
# "In order to measure the energy spectral hardness independantly of
# long term changes in the PCA instrument response, fluxes are
# generated in a model-independant way by dividing the PCA standard
# 2 mode spectrum by the effective area of the intstrument response
# in each spectral channel. This is carried out by unfolding the
# spectrum with respect to a zero-slope power law (i.e. a constant)
# in the XSPEC spectral-fitting software, and measuring the unfolded
# flux over the specified energy range (interpolating where the
# specified energy does not fall neatly at the each of a spectral
# channel)."
#xspec.Plot.device = '/xs'
s1 = xspec.Spectrum(sp)
s1.background = bkg_sp
s1.response = os.path.join(paths.data, rsp)
# Not really sure why you need to do ignore, and then notice
s1.ignore('**-' + str(low_e + 1.) + ' ' + str(high_e - 1) + '-**')
s1.notice(str(low_e) + '-' + str(high_e))
xspec.Model('powerlaw')
xspec.AllModels(1).setPars(0.0, 1.0) # Index, Norm
xspec.AllModels(1)(1).frozen = True
xspec.AllModels(1)(2).frozen = True
xspec.Plot('eufspec')
# Output unfolded spectrum to lists
e = xspec.Plot.x()
e_err = xspec.Plot.xErr()
ef = xspec.Plot.y()
ef_err = xspec.Plot.yErr()
model = xspec.Plot.model()
# Pipe output to file
eufspec = path_obsid + 'eufspec.dat'
with open(eufspec, 'w') as f:
#Give header of file - must be three lines
h = [
'#Unfolded spectrum', '#',
'#Energy EnergyError Energy*Flux Energy*FluxError ModelValues'
]
f.write('\n'.join(h) + '\n')
for i in range(len(e)):
data = [e[i], e_err[i], ef[i], ef_err[i], model[i]]
line = [str(j) for j in data]
f.write(' '.join(line) + '\n')
# Create a file to input into integflux
integflux = path_obsid + 'integflux.in'
with open(integflux, 'w') as f:
#intgr_low, intgr_high, soft_low, soft_high, hard_low, hard_high
line = [
'eufspec.dat',
str(low_e),
str(high_e),
str(soft[0]),
str(soft[-1]),
str(hard[0]),
str(hard[-1])
]
line = [str(e) for e in line]
f.write(' '.join(line) + '\n')
# Remove previous versions of the output
if os.path.isfile(path_obsid + 'hardint.out'):
os.remove(path_obsid + 'hardint.out')
# Run fortran script to create calculate hardness-intensity values
# Will output a file with the columns (with flux in Photons*ergs/cm^2/s)
# flux flux_err ratio ratio_error
os.chdir(path_obsid)
shell.execute(paths.subscripts + 'integflux.xf')
os.chdir(paths.data)
# Get ouput of the fortran script
txt = genfromtxt(path_obsid + 'hardint.out')
flux = float(txt[0])
flux_err = float(txt[1])
ratio = float(txt[2])
ratio_err = float(txt[3])
d['spectra'].append(sp)
d['flux_i3t16_s6p4t9p7_h9p7t16'].append(flux)
d['flux_err_i3t16_s6p4t9p7_h9p7t16'].append(flux_err)
d['hardness_i3t16_s6p4t9p7_h9p7t16'].append(ratio)
d['hardness_err_i3t16_s6p4t9p7_h9p7t16'].append(ratio_err)
# Clear xspec spectrum
xspec.AllData.clear()
# Update database and save
df = pd.DataFrame(d)
cols = [
'flux_i3t16_s6p4t9p7_h9p7t16', 'flux_err_i3t16_s6p4t9p7_h9p7t16',
'hardness_i3t16_s6p4t9p7_h9p7t16',
'hardness_err_i3t16_s6p4t9p7_h9p7t16'
]
db = database.merge(db, df, cols)
print 'Number of unique elements in database'
print '======================='
print db.apply(pd.Series.nunique)
print '======================='
print 'Pipeline completed'
database.save(db)
logs.stop_logging()
