def __init__(self, file, nints=1000, nskip=0, ddid=-1, selectpol=['RR','LL'], scan=0, datacol='data'):
"""Initializes the class "obs". This creates new object containing data and metadata for an observation.
It also includes functions to manipulate data and do transients analysis.
Note that this uses CASA libraries in a way that requires it to be run from within "casapy".
Use scan, nints, and nskip to control where to start.
datacol specifies column of MS to read. Standard MS data columns are: 'data', 'corrected_data', 'model_data'.
Examples of usage in python/casapy:
import vla_tpipe
obs = vla_tpipe.obs() -- create observation object for first file in a directory.
print obs.data.shape -- see the structure of data read in. dimensions are (time, baseline, channel, polarization)
results = obs.bisplc(show=1) -- create a bispectrum lightcurve and show any candidate transients. results are returned in 'return' object
"""
# critical parameters. may need to edit these
ants = range(28) # set what antennas to use. default is to use "range" to specify all antennas with range(n_ant+1)
self.file = file
# get spw info. either load pickled version (if found) or make new one
pklname = string.join(file.split('.')[:-1], '.') + '_init.pkl'
if os.path.exists(pklname):
print 'Pickle of initializing info found. Loading...'
pkl = open(pklname, 'r')
(self.npol_orig, self.npol, self.nbl, self.blarr, self.ants, self.nants, self.nants0, self.nskip, self.inttime, self.inttime0, spwinfo, scansummary) = pickle.load(pkl)
scanlist = scansummary['summary'].keys()
starttime_mjd = scansummary['summary'][scanlist[scan]]['0']['BeginTime']
self.nskip = int(nskip*self.nbl) # number of iterations to skip (for reading in different parts of buffer)
else:
print 'No pickle of initializing info found. Making anew...'
pkl = open(pklname, 'wb')
ms.open(self.file)
spwinfo = ms.getspectralwindowinfo()
scansummary = ms.getscansummary()
scanlist = scansummary['summary'].keys()
starttime_mjd = scansummary['summary'][scanlist[scan]]['0']['BeginTime']
starttime0 = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+0/(24.*60*60),'d'),form=['ymd'], prec=9), 's'))
stoptime0 = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+0.5/(24.*60*60), 'd'), form=['ymd'], prec=9), 's'))
ms.selectinit(datadescid=0) # initialize to initialize params
selection = {'time': [starttime0, stoptime0], 'antenna1': ants, 'antenna2': ants}
ms.select(items = selection)
da = ms.getdata([datacol,'axis_info'], ifraxis=True)
ms.close()
self.npol_orig = da[datacol].shape[0]
self.npol = len(selectpol)
self.nbl = da[datacol].shape[2]
print 'Initializing %d of %d polarizations' % (self.npol, self.npol_orig)
print 'Initializing nbl:', self.nbl
# good baselines
bls = da['axis_info']['ifr_axis']['ifr_shortname']
self.blarr = n.array([[int(bls[i].split('-')[0]),int(bls[i].split('-')[1])] for i in range(len(bls))])
self.ants = n.unique(self.blarr)
self.nants = len(self.ants)
self.nants0 = len(self.ants)
print 'Initializing nants:', self.nants
self.nskip = int(nskip*self.nbl) # number of iterations to skip (for reading in different parts of buffer)
# set integration time
ti0 = da['axis_info']['time_axis']['MJDseconds']
# self.inttime = n.mean([ti0[i+1] - ti0[i] for i in range(len(ti0)-1)])
self.inttime = scansummary['summary'][scanlist[scan]]['0']['IntegrationTime']
self.inttime0 = self.inttime
print 'Initializing integration time (s):', self.inttime
pickle.dump((self.npol_orig, self.npol, self.nbl, self.blarr, self.ants, self.nants, self.nants0, self.nskip, self.inttime, self.inttime0, spwinfo, scansummary), pkl)
pkl.close()
# read in multiple subbands ("data id" in casa parlance).
if ddid < 0:
ddidlist = range(len(spwinfo['spwInfo']))
else:
ddidlist = [ddid]
freq = n.array([])
for ddid in ddidlist:
nch = spwinfo['spwInfo'][str(ddid)]['NumChan']
ch0 = spwinfo['spwInfo'][str(ddid)]['Chan1Freq']
chw = spwinfo['spwInfo'][str(ddid)]['ChanWidth']
freq = n.concatenate( (freq, (ch0 + chw * n.arange(nch)) * 1e-9) )
# self.chans = n.array(range(2,62)) # can flag by omitting channels here
self.chans = n.arange(nch*len(ddidlist)) # default is to take all chans
self.freq = freq[self.chans]
self.nchan = len(self.freq)
self.track0 = [n.zeros(len(self.chans)), list(self.chans)]
self.track0 = [n.zeros(len(self.chans)), list(self.chans)]
# set requested time range based on given parameters
timeskip = self.inttime*nskip
starttime = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+timeskip/(24.*60*60),'d'),form=['ymd'], prec=9), 's'))
stoptime = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+(timeskip+nints*self.inttime)/(24.*60*60), 'd'), form=['ymd'], prec=9), 's'))
print 'First integration of scan:', qa.time(qa.quantity(starttime_mjd,'d'),form=['ymd'],prec=9)
print
print 'Reading from', qa.time(qa.quantity(starttime_mjd+timeskip/(24.*60*60),'d'),form=['hms'], prec=9), 'to', qa.time(qa.quantity(starttime_mjd+(timeskip+nints*self.inttime)/(24.*60*60), 'd'), form=['hms'], prec=9)
# read data into data structure
ms.open(self.file)
ms.selectinit(datadescid=ddidlist[0]) # reset select params for later data selection
selection = {'time': [starttime, stoptime], 'antenna1': ants, 'antenna2': ants}
ms.select(items = selection)
print 'Reading %s, SB %d, polarization %s...' % (datacol, ddidlist[0], selectpol)
ms.selectpolarization(selectpol)
da = ms.getdata([datacol,'axis_info'], ifraxis=True)
if da == {}:
print 'No data found.'
return 1
newda = n.transpose(da[datacol], axes=[3,2,1,0]) # if using multi-pol data.
if len(ddidlist) > 1:
for ddid in ddidlist[1:]:
ms.selectinit(datadescid=ddid) # reset select params for later data selection
ms.select(items = selection)
print 'Reading %s, SB %d, polarization %s...' % (datacol, ddid, selectpol)
ms.selectpolarization(selectpol)
da = ms.getdata([datacol,'axis_info'], ifraxis=True)
newda = n.concatenate( (newda, n.transpose(da[datacol], axes=[3,2,1,0])), axis=2 )
ms.close()
# check pol and baseline dimensions of data
self.npol_orig = da[datacol].shape[0]
self.npol = len(selectpol)
self.nbl = da[datacol].shape[2]
print 'Initializing %d of %d polarizations' % (self.npol, self.npol_orig)
print 'Initializing nchan:', self.nchan
print 'Initializing nbl:', self.nbl
self.nskip = int(nskip*self.nbl) # number of iterations to skip (for reading in different parts of buffer)
# create data structures
# self.rawdata = newda[len(newda)/2:] # hack to remove autos
self.rawdata = newda
self.data = self.rawdata[:,:,self.chans] # remove channels ignored earlier
self.dataph = (self.data.mean(axis=3).mean(axis=1)).real # create dataph, which is sum over all baselines. akin to calculating tied-array beam (possibly without calibration)
self.min = self.dataph.min()
self.max = self.dataph.max()
print 'Shape of rawdata, data:'
print self.rawdata.shape, self.data.shape
print 'Dataph min, max:'
print self.min, self.max
# set integration time and time axis
ti = da['axis_info']['time_axis']['MJDseconds']
self.reltime = ti - ti[0]
def read(self, file, nints, nskip, spw, selectpol, scan, datacol):
""" Reads in Measurement Set data using CASA.
spw is list of subbands. zero-based.
Scan is zero-based selection based on scan order, not actual scan number.
selectpol is list of polarization strings (e.g., ['RR','LL'])
"""
self.file = file
self.scan = scan
self.nints = nints
# get spw info. either load pickled version (if found) or make new one
pklname = string.join(file.split(".")[:-1], ".") + "_init.pkl"
# pklname = pklname.split('/')[-1] # hack to remove path and write locally
if os.path.exists(pklname):
print "Pickle of initializing info found. Loading..."
pkl = open(pklname, "r")
try:
(self.npol_orig, self.nbl, self.blarr, self.inttime, spwinfo, scansummary) = pickle.load(pkl)
except EOFError:
print "Bad pickle file. Exiting..."
return 1
# old way, casa 3.3?
# scanlist = scansummary['summary'].keys()
# starttime_mjd = scansummary['summary'][scanlist[scan]]['0']['BeginTime']
# new way, casa 4.0?
scanlist = scansummary.keys()
starttime_mjd = scansummary[scanlist[scan]]["0"]["BeginTime"]
self.nskip = int(
nskip * self.nbl
) # number of iterations to skip (for reading in different parts of buffer)
self.npol = len(selectpol)
else:
print "No pickle of initializing info found. Making anew..."
pkl = open(pklname, "wb")
ms.open(self.file)
spwinfo = ms.getspectralwindowinfo()
scansummary = ms.getscansummary()
# original (general version)
# scanlist = scansummary['summary'].keys()
# starttime_mjd = scansummary['summary'][scanlist[scan]]['0']['BeginTime']
# starttime0 = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+0/(24.*60*60),'d'),form=['ymd'], prec=9), 's'))
# stoptime0 = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+0.5/(24.*60*60), 'd'), form=['ymd'], prec=9), 's'))
# for casa 4.0 (?) and later
scanlist = scansummary.keys()
# set time info
self.inttime = scansummary[scanlist[scan]]["0"]["IntegrationTime"]
self.inttime0 = self.inttime
print "Initializing integration time (s):", self.inttime
starttime_mjd = scansummary[scanlist[scan]]["0"]["BeginTime"]
starttime0 = qa.getvalue(
qa.convert(
qa.time(qa.quantity(starttime_mjd + 0 / (24.0 * 60 * 60), "d"), form=["ymd"], prec=9)[0], "s"
)
)[0]
stoptime0 = qa.getvalue(
qa.convert(
qa.time(qa.quantity(starttime_mjd + self.inttime / (24.0 * 60 * 60), "d"), form=["ymd"], prec=9)[0],
"s",
)
)[0]
ms.selectinit(datadescid=0) # initialize to initialize params
selection = {"time": [starttime0, stoptime0]}
ms.select(items=selection)
da = ms.getdata([datacol, "axis_info"], ifraxis=True)
ms.close()
self.npol_orig = da[datacol].shape[0]
self.nbl = da[datacol].shape[2]
print "Initializing nbl:", self.nbl
# good baselines
bls = da["axis_info"]["ifr_axis"]["ifr_shortname"]
self.blarr = n.array([[int(bls[i].split("-")[0]), int(bls[i].split("-")[1])] for i in xrange(len(bls))])
self.nskip = int(
nskip * self.nbl
) # number of iterations to skip (for reading in different parts of buffer)
pickle.dump((self.npol_orig, self.nbl, self.blarr, self.inttime, spwinfo, scansummary), pkl)
pkl.close()
self.ants = n.unique(self.blarr)
self.nants = len(n.unique(self.blarr))
self.nants0 = len(n.unique(self.blarr))
print "Initializing nants:", self.nants
self.npol = len(selectpol)
print "Initializing %d of %d polarizations" % (self.npol, self.npol_orig)
# set desired spw
if (len(spw) == 1) & (spw[0] == -1):
# spwlist = spwinfo['spwInfo'].keys() # old way
spwlist = spwinfo.keys() # new way
else:
spwlist = spw
self.freq_orig = n.array([])
for spw in spwlist:
# new way
nch = spwinfo[str(spw)]["NumChan"]
ch0 = spwinfo[str(spw)]["Chan1Freq"]
chw = spwinfo[str(spw)]["ChanWidth"]
self.freq_orig = n.concatenate((self.freq_orig, (ch0 + chw * n.arange(nch)) * 1e-9))
# old way
# nch = spwinfo['spwInfo'][str(spw)]['NumChan']
# ch0 = spwinfo['spwInfo'][str(spw)]['Chan1Freq']
# chw = spwinfo['spwInfo'][str(spw)]['ChanWidth']
self.freq = self.freq_orig[self.chans]
self.nchan = len(self.freq)
print "Initializing nchan:", self.nchan
# set requested time range based on given parameters
timeskip = self.inttime * nskip
# new way
starttime = qa.getvalue(
qa.convert(
qa.time(qa.quantity(starttime_mjd + timeskip / (24.0 * 60 * 60), "d"), form=["ymd"], prec=9)[0], "s"
)
)[0]
stoptime = qa.getvalue(
qa.convert(
qa.time(
qa.quantity(starttime_mjd + (timeskip + nints * self.inttime) / (24.0 * 60 * 60), "d"),
form=["ymd"],
prec=9,
)[0],
"s",
)
)[0]
print "First integration of scan:", qa.time(qa.quantity(starttime_mjd, "d"), form=["ymd"], prec=9)[0]
print
# new way
print "Reading scan", str(scanlist[scan]), "for times", qa.time(
qa.quantity(starttime_mjd + timeskip / (24.0 * 60 * 60), "d"), form=["hms"], prec=9
)[0], "to", qa.time(
qa.quantity(starttime_mjd + (timeskip + nints * self.inttime) / (24.0 * 60 * 60), "d"), form=["hms"], prec=9
)[
0
]
# read data into data structure
ms.open(self.file)
ms.selectinit(datadescid=spwlist[0]) # reset select params for later data selection
selection = {"time": [starttime, stoptime]}
ms.select(items=selection)
print "Reading %s column, SB %d, polarization %s..." % (datacol, spwlist[0], selectpol)
ms.selectpolarization(selectpol)
da = ms.getdata([datacol, "axis_info", "u", "v", "w", "flag"], ifraxis=True)
u = da["u"]
v = da["v"]
w = da["w"]
if da == {}:
print "No data found."
return 1
newda = n.transpose(da[datacol], axes=[3, 2, 1, 0]) # if using multi-pol data.
flags = n.transpose(da["flag"], axes=[3, 2, 1, 0])
if len(spwlist) > 1:
for spw in spwlist[1:]:
ms.selectinit(datadescid=spw) # reset select params for later data selection
ms.select(items=selection)
print "Reading %s column, SB %d, polarization %s..." % (datacol, spw, selectpol)
ms.selectpolarization(selectpol)
da = ms.getdata([datacol, "axis_info", "flag"], ifraxis=True)
newda = n.concatenate((newda, n.transpose(da[datacol], axes=[3, 2, 1, 0])), axis=2)
flags = n.concatenate((flags, n.transpose(da["flag"], axes=[3, 2, 1, 0])), axis=2)
ms.close()
# Initialize more stuff...
self.nschan0 = self.nchan
# set variables for later writing data **some hacks here**
self.nspect0 = 1
self.nwide0 = 0
self.sdf0 = da["axis_info"]["freq_axis"]["resolution"][0][0] * 1e-9
self.sdf = self.sdf0
self.ischan0 = 1
self.sfreq0 = da["axis_info"]["freq_axis"]["chan_freq"][0][0] * 1e-9
self.sfreq = self.sfreq0
self.restfreq0 = 0.0
self.pol0 = -1 # assumes single pol?
# Assumes MS files store uvw in meters. Corrects by mean frequency of channels in use.
self.u = u.transpose() * self.freq_orig[0] * (1e9 / 3e8)
self.v = v.transpose() * self.freq_orig[0] * (1e9 / 3e8)
self.w = w.transpose() * self.freq_orig[0] * (1e9 / 3e8)
# set integration time and time axis
ti = da["axis_info"]["time_axis"]["MJDseconds"]
self.reltime = ti - ti[0]
# define relative phase center for each integration
self.l0 = n.zeros(self.nints)
self.m0 = n.zeros(self.nints)
self.rawdata = newda
self.flags = n.invert(
flags
) # tests show that MS has opposite flag convention as Miriad! using complement of MS flag in tpipe.
print "Shape of raw data, time:"
print self.rawdata.shape, self.reltime.shape
def __init__(self, filename, nints=1, nskip=0, selectpol=['XX','YY'], datacol='corrected'):
"""Initializes the class "lofar". This creates new object containing data and metadata for a set of files in a directory.
It also includes functions to manipulate data and do some analysis, like making lightcurves, etc.
Note that this uses CASA libraries in a way that requires it to be run from within "casapy". Other options exist elsewhere.
Default is to read in first file (alphabetically) in the directory. Use nints and nskip to control where to start and number of files to read. this assumes that the alphabetical order is the time order.
Examples of usage in python/casapy:
import lofarvis
obs = lofarvis.lofar('directory') -- create observation object for first file in a directory.
print obs.data.shape -- see the structure of data read in. dimensions are (time, baseline, channel, polarization)
results = obs.bisplc(show=1) -- create a bispectrum lightcurve and show any candidate transients. results are returned in 'return' object
"""
# critical parameters. need to edit these
ants = range(25) # set what antennas to use. default is to use "range" to specify all antennas with range(n_ant+1)
self.chans = n.array(range(1)) # set what channesl to use. default is to use range to select all channels.
self.track0 = [n.zeros(len(self.chans)), self.chans]
# open file and read a bit of data to define data structure
self.file = filename
print 'Reading ', self.file
ms.open(self.file)
spwinfo = ms.getspectralwindowinfo()
summary = ms.summary()
scansummary = ms.getscansummary()
starttime_mjd = scansummary['summary']['0']['0']['BeginTime']
starttime0 = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+0/(24.*60*60),'d'),form=['ymd'], prec=9), 's'))
stoptime0 = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+0.5/(24.*60*60), 'd'), form=['ymd'], prec=9), 's'))
ms.selectinit(datadescid=0) # initialize to initialize params
selection = {'time': [starttime0, stoptime0], 'antenna1': ants, 'antenna2': ants}
da = ms.getdata([datacol,'axis_info', 'u', 'v', 'w'], ifraxis=True)
ms.close()
self.npol_orig = da[datacol].shape[0]
self.npol = len(selectpol)
self.nbl = da[datacol].shape[2]
print 'Initializing %d of %d polarizations' % (self.npol, self.npol_orig)
print 'Initializing nbl:', self.nbl
# good baselines
bls = da['axis_info']['ifr_axis']['ifr_shortname']
self.blarr = n.array([[bls[i].split('-')[0],bls[i].split('-')[1]] for i in range(len(bls))])
self.ants = n.unique(self.blarr)
self.nants = len(self.ants)
self.nants0 = len(self.ants)
print 'Initializing nants:', self.nants
self.nskip = int(nskip*self.nbl) # number of iterations to skip (for reading in different parts of buffer)
# set integration time
ti0 = da['axis_info']['time_axis']['MJDseconds']
self.inttime = scansummary['summary']['0']['0']['IntegrationTime']
self.inttime0 = self.inttime
print 'Initializing integration time (s):', self.inttime
nch = spwinfo['spwInfo']['0']['NumChan']
ch0 = spwinfo['spwInfo']['0']['Chan1Freq']
chw = spwinfo['spwInfo']['0']['ChanWidth']
freq = (ch0 + chw * n.arange(nch)) * 1e-9
self.freq = freq[self.chans]
self.nchan = len(self.freq)
# read data into data structure. start with subband 0, then iterate over higher ones. lofar probably only has 0.
timeskip = self.inttime*nskip
starttime = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+timeskip/(24.*60*60),'d'),form=['ymd'], prec=9), 's'))
stoptime = qa.getvalue(qa.convert(qa.time(qa.quantity(starttime_mjd+(timeskip+nints*self.inttime)/(24.*60*60), 'd'), form=['ymd'], prec=9), 's'))
print 'First integration:', qa.time(qa.quantity(starttime_mjd,'d'),form=['ymd'],prec=9)
print
print 'Reading times', qa.time(qa.quantity(starttime_mjd+timeskip/(24.*60*60),'d'),form=['hms'], prec=9), 'to', qa.time(qa.quantity(starttime_mjd+(timeskip+nints*self.inttime)/(24.*60*60), 'd'), form=['hms'], prec=9)
ms.open(self.file)
ms.selectinit(datadescid=0) # reset select params for later data selection
selection = {'time': [starttime, stoptime], 'antenna1': ants, 'antenna2': ants}
ms.select(items = selection)
print 'Reading SB %d, polarization %s...' % (0, selectpol)
ms.selectpolarization(selectpol)
da = ms.getdata([datacol,'axis_info', 'u', 'v', 'w'], ifraxis=True)
u = da['u']; v = da['v']; w = da['w']
if da == {}:
print 'No data found.'
return 1
newda = n.transpose(da[datacol], axes=[3,2,1,0]) # if using multi-pol data.
ms.close()
rawdata = newda # array for collecting raw data
# create data structures
self.u = u.transpose() * (-self.freq.mean()*1e9/3e8) # uvw are in m on ground. scale by -wavelenth to get projected lamba uvw (as in miriad?)
self.v = v.transpose() * (-self.freq.mean()*1e9/3e8)
self.w = w.transpose() * (-self.freq.mean()*1e9/3e8)
self.rawdata = rawdata
self.data = rawdata[:,:,self.chans] # remove channels ignored earlier
self.dataph = (self.data.mean(axis=3).mean(axis=1)).real # create dataph, which is sum over all baselines. akin to calculating tied-array beam (possibly without calibration)
self.min = self.dataph.min()
self.max = self.dataph.max()
print 'Shape of rawdata, data:'
print self.rawdata.shape, self.data.shape
print 'Dataph min, max:'
print self.min, self.max
ti = da['axis_info']['time_axis']['MJDseconds']
self.reltime = ti - ti[0]