partition.py

Go to the documentation of this file.

#
# This file was generated using xslt from its XML file
#
# Copyright 2009, Associated Universities Inc., Washington DC
#
import sys
import os
from  casac import *
import string
from taskinit import casalog
#from taskmanager import tm
import task_partition
def partition(vis='', outputvis='', createmms=True, separationaxis='scan', numsubms=64, datacolumn='data', calmsselection='none', calmsname='', calfield='', calscan='', calintent='', field='', spw='', antenna='', timebin='0s', combine='', timerange='', scan='', scanintent='', array='', uvrange='', observation=''):

        """Experimental task to produce multi-MSs using parallelism
    Experimental version for use with parallelization framework.  
    Do not use this for standard analysis... yet.

    Partition is a task to create a multi-MS out of an MS. General selection
    parameters are included, and one or all of the various data columns
    (DATA, LAG_DATA and/or FLOAT_DATA, and possibly MODEL_DATA and/or
    CORRECTED_DATA) can be selected. It can also be used to create a normal
    MS, split based on the given data selection parameters.

    The partition task creates a multi-MS using the parallelization framework.
    If a cluster is not present, it will create a default cluster based on the
    resources of the system. One can create a simple_cluster prior to running
    partition by doing the following.

    from simple_cluster import *
    sc = simple_cluster()
    sc.init_cluster('cluster-config.txt', 'test')

    The file 'cluster-config.txt' contains information on the machine that will
    be used for the cluster. Please see the help of simple_cluster for more information.        

    A multi-MS is structured to have a reference MS on the top directory and a
    sub-directory called SUBMSS, which contain each partitioned sub-MS. The
    reference MS contains links to the sub-tables of the first sub-MS. The other
    sub-MSs contain a copy of the sub-tables each. A multi-MS looks like this in disk.

    ls ngc5921.mms
    ANTENNA           FLAG_CMD     POLARIZATION  SPECTRAL_WINDOW  table.dat
    DATA_DESCRIPTION  HISTORY      PROCESSOR     STATE            table.info
    FEED              OBSERVATION  SORTED_TABLE  SUBMSS           WEATHER
    FIELD             POINTING     SOURCE        SYSCAL

    ls ngc5921.mms/SUBMSS/
    ngc5921.0000.ms/  ngc5921t.0002.ms/  ngc5921.0004.ms/  ngc5921.0006.ms/
    ngc5921.0001.ms/  ngc5921.0003.ms/  ngc5921.0005.ms/

    Inside casapy, one can use the task listpartition to list the information
    from a multi-MS.
  

    Keyword arguments:
    vis -- Name of input visibility file
        default: none; example: vis='ngc5921.ms'

    outputvis -- Name of output visibility file
        default: none; example: outputvis='ngc5921.mms'

    createmms -- Create a multi-MS as the output.
        default: True
        If False, it will work like the split task and create a
        normal MS, split according to the given data selection parameters.
        Note that, when this parameter is set to False, a simple_cluster
        will not be created.

        separationaxis -- Axis to do parallelization across. 
            default: 'scan'
            Options: 'scan', 'spw', 'both'
            The 'both' option will try to partition in both scan and spw axes.

        numsubms -- The number of sub-MSs to create.
            default: 64
                                

    datacolumn -- Which data column to use when partitioning.
        default='data'; example: datacolumn='data'
        Options: 'data', 'model', 'corrected', 'all',
                'float_data', 'lag_data', 'float_data,data', and
                'lag_data,data'.
            N.B.: 'all' = whichever of the above that are present.
            Otherwise the selected column will go to DATA (or
            FLOAT_DATA) in the output.

    calmsselection -- Method by which the calibration scans will be identified
                    when creating a separate calibration MS.
        default:'none'
        Options: 'none', 'auto', 'manual'.

        'auto' -- 
            calmsname -- Name of output measurement set.
                default = ' '

        'manual'
            calmsname -- Name of output measurement set.
                default: ''
            calfield -- Field selection for calibration MS.
                default: ''
            calscans -- Scan selection for calibration MS.
                default: ''
            calintent -- Scan intent selection for calibration MS.
                default: ''

--- Data selection parameters (see help par.selectdata for more detailed
    information)

    field -- Select field using field id(s) or field name(s).
             [run listobs to obtain the list iof d's or names]
        default: ''=all fields If field string is a non-negative
           integer, it is assumed to be a field index
           otherwise, it is assumed to be a field name
           field='0~2'; field ids 0,1,2
           field='0,4,5~7'; field ids 0,4,5,6,7
           field='3C286,3C295'; fields named 3C286 and 3C295
           field = '3,4C*'; field id 3, all names starting with 4C

    spw -- Select spectral window/channels
        default: ''=all spectral windows and channels
           spw='0~2,4'; spectral windows 0,1,2,4 (all channels)
           spw='<2';  spectral windows less than 2 (i.e. 0,1)
           spw='0:5~61'; spw 0, channels 5 to 61
           spw='0,10,3:3~45'; spw 0,10 all channels, spw 3 - chans 3 to 45.
           spw='0~2:2~6'; spw 0,1,2 with channels 2 through 6 in each.
           spw = '*:3~64'  channels 3 through 64 for all sp id's
                   spw = ' :3~64' will NOT work.
           spw = '*:0;60~63'  channel 0 and channels 60 to 63 for all IFs 
                  ';' needed to separate different channel ranges in one spw
           spw='0:0~10;15~60'; spectral window 0 with channels 0-10,15-60
           spw='0:0~10,1:20~30,2:1;2;4'; spw 0, channels 0-10,
                    spw 1, channels 20-30, and spw 2, channels, 1, 2 and 4

    antenna -- Select data based on antenna/baseline
        default: '' (all)
            Non-negative integers are assumed to be antenna indices, and
            anything else is taken as an antenna name.

            Examples:
            antenna='5&6': baseline between antenna index 5 and index 6.
            antenna='VA05&VA06': baseline between VLA antenna 5 and 6.
            antenna='5&6;7&8': baselines 5-6 and 7-8
            antenna='5': all baselines with antenna 5
            antenna='5,6,10': all baselines including antennas 5, 6, or 10
            antenna='5,6,10&': all baselines with *only* antennas 5, 6, or
                                   10.  (cross-correlations only.  Use &&
                                   to include autocorrelations, and &&&
                                   to get only autocorrelations.)
            antenna='!ea03,ea12,ea17': all baselines except those that
                                       include EVLA antennas ea03, ea12, or
                                       ea17.

    timebin -- Interval width for time averaging.
        default: '0s' or '-1s' (no averaging)
        Example: timebin='30s'
                 '10' means '10s'

        combine -- Let time bins span changes in scan and/or state.
            default = '' (separate time bins by both of the above)
               combine = 'scan': Can be useful when the scan number
                                 goes up with each integration,
                                 as in many WSRT MSes.
               combine = ['scan', 'state']: disregard scan and state
                                            numbers when time averaging.
               combine = 'state,scan': Same as above.

    timerange -- Select data based on time range:
        default = '' (all); examples,
           timerange = 'YYYY/MM/DD/hh:mm:ss~YYYY/MM/DD/hh:mm:ss'
           Note: if YYYY/MM/DD is missing date, timerange defaults to the
           first day in the dataset
           timerange='09:14:0~09:54:0' picks 40 min on first day
           timerange='25:00:00~27:30:00' picks 1 hr to 3 hr 30min
           on next day
           timerange='09:44:00' data within one integration of time
           timerange='>10:24:00' data after this time

    array -- (Sub)array number range
        default: ''=all

    uvrange -- Select data within uvrange (default units meters)
        default: ''=all; example:
            uvrange='0~1000klambda'; uvrange from 0-1000 kilo-lambda
            uvrange='>4klambda';uvranges greater than 4 kilo-lambda
            uvrange='0~1000km'; uvrange in kilometers

    scan -- Scan number range
        default: ''=all

    observation -- Select by observation ID(s)
        default: ''=all



        """

#
#    The following is work around to avoid a bug with current python translation
#
        mytmp = {}

        mytmp['vis'] = vis
        mytmp['outputvis'] = outputvis
        mytmp['createmms'] = createmms
        mytmp['separationaxis'] = separationaxis
        mytmp['numsubms'] = numsubms
        mytmp['datacolumn'] = datacolumn
        mytmp['calmsselection'] = calmsselection
        mytmp['calmsname'] = calmsname
        mytmp['calfield'] = calfield
        mytmp['calscan'] = calscan
        mytmp['calintent'] = calintent
        mytmp['field'] = field
        mytmp['spw'] = spw
        mytmp['antenna'] = antenna
        mytmp['timebin'] = timebin
        mytmp['combine'] = combine
        mytmp['timerange'] = timerange
        mytmp['scan'] = scan
        mytmp['scanintent'] = scanintent
        mytmp['array'] = array
        mytmp['uvrange'] = uvrange
        mytmp['observation'] = observation
        pathname='file:///'+os.environ.get('CASAPATH').split()[0]+'/share/xml/'
        trec = casac.utils().torecord(pathname+'partition.xml')

        casalog.origin('partition')
        if trec.has_key('partition') and casac.utils().verify(mytmp, trec['partition']) :
            result = task_partition.partition(vis, outputvis, createmms, separationaxis, numsubms, datacolumn, calmsselection, calmsname, calfield, calscan, calintent, field, spw, antenna, timebin, combine, timerange, scan, scanintent, array, uvrange, observation)

        else :
          result = False
        return result