{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Selecting columns of CS82\n",
    "\n",
    "We want to publish the CS82 catalog through VO.\n",
    "To publish it in VO we will use DaCHS, which pretty much is an interface to a (Postgres) database.\n",
    "Although DaCHS does a great job on data management, ingesting a ~million entries + dozens columns catalog can be\n",
    "quite slow, so we want to improve this step.\n",
    "\n",
    "The way we will \"improve\" the data ingestion is by reducing the amount of data to ingest: all entries (rows) will be ingested, but most probably some columns are not really usefull (for our purposes) and we may avoid them.\n",
    "\n",
    "This note, then, is a superficial investigation of CS82 data and metadata features."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "filename = 'cs82_phz.fits'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "from importlib import reload"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<module 'table' from '/home/chbrandt/Dropbox/PhD/code_repositories/emptyspace/table/__init__.py'>"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# from emptyspace\n",
    "import table\n",
    "reload(table)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Help on package table:\n",
      "\n",
      "NAME\n",
      "    table\n",
      "\n",
      "PACKAGE CONTENTS\n",
      "    acolumn\n",
      "    adataframe\n",
      "    ametatable\n",
      "    atable\n",
      "    io (package)\n",
      "    ucd (package)\n",
      "    utils (package)\n",
      "\n",
      "FUNCTIONS\n",
      "    info(filename)\n",
      "        (FITS only) Print the list columns and table's metadata\n",
      "    \n",
      "    read(filename, format=None, columns=None, rows=None, ucds=None, metatable=None, metaonly=False, **kwargs)\n",
      "        Return ~ATable from catalog 'filename'\n",
      "        \n",
      "        Input:\n",
      "         - filename : string\n",
      "         - format   : string : 'fits','ecsv','csv'\n",
      "         - columns  : list of strings or integers\n",
      "         - rows     : integer, float, list of integers\n",
      "         - ucds     : list of strings\n",
      "         - metatable : string : name of the metatable file\n",
      "         - metaonly  : boolean\n",
      "\n",
      "DATA\n",
      "    absolute_import = _Feature((2, 5, 0, 'alpha', 1), (3, 0, 0, 'alpha', 0...\n",
      "\n",
      "FILE\n",
      "    /home/chbrandt/Dropbox/PhD/code_repositories/emptyspace/table/__init__.py\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "help(table)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "  file: cs82_phz.fits\n",
      "  extension: 1\n",
      "  type: BINARY_TBL\n",
      "  extname: Joined\n",
      "  rows: 5777379\n",
      "  column info:\n",
      "    OBJID_CS82          i4  \n",
      "    RA                  f8  \n",
      "    DEC                 f8  \n",
      "    FLAGS               i2  \n",
      "    WEIGHT              f4  \n",
      "    FITCLASS            i2  \n",
      "    MAG_AUTO            f4  \n",
      "    MAGERR_AUTO         f4  \n",
      "    MAG_EXP             f4  \n",
      "    MAG_PSF             f4  \n",
      "    REFF_EXP            f8  \n",
      "    ASPECT_EXP          f4  \n",
      "    MU_MEAN_EXP         f8  \n",
      "    P_EXP               f4  \n",
      "    N_SER               f4  \n",
      "    SPREAD_MODEL_SER\n",
      "                        f4  \n",
      "    LENS                i2  \n",
      "    OBJID_SDSS          i8  \n",
      "    MAG_DERED_U         f8  \n",
      "    MAG_DERED_G         f8  \n",
      "    MAG_DERED_R         f8  \n",
      "    MAG_DERED_I         f8  \n",
      "    MAG_DERED_Z         f8  \n",
      "    ZSPEC               f8  \n",
      "    ZPHOT               f8  \n",
      "    ZMORPH              f8  \n",
      "    ZBEST               f8  \n",
      "    ODDS_PHOT           f8  \n",
      "    ODDS_MORPH          f8  \n",
      "    ODDS_BEST           f8  \n",
      "    SOURCE_SPEC         S7  \n",
      "    CLASS_SPEC          S6  \n",
      "None\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<table.io._fitsio.FitsHandler at 0x7f6a362fa160>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "table.info(filename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = 'OBJID_CS82,RA,DEC,MAG_AUTO,MAGERR_AUTO'.split(',')\n",
    "cat = table.read(filename, columns=cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "cat.write('cs82_phz_REDUCED.fits', format='fits')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}