Hive step.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import boto\n",
    "from boto.emr.step import HiveStep\n",
    "from boto.s3.key import Key\n",
    "import pystache\n",
    "\n",
    "emr = boto.emr.connect_to_region('eu-west-1')\n",
    "bucket = boto.connect_s3().get_bucket('short-edition-big-data', validate=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "hql = u\"\"\"CREATE EXTERNAL TABLE IF NOT EXISTS table_02 (col_1 STRING, col_2 STRING)\n",
    "          ROW FORMAT DELIMITED FIELDS TERMINATED BY ','  \n",
    "          LOCATION 's3://short-edition-big-data/emr/runs/{{exp_name}}/table-02';\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CREATE EXTERNAL TABLE IF NOT EXISTS table_02 (col_1 STRING, col_2 STRING)\n",
      "          ROW FORMAT DELIMITED FIELDS TERMINATED BY ','  \n",
      "          LOCATION 's3://short-edition-big-data/emr/runs/dummy/table-02';\n"
     ]
    }
   ],
   "source": [
    "hive_script = pystache.render(hql, {'exp_name': 'dummy'})\n",
    "print hive_script"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "205"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Key(bucket, name=\"/emr/scripts/test-step.hql\").set_contents_from_string(hive_script)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "step = HiveStep(\n",
    "    name=\"Test de step Hive\",\n",
    "    hive_file=\"s3://short-edition-big-data/emr/scripts/test-step.hql\",\n",
    "    hive_versions='latest',\n",
    "    hive_args=None\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<boto.emr.emrobject.JobFlowStepList at 0x107a1b7d0>"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emr.add_jobflow_steps(\"j-3SIKYPKV5G6SE\", step)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}