python-toolbox/notebooks/count-db-tables-rows.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Count DB Tables Rows"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Getting spark session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from marvin_python_toolbox.common.data_source_provider import get_spark_session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "spark = get_spark_session(enable_hive=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Getting all hive local dbs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "dbs = spark.sql(\"show databases\").collect()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Connecting with core db ...\n",
      "   bsc_product [14953204]\n",
      "   mis_product_hierarchy [5796251]\n",
      "Connecting with default db ...\n",
      "Connecting with marvin db ...\n",
      "   simple_product_classification_engine_core_bsc_product_120374ac16e58cdf8f0c050d0f698addadf2c41c [14953204]\n",
      "   simple_product_classification_engine_core_mis_product_hierarchy_0b8069f3ba31eedca44b30bc8a61130f5776d119 [5796251]\n"
     ]
    }
   ],
   "source": [
    "for db in dbs:\n",
    "    db_name = db['databaseName']\n",
    "    print(\"Connecting with {} db ...\".format(db_name)) \n",
    "    spark.sql(\"use {}\".format(db_name))\n",
    "    tables = spark.sql(\"show tables\").collect()\n",
    "    \n",
    "    for table in tables:\n",
    "        table_name = table['tableName']\n",
    "        count = spark.sql(\"select 1 from {}\".format(table_name)).count()\n",
    "        print \"   {} [{}]\".format(table_name, count)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stoping and realease spark session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "spark.stop()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "14953204"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "spark.sql(\"select * from core.bsc_product\").count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}