docs/notebook/carbondata_notebook.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "910ebdc2",
   "metadata": {},
   "source": [
    "## 1. Init spark with CarbonExtensions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f73459bd",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "spark = SparkSession.builder.enableHiveSupport().config(\"spark.sql.extensions\", \"org.apache.spark.sql.CarbonExtensions\").getOrCreate()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b73232b2",
   "metadata": {},
   "source": [
    "## 2. Create CarbonData table and insert data by using spark sql"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d458dc3a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "++\n",
      "||\n",
      "++\n",
      "++\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "DataFrame[]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "spark.sql(\"DROP TABLE IF EXISTS carbondata_table\").show()\n",
    "spark.sql(\"CREATE TABLE IF NOT EXISTS carbondata_table( age INT,adult BOOLEAN) USING carbon\")\n",
    "spark.sql(\"INSERT INTO carbondata_table VALUES(20,true)\")\n",
    "spark.sql(\"INSERT INTO carbondata_table VALUES(10,false)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "edfc1eeb",
   "metadata": {},
   "source": [
    "## 3. Select data from CarbonData table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "2c234b64",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---+-----+\n",
      "|age|adult|\n",
      "+---+-----+\n",
      "| 10|false|\n",
      "| 20| true|\n",
      "+---+-----+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "spark.sql(\"SELECT * FROM carbondata_table\").show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c5df896b",
   "metadata": {},
   "source": [
    "## 4. Describe the CarbonData table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ac65cba3",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---------+-------+\n",
      "|col_name|data_type|comment|\n",
      "+--------+---------+-------+\n",
      "|     age|      int|   null|\n",
      "|   adult|  boolean|   null|\n",
      "+--------+---------+-------+\n",
      "\n",
      "+--------------------+--------------------+-------+\n",
      "|            col_name|           data_type|comment|\n",
      "+--------------------+--------------------+-------+\n",
      "|                 age|                 int|   null|\n",
      "|               adult|             boolean|   null|\n",
      "|                    |                    |       |\n",
      "|# Detailed Table ...|                    |       |\n",
      "|            Database|             default|       |\n",
      "|               Table|    carbondata_table|       |\n",
      "|               Owner|              jovyan|       |\n",
      "|        Created Time|Sat Apr 15 17:22:...|       |\n",
      "|         Last Access|             UNKNOWN|       |\n",
      "|          Created By|         Spark 3.1.1|       |\n",
      "|                Type|             MANAGED|       |\n",
      "|            Provider|              carbon|       |\n",
      "|            Location|file:/home/jovyan...|       |\n",
      "|       Serde Library|org.apache.carbon...|       |\n",
      "|         InputFormat|org.apache.carbon...|       |\n",
      "|        OutputFormat|org.apache.carbon...|       |\n",
      "+--------------------+--------------------+-------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "spark.sql(\"DESCRIBE carbondata_table\").show()\n",
    "spark.sql(\"DESCRIBE FORMATTED carbondata_table\").show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bfdcae5a",
   "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": "3.9.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}