Tutorial 4- Pyspark Dataframes- Filter operation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5d6364f6",
   "metadata": {},
   "source": [
    "### Pyspark Dataframes\n",
    "- Filter Operation\n",
    "- &,|,==\n",
    "- ~"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d8d843e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9fd2900c",
   "metadata": {},
   "outputs": [],
   "source": [
    "spark=SparkSession.builder.appName('dataframe').getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7964d064",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---------+---+----------+------+\n",
      "|     Name|age|Experience|Salary|\n",
      "+---------+---+----------+------+\n",
      "|    Krish| 31|        10| 30000|\n",
      "|Sudhanshu| 30|         8| 25000|\n",
      "|    Sunny| 29|         4| 20000|\n",
      "|     Paul| 24|         3| 20000|\n",
      "|   Harsha| 21|         1| 15000|\n",
      "|  Shubham| 23|         2| 18000|\n",
      "+---------+---+----------+------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df_pyspark=spark.read.csv('test1.csv',header=True,inferSchema=True)\n",
    "df_pyspark.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e0fdbb15",
   "metadata": {},
   "source": [
    "### Filter Operations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c21edffc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-------+---+----------+------+\n",
      "|   Name|age|Experience|Salary|\n",
      "+-------+---+----------+------+\n",
      "|  Sunny| 29|         4| 20000|\n",
      "|   Paul| 24|         3| 20000|\n",
      "| Harsha| 21|         1| 15000|\n",
      "|Shubham| 23|         2| 18000|\n",
      "+-------+---+----------+------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "### Salary of the people less than or equal to 20000\n",
    "df_pyspark.filter(\"Salary<=20000\").show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d5a5f3af",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-------+---+\n",
      "|   Name|age|\n",
      "+-------+---+\n",
      "|  Sunny| 29|\n",
      "|   Paul| 24|\n",
      "| Harsha| 21|\n",
      "|Shubham| 23|\n",
      "+-------+---+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter(\"Salary<=20000\").select(['Name','age']).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4bebe963",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-------+---+----------+------+\n",
      "|   Name|age|Experience|Salary|\n",
      "+-------+---+----------+------+\n",
      "|  Sunny| 29|         4| 20000|\n",
      "|   Paul| 24|         3| 20000|\n",
      "| Harsha| 21|         1| 15000|\n",
      "|Shubham| 23|         2| 18000|\n",
      "+-------+---+----------+------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter(df_pyspark['Salary']<=20000).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "26f76ee1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---------+---+----------+------+\n",
      "|     Name|age|Experience|Salary|\n",
      "+---------+---+----------+------+\n",
      "|    Krish| 31|        10| 30000|\n",
      "|Sudhanshu| 30|         8| 25000|\n",
      "|    Sunny| 29|         4| 20000|\n",
      "|     Paul| 24|         3| 20000|\n",
      "|   Harsha| 21|         1| 15000|\n",
      "|  Shubham| 23|         2| 18000|\n",
      "+---------+---+----------+------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter((df_pyspark['Salary']<=20000) | \n",
    "                  (df_pyspark['Salary']>=15000)).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5df3d5ab",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---------+---+----------+------+\n",
      "|     Name|age|Experience|Salary|\n",
      "+---------+---+----------+------+\n",
      "|    Krish| 31|        10| 30000|\n",
      "|Sudhanshu| 30|         8| 25000|\n",
      "+---------+---+----------+------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter(~(df_pyspark['Salary']<=20000)).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "afc87f75",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "060e065a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5a4c8d24",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "699d560f",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bd74ab0c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cbc4375a",
   "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": "3.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}