PYSPARK DATFRAME - FILTER OPERATION.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "f302546d-2c95-4ac9-8ad4-13a06f7fbdc5",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "### Pyspark Dataframes\n",
    "- Filter Operation\n",
    "- &,|,==\n",
    "- ~"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "1d4bdefb-3b66-45a0-9fe2-bf1978c3829a",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "609d1f9c-4733-46fb-b4c7-b35527f25390",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [],
   "source": [
    "spark=SparkSession.builder.appName('dataframe').getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "862c0113-4971-47f9-aefb-21676f6834bd",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---+----------+------+\n|    Name|Age|Experience|Salary|\n+--------+---+----------+------+\n|   Sapan| 31|        10| 30000|\n|Priyanka| 30|         8| 25000|\n|Gurpreet| 29|         4| 20000|\n|   Payal| 24|         3| 20000|\n|   Priya| 21|         1| 15000|\n|   Aayan| 23|         2| 18000|\n+--------+---+----------+------+\n\n"
     ]
    }
   ],
   "source": [
    "df_pyspark=spark.read.csv('/FileStore/shared_uploads/astartupcto@gmail.com/test1.csv',header=True,inferSchema=True)\n",
    "df_pyspark.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "56fbdb3e-49a3-40a7-b1dc-bc91793c461b",
     "showTitle": false,
     "title": ""
    }
   },
   "source": [
    "### Filter Operations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "93953745-2c9c-4eb4-88cf-930a48dc218f",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---+----------+------+\n|    Name|Age|Experience|Salary|\n+--------+---+----------+------+\n|Gurpreet| 29|         4| 20000|\n|   Payal| 24|         3| 20000|\n|   Priya| 21|         1| 15000|\n|   Aayan| 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": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "ef4caedc-7e8a-4e41-a2cb-5c0bb9f0db34",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---+\n|    Name|age|\n+--------+---+\n|Gurpreet| 29|\n|   Payal| 24|\n|   Priya| 21|\n|   Aayan| 23|\n+--------+---+\n\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter(\"Salary<=20000\").select(['Name','age']).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "d1c0121c-d04a-490c-8ec2-1a66c9ba32be",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---+----------+------+\n|    Name|Age|Experience|Salary|\n+--------+---+----------+------+\n|Gurpreet| 29|         4| 20000|\n|   Payal| 24|         3| 20000|\n|   Priya| 21|         1| 15000|\n|   Aayan| 23|         2| 18000|\n+--------+---+----------+------+\n\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter(df_pyspark['Salary']<=20000).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "ac344f46-7e10-4e5e-9a05-6b60a07009eb",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---+----------+------+\n|    Name|Age|Experience|Salary|\n+--------+---+----------+------+\n|   Sapan| 31|        10| 30000|\n|Priyanka| 30|         8| 25000|\n|Gurpreet| 29|         4| 20000|\n|   Payal| 24|         3| 20000|\n|   Priya| 21|         1| 15000|\n|   Aayan| 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": 0,
   "metadata": {
    "application/vnd.databricks.v1+cell": {
     "cellMetadata": {
      "byteLimit": 2048000,
      "rowLimit": 10000
     },
     "inputWidgets": {},
     "nuid": "b9fe3ffe-bef2-478c-814d-5b0de220a699",
     "showTitle": false,
     "title": ""
    }
   },
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+--------+---+----------+------+\n|    Name|Age|Experience|Salary|\n+--------+---+----------+------+\n|   Sapan| 31|        10| 30000|\n|Priyanka| 30|         8| 25000|\n+--------+---+----------+------+\n\n"
     ]
    }
   ],
   "source": [
    "df_pyspark.filter(~(df_pyspark['Salary']<=20000)).show()"
   ]
  }
 ],
 "metadata": {
  "application/vnd.databricks.v1+notebook": {
   "dashboards": [],
   "environmentMetadata": null,
   "language": "python",
   "notebookMetadata": {
    "pythonIndentUnit": 4
   },
   "notebookName": "PYSPARK DATFRAME - FILTER OPERATION",
   "widgets": {}
  },
  "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": 0
}