|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": {}, |
| 6 | + "source": [ |
| 7 | + "## How to run pyspark in Anaconda Jupyter Notebook" |
| 8 | + ] |
| 9 | + }, |
| 10 | + { |
| 11 | + "cell_type": "markdown", |
| 12 | + "metadata": {}, |
| 13 | + "source": [ |
| 14 | + " 1. Set following environment variables\n", |
| 15 | + " ```bat\n", |
| 16 | + " setx HADOOP_HOME C:\\demo\\hadoop27\n", |
| 17 | + " setx SPARK_HOME C:\\demo\\spark3\n", |
| 18 | + " setx PYSPARK_PYTHON C:\\Users\\prashant\\Anaconda3\\python \n", |
| 19 | + " \n", |
| 20 | + " ```\n", |
| 21 | + " 2. Start Anacoda Prompt\n", |
| 22 | + " 3. Install findspark uisng following command\n", |
| 23 | + " ```bat \n", |
| 24 | + " python -m pip install findspark\n", |
| 25 | + " \n", |
| 26 | + " ```\n", |
| 27 | + " 4. Start Jupyter Notenook" |
| 28 | + ] |
| 29 | + }, |
| 30 | + { |
| 31 | + "cell_type": "code", |
| 32 | + "execution_count": 1, |
| 33 | + "metadata": {}, |
| 34 | + "outputs": [], |
| 35 | + "source": [ |
| 36 | + "import findspark\n", |
| 37 | + "findspark.init()\n", |
| 38 | + "import pyspark\n", |
| 39 | + "from pyspark.sql import SparkSession" |
| 40 | + ] |
| 41 | + }, |
| 42 | + { |
| 43 | + "cell_type": "code", |
| 44 | + "execution_count": 4, |
| 45 | + "metadata": { |
| 46 | + "scrolled": true |
| 47 | + }, |
| 48 | + "outputs": [ |
| 49 | + { |
| 50 | + "name": "stdout", |
| 51 | + "output_type": "stream", |
| 52 | + "text": [ |
| 53 | + "+----+--------+\n", |
| 54 | + "| age| name|\n", |
| 55 | + "+----+--------+\n", |
| 56 | + "|null|Prashant|\n", |
| 57 | + "| 30| Abdul|\n", |
| 58 | + "| 19| Justin|\n", |
| 59 | + "| 43| Andy|\n", |
| 60 | + "+----+--------+\n", |
| 61 | + "\n" |
| 62 | + ] |
| 63 | + } |
| 64 | + ], |
| 65 | + "source": [ |
| 66 | + "spark = SparkSession.builder.getOrCreate()\n", |
| 67 | + "spark.read.json(\"C:/demo/notebook/data/people.json\").show()" |
| 68 | + ] |
| 69 | + } |
| 70 | + ], |
| 71 | + "metadata": { |
| 72 | + "kernelspec": { |
| 73 | + "display_name": "Python 3", |
| 74 | + "language": "python", |
| 75 | + "name": "python3" |
| 76 | + }, |
| 77 | + "language_info": { |
| 78 | + "codemirror_mode": { |
| 79 | + "name": "ipython", |
| 80 | + "version": 3 |
| 81 | + }, |
| 82 | + "file_extension": ".py", |
| 83 | + "mimetype": "text/x-python", |
| 84 | + "name": "python", |
| 85 | + "nbconvert_exporter": "python", |
| 86 | + "pygments_lexer": "ipython3", |
| 87 | + "version": "3.7.6" |
| 88 | + } |
| 89 | + }, |
| 90 | + "nbformat": 4, |
| 91 | + "nbformat_minor": 2 |
| 92 | +} |
0 commit comments