Jupyter Pyspark Examples

jupyter_pyspark_examples.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---+-------+---+------+-----+\n",
      "| id|   name|age|points|level|\n",
      "+---+-------+---+------+-----+\n",
      "|  1|Carleen| 24|   245|    5|\n",
      "|  2|  Steve| 31|   567|    7|\n",
      "|  3|    Ann| 41|   354|    5|\n",
      "|  4|   Lars| 30|   156|    3|\n",
      "+---+-------+---+------+-----+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df = sqlCtx.createDataFrame([(1, 'Carleen', 24, 245, 5),\n",
    "                            (2, 'Steve', 31, 567, 7),\n",
    "                            (3, 'Ann', 41, 354, 5),\n",
    "                            (4, 'Lars', 30, 156, 3)], ('id', 'name', 'age', 'points', 'level'))\n",
    "df.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+---+-----+---+------+-----+\n",
      "| id| name|age|points|level|\n",
      "+---+-----+---+------+-----+\n",
      "|  2|Steve| 31|   567|    7|\n",
      "|  3|  Ann| 41|   354|    5|\n",
      "+---+-----+---+------+-----+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df.where(df['age'] > 30).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-------+------------------+-----+-----------------+-----------------+-----------------+\n",
      "|summary|                id| name|              age|           points|            level|\n",
      "+-------+------------------+-----+-----------------+-----------------+-----------------+\n",
      "|  count|                 4|    4|                4|                4|                4|\n",
      "|   mean|               2.5| null|             31.5|            330.5|              5.0|\n",
      "| stddev|1.2909944487358056| null|7.047458170621991|177.2427713617681|1.632993161855452|\n",
      "|    min|                 1|  Ann|               24|              156|                3|\n",
      "|    max|                 4|Steve|               41|              567|                7|\n",
      "+-------+------------------+-----+-----------------+-----------------+-----------------+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df.describe().show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read from S3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = sqlContext.read.parquet('s3://us-east-1.elasticmapreduce.samples/flightdata/input')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "df = df.select('flightdate', 'origin', 'dest',  'airtime', 'distance', 'cancelled', 'securitydelay')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+----------+------+----+-------+--------+---------+-------------+\n",
      "|flightdate|origin|dest|airtime|distance|cancelled|securitydelay|\n",
      "+----------+------+----+-------+--------+---------+-------------+\n",
      "|2007-01-01|   MSP| DFW|    123|     852|        0|         null|\n",
      "|2007-01-01|   DFW| MSP|    110|     852|        0|         null|\n",
      "|2007-01-01|   ROC| MSP|    117|     783|        0|         null|\n",
      "|2007-01-01|   MSP| OKC|    102|     695|        0|            0|\n",
      "|2007-01-01|   MSP| OKC|    101|     695|        0|         null|\n",
      "|2007-01-01|   DTW| LNK|    105|     701|        0|         null|\n",
      "|2007-01-01|   MEM| MSP|    105|     700|        0|            0|\n",
      "|2007-01-01|   MSP| MDT|    110|     898|        0|         null|\n",
      "|2007-01-01|   MSP| AVL|    110|     861|        0|         null|\n",
      "|2007-01-01|   AVL| MSP|    120|     861|        0|         null|\n",
      "|2007-01-01|   DTW| XNA|    112|     716|        0|            0|\n",
      "|2007-01-01|   TUL| DTW|    107|     790|        0|            0|\n",
      "|2007-01-01|   DTW| TUL|    120|     790|        0|         null|\n",
      "|2007-01-01|   AUS| DTW|    161|    1149|        0|         null|\n",
      "|2007-01-01|   BGR| DTW|    132|     750|        0|            0|\n",
      "|2007-01-01|   BGR| DTW|    119|     750|        0|            0|\n",
      "|2007-01-01|   IND| FLL|    156|    1005|        0|            0|\n",
      "|2007-01-01|   FLL| IND|    138|    1005|        0|            0|\n",
      "|2007-01-01|   DSM| DCA|    112|     897|        0|         null|\n",
      "|2007-01-01|   DCA| DSM|    141|     897|        0|            0|\n",
      "+----------+------+----+-------+--------+---------+-------------+\n",
      "only showing top 20 rows\n",
      "\n"
     ]
    }
   ],
   "source": [
    "df.where(df['airtime'] > 100).show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}