spark编程python实例解读

IPYTHON_OPTS="notebook" /opt/spark/bin/pyspark

wxl@wxl-pc:/opt/spark/bin$ spark-submit /bin/spark-submit /home/wxl/Downloads/pysparkdemo.py

ValueError: Cannot run multiple SparkContexts at once; existing SparkContext(app=PySparkShell, master=local[*]) created by <module> at /usr/local/lib/python2.7/dist-packages/IPython/utils/py3compat.py:288

try:
    sc.stop()
except:
    pass
sc=SparkContext('local[2]','First Spark App')

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from pyspark import SparkContext"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "try:\n",
    "    sc.stop()\n",
    "except:\n",
    "    pass\n",
    "sc=SparkContext('local[2]','First Spark App')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "data = sc.textFile(\"data/UserPurchaseHistory.csv\").map(lambda line: line.split(\",\")).map(lambda record: (record[0], record[1], record[2]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total purchases: 5\n"
     ]
    }
   ],
   "source": [
    "numPurchases = data.count()\n",
    "print \"Total purchases: %d\" % numPurchases"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

# coding: utf-8

# In[1]:

from pyspark import SparkContext


# In[2]:

try:
    sc.stop()
except:
    pass
sc=SparkContext('local[2]','First Spark App')


# In[3]:

data = sc.textFile("data/UserPurchaseHistory.csv").map(lambda line: line.split(",")).map(lambda record: (record[0], record[1], record[2]))


# In[4]:

numPurchases = data.count()
print "Total purchases: %d" % numPurchases

# In[ ]: