spark notebook example

demo.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "\n",
    "def inside(p):\n",
    "    x, y = random.random(), random.random()\n",
    "    return x*x + y*y < 1\n",
    "\n",
    "NUM_SAMPLES=1000000\n",
    "\n",
    "count = sc.parallelize(range(0, NUM_SAMPLES)) \\\n",
    "             .filter(inside).count()\n",
    "\n",
    "print(\"Pi is roughly %f\" % (4.0 * count / NUM_SAMPLES))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.mllib.random import RandomRDDs\n",
    "\n",
    "# 1 million\n",
    "NUM_SAMPLES = 1000000\n",
    "\n",
    "# Generates an RDD comprised of i.i.d. samples from the standard normal distribution,\n",
    "# evenly distributed in 10 partitions.\n",
    "normal_01 = RandomRDDs.normalRDD(sc, NUM_SAMPLES, 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Apply a transformation\n",
    "# Transform to different normal dist (different mean and variance)\n",
    "mean = 20\n",
    "stdev = 10\n",
    "normal_2010 = normal_01.map(lambda x: mean + stdev * x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Count is an action - actually evaluates the lazy transformations we have done so far\n",
    "normal_2010.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "normal_2010.sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# collect() processes all transformations and collects the results on the driver\n",
    "# DANGER!!!\n",
    "local_normal_2010 = normal_2010.collect()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "s = pd.Series(local_normal_2010)\n",
    "ax = s.plot.kde()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sc.getConf().getAll()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Spark - Python (Kubernetes Mode)",
   "language": "python",
   "name": "spark_python_kubernetes"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}