summaryrefslogblamecommitdiff
path: root/site/docs/0.9.0/api/pyspark/pyspark.broadcast-pysrc.html
blob: e7e3934b9f0b76a9b6c92188f9caacc441120b49 (plain) (tree)






































































































































































                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            
                                                         


















                                                                
<?xml version="1.0" encoding="ascii"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
          "DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
  <title>pyspark.broadcast</title>
  <link rel="stylesheet" href="epydoc.css" type="text/css" />
  <script type="text/javascript" src="epydoc.js"></script>
</head>

<body bgcolor="white" text="black" link="blue" vlink="#204080"
      alink="#204080">
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
       bgcolor="#a0c0ff" cellspacing="0">
  <tr valign="middle">
  <!-- Home link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="pyspark-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Tree link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Index link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Help link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Project homepage -->
      <th class="navbar" align="right" width="100%">
        <table border="0" cellpadding="0" cellspacing="0">
          <tr><th class="navbar" align="center"
            ><a class="navbar" target="_top" href="http://spark-project.org">PySpark</a></th>
          </tr></table></th>
  </tr>
</table>
<table width="100%" cellpadding="0" cellspacing="0">
  <tr valign="top">
    <td width="100%">
      <span class="breadcrumbs">
        <a href="pyspark-module.html">Package&nbsp;pyspark</a> ::
        Module&nbsp;broadcast
      </span>
    </td>
    <td>
      <table cellpadding="0" cellspacing="0">
        <!-- hide/show private -->
        <tr><td align="right"><span class="options"
            >[<a href="frames.html" target="_top">frames</a
            >]&nbsp;|&nbsp;<a href="pyspark.broadcast-pysrc.html"
            target="_top">no&nbsp;frames</a>]</span></td></tr>
      </table>
    </td>
  </tr>
</table>
<h1 class="epydoc">Source Code for <a href="pyspark.broadcast-module.html">Module pyspark.broadcast</a></h1>
<pre class="py-src">
<a name="L1"></a><tt class="py-lineno"> 1</tt>  <tt class="py-line"><tt class="py-comment">#</tt> </tt>
<a name="L2"></a><tt class="py-lineno"> 2</tt>  <tt class="py-line"><tt class="py-comment"># Licensed to the Apache Software Foundation (ASF) under one or more</tt> </tt>
<a name="L3"></a><tt class="py-lineno"> 3</tt>  <tt class="py-line"><tt class="py-comment"># contributor license agreements.  See the NOTICE file distributed with</tt> </tt>
<a name="L4"></a><tt class="py-lineno"> 4</tt>  <tt class="py-line"><tt class="py-comment"># this work for additional information regarding copyright ownership.</tt> </tt>
<a name="L5"></a><tt class="py-lineno"> 5</tt>  <tt class="py-line"><tt class="py-comment"># The ASF licenses this file to You under the Apache License, Version 2.0</tt> </tt>
<a name="L6"></a><tt class="py-lineno"> 6</tt>  <tt class="py-line"><tt class="py-comment"># (the "License"); you may not use this file except in compliance with</tt> </tt>
<a name="L7"></a><tt class="py-lineno"> 7</tt>  <tt class="py-line"><tt class="py-comment"># the License.  You may obtain a copy of the License at</tt> </tt>
<a name="L8"></a><tt class="py-lineno"> 8</tt>  <tt class="py-line"><tt class="py-comment">#</tt> </tt>
<a name="L9"></a><tt class="py-lineno"> 9</tt>  <tt class="py-line"><tt class="py-comment">#    http://www.apache.org/licenses/LICENSE-2.0</tt> </tt>
<a name="L10"></a><tt class="py-lineno">10</tt>  <tt class="py-line"><tt class="py-comment">#</tt> </tt>
<a name="L11"></a><tt class="py-lineno">11</tt>  <tt class="py-line"><tt class="py-comment"># Unless required by applicable law or agreed to in writing, software</tt> </tt>
<a name="L12"></a><tt class="py-lineno">12</tt>  <tt class="py-line"><tt class="py-comment"># distributed under the License is distributed on an "AS IS" BASIS,</tt> </tt>
<a name="L13"></a><tt class="py-lineno">13</tt>  <tt class="py-line"><tt class="py-comment"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</tt> </tt>
<a name="L14"></a><tt class="py-lineno">14</tt>  <tt class="py-line"><tt class="py-comment"># See the License for the specific language governing permissions and</tt> </tt>
<a name="L15"></a><tt class="py-lineno">15</tt>  <tt class="py-line"><tt class="py-comment"># limitations under the License.</tt> </tt>
<a name="L16"></a><tt class="py-lineno">16</tt>  <tt class="py-line"><tt class="py-comment">#</tt> </tt>
<a name="L17"></a><tt class="py-lineno">17</tt>  <tt class="py-line"> </tt>
<a name="L18"></a><tt class="py-lineno">18</tt>  <tt class="py-line"><tt class="py-docstring">"""</tt> </tt>
<a name="L19"></a><tt class="py-lineno">19</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; from pyspark.context import SparkContext</tt> </tt>
<a name="L20"></a><tt class="py-lineno">20</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; sc = SparkContext('local', 'test')</tt> </tt>
<a name="L21"></a><tt class="py-lineno">21</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; b = sc.broadcast([1, 2, 3, 4, 5])</tt> </tt>
<a name="L22"></a><tt class="py-lineno">22</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; b.value</tt> </tt>
<a name="L23"></a><tt class="py-lineno">23</tt>  <tt class="py-line"><tt class="py-docstring">[1, 2, 3, 4, 5]</tt> </tt>
<a name="L24"></a><tt class="py-lineno">24</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L25"></a><tt class="py-lineno">25</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; from pyspark.broadcast import _broadcastRegistry</tt> </tt>
<a name="L26"></a><tt class="py-lineno">26</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; _broadcastRegistry[b.bid] = b</tt> </tt>
<a name="L27"></a><tt class="py-lineno">27</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; from cPickle import dumps, loads</tt> </tt>
<a name="L28"></a><tt class="py-lineno">28</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; loads(dumps(b)).value</tt> </tt>
<a name="L29"></a><tt class="py-lineno">29</tt>  <tt class="py-line"><tt class="py-docstring">[1, 2, 3, 4, 5]</tt> </tt>
<a name="L30"></a><tt class="py-lineno">30</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L31"></a><tt class="py-lineno">31</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; sc.parallelize([0, 0]).flatMap(lambda x: b.value).collect()</tt> </tt>
<a name="L32"></a><tt class="py-lineno">32</tt>  <tt class="py-line"><tt class="py-docstring">[1, 2, 3, 4, 5, 1, 2, 3, 4, 5]</tt> </tt>
<a name="L33"></a><tt class="py-lineno">33</tt>  <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L34"></a><tt class="py-lineno">34</tt>  <tt class="py-line"><tt class="py-docstring">&gt;&gt;&gt; large_broadcast = sc.broadcast(list(range(10000)))</tt> </tt>
<a name="L35"></a><tt class="py-lineno">35</tt>  <tt class="py-line"><tt class="py-docstring">"""</tt> </tt>
<a name="L36"></a><tt class="py-lineno">36</tt>  <tt class="py-line"><tt class="py-comment"># Holds broadcasted data received from Java, keyed by its id.</tt> </tt>
<a name="L37"></a><tt class="py-lineno">37</tt>  <tt class="py-line"><tt id="link-0" class="py-name" targets="Variable pyspark.broadcast._broadcastRegistry=pyspark.broadcast-module.html#_broadcastRegistry"><a title="pyspark.broadcast._broadcastRegistry" class="py-name" href="#" onclick="return doclink('link-0', '_broadcastRegistry', 'link-0');">_broadcastRegistry</a></tt> <tt class="py-op">=</tt> <tt class="py-op">{</tt><tt class="py-op">}</tt> </tt>
<a name="L38"></a><tt class="py-lineno">38</tt>  <tt class="py-line"> </tt>
<a name="L39"></a><tt class="py-lineno">39</tt>  <tt class="py-line"> </tt>
<a name="_from_id"></a><div id="_from_id-def"><a name="L40"></a><tt class="py-lineno">40</tt> <a class="py-toggle" href="#" id="_from_id-toggle" onclick="return toggle('_from_id');">-</a><tt class="py-line"><tt class="py-keyword">def</tt> <a class="py-def-name" href="pyspark.broadcast-module.html#_from_id">_from_id</a><tt class="py-op">(</tt><tt class="py-param">bid</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="_from_id-collapsed" style="display:none;" pad="++" indent="++++"></div><div id="_from_id-expanded"><a name="L41"></a><tt class="py-lineno">41</tt>  <tt class="py-line">    <tt class="py-keyword">from</tt> <tt id="link-1" class="py-name" targets="Package pyspark=pyspark-module.html"><a title="pyspark" class="py-name" href="#" onclick="return doclink('link-1', 'pyspark', 'link-1');">pyspark</a></tt><tt class="py-op">.</tt><tt id="link-2" class="py-name" targets="Module pyspark.broadcast=pyspark.broadcast-module.html,Method pyspark.context.SparkContext.broadcast()=pyspark.context.SparkContext-class.html#broadcast"><a title="pyspark.broadcast
pyspark.context.SparkContext.broadcast" class="py-name" href="#" onclick="return doclink('link-2', 'broadcast', 'link-2');">broadcast</a></tt> <tt class="py-keyword">import</tt> <tt id="link-3" class="py-name"><a title="pyspark.broadcast._broadcastRegistry" class="py-name" href="#" onclick="return doclink('link-3', '_broadcastRegistry', 'link-0');">_broadcastRegistry</a></tt> </tt>
<a name="L42"></a><tt class="py-lineno">42</tt>  <tt class="py-line">    <tt class="py-keyword">if</tt> <tt class="py-name">bid</tt> <tt class="py-keyword">not</tt> <tt class="py-keyword">in</tt> <tt id="link-4" class="py-name"><a title="pyspark.broadcast._broadcastRegistry" class="py-name" href="#" onclick="return doclink('link-4', '_broadcastRegistry', 'link-0');">_broadcastRegistry</a></tt><tt class="py-op">:</tt> </tt>
<a name="L43"></a><tt class="py-lineno">43</tt>  <tt class="py-line">        <tt class="py-keyword">raise</tt> <tt class="py-name">Exception</tt><tt class="py-op">(</tt><tt class="py-string">"Broadcast variable '%s' not loaded!"</tt> <tt class="py-op">%</tt> <tt class="py-name">bid</tt><tt class="py-op">)</tt> </tt>
<a name="L44"></a><tt class="py-lineno">44</tt>  <tt class="py-line">    <tt class="py-keyword">return</tt> <tt id="link-5" class="py-name"><a title="pyspark.broadcast._broadcastRegistry" class="py-name" href="#" onclick="return doclink('link-5', '_broadcastRegistry', 'link-0');">_broadcastRegistry</a></tt><tt class="py-op">[</tt><tt class="py-name">bid</tt><tt class="py-op">]</tt> </tt>
</div><a name="L45"></a><tt class="py-lineno">45</tt>  <tt class="py-line"> </tt>
<a name="L46"></a><tt class="py-lineno">46</tt>  <tt class="py-line"> </tt>
<a name="Broadcast"></a><div id="Broadcast-def"><a name="L47"></a><tt class="py-lineno">47</tt> <a class="py-toggle" href="#" id="Broadcast-toggle" onclick="return toggle('Broadcast');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="pyspark.broadcast.Broadcast-class.html">Broadcast</a><tt class="py-op">(</tt><tt class="py-base-class">object</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="Broadcast-collapsed" style="display:none;" pad="++" indent="++++"></div><div id="Broadcast-expanded"><a name="L48"></a><tt class="py-lineno">48</tt>  <tt class="py-line">    <tt class="py-docstring">"""</tt> </tt>
<a name="L49"></a><tt class="py-lineno">49</tt>  <tt class="py-line"><tt class="py-docstring">    A broadcast variable created with</tt> </tt>
<a name="L50"></a><tt class="py-lineno">50</tt>  <tt class="py-line"><tt class="py-docstring">    L{SparkContext.broadcast()&lt;pyspark.context.SparkContext.broadcast&gt;}.</tt> </tt>
<a name="L51"></a><tt class="py-lineno">51</tt>  <tt class="py-line"><tt class="py-docstring">    Access its value through C{.value}.</tt> </tt>
<a name="L52"></a><tt class="py-lineno">52</tt>  <tt class="py-line"><tt class="py-docstring">    """</tt> </tt>
<a name="L53"></a><tt class="py-lineno">53</tt>  <tt class="py-line"> </tt>
<a name="Broadcast.__init__"></a><div id="Broadcast.__init__-def"><a name="L54"></a><tt class="py-lineno">54</tt> <a class="py-toggle" href="#" id="Broadcast.__init__-toggle" onclick="return toggle('Broadcast.__init__');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="pyspark.broadcast.Broadcast-class.html#__init__">__init__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">bid</tt><tt class="py-op">,</tt> <tt class="py-param">value</tt><tt class="py-op">,</tt> <tt class="py-param">java_broadcast</tt><tt class="py-op">=</tt><tt class="py-name">None</tt><tt class="py-op">,</tt> <tt class="py-param">pickle_registry</tt><tt class="py-op">=</tt><tt class="py-name">None</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="Broadcast.__init__-collapsed" style="display:none;" pad="++" indent="++++++++"></div><div id="Broadcast.__init__-expanded"><a name="L55"></a><tt class="py-lineno">55</tt>  <tt class="py-line">        <tt class="py-docstring">"""</tt> </tt>
<a name="L56"></a><tt class="py-lineno">56</tt>  <tt class="py-line"><tt class="py-docstring">        Should not be called directly by users -- use</tt> </tt>
<a name="L57"></a><tt class="py-lineno">57</tt>  <tt class="py-line"><tt class="py-docstring">        L{SparkContext.broadcast()&lt;pyspark.context.SparkContext.broadcast&gt;}</tt> </tt>
<a name="L58"></a><tt class="py-lineno">58</tt>  <tt class="py-line"><tt class="py-docstring">        instead.</tt> </tt>
<a name="L59"></a><tt class="py-lineno">59</tt>  <tt class="py-line"><tt class="py-docstring">        """</tt> </tt>
<a name="L60"></a><tt class="py-lineno">60</tt>  <tt class="py-line">        <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-6" class="py-name" targets="Method pyspark.accumulators.Accumulator.value()=pyspark.accumulators.Accumulator-class.html#value"><a title="pyspark.accumulators.Accumulator.value" class="py-name" href="#" onclick="return doclink('link-6', 'value', 'link-6');">value</a></tt> <tt class="py-op">=</tt> <tt id="link-7" class="py-name"><a title="pyspark.accumulators.Accumulator.value" class="py-name" href="#" onclick="return doclink('link-7', 'value', 'link-6');">value</a></tt> </tt>
<a name="L61"></a><tt class="py-lineno">61</tt>  <tt class="py-line">        <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">bid</tt> <tt class="py-op">=</tt> <tt class="py-name">bid</tt> </tt>
<a name="L62"></a><tt class="py-lineno">62</tt>  <tt class="py-line">        <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_jbroadcast</tt> <tt class="py-op">=</tt> <tt class="py-name">java_broadcast</tt> </tt>
<a name="L63"></a><tt class="py-lineno">63</tt>  <tt class="py-line">        <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_pickle_registry</tt> <tt class="py-op">=</tt> <tt class="py-name">pickle_registry</tt> </tt>
</div><a name="L64"></a><tt class="py-lineno">64</tt>  <tt class="py-line"> </tt>
<a name="Broadcast.__reduce__"></a><div id="Broadcast.__reduce__-def"><a name="L65"></a><tt class="py-lineno">65</tt> <a class="py-toggle" href="#" id="Broadcast.__reduce__-toggle" onclick="return toggle('Broadcast.__reduce__');">-</a><tt class="py-line">    <tt class="py-keyword">def</tt> <a class="py-def-name" href="pyspark.broadcast.Broadcast-class.html#__reduce__">__reduce__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="Broadcast.__reduce__-collapsed" style="display:none;" pad="++" indent="++++++++"></div><div id="Broadcast.__reduce__-expanded"><a name="L66"></a><tt class="py-lineno">66</tt>  <tt class="py-line">        <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_pickle_registry</tt><tt class="py-op">.</tt><tt id="link-8" class="py-name" targets="Method pyspark.accumulators.Accumulator.add()=pyspark.accumulators.Accumulator-class.html#add"><a title="pyspark.accumulators.Accumulator.add" class="py-name" href="#" onclick="return doclink('link-8', 'add', 'link-8');">add</a></tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">)</tt> </tt>
<a name="L67"></a><tt class="py-lineno">67</tt>  <tt class="py-line">        <tt class="py-keyword">return</tt> <tt class="py-op">(</tt><tt class="py-name">_from_id</tt><tt class="py-op">,</tt> <tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">bid</tt><tt class="py-op">,</tt> <tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
</div></div><a name="L68"></a><tt class="py-lineno">68</tt>  <tt class="py-line"> </tt><script type="text/javascript">
<!--
expandto(location.href);
// -->
</script>
</pre>
<br />
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
       bgcolor="#a0c0ff" cellspacing="0">
  <tr valign="middle">
  <!-- Home link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="pyspark-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Tree link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Index link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Help link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Project homepage -->
      <th class="navbar" align="right" width="100%">
        <table border="0" cellpadding="0" cellspacing="0">
          <tr><th class="navbar" align="center"
            ><a class="navbar" target="_top" href="http://spark-project.org">PySpark</a></th>
          </tr></table></th>
  </tr>
</table>
<table border="0" cellpadding="0" cellspacing="0" width="100%%">
  <tr>
    <td align="left" class="footer">
    Generated by Epydoc 3.0.1 on Sun Mar  2 16:35:00 2014
    </td>
    <td align="right" class="footer">
      <a target="mainFrame" href="http://epydoc.sourceforge.net"
        >http://epydoc.sourceforge.net</a>
    </td>
  </tr>
</table>

<script type="text/javascript">
  <!--
  // Private objects are initially displayed (because if
  // javascript is turned off then we want them to be
  // visible); but by default, we want to hide them.  So hide
  // them unless we have a cookie that says to show them.
  checkCookie();
  // -->
</script>
</body>
</html>