| |
| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" > |
| <head> |
| <meta charset="utf-8" /> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| |
| <title>Memory and IO Interfaces — Apache Arrow v3.0.0</title> |
| |
| |
| |
| <link rel="stylesheet" href="../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" href="../_static/theme_overrides.css" type="text/css" /> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <!--[if lt IE 9]> |
| <script src="../_static/js/html5shiv.min.js"></script> |
| <![endif]--> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script> |
| <script src="../_static/jquery.js"></script> |
| <script src="../_static/underscore.js"></script> |
| <script src="../_static/doctools.js"></script> |
| <script src="../_static/language_data.js"></script> |
| |
| <script type="text/javascript" src="../_static/js/theme.js"></script> |
| |
| |
| <link rel="canonical" href="https://arrow.apache.org/docs/python/memory.html" /> |
| <link rel="index" title="Index" href="../genindex.html" /> |
| <link rel="search" title="Search" href="../search.html" /> |
| <link rel="next" title="Data Types and In-Memory Data Model" href="data.html" /> |
| <link rel="prev" title="Installing PyArrow" href="install.html" /> |
|
|
|
|
| <!-- Matomo -->
|
| <script>
|
| var _paq = window._paq = window._paq || [];
|
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */
|
| _paq.push(["setDoNotTrack", true]);
|
| _paq.push(["disableCookies"]);
|
| _paq.push(['trackPageView']);
|
| _paq.push(['enableLinkTracking']);
|
| (function() {
|
| var u="https://analytics.apache.org/";
|
| _paq.push(['setTrackerUrl', u+'matomo.php']);
|
| _paq.push(['setSiteId', '20']);
|
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0];
|
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s);
|
| })();
|
| </script>
|
| <!-- End Matomo Code -->
|
|
|
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../index.html" class="icon icon-home"> Apache Arrow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 3.0.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <p class="caption"><span class="caption-text">Specifications and Protocols</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Versioning.html">Format Versioning and Stability</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Columnar.html">Arrow Columnar Format</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Flight.html">Arrow Flight RPC</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Integration.html">Integration Testing</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/CDataInterface.html">The Arrow C data interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/CStreamInterface.html">The Arrow C stream interface</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../format/Other.html">Other Data Structures</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">Libraries</span></p> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../status.html">Implementation Status</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/docs/c_glib/">C/GLib</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../cpp/index.html">C++</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/csharp/README.md">C#</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://godoc.org/github.com/apache/arrow/go/arrow">Go</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../java/index.html">Java</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/docs/js/">JavaScript</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/julia/Arrow/README.md">Julia</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/matlab/README.md">MATLAB</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="index.html">Python</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="install.html">Installing PyArrow</a></li> |
| <li class="toctree-l2 current"><a class="current reference internal" href="#">Memory and IO Interfaces</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="#referencing-and-allocating-memory">Referencing and Allocating Memory</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#pyarrow-buffer">pyarrow.Buffer</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#memory-pools">Memory Pools</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="#input-and-output">Input and Output</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#high-level-api">High-Level API</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#on-disk-and-memory-mapped-files">On-Disk and Memory Mapped Files</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="#in-memory-reading-and-writing">In-Memory Reading and Writing</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="data.html">Data Types and In-Memory Data Model</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="compute.html">Compute Functions</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="ipc.html">Streaming, Serialization, and IPC</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="filesystems.html">Filesystem Interface</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="filesystems_deprecated.html">Filesystem Interface (legacy)</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="plasma.html">The Plasma In-Memory Object Store</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="numpy.html">NumPy Integration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="pandas.html">Pandas Integration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="timestamps.html">Timestamps</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="csv.html">Reading CSV files</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="feather.html">Feather File Format</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="json.html">Reading JSON files</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="parquet.html">Reading and Writing the Apache Parquet Format</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="dataset.html">Tabular Datasets</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="cuda.html">CUDA Integration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="extending_types.html">Extending pyarrow</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="extending.html">Using pyarrow from C++ and Cython Code</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="api.html">API Reference</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="getting_involved.html">Getting Involved</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="benchmarks.html">Benchmarks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference external" href="https://arrow.apache.org/docs/r/">R</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://github.com/apache/arrow/blob/master/ruby/README.md">Ruby</a></li> |
| <li class="toctree-l1"><a class="reference external" href="https://docs.rs/crate/arrow/">Rust</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">Development</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/contributing.html">Contributing to Apache Arrow</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/cpp/index.html">C++ Development</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/python.html">Python Development</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/archery.html">Daily Development using Archery</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/crossbow.html">Packaging and Testing with Crossbow</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/docker.html">Running Docker Builds</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/benchmarks.html">Benchmarks</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../developers/documentation.html">Building the Documentation</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../index.html">Apache Arrow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../index.html" class="icon icon-home"></a> »</li> |
| |
| <li><a href="index.html">Python bindings</a> »</li> |
| |
| <li>Memory and IO Interfaces</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="../_sources/python/memory.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <div class="section" id="memory-and-io-interfaces"> |
| <span id="io"></span><h1>Memory and IO Interfaces<a class="headerlink" href="#memory-and-io-interfaces" title="Permalink to this headline">¶</a></h1> |
| <p>This section will introduce you to the major concepts in PyArrow’s memory |
| management and IO systems:</p> |
| <ul class="simple"> |
| <li><p>Buffers</p></li> |
| <li><p>Memory pools</p></li> |
| <li><p>File-like and stream-like objects</p></li> |
| </ul> |
| <div class="section" id="referencing-and-allocating-memory"> |
| <h2>Referencing and Allocating Memory<a class="headerlink" href="#referencing-and-allocating-memory" title="Permalink to this headline">¶</a></h2> |
| <div class="section" id="pyarrow-buffer"> |
| <h3>pyarrow.Buffer<a class="headerlink" href="#pyarrow-buffer" title="Permalink to this headline">¶</a></h3> |
| <p>The <a class="reference internal" href="generated/pyarrow.Buffer.html#pyarrow.Buffer" title="pyarrow.Buffer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Buffer</span></code></a> object wraps the C++ <a class="reference internal" href="../cpp/api/memory.html#_CPPv4N5arrow6BufferE" title="arrow::Buffer"><code class="xref cpp cpp-class docutils literal notranslate"><span class="pre">arrow::Buffer</span></code></a> type |
| which is the primary tool for memory management in Apache Arrow in C++. It permits |
| higher-level array classes to safely interact with memory which they may or may |
| not own. <code class="docutils literal notranslate"><span class="pre">arrow::Buffer</span></code> can be zero-copy sliced to permit Buffers to cheaply |
| reference other Buffers, while preserving memory lifetime and clean |
| parent-child relationships.</p> |
| <p>There are many implementations of <code class="docutils literal notranslate"><span class="pre">arrow::Buffer</span></code>, but they all provide a |
| standard interface: a data pointer and length. This is similar to Python’s |
| built-in <cite>buffer protocol</cite> and <code class="docutils literal notranslate"><span class="pre">memoryview</span></code> objects.</p> |
| <p>A <a class="reference internal" href="generated/pyarrow.Buffer.html#pyarrow.Buffer" title="pyarrow.Buffer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Buffer</span></code></a> can be created from any Python object implementing |
| the buffer protocol by calling the <a class="reference internal" href="generated/pyarrow.py_buffer.html#pyarrow.py_buffer" title="pyarrow.py_buffer"><code class="xref py py-func docutils literal notranslate"><span class="pre">py_buffer()</span></code></a> function. Let’s consider |
| a bytes object:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [1]: </span><span class="kn">import</span> <span class="nn">pyarrow</span> <span class="kn">as</span> <span class="nn">pa</span> |
| |
| <span class="gp">In [2]: </span><span class="n">data</span> <span class="o">=</span> <span class="sa">b</span><span class="s1">'abcdefghijklmnopqrstuvwxyz'</span> |
| |
| <span class="gp">In [3]: </span><span class="n">buf</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">py_buffer</span><span class="p">(</span><span class="n">data</span><span class="p">)</span> |
| |
| <span class="gp">In [4]: </span><span class="n">buf</span> |
| <span class="gh">Out[4]: </span><span class="go"><pyarrow.lib.Buffer at 0x7efd799b9870></span> |
| |
| <span class="gp">In [5]: </span><span class="n">buf</span><span class="o">.</span><span class="n">size</span> |
| <span class="gh">Out[5]: </span><span class="go">26</span> |
| </pre></div> |
| </div> |
| <p>Creating a Buffer in this way does not allocate any memory; it is a zero-copy |
| view on the memory exported from the <code class="docutils literal notranslate"><span class="pre">data</span></code> bytes object.</p> |
| <p>External memory, under the form of a raw pointer and size, can also be |
| referenced using the <a class="reference internal" href="generated/pyarrow.foreign_buffer.html#pyarrow.foreign_buffer" title="pyarrow.foreign_buffer"><code class="xref py py-func docutils literal notranslate"><span class="pre">foreign_buffer()</span></code></a> function.</p> |
| <p>Buffers can be used in circumstances where a Python buffer or memoryview is |
| required, and such conversions are zero-copy:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [6]: </span><span class="n">memoryview</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span> |
| <span class="gh">Out[6]: </span><span class="go"><memory at 0x7efd799ce408></span> |
| </pre></div> |
| </div> |
| <p>The Buffer’s <a class="reference internal" href="generated/pyarrow.Buffer.html#pyarrow.Buffer.to_pybytes" title="pyarrow.Buffer.to_pybytes"><code class="xref py py-meth docutils literal notranslate"><span class="pre">to_pybytes()</span></code></a> method converts the Buffer’s data to a |
| Python bytestring (thus making a copy of the data):</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [7]: </span><span class="n">buf</span><span class="o">.</span><span class="n">to_pybytes</span><span class="p">()</span> |
| <span class="gh">Out[7]: </span><span class="go">b'abcdefghijklmnopqrstuvwxyz'</span> |
| </pre></div> |
| </div> |
| </div> |
| <div class="section" id="memory-pools"> |
| <h3>Memory Pools<a class="headerlink" href="#memory-pools" title="Permalink to this headline">¶</a></h3> |
| <p>All memory allocations and deallocations (like <code class="docutils literal notranslate"><span class="pre">malloc</span></code> and <code class="docutils literal notranslate"><span class="pre">free</span></code> in C) |
| are tracked in an instance of <a class="reference internal" href="generated/pyarrow.MemoryPool.html#pyarrow.MemoryPool" title="pyarrow.MemoryPool"><code class="xref py py-class docutils literal notranslate"><span class="pre">MemoryPool</span></code></a>. This means that we can |
| then precisely track amount of memory that has been allocated:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [8]: </span><span class="n">pa</span><span class="o">.</span><span class="n">total_allocated_bytes</span><span class="p">()</span> |
| <span class="gh">Out[8]: </span><span class="go">200045632</span> |
| </pre></div> |
| </div> |
| <p>Let’s allocate a resizable <a class="reference internal" href="generated/pyarrow.Buffer.html#pyarrow.Buffer" title="pyarrow.Buffer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Buffer</span></code></a> from the default pool:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [9]: </span><span class="n">buf</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">allocate_buffer</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="n">resizable</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span> |
| |
| <span class="gp">In [10]: </span><span class="n">pa</span><span class="o">.</span><span class="n">total_allocated_bytes</span><span class="p">()</span> |
| <span class="gh">Out[10]: </span><span class="go">200046656</span> |
| |
| <span class="gp">In [11]: </span><span class="n">buf</span><span class="o">.</span><span class="n">resize</span><span class="p">(</span><span class="mi">2048</span><span class="p">)</span> |
| |
| <span class="gp">In [12]: </span><span class="n">pa</span><span class="o">.</span><span class="n">total_allocated_bytes</span><span class="p">()</span> |
| <span class="gh">Out[12]: </span><span class="go">200047680</span> |
| </pre></div> |
| </div> |
| <p>The default allocator requests memory in a minimum increment of 64 bytes. If |
| the buffer is garbaged-collected, all of the memory is freed:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [13]: </span><span class="n">buf</span> <span class="o">=</span> <span class="bp">None</span> |
| |
| <span class="gp">In [14]: </span><span class="n">pa</span><span class="o">.</span><span class="n">total_allocated_bytes</span><span class="p">()</span> |
| <span class="gh">Out[14]: </span><span class="go">200045632</span> |
| </pre></div> |
| </div> |
| <p>Besides the default built-in memory pool, there may be additional memory pools |
| to choose (such as <a class="reference external" href="https://github.com/microsoft/mimalloc">mimalloc</a>) |
| from depending on how Arrow was built. One can get the backend |
| name for a memory pool:</p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">pa</span><span class="o">.</span><span class="n">default_memory_pool</span><span class="p">()</span><span class="o">.</span><span class="n">backend_name</span> |
| <span class="go">'jemalloc'</span> |
| </pre></div> |
| </div> |
| <div class="admonition seealso"> |
| <p class="admonition-title">See also</p> |
| <p><a class="reference internal" href="api/memory.html#api-memory-pool"><span class="std std-ref">API documentation for memory pools</span></a>.</p> |
| </div> |
| <div class="admonition seealso"> |
| <p class="admonition-title">See also</p> |
| <p>On-GPU buffers using Arrow’s optional <a class="reference internal" href="cuda.html"><span class="doc">CUDA integration</span></a>.</p> |
| </div> |
| </div> |
| </div> |
| <div class="section" id="input-and-output"> |
| <h2>Input and Output<a class="headerlink" href="#input-and-output" title="Permalink to this headline">¶</a></h2> |
| <p id="io-native-file">The Arrow C++ libraries have several abstract interfaces for different kinds of |
| IO objects:</p> |
| <ul class="simple"> |
| <li><p>Read-only streams</p></li> |
| <li><p>Read-only files supporting random access</p></li> |
| <li><p>Write-only streams</p></li> |
| <li><p>Write-only files supporting random access</p></li> |
| <li><p>File supporting reads, writes, and random access</p></li> |
| </ul> |
| <p>In the interest of making these objects behave more like Python’s built-in |
| <code class="docutils literal notranslate"><span class="pre">file</span></code> objects, we have defined a <a class="reference internal" href="generated/pyarrow.NativeFile.html#pyarrow.NativeFile" title="pyarrow.NativeFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">NativeFile</span></code></a> base class |
| which implements the same API as regular Python file objects.</p> |
| <p><a class="reference internal" href="generated/pyarrow.NativeFile.html#pyarrow.NativeFile" title="pyarrow.NativeFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">NativeFile</span></code></a> has some important features which make it |
| preferable to using Python files with PyArrow where possible:</p> |
| <ul class="simple"> |
| <li><p>Other Arrow classes can access the internal C++ IO objects natively, and do |
| not need to acquire the Python GIL</p></li> |
| <li><p>Native C++ IO may be able to do zero-copy IO, such as with memory maps</p></li> |
| </ul> |
| <p>There are several kinds of <a class="reference internal" href="generated/pyarrow.NativeFile.html#pyarrow.NativeFile" title="pyarrow.NativeFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">NativeFile</span></code></a> options available:</p> |
| <ul class="simple"> |
| <li><p><a class="reference internal" href="generated/pyarrow.OSFile.html#pyarrow.OSFile" title="pyarrow.OSFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">OSFile</span></code></a>, a native file that uses your operating system’s |
| file descriptors</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.MemoryMappedFile.html#pyarrow.MemoryMappedFile" title="pyarrow.MemoryMappedFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">MemoryMappedFile</span></code></a>, for reading (zero-copy) and writing with |
| memory maps</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.BufferReader.html#pyarrow.BufferReader" title="pyarrow.BufferReader"><code class="xref py py-class docutils literal notranslate"><span class="pre">BufferReader</span></code></a>, for reading <a class="reference internal" href="generated/pyarrow.Buffer.html#pyarrow.Buffer" title="pyarrow.Buffer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Buffer</span></code></a> objects |
| as a file</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.BufferOutputStream.html#pyarrow.BufferOutputStream" title="pyarrow.BufferOutputStream"><code class="xref py py-class docutils literal notranslate"><span class="pre">BufferOutputStream</span></code></a>, for writing data in-memory, producing a |
| Buffer at the end</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.FixedSizeBufferWriter.html#pyarrow.FixedSizeBufferWriter" title="pyarrow.FixedSizeBufferWriter"><code class="xref py py-class docutils literal notranslate"><span class="pre">FixedSizeBufferWriter</span></code></a>, for writing data into an already |
| allocated Buffer</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.HdfsFile.html#pyarrow.HdfsFile" title="pyarrow.HdfsFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">HdfsFile</span></code></a>, for reading and writing data to the Hadoop Filesystem</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.PythonFile.html#pyarrow.PythonFile" title="pyarrow.PythonFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">PythonFile</span></code></a>, for interfacing with Python file objects in C++</p></li> |
| <li><p><a class="reference internal" href="generated/pyarrow.CompressedInputStream.html#pyarrow.CompressedInputStream" title="pyarrow.CompressedInputStream"><code class="xref py py-class docutils literal notranslate"><span class="pre">CompressedInputStream</span></code></a> and |
| <a class="reference internal" href="generated/pyarrow.CompressedOutputStream.html#pyarrow.CompressedOutputStream" title="pyarrow.CompressedOutputStream"><code class="xref py py-class docutils literal notranslate"><span class="pre">CompressedOutputStream</span></code></a>, for on-the-fly compression or |
| decompression to/from another stream</p></li> |
| </ul> |
| <p>There are also high-level APIs to make instantiating common kinds of streams |
| easier.</p> |
| <div class="section" id="high-level-api"> |
| <h3>High-Level API<a class="headerlink" href="#high-level-api" title="Permalink to this headline">¶</a></h3> |
| <div class="section" id="input-streams"> |
| <h4>Input Streams<a class="headerlink" href="#input-streams" title="Permalink to this headline">¶</a></h4> |
| <p>The <a class="reference internal" href="generated/pyarrow.input_stream.html#pyarrow.input_stream" title="pyarrow.input_stream"><code class="xref py py-func docutils literal notranslate"><span class="pre">input_stream()</span></code></a> function allows creating a readable |
| <a class="reference internal" href="generated/pyarrow.NativeFile.html#pyarrow.NativeFile" title="pyarrow.NativeFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">NativeFile</span></code></a> from various kinds of sources.</p> |
| <ul> |
| <li><p>If passed a <a class="reference internal" href="generated/pyarrow.Buffer.html#pyarrow.Buffer" title="pyarrow.Buffer"><code class="xref py py-class docutils literal notranslate"><span class="pre">Buffer</span></code></a> or a <code class="docutils literal notranslate"><span class="pre">memoryview</span></code> object, a |
| <a class="reference internal" href="generated/pyarrow.BufferReader.html#pyarrow.BufferReader" title="pyarrow.BufferReader"><code class="xref py py-class docutils literal notranslate"><span class="pre">BufferReader</span></code></a> will be returned:</p> |
| <blockquote> |
| <div><div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [15]: </span><span class="n">buf</span> <span class="o">=</span> <span class="n">memoryview</span><span class="p">(</span><span class="sa">b</span><span class="s2">"some data"</span><span class="p">)</span> |
| |
| <span class="gp">In [16]: </span><span class="n">stream</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">input_stream</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span> |
| |
| <span class="gp">In [17]: </span><span class="n">stream</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="mi">4</span><span class="p">)</span> |
| <span class="gh">Out[17]: </span><span class="go">b'some'</span> |
| </pre></div> |
| </div> |
| </div></blockquote> |
| </li> |
| <li><p>If passed a string or file path, it will open the given file on disk |
| for reading, creating a <a class="reference internal" href="generated/pyarrow.OSFile.html#pyarrow.OSFile" title="pyarrow.OSFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">OSFile</span></code></a>. Optionally, the file |
| can be compressed: if its filename ends with a recognized extension |
| such as <code class="docutils literal notranslate"><span class="pre">.gz</span></code>, its contents will automatically be decompressed on |
| reading.</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [18]: </span><span class="kn">import</span> <span class="nn">gzip</span> |
| |
| <span class="gp">In [19]: </span><span class="k">with</span> <span class="n">gzip</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="s1">'example.gz'</span><span class="p">,</span> <span class="s1">'wb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="gp"> ....: </span> <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'some data</span><span class="se">\n</span><span class="s1">'</span> <span class="o">*</span> <span class="mi">3</span><span class="p">)</span> |
| <span class="gp"> ....: </span> |
| |
| <span class="gp">In [20]: </span><span class="n">stream</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">input_stream</span><span class="p">(</span><span class="s1">'example.gz'</span><span class="p">)</span> |
| |
| <span class="gp">In [21]: </span><span class="n">stream</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gh">Out[21]: </span><span class="go">b'some data\nsome data\nsome data\n'</span> |
| </pre></div> |
| </div> |
| </li> |
| <li><p>If passed a Python file object, it will wrapped in a <a class="reference internal" href="generated/pyarrow.PythonFile.html#pyarrow.PythonFile" title="pyarrow.PythonFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">PythonFile</span></code></a> |
| such that the Arrow C++ libraries can read data from it (at the expense |
| of a slight overhead).</p></li> |
| </ul> |
| </div> |
| <div class="section" id="output-streams"> |
| <h4>Output Streams<a class="headerlink" href="#output-streams" title="Permalink to this headline">¶</a></h4> |
| <p><a class="reference internal" href="generated/pyarrow.output_stream.html#pyarrow.output_stream" title="pyarrow.output_stream"><code class="xref py py-func docutils literal notranslate"><span class="pre">output_stream()</span></code></a> is the equivalent function for output streams |
| and allows creating a writable <a class="reference internal" href="generated/pyarrow.NativeFile.html#pyarrow.NativeFile" title="pyarrow.NativeFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">NativeFile</span></code></a>. It has the same |
| features as explained above for <a class="reference internal" href="generated/pyarrow.input_stream.html#pyarrow.input_stream" title="pyarrow.input_stream"><code class="xref py py-func docutils literal notranslate"><span class="pre">input_stream()</span></code></a>, such as being |
| able to write to buffers or do on-the-fly compression.</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [22]: </span><span class="k">with</span> <span class="n">pa</span><span class="o">.</span><span class="n">output_stream</span><span class="p">(</span><span class="s1">'example1.dat'</span><span class="p">)</span> <span class="k">as</span> <span class="n">stream</span><span class="p">:</span> |
| <span class="gp"> ....: </span> <span class="n">stream</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'some data'</span><span class="p">)</span> |
| <span class="gp"> ....: </span> |
| |
| <span class="gp">In [23]: </span><span class="n">f</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="s1">'example1.dat'</span><span class="p">,</span> <span class="s1">'rb'</span><span class="p">)</span> |
| |
| <span class="gp">In [24]: </span><span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span> |
| <span class="gh">Out[24]: </span><span class="go">b'some data'</span> |
| </pre></div> |
| </div> |
| </div> |
| </div> |
| <div class="section" id="on-disk-and-memory-mapped-files"> |
| <h3>On-Disk and Memory Mapped Files<a class="headerlink" href="#on-disk-and-memory-mapped-files" title="Permalink to this headline">¶</a></h3> |
| <p>PyArrow includes two ways to interact with data on disk: standard operating |
| system-level file APIs, and memory-mapped files. In regular Python we can |
| write:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [25]: </span><span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s1">'example2.dat'</span><span class="p">,</span> <span class="s1">'wb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="gp"> ....: </span> <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'some example data'</span><span class="p">)</span> |
| <span class="gp"> ....: </span> |
| </pre></div> |
| </div> |
| <p>Using pyarrow’s <a class="reference internal" href="generated/pyarrow.OSFile.html#pyarrow.OSFile" title="pyarrow.OSFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">OSFile</span></code></a> class, you can write:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [26]: </span><span class="k">with</span> <span class="n">pa</span><span class="o">.</span><span class="n">OSFile</span><span class="p">(</span><span class="s1">'example3.dat'</span><span class="p">,</span> <span class="s1">'wb'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span> |
| <span class="gp"> ....: </span> <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'some example data'</span><span class="p">)</span> |
| <span class="gp"> ....: </span> |
| </pre></div> |
| </div> |
| <p>For reading files, you can use <a class="reference internal" href="generated/pyarrow.OSFile.html#pyarrow.OSFile" title="pyarrow.OSFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">OSFile</span></code></a> or |
| <a class="reference internal" href="generated/pyarrow.MemoryMappedFile.html#pyarrow.MemoryMappedFile" title="pyarrow.MemoryMappedFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">MemoryMappedFile</span></code></a>. The difference between these is that |
| <a class="reference internal" href="generated/pyarrow.OSFile.html#pyarrow.OSFile" title="pyarrow.OSFile"><code class="xref py py-class docutils literal notranslate"><span class="pre">OSFile</span></code></a> allocates new memory on each read, like Python file |
| objects. In reads from memory maps, the library constructs a buffer referencing |
| the mapped memory without any memory allocation or copying:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [27]: </span><span class="n">file_obj</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">OSFile</span><span class="p">(</span><span class="s1">'example2.dat'</span><span class="p">)</span> |
| |
| <span class="gp">In [28]: </span><span class="n">mmap</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">memory_map</span><span class="p">(</span><span class="s1">'example3.dat'</span><span class="p">)</span> |
| |
| <span class="gp">In [29]: </span><span class="n">file_obj</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="mi">4</span><span class="p">)</span> |
| <span class="gh">Out[29]: </span><span class="go">b'some'</span> |
| |
| <span class="gp">In [30]: </span><span class="n">mmap</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="mi">4</span><span class="p">)</span> |
| <span class="gh">Out[30]: </span><span class="go">b'some'</span> |
| </pre></div> |
| </div> |
| <p>The <code class="docutils literal notranslate"><span class="pre">read</span></code> method implements the standard Python file <code class="docutils literal notranslate"><span class="pre">read</span></code> API. To read |
| into Arrow Buffer objects, use <code class="docutils literal notranslate"><span class="pre">read_buffer</span></code>:</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [31]: </span><span class="n">mmap</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span> |
| <span class="gh">Out[31]: </span><span class="go">0</span> |
| |
| <span class="gp">In [32]: </span><span class="n">buf</span> <span class="o">=</span> <span class="n">mmap</span><span class="o">.</span><span class="n">read_buffer</span><span class="p">(</span><span class="mi">4</span><span class="p">)</span> |
| |
| <span class="gp">In [33]: </span><span class="k">print</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span> |
| <span class="go"><pyarrow.lib.Buffer object at 0x7efd79a5f470></span> |
| |
| <span class="gp">In [34]: </span><span class="n">buf</span><span class="o">.</span><span class="n">to_pybytes</span><span class="p">()</span> |
| <span class="gh">Out[34]: </span><span class="go">b'some'</span> |
| </pre></div> |
| </div> |
| <p>Many tools in PyArrow, particular the Apache Parquet interface and the file and |
| stream messaging tools, are more efficient when used with these <code class="docutils literal notranslate"><span class="pre">NativeFile</span></code> |
| types than with normal Python file objects.</p> |
| </div> |
| <div class="section" id="in-memory-reading-and-writing"> |
| <h3>In-Memory Reading and Writing<a class="headerlink" href="#in-memory-reading-and-writing" title="Permalink to this headline">¶</a></h3> |
| <p>To assist with serialization and deserialization of in-memory data, we have |
| file interfaces that can read and write to Arrow Buffers.</p> |
| <div class="highlight-ipython notranslate"><div class="highlight"><pre><span></span><span class="gp">In [35]: </span><span class="n">writer</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">BufferOutputStream</span><span class="p">()</span> |
| |
| <span class="gp">In [36]: </span><span class="n">writer</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="sa">b</span><span class="s1">'hello, friends'</span><span class="p">)</span> |
| <span class="gh">Out[36]: </span><span class="go">14</span> |
| |
| <span class="gp">In [37]: </span><span class="n">buf</span> <span class="o">=</span> <span class="n">writer</span><span class="o">.</span><span class="n">getvalue</span><span class="p">()</span> |
| |
| <span class="gp">In [38]: </span><span class="n">buf</span> |
| <span class="gh">Out[38]: </span><span class="go"><pyarrow.lib.Buffer at 0x7efd79a7a5b0></span> |
| |
| <span class="gp">In [39]: </span><span class="n">buf</span><span class="o">.</span><span class="n">size</span> |
| <span class="gh">Out[39]: </span><span class="go">14</span> |
| |
| <span class="gp">In [40]: </span><span class="n">reader</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">BufferReader</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span> |
| |
| <span class="gp">In [41]: </span><span class="n">reader</span><span class="o">.</span><span class="n">seek</span><span class="p">(</span><span class="mi">7</span><span class="p">)</span> |
| <span class="gh">Out[41]: </span><span class="go">7</span> |
| |
| <span class="gp">In [42]: </span><span class="n">reader</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="mi">7</span><span class="p">)</span> |
| <span class="gh">Out[42]: </span><span class="go">b'friends'</span> |
| </pre></div> |
| </div> |
| <p>These have similar semantics to Python’s built-in <code class="docutils literal notranslate"><span class="pre">io.BytesIO</span></code>.</p> |
| </div> |
| </div> |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| <a href="data.html" class="btn btn-neutral float-right" title="Data Types and In-Memory Data Model" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| <a href="install.html" class="btn btn-neutral float-left" title="Installing PyArrow" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright 2016-2019 Apache Software Foundation. |
| |
| </p> |
| </div> |
| |
| |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="/docs/_static/versionwarning.js"></script></body> |
| </html> |
