| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.mllib.linalg — PySpark 3.5.0 documentation</title> |
| |
| <link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/styles/pydata-sphinx-theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"> |
| |
| <script 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 src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/mllib/linalg.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="None"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl"> |
| |
| <div id="navbar-start"> |
| |
| |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo"> |
| </a> |
| |
| |
| |
| </div> |
| |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| |
| <div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse"> |
| <div id="navbar-center" class="mr-auto"> |
| |
| <div class="navbar-center-item"> |
| <ul id="navbar-main-elements" class="navbar-nav"> |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| |
| </ul> |
| </div> |
| |
| </div> |
| |
| <div id="navbar-end"> |
| |
| <div class="navbar-end-item"> |
| <ul id="navbar-icon-links" class="navbar-nav" aria-label="Icon Links"> |
| </ul> |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form><nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| <div class="bd-toc-item active"> |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| </div> |
| |
| |
| |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.mllib.linalg</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| <span class="c1">#</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">MLlib utilities for linear algebra. For dense vectors, MLlib</span> |
| <span class="sd">uses the NumPy `array` type, so you can simply pass NumPy arrays</span> |
| <span class="sd">around. For sparse vectors, users can construct a :class:`SparseVector`</span> |
| <span class="sd">object from MLlib or pass SciPy `scipy.sparse` column vectors if</span> |
| <span class="sd">SciPy is available in their environment.</span> |
| <span class="sd">"""</span> |
| |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">import</span> <span class="nn">array</span> |
| <span class="kn">import</span> <span class="nn">struct</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark</span> <span class="kn">import</span> <span class="n">since</span> |
| <span class="kn">from</span> <span class="nn">pyspark.ml</span> <span class="kn">import</span> <span class="n">linalg</span> <span class="k">as</span> <span class="n">newlinalg</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">UserDefinedType</span><span class="p">,</span> |
| <span class="n">StructField</span><span class="p">,</span> |
| <span class="n">StructType</span><span class="p">,</span> |
| <span class="n">ArrayType</span><span class="p">,</span> |
| <span class="n">DoubleType</span><span class="p">,</span> |
| <span class="n">IntegerType</span><span class="p">,</span> |
| <span class="n">ByteType</span><span class="p">,</span> |
| <span class="n">BooleanType</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="p">(</span> |
| <span class="n">Any</span><span class="p">,</span> |
| <span class="n">Callable</span><span class="p">,</span> |
| <span class="n">cast</span><span class="p">,</span> |
| <span class="n">Dict</span><span class="p">,</span> |
| <span class="n">Generic</span><span class="p">,</span> |
| <span class="n">Iterable</span><span class="p">,</span> |
| <span class="n">List</span><span class="p">,</span> |
| <span class="n">Optional</span><span class="p">,</span> |
| <span class="n">overload</span><span class="p">,</span> |
| <span class="n">Sequence</span><span class="p">,</span> |
| <span class="n">Tuple</span><span class="p">,</span> |
| <span class="n">Type</span><span class="p">,</span> |
| <span class="n">TypeVar</span><span class="p">,</span> |
| <span class="n">TYPE_CHECKING</span><span class="p">,</span> |
| <span class="n">Union</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib._typing</span> <span class="kn">import</span> <span class="n">VectorLike</span><span class="p">,</span> <span class="n">NormType</span> |
| <span class="kn">from</span> <span class="nn">scipy.sparse</span> <span class="kn">import</span> <span class="n">spmatrix</span> |
| <span class="kn">from</span> <span class="nn">numpy.typing</span> <span class="kn">import</span> <span class="n">ArrayLike</span> |
| |
| |
| <span class="n">QT</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"QT"</span><span class="p">)</span> |
| <span class="n">RT</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s2">"RT"</span><span class="p">)</span> |
| |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s2">"Vector"</span><span class="p">,</span> |
| <span class="s2">"DenseVector"</span><span class="p">,</span> |
| <span class="s2">"SparseVector"</span><span class="p">,</span> |
| <span class="s2">"Vectors"</span><span class="p">,</span> |
| <span class="s2">"Matrix"</span><span class="p">,</span> |
| <span class="s2">"DenseMatrix"</span><span class="p">,</span> |
| <span class="s2">"SparseMatrix"</span><span class="p">,</span> |
| <span class="s2">"Matrices"</span><span class="p">,</span> |
| <span class="s2">"QRDecomposition"</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| |
| <span class="c1"># Check whether we have SciPy. MLlib works without it too, but if we have it, some methods,</span> |
| <span class="c1"># such as _dot and _serialize_double_vector, start to support scipy.sparse matrices.</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">scipy.sparse</span> |
| |
| <span class="n">_have_scipy</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">except</span> <span class="ne">BaseException</span><span class="p">:</span> |
| <span class="c1"># No SciPy in environment, but that's okay</span> |
| <span class="n">_have_scipy</span> <span class="o">=</span> <span class="kc">False</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_convert_to_vector</span><span class="p">(</span><span class="n">d</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="s2">"spmatrix"</span><span class="p">,</span> <span class="nb">range</span><span class="p">])</span> <span class="o">-></span> <span class="s2">"Vector"</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">d</span><span class="p">,</span> <span class="n">Vector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">d</span> |
| <span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="n">d</span><span class="p">)</span> <span class="ow">in</span> <span class="p">(</span><span class="n">array</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">,</span> <span class="nb">range</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="n">d</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">_have_scipy</span> <span class="ow">and</span> <span class="n">scipy</span><span class="o">.</span><span class="n">sparse</span><span class="o">.</span><span class="n">issparse</span><span class="p">(</span><span class="n">d</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"Expected column vector"</span> |
| <span class="c1"># Make sure the converted csc_matrix has sorted indices.</span> |
| <span class="n">csc</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">tocsc</span><span class="p">()</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">csc</span><span class="o">.</span><span class="n">has_sorted_indices</span><span class="p">:</span> |
| <span class="n">csc</span><span class="o">.</span><span class="n">sort_indices</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">d</span><span class="p">)</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">csc</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="n">csc</span><span class="o">.</span><span class="n">data</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Cannot convert type </span><span class="si">%s</span><span class="s2"> into Vector"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">d</span><span class="p">))</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_vector_size</span><span class="p">(</span><span class="n">v</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="s2">"VectorLike"</span><span class="p">,</span> <span class="s2">"spmatrix"</span><span class="p">,</span> <span class="nb">range</span><span class="p">])</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns the size of the vector.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> _vector_size([1., 2., 3.])</span> |
| <span class="sd"> 3</span> |
| <span class="sd"> >>> _vector_size((1., 2., 3.))</span> |
| <span class="sd"> 3</span> |
| <span class="sd"> >>> _vector_size(array.array('d', [1., 2., 3.]))</span> |
| <span class="sd"> 3</span> |
| <span class="sd"> >>> _vector_size(np.zeros(3))</span> |
| <span class="sd"> 3</span> |
| <span class="sd"> >>> _vector_size(np.zeros((3, 1)))</span> |
| <span class="sd"> 3</span> |
| <span class="sd"> >>> _vector_size(np.zeros((1, 3)))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> ValueError: Cannot treat an ndarray of shape (1, 3) as a vector</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">v</span><span class="p">,</span> <span class="n">Vector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="ow">in</span> <span class="p">(</span><span class="n">array</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">,</span> <span class="nb">range</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">type</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="o">==</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">v</span><span class="o">.</span><span class="n">ndim</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">or</span> <span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">ndim</span> <span class="o">==</span> <span class="mi">2</span> <span class="ow">and</span> <span class="n">v</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Cannot treat an ndarray of shape </span><span class="si">%s</span><span class="s2"> as a vector"</span> <span class="o">%</span> <span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span> |
| <span class="k">elif</span> <span class="n">_have_scipy</span> <span class="ow">and</span> <span class="n">scipy</span><span class="o">.</span><span class="n">sparse</span><span class="o">.</span><span class="n">issparse</span><span class="p">(</span><span class="n">v</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> <span class="s2">"Expected column vector"</span> |
| <span class="k">return</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">v</span><span class="p">)</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Cannot treat type </span><span class="si">%s</span><span class="s2"> as a vector"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">v</span><span class="p">))</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_format_float</span><span class="p">(</span><span class="n">f</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">digits</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">4</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="n">digits</span><span class="p">))</span> |
| <span class="k">if</span> <span class="s2">"."</span> <span class="ow">in</span> <span class="n">s</span><span class="p">:</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="p">[:</span> <span class="n">s</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"."</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span> <span class="o">+</span> <span class="n">digits</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">s</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_format_float_list</span><span class="p">(</span><span class="n">xs</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">_format_float</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">xs</span><span class="p">]</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_double_to_long_bits</span><span class="p">(</span><span class="n">value</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">np</span><span class="o">.</span><span class="n">isnan</span><span class="p">(</span><span class="n">value</span><span class="p">):</span> |
| <span class="n">value</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="s2">"nan"</span><span class="p">)</span> |
| <span class="c1"># pack double into 64 bits, then unpack as long int</span> |
| <span class="k">return</span> <span class="n">struct</span><span class="o">.</span><span class="n">unpack</span><span class="p">(</span><span class="s2">"Q"</span><span class="p">,</span> <span class="n">struct</span><span class="o">.</span><span class="n">pack</span><span class="p">(</span><span class="s2">"d"</span><span class="p">,</span> <span class="n">value</span><span class="p">))[</span><span class="mi">0</span><span class="p">]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">VectorUDT</span><span class="p">(</span><span class="n">UserDefinedType</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> SQL user-defined type (UDT) for Vector.</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">sqlType</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="n">StructType</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">StructType</span><span class="p">(</span> |
| <span class="p">[</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"type"</span><span class="p">,</span> <span class="n">ByteType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"size"</span><span class="p">,</span> <span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"indices"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"values"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="p">]</span> |
| <span class="p">)</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">module</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"pyspark.mllib.linalg"</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">scalaUDT</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"org.apache.spark.mllib.linalg.VectorUDT"</span> |
| |
| <span class="k">def</span> <span class="nf">serialize</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">:</span> <span class="s2">"Vector"</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]]:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="n">indices</span> <span class="o">=</span> <span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">obj</span><span class="o">.</span><span class="n">indices</span><span class="p">]</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">obj</span><span class="o">.</span><span class="n">values</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">obj</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="n">indices</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">obj</span><span class="p">]</span> <span class="c1"># type: ignore[attr-defined]</span> |
| <span class="k">return</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"cannot serialize </span><span class="si">%r</span><span class="s2"> of type </span><span class="si">%r</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">obj</span><span class="p">)))</span> |
| |
| <span class="k">def</span> <span class="nf">deserialize</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">datum</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">]]</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"Vector"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="p">(</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">datum</span><span class="p">)</span> <span class="o">==</span> <span class="mi">4</span> |
| <span class="p">),</span> <span class="s2">"VectorUDT.deserialize given row with length </span><span class="si">%d</span><span class="s2"> but requires 4"</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="n">datum</span><span class="p">)</span> |
| <span class="n">tpe</span> <span class="o">=</span> <span class="n">datum</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">tpe</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="n">cast</span><span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="n">datum</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span> <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">datum</span><span class="p">[</span><span class="mi">2</span><span class="p">]),</span> <span class="n">datum</span><span class="p">[</span><span class="mi">3</span><span class="p">])</span> |
| <span class="k">elif</span> <span class="n">tpe</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="n">datum</span><span class="p">[</span><span class="mi">3</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"do not recognize type </span><span class="si">%r</span><span class="s2">"</span> <span class="o">%</span> <span class="n">tpe</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">simpleString</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"vector"</span> |
| |
| |
| <span class="k">class</span> <span class="nc">MatrixUDT</span><span class="p">(</span><span class="n">UserDefinedType</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> SQL user-defined type (UDT) for Matrix.</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">sqlType</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="n">StructType</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">StructType</span><span class="p">(</span> |
| <span class="p">[</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"type"</span><span class="p">,</span> <span class="n">ByteType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"numRows"</span><span class="p">,</span> <span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"numCols"</span><span class="p">,</span> <span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"colPtrs"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"rowIndices"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">IntegerType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"values"</span><span class="p">,</span> <span class="n">ArrayType</span><span class="p">(</span><span class="n">DoubleType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> <span class="kc">True</span><span class="p">),</span> |
| <span class="n">StructField</span><span class="p">(</span><span class="s2">"isTransposed"</span><span class="p">,</span> <span class="n">BooleanType</span><span class="p">(),</span> <span class="kc">False</span><span class="p">),</span> |
| <span class="p">]</span> |
| <span class="p">)</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">module</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"pyspark.mllib.linalg"</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">scalaUDT</span><span class="p">(</span><span class="bp">cls</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"org.apache.spark.mllib.linalg.MatrixUDT"</span> |
| |
| <span class="k">def</span> <span class="nf">serialize</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">:</span> <span class="s2">"Matrix"</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="nb">bool</span><span class="p">]:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="n">SparseMatrix</span><span class="p">):</span> |
| <span class="n">colPtrs</span> <span class="o">=</span> <span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">obj</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">]</span> |
| <span class="n">rowIndices</span> <span class="o">=</span> <span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">obj</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">]</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">obj</span><span class="o">.</span><span class="n">values</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="mi">0</span><span class="p">,</span> |
| <span class="n">obj</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> |
| <span class="n">obj</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> |
| <span class="n">colPtrs</span><span class="p">,</span> |
| <span class="n">rowIndices</span><span class="p">,</span> |
| <span class="n">values</span><span class="p">,</span> |
| <span class="nb">bool</span><span class="p">(</span><span class="n">obj</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">),</span> |
| <span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="n">DenseMatrix</span><span class="p">):</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">obj</span><span class="o">.</span><span class="n">values</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">obj</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="n">obj</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">values</span><span class="p">,</span> <span class="nb">bool</span><span class="p">(</span><span class="n">obj</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"cannot serialize type </span><span class="si">%r</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">obj</span><span class="p">)))</span> |
| |
| <span class="k">def</span> <span class="nf">deserialize</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">datum</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> <span class="n">Optional</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> <span class="n">List</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="nb">bool</span><span class="p">],</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="s2">"Matrix"</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="p">(</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">datum</span><span class="p">)</span> <span class="o">==</span> <span class="mi">7</span> |
| <span class="p">),</span> <span class="s2">"MatrixUDT.deserialize given row with length </span><span class="si">%d</span><span class="s2"> but requires 7"</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="n">datum</span><span class="p">)</span> |
| <span class="n">tpe</span> <span class="o">=</span> <span class="n">datum</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">tpe</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">SparseMatrix</span><span class="p">(</span> |
| <span class="n">datum</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> |
| <span class="n">datum</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> |
| <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">datum</span><span class="p">[</span><span class="mi">3</span><span class="p">]),</span> |
| <span class="n">cast</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">datum</span><span class="p">[</span><span class="mi">4</span><span class="p">]),</span> |
| <span class="n">datum</span><span class="p">[</span><span class="mi">5</span><span class="p">],</span> |
| <span class="n">datum</span><span class="p">[</span><span class="mi">6</span><span class="p">],</span> |
| <span class="p">)</span> |
| <span class="k">elif</span> <span class="n">tpe</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DenseMatrix</span><span class="p">(</span><span class="n">datum</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">datum</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">datum</span><span class="p">[</span><span class="mi">5</span><span class="p">],</span> <span class="n">datum</span><span class="p">[</span><span class="mi">6</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"do not recognize type </span><span class="si">%r</span><span class="s2">"</span> <span class="o">%</span> <span class="n">tpe</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">simpleString</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"matrix"</span> |
| |
| |
| <div class="viewcode-block" id="Vector"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector">[docs]</a><span class="k">class</span> <span class="nc">Vector</span><span class="p">:</span> |
| |
| <span class="n">__UDT__</span> <span class="o">=</span> <span class="n">VectorUDT</span><span class="p">()</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Abstract class for DenseVector and SparseVector</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="Vector.toArray"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector.toArray">[docs]</a> <span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert the vector into an numpy.ndarray</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`numpy.ndarray`</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="Vector.asML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vector.html#pyspark.mllib.linalg.Vector.asML">[docs]</a> <span class="k">def</span> <span class="nf">asML</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">Vector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert this vector to the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.Vector`</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| |
| <div class="viewcode-block" id="DenseVector"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector">[docs]</a><span class="k">class</span> <span class="nc">DenseVector</span><span class="p">(</span><span class="n">Vector</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A dense vector represented by a value array. We use numpy array for</span> |
| <span class="sd"> storage and arithmetics will be delegated to the underlying numpy</span> |
| <span class="sd"> array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> v = Vectors.dense([1.0, 2.0])</span> |
| <span class="sd"> >>> u = Vectors.dense([3.0, 4.0])</span> |
| <span class="sd"> >>> v + u</span> |
| <span class="sd"> DenseVector([4.0, 6.0])</span> |
| <span class="sd"> >>> 2 - v</span> |
| <span class="sd"> DenseVector([1.0, 0.0])</span> |
| <span class="sd"> >>> v / 2</span> |
| <span class="sd"> DenseVector([0.5, 1.0])</span> |
| <span class="sd"> >>> v * u</span> |
| <span class="sd"> DenseVector([3.0, 8.0])</span> |
| <span class="sd"> >>> u / v</span> |
| <span class="sd"> DenseVector([3.0, 2.0])</span> |
| <span class="sd"> >>> u % 2</span> |
| <span class="sd"> DenseVector([1.0, 0.0])</span> |
| <span class="sd"> >>> -v</span> |
| <span class="sd"> DenseVector([-1.0, -2.0])</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ar</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]]):</span> |
| <span class="n">ar_</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">ar</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">):</span> |
| <span class="n">ar_</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">frombuffer</span><span class="p">(</span><span class="n">ar</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">ar</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span> |
| <span class="n">ar_</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">ar</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">ar_</span> <span class="o">=</span> <span class="n">ar</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> <span class="k">if</span> <span class="n">ar</span><span class="o">.</span><span class="n">dtype</span> <span class="o">!=</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span> <span class="k">else</span> <span class="n">ar</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">array</span> <span class="o">=</span> <span class="n">ar_</span> |
| |
| <div class="viewcode-block" id="DenseVector.parse"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.parse">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">parse</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DenseVector"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Parse string representation back into the DenseVector.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> DenseVector.parse(' [ 0.0,1.0,2.0, 3.0]')</span> |
| <span class="sd"> DenseVector([0.0, 1.0, 2.0, 3.0])</span> |
| <span class="sd"> """</span> |
| <span class="n">start</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"["</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">start</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Array should start with '['."</span><span class="p">)</span> |
| <span class="n">end</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"]"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">end</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Array should end with ']'."</span><span class="p">)</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">start</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:</span> <span class="n">end</span><span class="p">]</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">val</span><span class="p">)</span> <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">s</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">","</span><span class="p">)</span> <span class="k">if</span> <span class="n">val</span><span class="p">]</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Unable to parse values from </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">s</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="n">values</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Type</span><span class="p">[</span><span class="s2">"DenseVector"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">bytes</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">,</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),)</span> |
| |
| <div class="viewcode-block" id="DenseVector.numNonzeros"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.numNonzeros">[docs]</a> <span class="k">def</span> <span class="nf">numNonzeros</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Number of nonzero elements. This scans all active values and count non zeros</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">count_nonzero</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DenseVector.norm"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.norm">[docs]</a> <span class="k">def</span> <span class="nf">norm</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">p</span><span class="p">:</span> <span class="s2">"NormType"</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Calculates the norm of a DenseVector.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> a = DenseVector([0, -1, 2, -3])</span> |
| <span class="sd"> >>> a.norm(2)</span> |
| <span class="sd"> 3.7...</span> |
| <span class="sd"> >>> a.norm(1)</span> |
| <span class="sd"> 6.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">p</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DenseVector.dot"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.dot">[docs]</a> <span class="k">def</span> <span class="nf">dot</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Compute the dot product of two Vectors. We support</span> |
| <span class="sd"> (Numpy array, list, SparseVector, or SciPy sparse)</span> |
| <span class="sd"> and a target NumPy array that is either 1- or 2-dimensional.</span> |
| <span class="sd"> Equivalent to calling numpy.dot of the two vectors.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> dense = DenseVector(array.array('d', [1., 2.]))</span> |
| <span class="sd"> >>> dense.dot(dense)</span> |
| <span class="sd"> 5.0</span> |
| <span class="sd"> >>> dense.dot(SparseVector(2, [0, 1], [2., 1.]))</span> |
| <span class="sd"> 4.0</span> |
| <span class="sd"> >>> dense.dot(range(1, 3))</span> |
| <span class="sd"> 5.0</span> |
| <span class="sd"> >>> dense.dot(np.array(range(1, 3)))</span> |
| <span class="sd"> 5.0</span> |
| <span class="sd"> >>> dense.dot([1.,])</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> >>> dense.dot(np.reshape([1., 2., 3., 4.], (2, 2), order='F'))</span> |
| <span class="sd"> array([ 5., 11.])</span> |
| <span class="sd"> >>> dense.dot(np.reshape([1., 2., 3.], (3, 1), order='F'))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> <span class="o">==</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">other</span><span class="o">.</span><span class="n">ndim</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="s2">"dimension mismatch"</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">other</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">_have_scipy</span> <span class="ow">and</span> <span class="n">scipy</span><span class="o">.</span><span class="n">sparse</span><span class="o">.</span><span class="n">issparse</span><span class="p">(</span><span class="n">other</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">other</span><span class="p">)</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="s2">"dimension mismatch"</span> |
| <span class="k">return</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"spmatrix"</span><span class="p">,</span> <span class="n">other</span><span class="p">)</span><span class="o">.</span><span class="n">transpose</span><span class="p">()</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">())</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">_vector_size</span><span class="p">(</span><span class="n">other</span><span class="p">),</span> <span class="s2">"dimension mismatch"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">other</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Vector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">other</span><span class="o">.</span><span class="n">toArray</span><span class="p">())</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">cast</span><span class="p">(</span><span class="s2">"ArrayLike"</span><span class="p">,</span> <span class="n">other</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="DenseVector.squared_distance"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.squared_distance">[docs]</a> <span class="k">def</span> <span class="nf">squared_distance</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Squared distance of two Vectors.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> dense1 = DenseVector(array.array('d', [1., 2.]))</span> |
| <span class="sd"> >>> dense1.squared_distance(dense1)</span> |
| <span class="sd"> 0.0</span> |
| <span class="sd"> >>> dense2 = np.array([2., 1.])</span> |
| <span class="sd"> >>> dense1.squared_distance(dense2)</span> |
| <span class="sd"> 2.0</span> |
| <span class="sd"> >>> dense3 = [2., 1.]</span> |
| <span class="sd"> >>> dense1.squared_distance(dense3)</span> |
| <span class="sd"> 2.0</span> |
| <span class="sd"> >>> sparse1 = SparseVector(2, [0, 1], [2., 1.])</span> |
| <span class="sd"> >>> dense1.squared_distance(sparse1)</span> |
| <span class="sd"> 2.0</span> |
| <span class="sd"> >>> dense1.squared_distance([1.,])</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> >>> dense1.squared_distance(SparseVector(1, [0,], [1.,]))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">_vector_size</span><span class="p">(</span><span class="n">other</span><span class="p">),</span> <span class="s2">"dimension mismatch"</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">other</span><span class="o">.</span><span class="n">squared_distance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">_have_scipy</span> <span class="ow">and</span> <span class="n">scipy</span><span class="o">.</span><span class="n">sparse</span><span class="o">.</span><span class="n">issparse</span><span class="p">(</span><span class="n">other</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">other</span><span class="p">)</span><span class="o">.</span><span class="n">squared_distance</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Vector</span><span class="p">):</span> |
| <span class="n">other</span> <span class="o">=</span> <span class="n">other</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> |
| <span class="k">elif</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span> |
| <span class="n">other</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> |
| <span class="n">diff</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> <span class="o">-</span> <span class="n">other</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">diff</span><span class="p">,</span> <span class="n">diff</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DenseVector.toArray"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.toArray">[docs]</a> <span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns an numpy.ndarray</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span></div> |
| |
| <div class="viewcode-block" id="DenseVector.asML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseVector.html#pyspark.mllib.linalg.DenseVector.asML">[docs]</a> <span class="k">def</span> <span class="nf">asML</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseVector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert this vector to the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.DenseVector`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseVector</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">)</span></div> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">values</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a list of values</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">item</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">item</span><span class="p">:</span> <span class="nb">slice</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">item</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">slice</span><span class="p">])</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">]:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">[</span><span class="n">item</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"["</span> <span class="o">+</span> <span class="s2">","</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">])</span> <span class="o">+</span> <span class="s2">"]"</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"DenseVector([</span><span class="si">%s</span><span class="s2">])"</span> <span class="o">%</span> <span class="p">(</span><span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">_format_float</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="fm">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">array_equal</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">other</span><span class="o">.</span><span class="n">array</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">!=</span> <span class="n">other</span><span class="o">.</span><span class="n">size</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">return</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">_equals</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">))),</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| |
| <span class="k">def</span> <span class="fm">__ne__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="k">return</span> <span class="ow">not</span> <span class="bp">self</span> <span class="o">==</span> <span class="n">other</span> |
| |
| <span class="k">def</span> <span class="fm">__hash__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="n">size</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mi">31</span> <span class="o">+</span> <span class="n">size</span> |
| <span class="n">nnz</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">while</span> <span class="n">i</span> <span class="o"><</span> <span class="n">size</span> <span class="ow">and</span> <span class="n">nnz</span> <span class="o"><</span> <span class="mi">128</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mi">31</span> <span class="o">*</span> <span class="n">result</span> <span class="o">+</span> <span class="n">i</span> |
| <span class="n">bits</span> <span class="o">=</span> <span class="n">_double_to_long_bits</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mi">31</span> <span class="o">*</span> <span class="n">result</span> <span class="o">+</span> <span class="p">(</span><span class="n">bits</span> <span class="o">^</span> <span class="p">(</span><span class="n">bits</span> <span class="o">>></span> <span class="mi">32</span><span class="p">))</span> |
| <span class="n">nnz</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| <span class="k">def</span> <span class="fm">__getattr__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">item</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">item</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__neg__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DenseVector"</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_delegate</span><span class="p">(</span><span class="n">op</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Callable</span><span class="p">[[</span><span class="s2">"DenseVector"</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span> <span class="s2">"DenseVector"</span><span class="p">]:</span> <span class="c1"># type: ignore[misc]</span> |
| <span class="k">def</span> <span class="nf">func</span><span class="p">(</span><span class="bp">self</span><span class="p">:</span> <span class="s2">"DenseVector"</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DenseVector"</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="n">other</span> <span class="o">=</span> <span class="n">other</span><span class="o">.</span><span class="n">array</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">array</span><span class="p">,</span> <span class="n">op</span><span class="p">)(</span><span class="n">other</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">func</span> |
| |
| <span class="fm">__add__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__add__"</span><span class="p">)</span> |
| <span class="fm">__sub__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__sub__"</span><span class="p">)</span> |
| <span class="fm">__mul__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__mul__"</span><span class="p">)</span> |
| <span class="n">__div__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__div__"</span><span class="p">)</span> |
| <span class="fm">__truediv__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__truediv__"</span><span class="p">)</span> |
| <span class="fm">__mod__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__mod__"</span><span class="p">)</span> |
| <span class="fm">__radd__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__radd__"</span><span class="p">)</span> |
| <span class="fm">__rsub__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__rsub__"</span><span class="p">)</span> |
| <span class="fm">__rmul__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__rmul__"</span><span class="p">)</span> |
| <span class="n">__rdiv__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__rdiv__"</span><span class="p">)</span> |
| <span class="fm">__rtruediv__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__rtruediv__"</span><span class="p">)</span> |
| <span class="fm">__rmod__</span> <span class="o">=</span> <span class="n">_delegate</span><span class="p">(</span><span class="s2">"__rmod__"</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="SparseVector"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector">[docs]</a><span class="k">class</span> <span class="nc">SparseVector</span><span class="p">(</span><span class="n">Vector</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A simple sparse vector class for passing data to MLlib. Users may</span> |
| <span class="sd"> alternatively pass SciPy's {scipy.sparse} data types.</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__indices</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">__values</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">):</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]):</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__indices</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">__values</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]):</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__pairs</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]]):</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__map</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]):</span> |
| <span class="o">...</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span> |
| <span class="nb">bytes</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]],</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> |
| <span class="p">],</span> |
| <span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Create a sparse vector, using either a dictionary, a list of</span> |
| <span class="sd"> (index, value) pairs, or two separate arrays of indices and</span> |
| <span class="sd"> values (sorted by index).</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the vector.</span> |
| <span class="sd"> args</span> |
| <span class="sd"> Active entries, as a dictionary {index: value, ...},</span> |
| <span class="sd"> a list of tuples [(index, value), ...], or a list of strictly</span> |
| <span class="sd"> increasing indices and a list of corresponding values [index, ...],</span> |
| <span class="sd"> [value, ...]. Inactive entries are treated as zeros.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> >>> SparseVector(4, [(1, 1.0), (3, 5.5)])</span> |
| <span class="sd"> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> >>> SparseVector(4, [1, 3], [1.0, 5.5])</span> |
| <span class="sd"> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">size</span><span class="p">)</span> |
| <span class="w"> </span><span class="sd">""" Size of the vector. """</span> |
| <span class="k">assert</span> <span class="mi">1</span> <span class="o"><=</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> <span class="o"><=</span> <span class="mi">2</span><span class="p">,</span> <span class="s2">"must pass either 2 or 3 arguments"</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="n">pairs</span> <span class="o">=</span> <span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">pairs</span><span class="p">)</span> <span class="o">==</span> <span class="nb">dict</span><span class="p">:</span> |
| <span class="n">pairs</span> <span class="o">=</span> <span class="n">pairs</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> |
| <span class="n">pairs</span> <span class="o">=</span> <span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]],</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">pairs</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">p</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">pairs</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="w"> </span><span class="sd">""" A list of indices corresponding to active entries. """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">p</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">pairs</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="w"> </span><span class="sd">""" A list of values corresponding to active entries. """</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">bytes</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">args</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="nb">bytes</span><span class="p">),</span> <span class="s2">"values should be string too"</span> |
| <span class="k">if</span> <span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">]:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">frombuffer</span><span class="p">(</span><span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">frombuffer</span><span class="p">(</span><span class="n">args</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># np.frombuffer() doesn't work well with empty string in older version</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">args</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">)</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">),</span> <span class="s2">"index and value arrays not same length"</span> |
| <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"Indices </span><span class="si">%s</span><span class="s2"> and </span><span class="si">%s</span><span class="s2"> are not strictly increasing"</span> |
| <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="mi">1</span><span class="p">])</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="SparseVector.numNonzeros"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.numNonzeros">[docs]</a> <span class="k">def</span> <span class="nf">numNonzeros</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Number of nonzero elements. This scans all active values and count non zeros.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">count_nonzero</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SparseVector.norm"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.norm">[docs]</a> <span class="k">def</span> <span class="nf">norm</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">p</span><span class="p">:</span> <span class="s2">"NormType"</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Calculates the norm of a SparseVector.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> a = SparseVector(4, [0, 1], [3., -4.])</span> |
| <span class="sd"> >>> a.norm(1)</span> |
| <span class="sd"> 7.0</span> |
| <span class="sd"> >>> a.norm(2)</span> |
| <span class="sd"> 5.0</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="n">p</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Type</span><span class="p">[</span><span class="s2">"SparseVector"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">SparseVector</span><span class="p">,</span> |
| <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),</span> |
| <span class="p">),</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="SparseVector.parse"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.parse">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">parse</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"SparseVector"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Parse string representation back into the SparseVector.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> SparseVector.parse(' (4, [0,1 ],[ 4.0,5.0] )')</span> |
| <span class="sd"> SparseVector(4, {0: 4.0, 1: 5.0})</span> |
| <span class="sd"> """</span> |
| <span class="n">start</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"("</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">start</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Tuple should start with '('"</span><span class="p">)</span> |
| <span class="n">end</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">")"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">end</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Tuple should end with ')'"</span><span class="p">)</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">start</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:</span> <span class="n">end</span><span class="p">]</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> |
| |
| <span class="n">size</span> <span class="o">=</span> <span class="n">s</span><span class="p">[:</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">","</span><span class="p">)]</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">size</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">size</span><span class="p">)</span> <span class="c1"># type: ignore[assignment]</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Cannot parse size </span><span class="si">%s</span><span class="s2">."</span> <span class="o">%</span> <span class="n">size</span><span class="p">)</span> |
| |
| <span class="n">ind_start</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"["</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">ind_start</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Indices array should start with '['."</span><span class="p">)</span> |
| <span class="n">ind_end</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"]"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">ind_end</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Indices array should end with ']'"</span><span class="p">)</span> |
| <span class="n">new_s</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">ind_start</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:</span> <span class="n">ind_end</span><span class="p">]</span> |
| <span class="n">ind_list</span> <span class="o">=</span> <span class="n">new_s</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">","</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">indices</span> <span class="o">=</span> <span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">ind</span><span class="p">)</span> <span class="k">for</span> <span class="n">ind</span> <span class="ow">in</span> <span class="n">ind_list</span> <span class="k">if</span> <span class="n">ind</span><span class="p">]</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Unable to parse indices from </span><span class="si">%s</span><span class="s2">."</span> <span class="o">%</span> <span class="n">new_s</span><span class="p">)</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">ind_end</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:]</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> |
| |
| <span class="n">val_start</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"["</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">val_start</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Values array should start with '['."</span><span class="p">)</span> |
| <span class="n">val_end</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"]"</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">val_end</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Values array should end with ']'."</span><span class="p">)</span> |
| <span class="n">val_list</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="n">val_start</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:</span> <span class="n">val_end</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">","</span><span class="p">)</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">val</span><span class="p">)</span> <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">val_list</span> <span class="k">if</span> <span class="n">val</span><span class="p">]</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Unable to parse values from </span><span class="si">%s</span><span class="s2">."</span> <span class="o">%</span> <span class="n">s</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="n">cast</span><span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="n">size</span><span class="p">),</span> <span class="n">indices</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SparseVector.dot"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.dot">[docs]</a> <span class="k">def</span> <span class="nf">dot</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Dot product with a SparseVector or 1- or 2-dimensional Numpy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> a = SparseVector(4, [1, 3], [3.0, 4.0])</span> |
| <span class="sd"> >>> a.dot(a)</span> |
| <span class="sd"> 25.0</span> |
| <span class="sd"> >>> a.dot(array.array('d', [1., 2., 3., 4.]))</span> |
| <span class="sd"> 22.0</span> |
| <span class="sd"> >>> b = SparseVector(4, [2], [1.0])</span> |
| <span class="sd"> >>> a.dot(b)</span> |
| <span class="sd"> 0.0</span> |
| <span class="sd"> >>> a.dot(np.array([[1, 1], [2, 2], [3, 3], [4, 4]]))</span> |
| <span class="sd"> array([ 22., 22.])</span> |
| <span class="sd"> >>> a.dot([1., 2., 3.])</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> >>> a.dot(np.array([1., 2.]))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> >>> a.dot(DenseVector([1., 2.]))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> >>> a.dot(np.zeros((3, 2)))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">other</span><span class="o">.</span><span class="n">ndim</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">]:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Cannot call dot with </span><span class="si">%d</span><span class="s2">-dimensional array"</span> <span class="o">%</span> <span class="n">other</span><span class="o">.</span><span class="n">ndim</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="s2">"dimension mismatch"</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="n">other</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">])</span> |
| |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">_vector_size</span><span class="p">(</span><span class="n">other</span><span class="p">),</span> <span class="s2">"dimension mismatch"</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">array</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="c1"># Find out common indices.</span> |
| <span class="n">self_cmind</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">in1d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="n">assume_unique</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="n">self_values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">self_cmind</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">self_values</span><span class="o">.</span><span class="n">size</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">other_cmind</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">in1d</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="n">assume_unique</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">self_values</span><span class="p">,</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">other_cmind</span><span class="p">])</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">other</span><span class="p">))</span> <span class="c1"># type: ignore[arg-type]</span></div> |
| |
| <div class="viewcode-block" id="SparseVector.squared_distance"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.squared_distance">[docs]</a> <span class="k">def</span> <span class="nf">squared_distance</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Squared distance from a SparseVector or 1-dimensional NumPy array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> a = SparseVector(4, [1, 3], [3.0, 4.0])</span> |
| <span class="sd"> >>> a.squared_distance(a)</span> |
| <span class="sd"> 0.0</span> |
| <span class="sd"> >>> a.squared_distance(array.array('d', [1., 2., 3., 4.]))</span> |
| <span class="sd"> 11.0</span> |
| <span class="sd"> >>> a.squared_distance(np.array([1., 2., 3., 4.]))</span> |
| <span class="sd"> 11.0</span> |
| <span class="sd"> >>> b = SparseVector(4, [2], [1.0])</span> |
| <span class="sd"> >>> a.squared_distance(b)</span> |
| <span class="sd"> 26.0</span> |
| <span class="sd"> >>> b.squared_distance(a)</span> |
| <span class="sd"> 26.0</span> |
| <span class="sd"> >>> b.squared_distance([1., 2.])</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> >>> b.squared_distance(SparseVector(3, [1,], [1.0,]))</span> |
| <span class="sd"> Traceback (most recent call last):</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> AssertionError: dimension mismatch</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="n">_vector_size</span><span class="p">(</span><span class="n">other</span><span class="p">),</span> <span class="s2">"dimension mismatch"</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">or</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="ow">and</span> <span class="n">other</span><span class="o">.</span><span class="n">ndim</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Cannot call squared_distance with </span><span class="si">%d</span><span class="s2">-dimensional array"</span> <span class="o">%</span> <span class="n">other</span><span class="o">.</span><span class="n">ndim</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="n">other</span> <span class="o">=</span> <span class="n">other</span><span class="o">.</span><span class="n">array</span> |
| <span class="n">sparse_ind</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="nb">bool</span><span class="p">)</span> |
| <span class="n">sparse_ind</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="n">dist</span> <span class="o">=</span> <span class="n">other</span><span class="p">[</span><span class="n">sparse_ind</span><span class="p">]</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">dist</span><span class="p">,</span> <span class="n">dist</span><span class="p">)</span> |
| |
| <span class="n">other_ind</span> <span class="o">=</span> <span class="n">other</span><span class="p">[</span><span class="o">~</span><span class="n">sparse_ind</span><span class="p">]</span> |
| <span class="n">result</span> <span class="o">+=</span> <span class="n">np</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">other_ind</span><span class="p">,</span> <span class="n">other_ind</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mf">0.0</span> |
| <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span> |
| <span class="k">while</span> <span class="n">i</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">)</span> <span class="ow">and</span> <span class="n">j</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">j</span><span class="p">]:</span> |
| <span class="n">diff</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">-</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> |
| <span class="n">result</span> <span class="o">+=</span> <span class="n">diff</span> <span class="o">*</span> <span class="n">diff</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">j</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o"><</span> <span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">j</span><span class="p">]:</span> |
| <span class="n">result</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">+=</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> <span class="o">*</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> |
| <span class="n">j</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">while</span> <span class="n">i</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">):</span> |
| <span class="n">result</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">while</span> <span class="n">j</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">):</span> |
| <span class="n">result</span> <span class="o">+=</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> <span class="o">*</span> <span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> |
| <span class="n">j</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">result</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">squared_distance</span><span class="p">(</span><span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">other</span><span class="p">))</span> <span class="c1"># type: ignore[arg-type]</span></div> |
| |
| <div class="viewcode-block" id="SparseVector.toArray"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.toArray">[docs]</a> <span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a copy of this SparseVector as a 1-dimensional NumPy array.</span> |
| <span class="sd"> """</span> |
| <span class="n">arr</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">,),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="n">arr</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span> |
| <span class="k">return</span> <span class="n">arr</span></div> |
| |
| <div class="viewcode-block" id="SparseVector.asML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseVector.html#pyspark.mllib.linalg.SparseVector.asML">[docs]</a> <span class="k">def</span> <span class="nf">asML</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">SparseVector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert this vector to the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.SparseVector`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">SparseVector</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> |
| |
| <span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="n">inds</span> <span class="o">=</span> <span class="s2">"["</span> <span class="o">+</span> <span class="s2">","</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">])</span> <span class="o">+</span> <span class="s2">"]"</span> |
| <span class="n">vals</span> <span class="o">=</span> <span class="s2">"["</span> <span class="o">+</span> <span class="s2">","</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">v</span><span class="p">)</span> <span class="k">for</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">])</span> <span class="o">+</span> <span class="s2">"]"</span> |
| <span class="k">return</span> <span class="s2">"("</span> <span class="o">+</span> <span class="s2">","</span><span class="o">.</span><span class="n">join</span><span class="p">((</span><span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">),</span> <span class="n">inds</span><span class="p">,</span> <span class="n">vals</span><span class="p">))</span> <span class="o">+</span> <span class="s2">")"</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="n">inds</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span> |
| <span class="n">vals</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span> |
| <span class="n">entries</span> <span class="o">=</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span> |
| <span class="p">[</span><span class="s2">"</span><span class="si">{0}</span><span class="s2">: </span><span class="si">{1}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">inds</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">_format_float</span><span class="p">(</span><span class="n">vals</span><span class="p">[</span><span class="n">i</span><span class="p">]))</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">inds</span><span class="p">))]</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="s2">"SparseVector(</span><span class="si">{0}</span><span class="s2">, {{</span><span class="si">{1}</span><span class="s2">}})"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="n">entries</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">(</span> |
| <span class="n">other</span><span class="o">.</span><span class="n">size</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> |
| <span class="ow">and</span> <span class="n">np</span><span class="o">.</span><span class="n">array_equal</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">)</span> |
| <span class="ow">and</span> <span class="n">np</span><span class="o">.</span><span class="n">array_equal</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DenseVector</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="o">!=</span> <span class="nb">len</span><span class="p">(</span><span class="n">other</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">return</span> <span class="n">Vectors</span><span class="o">.</span><span class="n">_equals</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">other</span><span class="p">))),</span> <span class="n">other</span><span class="o">.</span><span class="n">array</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">index</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="n">inds</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">indices</span> |
| <span class="n">vals</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">index</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Indices must be of type integer, got type </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">index</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="n">index</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="ow">or</span> <span class="n">index</span> <span class="o"><</span> <span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">IndexError</span><span class="p">(</span><span class="s2">"Index </span><span class="si">%d</span><span class="s2"> out of bounds."</span> <span class="o">%</span> <span class="n">index</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">index</span> <span class="o"><</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">index</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="n">inds</span><span class="o">.</span><span class="n">size</span> <span class="o">==</span> <span class="mi">0</span><span class="p">)</span> <span class="ow">or</span> <span class="p">(</span><span class="n">index</span> <span class="o">></span> <span class="n">inds</span><span class="o">.</span><span class="n">item</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)):</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)</span> |
| |
| <span class="n">insert_index</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">searchsorted</span><span class="p">(</span><span class="n">inds</span><span class="p">,</span> <span class="n">index</span><span class="p">)</span> |
| <span class="n">row_ind</span> <span class="o">=</span> <span class="n">inds</span><span class="p">[</span><span class="n">insert_index</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">row_ind</span> <span class="o">==</span> <span class="n">index</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">vals</span><span class="p">[</span><span class="n">insert_index</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__ne__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="k">return</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="fm">__eq__</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__hash__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">int</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mi">31</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> |
| <span class="n">nnz</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">while</span> <span class="n">i</span> <span class="o"><</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> <span class="ow">and</span> <span class="n">nnz</span> <span class="o"><</span> <span class="mi">128</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mi">31</span> <span class="o">*</span> <span class="n">result</span> <span class="o">+</span> <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">indices</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> |
| <span class="n">bits</span> <span class="o">=</span> <span class="n">_double_to_long_bits</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="mi">31</span> <span class="o">*</span> <span class="n">result</span> <span class="o">+</span> <span class="p">(</span><span class="n">bits</span> <span class="o">^</span> <span class="p">(</span><span class="n">bits</span> <span class="o">>></span> <span class="mi">32</span><span class="p">))</span> |
| <span class="n">nnz</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">i</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">result</span></div> |
| |
| |
| <div class="viewcode-block" id="Vectors"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors">[docs]</a><span class="k">class</span> <span class="nc">Vectors</span><span class="p">:</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Factory methods for working with vectors.</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Dense vectors are simply represented as NumPy array objects,</span> |
| <span class="sd"> so there is no need to convert them for use in MLlib. For sparse vectors,</span> |
| <span class="sd"> the factory methods in this class create an MLlib-compatible type, or users</span> |
| <span class="sd"> can pass in SciPy's `scipy.sparse` column vectors.</span> |
| <span class="sd"> """</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span><span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__indices</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">__values</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">)</span> <span class="o">-></span> <span class="n">SparseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span><span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">SparseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span><span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__indices</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">__values</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">SparseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span><span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__pairs</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]])</span> <span class="o">-></span> <span class="n">SparseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@overload</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span><span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">__map</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">SparseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="Vectors.sparse"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.sparse">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span> |
| <span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span> |
| <span class="nb">bytes</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]],</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">]</span> |
| <span class="p">],</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">SparseVector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Create a sparse vector, using either a dictionary, a list of</span> |
| <span class="sd"> (index, value) pairs, or two separate arrays of indices and</span> |
| <span class="sd"> values (sorted by index).</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> size : int</span> |
| <span class="sd"> Size of the vector.</span> |
| <span class="sd"> args</span> |
| <span class="sd"> Non-zero entries, as a dictionary, list of tuples,</span> |
| <span class="sd"> or two sorted lists containing indices and values.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> Vectors.sparse(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> >>> Vectors.sparse(4, [(1, 1.0), (3, 5.5)])</span> |
| <span class="sd"> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> >>> Vectors.sparse(4, [1, 3], [1.0, 5.5])</span> |
| <span class="sd"> SparseVector(4, {1: 1.0, 3: 5.5})</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">)</span> <span class="c1"># type: ignore[arg-type]</span></div> |
| |
| <span class="nd">@overload</span> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">dense</span><span class="p">(</span><span class="o">*</span><span class="n">elements</span><span class="p">:</span> <span class="nb">float</span><span class="p">)</span> <span class="o">-></span> <span class="n">DenseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">dense</span><span class="p">(</span><span class="n">__arr</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">)</span> <span class="o">-></span> <span class="n">DenseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <span class="nd">@overload</span> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">dense</span><span class="p">(</span><span class="n">__arr</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">])</span> <span class="o">-></span> <span class="n">DenseVector</span><span class="p">:</span> |
| <span class="o">...</span> |
| |
| <div class="viewcode-block" id="Vectors.dense"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.dense">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">dense</span><span class="p">(</span><span class="o">*</span><span class="n">elements</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]])</span> <span class="o">-></span> <span class="n">DenseVector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Create a dense vector of 64-bit floats from a Python list or numbers.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> Vectors.dense([1, 2, 3])</span> |
| <span class="sd"> DenseVector([1.0, 2.0, 3.0])</span> |
| <span class="sd"> >>> Vectors.dense(1.0, 2.0)</span> |
| <span class="sd"> DenseVector([1.0, 2.0])</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">elements</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">elements</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="p">(</span><span class="nb">float</span><span class="p">,</span> <span class="nb">int</span><span class="p">)):</span> |
| <span class="c1"># it's list, numpy.array or other iterable object.</span> |
| <span class="n">elements</span> <span class="o">=</span> <span class="n">elements</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="c1"># type: ignore[assignment]</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="n">cast</span><span class="p">(</span><span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">elements</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Vectors.fromML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.fromML">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">fromML</span><span class="p">(</span><span class="n">vec</span><span class="p">:</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseVector</span><span class="p">)</span> <span class="o">-></span> <span class="n">DenseVector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert a vector from the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> vec : :py:class:`pyspark.ml.linalg.Vector`</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Vector`</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vec</span><span class="p">,</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">array</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vec</span><span class="p">,</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">SparseVector</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="p">(</span><span class="n">vec</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="n">vec</span><span class="o">.</span><span class="n">indices</span><span class="p">,</span> <span class="n">vec</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Unsupported vector type </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">vec</span><span class="p">))</span></div> |
| |
| <div class="viewcode-block" id="Vectors.stringify"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.stringify">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">stringify</span><span class="p">(</span><span class="n">vector</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Converts a vector into a string, which can be recognized by</span> |
| <span class="sd"> Vectors.parse().</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> Vectors.stringify(Vectors.sparse(2, [1], [1.0]))</span> |
| <span class="sd"> '(2,[1],[1.0])'</span> |
| <span class="sd"> >>> Vectors.stringify(Vectors.dense([0.0, 1.0]))</span> |
| <span class="sd"> '[0.0,1.0]'</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Vectors.squared_distance"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.squared_distance">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">squared_distance</span><span class="p">(</span><span class="n">v1</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">v2</span><span class="p">:</span> <span class="n">Vector</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Squared distance between two vectors.</span> |
| <span class="sd"> a and b can be of type SparseVector, DenseVector, np.ndarray</span> |
| <span class="sd"> or array.array.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> a = Vectors.sparse(4, [(0, 1), (3, 4)])</span> |
| <span class="sd"> >>> b = Vectors.dense([2, 5, 4, 1])</span> |
| <span class="sd"> >>> a.squared_distance(b)</span> |
| <span class="sd"> 51.0</span> |
| <span class="sd"> """</span> |
| <span class="n">v1</span><span class="p">,</span> <span class="n">v2</span> <span class="o">=</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">v1</span><span class="p">),</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">v2</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">v1</span><span class="o">.</span><span class="n">squared_distance</span><span class="p">(</span><span class="n">v2</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span></div> |
| |
| <div class="viewcode-block" id="Vectors.norm"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.norm">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">norm</span><span class="p">(</span><span class="n">vector</span><span class="p">:</span> <span class="n">Vector</span><span class="p">,</span> <span class="n">p</span><span class="p">:</span> <span class="s2">"NormType"</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Find norm of the given vector.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">_convert_to_vector</span><span class="p">(</span><span class="n">vector</span><span class="p">)</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="c1"># type: ignore[attr-defined]</span></div> |
| |
| <div class="viewcode-block" id="Vectors.parse"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.parse">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">parse</span><span class="p">(</span><span class="n">s</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="n">Vector</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Parse a string representation back into the Vector.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> Vectors.parse('[2,1,2 ]')</span> |
| <span class="sd"> DenseVector([2.0, 1.0, 2.0])</span> |
| <span class="sd"> >>> Vectors.parse(' ( 100, [0], [2])')</span> |
| <span class="sd"> SparseVector(100, {0: 2.0})</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"("</span><span class="p">)</span> <span class="o">==</span> <span class="o">-</span><span class="mi">1</span> <span class="ow">and</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"["</span><span class="p">)</span> <span class="o">!=</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">s</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"("</span><span class="p">)</span> <span class="o">!=</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">SparseVector</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">s</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Cannot find tokens '[' or '(' from the input string."</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Vectors.zeros"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Vectors.html#pyspark.mllib.linalg.Vectors.zeros">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">zeros</span><span class="p">(</span><span class="n">size</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">DenseVector</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DenseVector</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">size</span><span class="p">))</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_equals</span><span class="p">(</span> |
| <span class="n">v1_indices</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Sequence</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span> |
| <span class="n">v1_values</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Sequence</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span> |
| <span class="n">v2_indices</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Sequence</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span> |
| <span class="n">v2_values</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">Sequence</span><span class="p">[</span><span class="nb">float</span><span class="p">],</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Check equality between sparse/dense vectors,</span> |
| <span class="sd"> v1_indices and v2_indices assume to be strictly increasing.</span> |
| <span class="sd"> """</span> |
| <span class="n">v1_size</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">v1_values</span><span class="p">)</span> |
| <span class="n">v2_size</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">v2_values</span><span class="p">)</span> |
| <span class="n">k1</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">k2</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">all_equal</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">while</span> <span class="n">all_equal</span><span class="p">:</span> |
| <span class="k">while</span> <span class="n">k1</span> <span class="o"><</span> <span class="n">v1_size</span> <span class="ow">and</span> <span class="n">v1_values</span><span class="p">[</span><span class="n">k1</span><span class="p">]</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">k1</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">while</span> <span class="n">k2</span> <span class="o"><</span> <span class="n">v2_size</span> <span class="ow">and</span> <span class="n">v2_values</span><span class="p">[</span><span class="n">k2</span><span class="p">]</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">k2</span> <span class="o">+=</span> <span class="mi">1</span> |
| |
| <span class="k">if</span> <span class="n">k1</span> <span class="o">>=</span> <span class="n">v1_size</span> <span class="ow">or</span> <span class="n">k2</span> <span class="o">>=</span> <span class="n">v2_size</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">k1</span> <span class="o">>=</span> <span class="n">v1_size</span> <span class="ow">and</span> <span class="n">k2</span> <span class="o">>=</span> <span class="n">v2_size</span> |
| |
| <span class="n">all_equal</span> <span class="o">=</span> <span class="n">v1_indices</span><span class="p">[</span><span class="n">k1</span><span class="p">]</span> <span class="o">==</span> <span class="n">v2_indices</span><span class="p">[</span><span class="n">k2</span><span class="p">]</span> <span class="ow">and</span> <span class="n">v1_values</span><span class="p">[</span><span class="n">k1</span><span class="p">]</span> <span class="o">==</span> <span class="n">v2_values</span><span class="p">[</span><span class="n">k2</span><span class="p">]</span> |
| <span class="n">k1</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="n">k2</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">all_equal</span></div> |
| |
| |
| <div class="viewcode-block" id="Matrix"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix">[docs]</a><span class="k">class</span> <span class="nc">Matrix</span><span class="p">:</span> |
| |
| <span class="n">__UDT__</span> <span class="o">=</span> <span class="n">MatrixUDT</span><span class="p">()</span> |
| |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Represents a local matrix.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">isTransposed</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span> <span class="o">=</span> <span class="n">numRows</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span> <span class="o">=</span> <span class="n">numCols</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span> <span class="o">=</span> <span class="n">isTransposed</span> |
| |
| <div class="viewcode-block" id="Matrix.toArray"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix.toArray">[docs]</a> <span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns its elements in a NumPy ndarray.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="Matrix.asML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrix.html#pyspark.mllib.linalg.Matrix.asML">[docs]</a> <span class="k">def</span> <span class="nf">asML</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">Matrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert this matrix to the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">_convert_to_array</span><span class="p">(</span><span class="n">array_like</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]],</span> <span class="n">dtype</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert Matrix attributes which are array-like or buffer to array.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">array_like</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">frombuffer</span><span class="p">(</span><span class="n">array_like</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">array_like</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="DenseMatrix"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseMatrix.html#pyspark.mllib.linalg.DenseMatrix">[docs]</a><span class="k">class</span> <span class="nc">DenseMatrix</span><span class="p">(</span><span class="n">Matrix</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Column-major dense matrix.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">values</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]],</span> |
| <span class="n">isTransposed</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="p">):</span> |
| <span class="n">Matrix</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">isTransposed</span><span class="p">)</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_convert_to_array</span><span class="p">(</span><span class="n">values</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">values</span><span class="p">)</span> <span class="o">==</span> <span class="n">numRows</span> <span class="o">*</span> <span class="n">numCols</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span> <span class="o">=</span> <span class="n">values</span> |
| |
| <span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Type</span><span class="p">[</span><span class="s2">"DenseMatrix"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">,</span> <span class="nb">int</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="n">DenseMatrix</span><span class="p">,</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Pretty printing of a DenseMatrix</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> dm = DenseMatrix(2, 2, range(4))</span> |
| <span class="sd"> >>> print(dm)</span> |
| <span class="sd"> DenseMatrix([[ 0., 2.],</span> |
| <span class="sd"> [ 1., 3.]])</span> |
| <span class="sd"> >>> dm = DenseMatrix(2, 2, range(4), isTransposed=True)</span> |
| <span class="sd"> >>> print(dm)</span> |
| <span class="sd"> DenseMatrix([[ 0., 1.],</span> |
| <span class="sd"> [ 2., 3.]])</span> |
| <span class="sd"> """</span> |
| <span class="c1"># Inspired by __repr__ in scipy matrices.</span> |
| <span class="n">array_lines</span> <span class="o">=</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">())</span><span class="o">.</span><span class="n">splitlines</span><span class="p">()</span> |
| |
| <span class="c1"># We need to adjust six spaces which is the difference in number</span> |
| <span class="c1"># of letters between "DenseMatrix" and "array"</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">([(</span><span class="s2">" "</span> <span class="o">*</span> <span class="mi">6</span> <span class="o">+</span> <span class="n">line</span><span class="p">)</span> <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">array_lines</span><span class="p">[</span><span class="mi">1</span><span class="p">:]])</span> |
| <span class="k">return</span> <span class="n">array_lines</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"array"</span><span class="p">,</span> <span class="s2">"DenseMatrix"</span><span class="p">)</span> <span class="o">+</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span> <span class="o">+</span> <span class="n">x</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Representation of a DenseMatrix</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> dm = DenseMatrix(2, 2, range(4))</span> |
| <span class="sd"> >>> dm</span> |
| <span class="sd"> DenseMatrix(2, 2, [0.0, 1.0, 2.0, 3.0], False)</span> |
| <span class="sd"> """</span> |
| <span class="c1"># If the number of values are less than seventeen then return as it is.</span> |
| <span class="c1"># Else return first eight values and last eight values.</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> <span class="o"><</span> <span class="mi">17</span><span class="p">:</span> |
| <span class="n">entries</span> <span class="o">=</span> <span class="n">_format_float_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">entries</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">_format_float_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[:</span><span class="mi">8</span><span class="p">])</span> <span class="o">+</span> <span class="p">[</span><span class="s2">"..."</span><span class="p">]</span> <span class="o">+</span> <span class="n">_format_float_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="o">-</span><span class="mi">8</span><span class="p">:])</span> |
| <span class="p">)</span> |
| |
| <span class="k">return</span> <span class="s2">"DenseMatrix(</span><span class="si">{0}</span><span class="s2">, </span><span class="si">{1}</span><span class="s2">, [</span><span class="si">{2}</span><span class="s2">], </span><span class="si">{3}</span><span class="s2">)"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">entries</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span> |
| <span class="p">)</span> |
| |
| <div class="viewcode-block" id="DenseMatrix.toArray"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseMatrix.html#pyspark.mllib.linalg.DenseMatrix.toArray">[docs]</a> <span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Return an numpy.ndarray</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> m = DenseMatrix(2, 2, range(4))</span> |
| <span class="sd"> >>> m.toArray()</span> |
| <span class="sd"> array([[ 0., 2.],</span> |
| <span class="sd"> [ 1., 3.]])</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">asfortranarray</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">)))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">),</span> <span class="n">order</span><span class="o">=</span><span class="s2">"F"</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DenseMatrix.toSparse"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseMatrix.html#pyspark.mllib.linalg.DenseMatrix.toSparse">[docs]</a> <span class="k">def</span> <span class="nf">toSparse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"SparseMatrix"</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Convert to SparseMatrix"""</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ravel</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">order</span><span class="o">=</span><span class="s2">"F"</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span> |
| <span class="n">indices</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">nonzero</span><span class="p">(</span><span class="n">values</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">colCounts</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">bincount</span><span class="p">(</span><span class="n">indices</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">)</span> |
| <span class="n">colPtrs</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">cumsum</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">hstack</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="n">colCounts</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numCols</span> <span class="o">-</span> <span class="n">colCounts</span><span class="o">.</span><span class="n">size</span><span class="p">))))</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="n">values</span><span class="p">[</span><span class="n">indices</span><span class="p">]</span> |
| <span class="n">rowIndices</span> <span class="o">=</span> <span class="n">indices</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span> |
| |
| <span class="k">return</span> <span class="n">SparseMatrix</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="n">colPtrs</span><span class="p">,</span> <span class="n">rowIndices</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="DenseMatrix.asML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.DenseMatrix.html#pyspark.mllib.linalg.DenseMatrix.asML">[docs]</a> <span class="k">def</span> <span class="nf">asML</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseMatrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert this matrix to the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.DenseMatrix`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseMatrix</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">indices</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">])</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="o">=</span> <span class="n">indices</span> |
| <span class="k">if</span> <span class="n">i</span> <span class="o"><</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">i</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">IndexError</span><span class="p">(</span><span class="s2">"Row index </span><span class="si">%d</span><span class="s2"> is out of range [0, </span><span class="si">%d</span><span class="s2">)"</span> <span class="o">%</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">j</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span> <span class="ow">or</span> <span class="n">j</span> <span class="o"><</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">IndexError</span><span class="p">(</span><span class="s2">"Column index </span><span class="si">%d</span><span class="s2"> is out of range [0, </span><span class="si">%d</span><span class="s2">)"</span> <span class="o">%</span> <span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">))</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span> <span class="o">+</span> <span class="n">j</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">i</span> <span class="o">+</span> <span class="n">j</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="fm">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span> <span class="o">!=</span> <span class="n">other</span><span class="o">.</span><span class="n">numRows</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span> <span class="o">!=</span> <span class="n">other</span><span class="o">.</span><span class="n">numCols</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">SparseMatrix</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">toArray</span><span class="p">())</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span> |
| |
| <span class="n">self_values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ravel</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">order</span><span class="o">=</span><span class="s2">"F"</span><span class="p">)</span> |
| <span class="n">other_values</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ravel</span><span class="p">(</span><span class="n">other</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">order</span><span class="o">=</span><span class="s2">"F"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">all</span><span class="p">(</span><span class="n">self_values</span> <span class="o">==</span> <span class="n">other_values</span><span class="p">)</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span></div> |
| |
| |
| <div class="viewcode-block" id="SparseMatrix"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseMatrix.html#pyspark.mllib.linalg.SparseMatrix">[docs]</a><span class="k">class</span> <span class="nc">SparseMatrix</span><span class="p">(</span><span class="n">Matrix</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Sparse Matrix stored in CSC format."""</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">colPtrs</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> |
| <span class="n">rowIndices</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> |
| <span class="n">values</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]],</span> |
| <span class="n">isTransposed</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">Matrix</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">isTransposed</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_convert_to_array</span><span class="p">(</span><span class="n">colPtrs</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_convert_to_array</span><span class="p">(</span><span class="n">rowIndices</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_convert_to_array</span><span class="p">(</span><span class="n">values</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="o">.</span><span class="n">size</span> <span class="o">!=</span> <span class="n">numRows</span> <span class="o">+</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Expected colPtrs of size </span><span class="si">%d</span><span class="s2">, got </span><span class="si">%d</span><span class="s2">."</span> <span class="o">%</span> <span class="p">(</span><span class="n">numRows</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="o">.</span><span class="n">size</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="o">.</span><span class="n">size</span> <span class="o">!=</span> <span class="n">numCols</span> <span class="o">+</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Expected colPtrs of size </span><span class="si">%d</span><span class="s2">, got </span><span class="si">%d</span><span class="s2">."</span> <span class="o">%</span> <span class="p">(</span><span class="n">numCols</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="o">.</span><span class="n">size</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="o">.</span><span class="n">size</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">size</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s2">"Expected rowIndices of length </span><span class="si">%d</span><span class="s2">, got </span><span class="si">%d</span><span class="s2">."</span> |
| <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="o">.</span><span class="n">size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">size</span><span class="p">)</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Pretty printing of a SparseMatrix</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> sm1 = SparseMatrix(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4])</span> |
| <span class="sd"> >>> print(sm1)</span> |
| <span class="sd"> 2 X 2 CSCMatrix</span> |
| <span class="sd"> (0,0) 2.0</span> |
| <span class="sd"> (1,0) 3.0</span> |
| <span class="sd"> (1,1) 4.0</span> |
| <span class="sd"> >>> sm1 = SparseMatrix(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4], True)</span> |
| <span class="sd"> >>> print(sm1)</span> |
| <span class="sd"> 2 X 2 CSRMatrix</span> |
| <span class="sd"> (0,0) 2.0</span> |
| <span class="sd"> (0,1) 3.0</span> |
| <span class="sd"> (1,1) 4.0</span> |
| <span class="sd"> """</span> |
| <span class="n">spstr</span> <span class="o">=</span> <span class="s2">"</span><span class="si">{0}</span><span class="s2"> X </span><span class="si">{1}</span><span class="s2"> "</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="n">spstr</span> <span class="o">+=</span> <span class="s2">"CSRMatrix</span><span class="se">\n</span><span class="s2">"</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">spstr</span> <span class="o">+=</span> <span class="s2">"CSCMatrix</span><span class="se">\n</span><span class="s2">"</span> |
| |
| <span class="n">cur_col</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">smlist</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="c1"># Display first 16 values.</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> <span class="o"><=</span> <span class="mi">16</span><span class="p">:</span> |
| <span class="n">zipindval</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">zipindval</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">[:</span><span class="mi">16</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[:</span><span class="mi">16</span><span class="p">])</span> |
| <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="p">(</span><span class="n">rowInd</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">zipindval</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">[</span><span class="n">cur_col</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> <span class="o"><=</span> <span class="n">i</span><span class="p">:</span> |
| <span class="n">cur_col</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="n">smlist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"(</span><span class="si">{0}</span><span class="s2">,</span><span class="si">{1}</span><span class="s2">) </span><span class="si">{2}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">cur_col</span><span class="p">,</span> <span class="n">rowInd</span><span class="p">,</span> <span class="n">_format_float</span><span class="p">(</span><span class="n">value</span><span class="p">)))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">smlist</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s2">"(</span><span class="si">{0}</span><span class="s2">,</span><span class="si">{1}</span><span class="s2">) </span><span class="si">{2}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">rowInd</span><span class="p">,</span> <span class="n">cur_col</span><span class="p">,</span> <span class="n">_format_float</span><span class="p">(</span><span class="n">value</span><span class="p">)))</span> |
| <span class="n">spstr</span> <span class="o">+=</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">smlist</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> <span class="o">></span> <span class="mi">16</span><span class="p">:</span> |
| <span class="n">spstr</span> <span class="o">+=</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">.."</span> <span class="o">*</span> <span class="mi">2</span> |
| <span class="k">return</span> <span class="n">spstr</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Representation of a SparseMatrix</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> >>> sm1 = SparseMatrix(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4])</span> |
| <span class="sd"> >>> sm1</span> |
| <span class="sd"> SparseMatrix(2, 2, [0, 2, 3], [0, 1, 1], [2.0, 3.0, 4.0], False)</span> |
| <span class="sd"> """</span> |
| <span class="n">rowIndices</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">)</span> |
| <span class="n">colPtrs</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> <span class="o"><=</span> <span class="mi">16</span><span class="p">:</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="n">_format_float_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">)</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">values</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">_format_float_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[:</span><span class="mi">8</span><span class="p">])</span> <span class="o">+</span> <span class="p">[</span><span class="s2">"..."</span><span class="p">]</span> <span class="o">+</span> <span class="n">_format_float_list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="o">-</span><span class="mi">8</span><span class="p">:])</span> |
| <span class="p">)</span> |
| <span class="n">rowIndices</span> <span class="o">=</span> <span class="n">rowIndices</span><span class="p">[:</span><span class="mi">8</span><span class="p">]</span> <span class="o">+</span> <span class="p">[</span><span class="s2">"..."</span><span class="p">]</span> <span class="o">+</span> <span class="n">rowIndices</span><span class="p">[</span><span class="o">-</span><span class="mi">8</span><span class="p">:]</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">)</span> <span class="o">></span> <span class="mi">16</span><span class="p">:</span> |
| <span class="n">colPtrs</span> <span class="o">=</span> <span class="n">colPtrs</span><span class="p">[:</span><span class="mi">8</span><span class="p">]</span> <span class="o">+</span> <span class="p">[</span><span class="s2">"..."</span><span class="p">]</span> <span class="o">+</span> <span class="n">colPtrs</span><span class="p">[</span><span class="o">-</span><span class="mi">8</span><span class="p">:]</span> |
| |
| <span class="k">return</span> <span class="s2">"SparseMatrix(</span><span class="si">{0}</span><span class="s2">, </span><span class="si">{1}</span><span class="s2">, [</span><span class="si">{2}</span><span class="s2">], [</span><span class="si">{3}</span><span class="s2">], [</span><span class="si">{4}</span><span class="s2">], </span><span class="si">{5}</span><span class="s2">)"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> |
| <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">ptr</span><span class="p">)</span> <span class="k">for</span> <span class="n">ptr</span> <span class="ow">in</span> <span class="n">colPtrs</span><span class="p">]),</span> |
| <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">ind</span><span class="p">)</span> <span class="k">for</span> <span class="n">ind</span> <span class="ow">in</span> <span class="n">rowIndices</span><span class="p">]),</span> |
| <span class="s2">", "</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">values</span><span class="p">),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">,</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Type</span><span class="p">[</span><span class="s2">"SparseMatrix"</span><span class="p">],</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">,</span> <span class="nb">int</span><span class="p">]]:</span> |
| <span class="k">return</span> <span class="n">SparseMatrix</span><span class="p">,</span> <span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">tobytes</span><span class="p">(),</span> |
| <span class="nb">int</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">),</span> |
| <span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">indices</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">int</span><span class="p">])</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">:</span> |
| <span class="n">i</span><span class="p">,</span> <span class="n">j</span> <span class="o">=</span> <span class="n">indices</span> |
| <span class="k">if</span> <span class="n">i</span> <span class="o"><</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">i</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">IndexError</span><span class="p">(</span><span class="s2">"Row index </span><span class="si">%d</span><span class="s2"> is out of range [0, </span><span class="si">%d</span><span class="s2">)"</span> <span class="o">%</span> <span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">j</span> <span class="o"><</span> <span class="mi">0</span> <span class="ow">or</span> <span class="n">j</span> <span class="o">>=</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">IndexError</span><span class="p">(</span><span class="s2">"Column index </span><span class="si">%d</span><span class="s2"> is out of range [0, </span><span class="si">%d</span><span class="s2">)"</span> <span class="o">%</span> <span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">))</span> |
| |
| <span class="c1"># If a CSR matrix is given, then the row index should be searched</span> |
| <span class="c1"># for in ColPtrs, and the column index should be searched for in the</span> |
| <span class="c1"># corresponding slice obtained from rowIndices.</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="n">j</span><span class="p">,</span> <span class="n">i</span> <span class="o">=</span> <span class="n">i</span><span class="p">,</span> <span class="n">j</span> |
| |
| <span class="n">colStart</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">[</span><span class="n">j</span><span class="p">]</span> |
| <span class="n">colEnd</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">[</span><span class="n">j</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> |
| <span class="n">nz</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">[</span><span class="n">colStart</span><span class="p">:</span><span class="n">colEnd</span><span class="p">]</span> |
| <span class="n">ind</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">searchsorted</span><span class="p">(</span><span class="n">nz</span><span class="p">,</span> <span class="n">i</span><span class="p">)</span> <span class="o">+</span> <span class="n">colStart</span> |
| <span class="k">if</span> <span class="n">ind</span> <span class="o"><</span> <span class="n">colEnd</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">[</span><span class="n">ind</span><span class="p">]</span> <span class="o">==</span> <span class="n">i</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">ind</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="SparseMatrix.toArray"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseMatrix.html#pyspark.mllib.linalg.SparseMatrix.toArray">[docs]</a> <span class="k">def</span> <span class="nf">toArray</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Return an numpy.ndarray</span> |
| <span class="sd"> """</span> |
| <span class="n">A</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">),</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span> <span class="n">order</span><span class="o">=</span><span class="s2">"F"</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="o">.</span><span class="n">size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span> |
| <span class="n">startptr</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> |
| <span class="n">endptr</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">[</span><span class="n">k</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">:</span> |
| <span class="n">A</span><span class="p">[</span><span class="n">k</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">[</span><span class="n">startptr</span><span class="p">:</span><span class="n">endptr</span><span class="p">]]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">startptr</span><span class="p">:</span><span class="n">endptr</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">A</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">[</span><span class="n">startptr</span><span class="p">:</span><span class="n">endptr</span><span class="p">],</span> <span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">[</span><span class="n">startptr</span><span class="p">:</span><span class="n">endptr</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">A</span></div> |
| |
| <div class="viewcode-block" id="SparseMatrix.toDense"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseMatrix.html#pyspark.mllib.linalg.SparseMatrix.toDense">[docs]</a> <span class="k">def</span> <span class="nf">toDense</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"DenseMatrix"</span><span class="p">:</span> |
| <span class="n">densevals</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ravel</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">(),</span> <span class="n">order</span><span class="o">=</span><span class="s2">"F"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">DenseMatrix</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="n">densevals</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="SparseMatrix.asML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.SparseMatrix.html#pyspark.mllib.linalg.SparseMatrix.asML">[docs]</a> <span class="k">def</span> <span class="nf">asML</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">SparseMatrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert this matrix to the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.ml.linalg.SparseMatrix`</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">SparseMatrix</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">,</span> |
| <span class="p">)</span></div> |
| |
| <span class="c1"># TODO: More efficient implementation:</span> |
| <span class="k">def</span> <span class="fm">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Matrix</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">all</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">toArray</span><span class="p">()</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">toArray</span><span class="p">())</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span></div> |
| |
| |
| <div class="viewcode-block" id="Matrices"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrices.html#pyspark.mllib.linalg.Matrices">[docs]</a><span class="k">class</span> <span class="nc">Matrices</span><span class="p">:</span> |
| <div class="viewcode-block" id="Matrices.dense"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrices.html#pyspark.mllib.linalg.Matrices.dense">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">dense</span><span class="p">(</span><span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">values</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]])</span> <span class="o">-></span> <span class="n">DenseMatrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Create a DenseMatrix</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">DenseMatrix</span><span class="p">(</span><span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Matrices.sparse"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrices.html#pyspark.mllib.linalg.Matrices.sparse">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">sparse</span><span class="p">(</span> |
| <span class="n">numRows</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">numCols</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> |
| <span class="n">colPtrs</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> |
| <span class="n">rowIndices</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">int</span><span class="p">]],</span> |
| <span class="n">values</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">bytes</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">[</span><span class="nb">float</span><span class="p">]],</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">SparseMatrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Create a SparseMatrix</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">SparseMatrix</span><span class="p">(</span><span class="n">numRows</span><span class="p">,</span> <span class="n">numCols</span><span class="p">,</span> <span class="n">colPtrs</span><span class="p">,</span> <span class="n">rowIndices</span><span class="p">,</span> <span class="n">values</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Matrices.fromML"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.Matrices.html#pyspark.mllib.linalg.Matrices.fromML">[docs]</a> <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">fromML</span><span class="p">(</span><span class="n">mat</span><span class="p">:</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">Matrix</span><span class="p">)</span> <span class="o">-></span> <span class="n">Matrix</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Convert a matrix from the new mllib-local representation.</span> |
| <span class="sd"> This does NOT copy the data; it copies references.</span> |
| |
| <span class="sd"> .. versionadded:: 2.0.0</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> mat : :py:class:`pyspark.ml.linalg.Matrix`</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> :py:class:`pyspark.mllib.linalg.Matrix`</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">mat</span><span class="p">,</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">DenseMatrix</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">DenseMatrix</span><span class="p">(</span><span class="n">mat</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">isTransposed</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">mat</span><span class="p">,</span> <span class="n">newlinalg</span><span class="o">.</span><span class="n">SparseMatrix</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">SparseMatrix</span><span class="p">(</span> |
| <span class="n">mat</span><span class="o">.</span><span class="n">numRows</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">numCols</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">colPtrs</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">rowIndices</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">values</span><span class="p">,</span> <span class="n">mat</span><span class="o">.</span><span class="n">isTransposed</span> |
| <span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s2">"Unsupported matrix type </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">mat</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="QRDecomposition"><a class="viewcode-back" href="../../../reference/api/pyspark.mllib.linalg.QRDecomposition.html#pyspark.mllib.linalg.QRDecomposition">[docs]</a><span class="k">class</span> <span class="nc">QRDecomposition</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">QT</span><span class="p">,</span> <span class="n">RT</span><span class="p">]):</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Represents QR factors.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">Q</span><span class="p">:</span> <span class="n">QT</span><span class="p">,</span> <span class="n">R</span><span class="p">:</span> <span class="n">RT</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_Q</span> <span class="o">=</span> <span class="n">Q</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_R</span> <span class="o">=</span> <span class="n">R</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">Q</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">QT</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> An orthogonal matrix Q in a QR decomposition.</span> |
| <span class="sd"> May be null if not computed.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_Q</span> |
| |
| <span class="nd">@property</span> |
| <span class="nd">@since</span><span class="p">(</span><span class="s2">"2.0.0"</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">R</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">RT</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> An upper triangular matrix R in a QR decomposition.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_R</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">numpy</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="c1"># Numpy 1.14+ changed it's string format.</span> |
| <span class="n">numpy</span><span class="o">.</span><span class="n">set_printoptions</span><span class="p">(</span><span class="n">legacy</span><span class="o">=</span><span class="s2">"1.13"</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">TypeError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span><span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="n">_test</span><span class="p">()</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <div class="footer-item"> |
| <p class="copyright"> |
| © Copyright .<br> |
| </p> |
| </div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br> |
| </p> |
| </div> |
| |
| </div> |
| </footer> |
| </body> |
| </html> |
