Files
dima/docs/build/html/_modules/pipelines/data_integration.html

359 lines
44 KiB
HTML

<!DOCTYPE html>
<html class="writer-html5" lang="en" data-content_root="../../">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>pipelines.data_integration &mdash; DIMA 1.0.0 documentation</title>
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=80d5e7a1" />
<link rel="stylesheet" type="text/css" href="../../_static/css/theme.css?v=19f00094" />
<!--[if lt IE 9]>
<script src="../../_static/js/html5shiv.min.js"></script>
<![endif]-->
<script src="../../_static/jquery.js?v=5d32c60e"></script>
<script src="../../_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="../../_static/documentation_options.js?v=8d563738"></script>
<script src="../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></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 src="../../_static/js/theme.js"></script>
<link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../index.html" class="icon icon-home">
DIMA
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" aria-label="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu">
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../modules/src.html">HDF5 data operations</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../modules/src.html#module-src.hdf5_writer">Data integration with HDF5</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../modules/src.html#module-src.hdf5_vis">Data visualization</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../modules/pipelines.html">Pipelines and workflows</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../modules/utils.html">Utilities</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" >
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../index.html">DIMA</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="../index.html">Module code</a></li>
<li class="breadcrumb-item active">pipelines.data_integration</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for pipelines.data_integration</h1><div class="highlight"><pre>
<span></span><span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">thisFilePath</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="vm">__file__</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">NameError</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Error: __file__ is not available. Ensure the script is being run from a file.&quot;</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;[Notice] Path to DIMA package may not be resolved properly.&quot;</span><span class="p">)</span>
<span class="n">thisFilePath</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">getcwd</span><span class="p">()</span> <span class="c1"># Use current directory or specify a default</span>
<span class="n">dimaPath</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">normpath</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">thisFilePath</span><span class="p">,</span> <span class="s2">&quot;..&quot;</span><span class="p">,</span><span class="s1">&#39;..&#39;</span><span class="p">))</span> <span class="c1"># Move up to project root</span>
<span class="k">if</span> <span class="n">dimaPath</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="p">:</span> <span class="c1"># Avoid duplicate entries</span>
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">dimaPath</span><span class="p">)</span>
<span class="kn">import</span> <span class="nn">yaml</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">datetime</span>
<span class="c1"># Importing chain class from itertools </span>
<span class="kn">from</span> <span class="nn">itertools</span> <span class="kn">import</span> <span class="n">chain</span>
<span class="c1"># Import DIMA modules</span>
<span class="kn">import</span> <span class="nn">src.hdf5_writer</span> <span class="k">as</span> <span class="nn">hdf5_lib</span>
<span class="kn">import</span> <span class="nn">utils.g5505_utils</span> <span class="k">as</span> <span class="nn">utils</span>
<span class="kn">from</span> <span class="nn">instruments.readers</span> <span class="kn">import</span> <span class="n">filereader_registry</span>
<span class="n">allowed_file_extensions</span> <span class="o">=</span> <span class="n">filereader_registry</span><span class="o">.</span><span class="n">file_extensions</span>
<span class="k">def</span> <span class="nf">_generate_datetime_dict</span><span class="p">(</span><span class="n">datetime_steps</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot; Generate the datetime augment dictionary from datetime steps. &quot;&quot;&quot;</span>
<span class="n">datetime_augment_dict</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">datetime_step</span> <span class="ow">in</span> <span class="n">datetime_steps</span><span class="p">:</span>
<span class="c1">#tmp = datetime.strptime(datetime_step, &#39;%Y-%m-%d %H-%M-%S&#39;)</span>
<span class="n">datetime_augment_dict</span><span class="p">[</span><span class="n">datetime_step</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">datetime_step</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">),</span> <span class="n">datetime_step</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y_%m_</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">),</span> <span class="n">datetime_step</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y.%m.</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">),</span> <span class="n">datetime_step</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y%m</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="p">]</span>
<span class="k">return</span> <span class="n">datetime_augment_dict</span>
<div class="viewcode-block" id="load_config_and_setup_logging">
<a class="viewcode-back" href="../../modules/pipelines.html#pipelines.data_integration.load_config_and_setup_logging">[docs]</a>
<span class="k">def</span> <span class="nf">load_config_and_setup_logging</span><span class="p">(</span><span class="n">yaml_config_file_path</span><span class="p">,</span> <span class="n">log_dir</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Load YAML configuration file, set up logging, and validate required keys and datetime_steps.&quot;&quot;&quot;</span>
<span class="c1"># Define required keys</span>
<span class="n">required_keys</span> <span class="o">=</span> <span class="p">[</span>
<span class="s1">&#39;experiment&#39;</span><span class="p">,</span> <span class="s1">&#39;contact&#39;</span><span class="p">,</span> <span class="s1">&#39;input_file_directory&#39;</span><span class="p">,</span> <span class="s1">&#39;output_file_directory&#39;</span><span class="p">,</span>
<span class="s1">&#39;instrument_datafolder&#39;</span><span class="p">,</span> <span class="s1">&#39;project&#39;</span><span class="p">,</span> <span class="s1">&#39;actris_level&#39;</span>
<span class="p">]</span>
<span class="c1"># Supported integration modes</span>
<span class="n">supported_integration_modes</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;collection&#39;</span><span class="p">,</span> <span class="s1">&#39;single_experiment&#39;</span><span class="p">]</span>
<span class="c1"># Set up logging</span>
<span class="n">date</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">created_at</span><span class="p">(</span><span class="s2">&quot;%Y_%m&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;:&quot;</span><span class="p">,</span> <span class="s2">&quot;-&quot;</span><span class="p">)</span>
<span class="n">utils</span><span class="o">.</span><span class="n">setup_logging</span><span class="p">(</span><span class="n">log_dir</span><span class="p">,</span> <span class="sa">f</span><span class="s2">&quot;integrate_data_sources_</span><span class="si">{</span><span class="n">date</span><span class="si">}</span><span class="s2">.log&quot;</span><span class="p">)</span>
<span class="c1"># Load YAML configuration file</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">yaml_config_file_path</span><span class="p">,</span> <span class="s1">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">stream</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">config_dict</span> <span class="o">=</span> <span class="n">yaml</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">stream</span><span class="p">,</span> <span class="n">Loader</span><span class="o">=</span><span class="n">yaml</span><span class="o">.</span><span class="n">FullLoader</span><span class="p">)</span>
<span class="k">except</span> <span class="n">yaml</span><span class="o">.</span><span class="n">YAMLError</span> <span class="k">as</span> <span class="n">exc</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">&quot;Error loading YAML file: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">exc</span><span class="p">)</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Failed to load YAML file: </span><span class="si">{</span><span class="n">exc</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="c1"># Check if required keys are present</span>
<span class="n">missing_keys</span> <span class="o">=</span> <span class="p">[</span><span class="n">key</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">required_keys</span> <span class="k">if</span> <span class="n">key</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">]</span>
<span class="k">if</span> <span class="n">missing_keys</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">KeyError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Missing required keys in YAML configuration: </span><span class="si">{</span><span class="n">missing_keys</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="c1"># Validate integration_mode</span>
<span class="n">integration_mode</span> <span class="o">=</span> <span class="n">config_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;integration_mode&#39;</span><span class="p">,</span> <span class="s1">&#39;N/A&#39;</span><span class="p">)</span> <span class="c1"># Default to &#39;collection&#39;</span>
<span class="k">if</span> <span class="n">integration_mode</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">supported_integration_modes</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeWarning</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Unsupported integration_mode &#39;</span><span class="si">{</span><span class="n">integration_mode</span><span class="si">}</span><span class="s2">&#39;. Supported modes are </span><span class="si">{</span><span class="n">supported_integration_modes</span><span class="si">}</span><span class="s2">. Setting &#39;</span><span class="si">{</span><span class="n">integration_mode</span><span class="si">}</span><span class="s2">&#39; to &#39;single_experiment&#39;.&quot;</span>
<span class="p">)</span>
<span class="c1"># Validate datetime_steps format if it exists</span>
<span class="k">if</span> <span class="s1">&#39;datetime_steps&#39;</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">:</span>
<span class="n">datetime_steps</span> <span class="o">=</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;datetime_steps&#39;</span><span class="p">]</span>
<span class="n">expected_format</span> <span class="o">=</span> <span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1"> %H-%M-%S&#39;</span>
<span class="c1"># Check if datetime_steps is a list or a falsy value</span>
<span class="k">if</span> <span class="n">datetime_steps</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">datetime_steps</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;datetime_steps should be a list of strings or a falsy value (None, empty), but got </span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">datetime_steps</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="k">for</span> <span class="n">step_idx</span><span class="p">,</span> <span class="n">step</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">datetime_steps</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="c1"># Attempt to parse the datetime to ensure correct format</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;datetime_steps&#39;</span><span class="p">][</span><span class="n">step_idx</span><span class="p">]</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">step</span><span class="p">,</span> <span class="n">expected_format</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="sa">f</span><span class="s2">&quot;Invalid datetime format for &#39;</span><span class="si">{</span><span class="n">step</span><span class="si">}</span><span class="s2">&#39;. Expected format: </span><span class="si">{</span><span class="n">expected_format</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
<span class="c1"># Augment datatime_steps list as a dictionary. This to speed up single-experiment file generation</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;datetime_steps_dict&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">_generate_datetime_dict</span><span class="p">(</span><span class="n">datetime_steps</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># If datetime_steps is not present, set the integration mode to &#39;collection&#39;</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;datetime_steps missing, setting integration_mode to &#39;collection&#39;.&quot;</span><span class="p">)</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;integration_mode&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;collection&#39;</span>
<span class="c1"># Validate filename_format if defined</span>
<span class="k">if</span> <span class="s1">&#39;filename_format&#39;</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">],</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;&quot;Specified filename_format needs to be of String type&quot; &#39;</span><span class="p">)</span>
<span class="c1"># Split the string and check if each key exists in config_dict</span>
<span class="n">keys</span> <span class="o">=</span> <span class="p">[</span><span class="n">key</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;,&#39;</span><span class="p">)]</span>
<span class="n">missing_keys</span> <span class="o">=</span> <span class="p">[</span><span class="n">key</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">keys</span> <span class="k">if</span> <span class="n">key</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">]</span>
<span class="c1"># If there are any missing keys, raise an assertion error</span>
<span class="c1"># assert not missing_keys, f&#39;Missing key(s) in config_dict: {&quot;, &quot;.join(missing_keys)}&#39;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">missing_keys</span><span class="p">:</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;,&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">keys</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;&quot;filename_format&quot; should contain comma-separated keys that match existing keys in the YAML config file.&#39;</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">&#39;Setting &quot;filename_format&quot; as None&#39;</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
<span class="c1"># Compute complementary metadata elements</span>
<span class="c1"># Create output filename prefix</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">]:</span> <span class="c1"># default behavior</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_prefix&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;_&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">config_dict</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;experiment&#39;</span><span class="p">,</span> <span class="s1">&#39;contact&#39;</span><span class="p">]])</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_prefix&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;_&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">config_dict</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_format&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">sep</span><span class="o">=</span><span class="s1">&#39;,&#39;</span><span class="p">)])</span>
<span class="c1"># Set default dates from datetime_steps if not provided</span>
<span class="n">current_date</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="n">dates</span> <span class="o">=</span> <span class="n">config_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;datetime_steps&#39;</span><span class="p">,[])</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">config_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;dataset_startdate&#39;</span><span class="p">):</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;dataset_startdate&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;datetime_steps&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span> <span class="k">if</span> <span class="n">dates</span> <span class="k">else</span> <span class="n">current_date</span> <span class="c1"># Earliest datetime step</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">config_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;dataset_enddate&#39;</span><span class="p">):</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;dataset_enddate&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;datetime_steps&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span> <span class="k">if</span> <span class="n">dates</span> <span class="k">else</span> <span class="n">current_date</span> <span class="c1"># Latest datetime step</span>
<span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;expected_datetime_format&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1"> %H-%M-%S&#39;</span>
<span class="k">return</span> <span class="n">config_dict</span></div>
<div class="viewcode-block" id="copy_subtree_and_create_hdf5">
<a class="viewcode-back" href="../../modules/pipelines.html#pipelines.data_integration.copy_subtree_and_create_hdf5">[docs]</a>
<span class="k">def</span> <span class="nf">copy_subtree_and_create_hdf5</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">dst</span><span class="p">,</span> <span class="n">select_dir_keywords</span><span class="p">,</span> <span class="n">select_file_keywords</span><span class="p">,</span> <span class="n">allowed_file_extensions</span><span class="p">,</span> <span class="n">root_metadata_dict</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Helper function to copy directory with constraints and create HDF5.&quot;&quot;&quot;</span>
<span class="n">src</span> <span class="o">=</span> <span class="n">src</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">sep</span><span class="p">,</span><span class="s1">&#39;/&#39;</span><span class="p">)</span>
<span class="n">dst</span> <span class="o">=</span> <span class="n">dst</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">sep</span><span class="p">,</span><span class="s1">&#39;/&#39;</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Creating constrained copy of the experimental campaign folder </span><span class="si">%s</span><span class="s2"> at: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">src</span><span class="p">,</span> <span class="n">dst</span><span class="p">)</span>
<span class="n">path_to_files_dict</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">copy_directory_with_contraints</span><span class="p">(</span><span class="n">src</span><span class="p">,</span> <span class="n">dst</span><span class="p">,</span> <span class="n">select_dir_keywords</span><span class="p">,</span> <span class="n">select_file_keywords</span><span class="p">,</span> <span class="n">allowed_file_extensions</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Finished creating a copy of the experimental campaign folder tree at: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">dst</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Creating HDF5 file at: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">dst</span><span class="p">)</span>
<span class="n">hdf5_path</span> <span class="o">=</span> <span class="n">hdf5_lib</span><span class="o">.</span><span class="n">create_hdf5_file_from_filesystem_path</span><span class="p">(</span><span class="n">dst</span><span class="p">,</span> <span class="n">path_to_files_dict</span><span class="p">,</span> <span class="n">select_dir_keywords</span><span class="p">,</span> <span class="n">root_metadata_dict</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Completed creation of HDF5 file </span><span class="si">%s</span><span class="s2"> at: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">hdf5_path</span><span class="p">,</span> <span class="n">dst</span><span class="p">)</span>
<span class="k">return</span> <span class="n">hdf5_path</span></div>
<div class="viewcode-block" id="run_pipeline">
<a class="viewcode-back" href="../../modules/pipelines.html#pipelines.data_integration.run_pipeline">[docs]</a>
<span class="k">def</span> <span class="nf">run_pipeline</span><span class="p">(</span><span class="n">path_to_config_yamlFile</span><span class="p">,</span> <span class="n">log_dir</span><span class="o">=</span><span class="s1">&#39;logs/&#39;</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Integrates data sources specified by the input configuration file into HDF5 files.</span>
<span class="sd"> Parameters:</span>
<span class="sd"> yaml_config_file_path (str): Path to the YAML configuration file.</span>
<span class="sd"> log_dir (str): Directory to save the log file.</span>
<span class="sd"> Returns:</span>
<span class="sd"> list: List of Paths to the created HDF5 file(s).</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">config_dict</span> <span class="o">=</span> <span class="n">load_config_and_setup_logging</span><span class="p">(</span><span class="n">path_to_config_yamlFile</span><span class="p">,</span> <span class="n">log_dir</span><span class="p">)</span>
<span class="n">path_to_input_dir</span> <span class="o">=</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;input_file_directory&#39;</span><span class="p">]</span>
<span class="n">path_to_output_dir</span> <span class="o">=</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;output_file_directory&#39;</span><span class="p">]</span>
<span class="n">select_dir_keywords</span> <span class="o">=</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;instrument_datafolder&#39;</span><span class="p">]</span>
<span class="c1"># Define root folder metadata dictionary</span>
<span class="n">root_metadata_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">key</span> <span class="p">:</span> <span class="n">config_dict</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;project&#39;</span><span class="p">,</span> <span class="s1">&#39;experiment&#39;</span><span class="p">,</span> <span class="s1">&#39;contact&#39;</span><span class="p">,</span> <span class="s1">&#39;actris_level&#39;</span><span class="p">]}</span>
<span class="c1"># Get dataset start and end dates</span>
<span class="n">dataset_startdate</span> <span class="o">=</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;dataset_startdate&#39;</span><span class="p">]</span>
<span class="n">dataset_enddate</span> <span class="o">=</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;dataset_enddate&#39;</span><span class="p">]</span>
<span class="c1"># Determine mode and process accordingly</span>
<span class="n">output_filename_path</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">campaign_name_template</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">filename_prefix</span><span class="p">,</span> <span class="n">suffix</span><span class="p">:</span> <span class="s1">&#39;_&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">filename_prefix</span><span class="p">,</span> <span class="n">suffix</span><span class="p">])</span>
<span class="n">date_str</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="n">dataset_startdate</span><span class="si">}</span><span class="s1">_</span><span class="si">{</span><span class="n">dataset_enddate</span><span class="si">}</span><span class="s1">&#39;</span>
<span class="c1"># Create path to new raw datafolder and standardize with forward slashes</span>
<span class="n">path_to_rawdata_folder</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
<span class="n">path_to_output_dir</span><span class="p">,</span> <span class="s1">&#39;collection_&#39;</span> <span class="o">+</span> <span class="n">campaign_name_template</span><span class="p">(</span><span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_prefix&#39;</span><span class="p">],</span> <span class="n">date_str</span><span class="p">),</span> <span class="s2">&quot;&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">sep</span><span class="p">,</span> <span class="s1">&#39;/&#39;</span><span class="p">)</span>
<span class="c1"># Process individual datetime steps if available, regardless of mode </span>
<span class="k">if</span> <span class="n">config_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;datetime_steps_dict&#39;</span><span class="p">,</span> <span class="p">{}):</span>
<span class="c1"># Single experiment mode</span>
<span class="k">for</span> <span class="n">datetime_step</span><span class="p">,</span> <span class="n">file_keywords</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;datetime_steps_dict&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="n">date_str</span> <span class="o">=</span> <span class="n">datetime_step</span><span class="o">.</span><span class="n">strftime</span><span class="p">(</span><span class="s1">&#39;%Y-%m-</span><span class="si">%d</span><span class="s1">&#39;</span><span class="p">)</span>
<span class="n">single_campaign_name</span> <span class="o">=</span> <span class="n">campaign_name_template</span><span class="p">(</span><span class="n">config_dict</span><span class="p">[</span><span class="s1">&#39;filename_prefix&#39;</span><span class="p">],</span> <span class="n">date_str</span><span class="p">)</span>
<span class="n">path_to_rawdata_subfolder</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">path_to_rawdata_folder</span><span class="p">,</span> <span class="n">single_campaign_name</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">)</span>
<span class="n">path_to_integrated_stepwise_hdf5_file</span> <span class="o">=</span> <span class="n">copy_subtree_and_create_hdf5</span><span class="p">(</span>
<span class="n">path_to_input_dir</span><span class="p">,</span> <span class="n">path_to_rawdata_subfolder</span><span class="p">,</span> <span class="n">select_dir_keywords</span><span class="p">,</span>
<span class="n">file_keywords</span><span class="p">,</span> <span class="n">allowed_file_extensions</span><span class="p">,</span> <span class="n">root_metadata_dict</span><span class="p">)</span>
<span class="n">output_filename_path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path_to_integrated_stepwise_hdf5_file</span><span class="p">)</span>
<span class="c1"># Collection mode processing if specified</span>
<span class="k">if</span> <span class="s1">&#39;collection&#39;</span> <span class="ow">in</span> <span class="n">config_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;integration_mode&#39;</span><span class="p">,</span> <span class="s1">&#39;single_experiment&#39;</span><span class="p">):</span>
<span class="n">path_to_filenames_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">path_to_rawdata_folder</span><span class="p">:</span> <span class="p">[</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">basename</span><span class="p">(</span><span class="n">path</span><span class="p">)</span> <span class="k">for</span> <span class="n">path</span> <span class="ow">in</span> <span class="n">output_filename_path</span><span class="p">]}</span> <span class="k">if</span> <span class="n">output_filename_path</span> <span class="k">else</span> <span class="p">{}</span>
<span class="n">hdf5_path</span> <span class="o">=</span> <span class="n">hdf5_lib</span><span class="o">.</span><span class="n">create_hdf5_file_from_filesystem_path</span><span class="p">(</span><span class="n">path_to_rawdata_folder</span><span class="p">,</span> <span class="n">path_to_filenames_dict</span><span class="p">,</span> <span class="p">[],</span> <span class="n">root_metadata_dict</span><span class="p">)</span>
<span class="n">output_filename_path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">hdf5_path</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">path_to_integrated_stepwise_hdf5_file</span> <span class="o">=</span> <span class="n">copy_subtree_and_create_hdf5</span><span class="p">(</span>
<span class="n">path_to_input_dir</span><span class="p">,</span> <span class="n">path_to_rawdata_folder</span><span class="p">,</span> <span class="n">select_dir_keywords</span><span class="p">,</span> <span class="p">[],</span>
<span class="n">allowed_file_extensions</span><span class="p">,</span> <span class="n">root_metadata_dict</span><span class="p">)</span>
<span class="n">output_filename_path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">path_to_integrated_stepwise_hdf5_file</span><span class="p">)</span>
<span class="k">return</span> <span class="n">output_filename_path</span></div>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o">&lt;</span> <span class="mi">2</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Usage: python data_integration.py &lt;function_name&gt; &lt;function_args&gt;&quot;</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="mi">1</span><span class="p">)</span>
<span class="c1"># Extract the function name from the command line arguments</span>
<span class="n">function_name</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="c1"># Handle function execution based on the provided function name</span>
<span class="k">if</span> <span class="n">function_name</span> <span class="o">==</span> <span class="s1">&#39;run&#39;</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">3</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Usage: python data_integration.py run &lt;path_to_config_yamlFile&gt;&quot;</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="mi">1</span><span class="p">)</span>
<span class="c1"># Extract path to configuration file, specifying the data integration task </span>
<span class="n">path_to_config_yamlFile</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
<span class="n">run_pipeline</span><span class="p">(</span><span class="n">path_to_config_yamlFile</span><span class="p">)</span>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>&#169; Copyright 2024, JFFO.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>