<spanid="pyfts-benchmarks-benchmarks-module"></span><h2>pyFTS.benchmarks.benchmarks module<aclass="headerlink"href="#module-pyFTS.benchmarks.benchmarks"title="Permalink to this headline">¶</a></h2>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">SelecaoSimples_MenorRMSE</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">original</span></em>, <emclass="sig-param"><spanclass="n">parameters</span></em>, <emclass="sig-param"><spanclass="n">modelo</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#SelecaoSimples_MenorRMSE"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.SelecaoSimples_MenorRMSE"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">common_process_interval_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">conn</span></em>, <emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">job</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#common_process_interval_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.common_process_interval_jobs"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">common_process_point_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">conn</span></em>, <emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">job</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#common_process_point_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.common_process_point_jobs"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">common_process_probabilistic_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">conn</span></em>, <emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">job</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#common_process_probabilistic_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.common_process_probabilistic_jobs"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">common_process_time_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">conn</span></em>, <emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">job</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#common_process_time_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.common_process_time_jobs"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">compareModelsPlot</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">original</span></em>, <emclass="sig-param"><spanclass="n">models_fo</span></em>, <emclass="sig-param"><spanclass="n">models_ho</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#compareModelsPlot"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.compareModelsPlot"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">compareModelsTable</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">original</span></em>, <emclass="sig-param"><spanclass="n">models_fo</span></em>, <emclass="sig-param"><spanclass="n">models_ho</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#compareModelsTable"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.compareModelsTable"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_benchmark_interval_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_benchmark_interval_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_benchmark_interval_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all non FTS methods for point_to_interval forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_benchmark_point_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_benchmark_point_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_benchmark_point_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all non FTS methods for point forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_benchmark_probabilistic_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_benchmark_probabilistic_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_benchmark_probabilistic_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all FTS methods for probabilistic forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_interval_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_interval_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_interval_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all FTS methods for point_to_interval forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_point_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_point_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_point_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all FTS methods for point forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_point_multivariate_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_point_multivariate_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_point_multivariate_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all multivariate FTS methods por point forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">get_probabilistic_methods</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#get_probabilistic_methods"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.get_probabilistic_methods"title="Permalink to this definition">¶</a></dt>
<dd><p>Return all FTS methods for probabilistic forecasting</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">multivariate_sliding_window_benchmarks2</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">windowsize</span></em>, <emclass="sig-param"><spanclass="n">train</span><spanclass="o">=</span><spanclass="default_value">0.8</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#multivariate_sliding_window_benchmarks2"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.multivariate_sliding_window_benchmarks2"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">pftsExploreOrderAndPartitions</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">save</span><spanclass="o">=</span><spanclass="default_value">False</span></em>, <emclass="sig-param"><spanclass="n">file</span><spanclass="o">=</span><spanclass="default_value">None</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#pftsExploreOrderAndPartitions"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.pftsExploreOrderAndPartitions"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.benchmarks.plotCompared">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">plotCompared</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">original</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em>, <emclass="sig-param"><spanclass="n">labels</span></em>, <emclass="sig-param"><spanclass="n">title</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#plotCompared"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.plotCompared"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">print_distribution_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">original</span></em>, <emclass="sig-param"><spanclass="n">models</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="n">resolution</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#print_distribution_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.print_distribution_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Run probabilistic benchmarks on given models and data and print the results</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>models</strong>– a list of FTS models to benchmark</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">print_interval_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">original</span></em>, <emclass="sig-param"><spanclass="n">models</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#print_interval_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.print_interval_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Run interval benchmarks on given models and data and print the results</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>models</strong>– a list of FTS models to benchmark</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">process_interval_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">job</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#process_interval_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.process_interval_jobs"title="Permalink to this definition">¶</a></dt>
<dd><p>Extract information from an dictionary with interval benchmark results and save it on a database</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>dataset</strong>– the benchmark dataset name</p></li>
<li><p><strong>tag</strong>– alias for the benchmark group being executed</p></li>
<li><p><strong>job</strong>– a dictionary with the benchmark results</p></li>
<li><p><strong>conn</strong>– a connection to a Sqlite database</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">process_interval_jobs2</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">job</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#process_interval_jobs2"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.process_interval_jobs2"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">process_point_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">job</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#process_point_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.process_point_jobs"title="Permalink to this definition">¶</a></dt>
<dd><p>Extract information from a dictionary with point benchmark results and save it on a database</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>dataset</strong>– the benchmark dataset name</p></li>
<li><p><strong>tag</strong>– alias for the benchmark group being executed</p></li>
<li><p><strong>job</strong>– a dictionary with the benchmark results</p></li>
<li><p><strong>conn</strong>– a connection to a Sqlite database</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">process_point_jobs2</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">job</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#process_point_jobs2"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.process_point_jobs2"title="Permalink to this definition">¶</a></dt>
<dd><p>Extract information from a dictionary with point benchmark results and save it on a database</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>dataset</strong>– the benchmark dataset name</p></li>
<li><p><strong>tag</strong>– alias for the benchmark group being executed</p></li>
<li><p><strong>job</strong>– a dictionary with the benchmark results</p></li>
<li><p><strong>conn</strong>– a connection to a Sqlite database</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">process_probabilistic_jobs</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">job</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#process_probabilistic_jobs"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.process_probabilistic_jobs"title="Permalink to this definition">¶</a></dt>
<dd><p>Extract information from an dictionary with probabilistic benchmark results and save it on a database</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>dataset</strong>– the benchmark dataset name</p></li>
<li><p><strong>tag</strong>– alias for the benchmark group being executed</p></li>
<li><p><strong>job</strong>– a dictionary with the benchmark results</p></li>
<li><p><strong>conn</strong>– a connection to a Sqlite database</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">process_probabilistic_jobs2</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">job</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#process_probabilistic_jobs2"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.process_probabilistic_jobs2"title="Permalink to this definition">¶</a></dt>
<dd><p>Extract information from an dictionary with probabilistic benchmark results and save it on a database</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>dataset</strong>– the benchmark dataset name</p></li>
<li><p><strong>tag</strong>– alias for the benchmark group being executed</p></li>
<li><p><strong>job</strong>– a dictionary with the benchmark results</p></li>
<li><p><strong>conn</strong>– a connection to a Sqlite database</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.benchmarks.run_interval">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">run_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">mfts</span></em>, <emclass="sig-param"><spanclass="n">partitioner</span></em>, <emclass="sig-param"><spanclass="n">train_data</span></em>, <emclass="sig-param"><spanclass="n">test_data</span></em>, <emclass="sig-param"><spanclass="n">window_key</span><spanclass="o">=</span><spanclass="default_value">None</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#run_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.run_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Run the interval forecasting benchmarks</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>mfts</strong>– FTS model</p></li>
<li><p><strong>partitioner</strong>– Universe of Discourse partitioner</p></li>
<li><p><strong>train_data</strong>– data used to train the model</p></li>
<li><p><strong>test_data</strong>– ata used to test the model</p></li>
<li><p><strong>window_key</strong>– id of the sliding window</p></li>
<li><p><strong>transformation</strong>– data transformation</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">sliding_window_benchmarks</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">windowsize</span></em>, <emclass="sig-param"><spanclass="n">train</span><spanclass="o">=</span><spanclass="default_value">0.8</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#sliding_window_benchmarks"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.sliding_window_benchmarks"title="Permalink to this definition">¶</a></dt>
<dd><p>Sliding window benchmarks for FTS forecasters.</p>
<p>For each data window, a train and test datasets will be splitted. For each train split, number of
partitions and partitioning method will be created a partitioner model. And for each partitioner, order,
steps ahead and FTS method a foreasting model will be trained.</p>
<p>Then all trained models are benchmarked on the test data and the metrics are stored on a sqlite3 database
(identified by the ‘file’ parameter) for posterior analysis.</p>
<p>All these process can be distributed on a dispy cluster, setting the atributed ‘distributed’ to true and
informing the list of dispy nodes on ‘nodes’ parameter.</p>
<p>The number of experiments is determined by ‘windowsize’ and ‘inc’ parameters.</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>windowsize</strong>– size of sliding window</p></li>
<li><p><strong>train</strong>– percentual of sliding window data used to train the models</p></li>
<li><p><strong>benchmark_methods</strong>– a list with Non FTS models to benchmark. The default is None.</p></li>
<li><p><strong>benchmark_methods_parameters</strong>– a list with Non FTS models parameters. The default is None.</p></li>
<li><p><strong>benchmark_models</strong>– A boolean value indicating if external FTS methods will be used on benchmark. The default is False.</p></li>
<li><p><strong>build_methods</strong>– A boolean value indicating if the default FTS methods will be used on benchmark. The default is True.</p></li>
<li><p><strong>dataset</strong>– the dataset name to identify the current set of benchmarks results on database.</p></li>
<li><p><strong>distributed</strong>– A boolean value indicating if the forecasting procedure will be distributed in a dispy cluster. . The default is False</p></li>
<li><p><strong>file</strong>– file path to save the results. The default is benchmarks.db.</p></li>
<li><p><strong>inc</strong>– a float on interval [0,1] indicating the percentage of the windowsize to move the window</p></li>
<li><p><strong>methods</strong>– a list with FTS class names. The default depends on the forecasting type and contains the list of all FTS methods.</p></li>
<li><p><strong>models</strong>– a list with prebuilt FTS objects. The default is None.</p></li>
<li><p><strong>nodes</strong>– a list with the dispy cluster nodes addresses. The default is [127.0.0.1].</p></li>
<li><p><strong>orders</strong>– a list with orders of the models (for high order models). The default is [1,2,3].</p></li>
<li><p><strong>partitions</strong>– a list with the numbers of partitions on the Universe of Discourse. The default is [10].</p></li>
<li><p><strong>partitioners_models</strong>– a list with prebuilt Universe of Discourse partitioners objects. The default is None.</p></li>
<li><p><strong>partitioners_methods</strong>– a list with Universe of Discourse partitioners class names. The default is [partitioners.Grid.GridPartitioner].</p></li>
<li><p><strong>progress</strong>– If true a progress bar will be displayed during the benchmarks. The default is False.</p></li>
<li><p><strong>start</strong>– in the multi step forecasting, the index of the data where to start forecasting. The default is 0.</p></li>
<li><p><strong>steps_ahead</strong>– a list with the forecasting horizons, i. e., the number of steps ahead to forecast. The default is 1.</p></li>
<li><p><strong>tag</strong>– a name to identify the current set of benchmarks results on database.</p></li>
<li><p><strong>type</strong>– the forecasting type, one of these values: point(default), interval or distribution. The default is point.</p></li>
<li><p><strong>transformations</strong>– a list with data transformations do apply . The default is [None].</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">sliding_window_benchmarks2</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">windowsize</span></em>, <emclass="sig-param"><spanclass="n">train</span><spanclass="o">=</span><spanclass="default_value">0.8</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#sliding_window_benchmarks2"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.sliding_window_benchmarks2"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.benchmarks.</code><codeclass="sig-name descname">train_test_time</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">windowsize</span></em>, <emclass="sig-param"><spanclass="n">train</span><spanclass="o">=</span><spanclass="default_value">0.8</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/benchmarks.html#train_test_time"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.benchmarks.train_test_time"title="Permalink to this definition">¶</a></dt>
<spanid="pyfts-benchmarks-measures-module"></span><h2>pyFTS.benchmarks.Measures module<aclass="headerlink"href="#module-pyFTS.benchmarks.Measures"title="Permalink to this headline">¶</a></h2>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">TheilsInequality</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#TheilsInequality"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.TheilsInequality"title="Permalink to this definition">¶</a></dt>
<dd><p>Theil’s Inequality Coefficient</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>–</p></li>
<li><p><strong>forecasts</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.UStatistic">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">UStatistic</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#UStatistic"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.UStatistic"title="Permalink to this definition">¶</a></dt>
<dd><p>Theil’s U Statistic</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>–</p></li>
<li><p><strong>forecasts</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.acf">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">acf</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">k</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#acf"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.acf"title="Permalink to this definition">¶</a></dt>
<dd><p>Autocorrelation function estimative</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>–</p></li>
<li><p><strong>k</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.brier_score">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">brier_score</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">densities</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#brier_score"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.brier_score"title="Permalink to this definition">¶</a></dt>
<dd><p>Brier Score for probabilistic forecasts.
Brier (1950). “Verification of Forecasts Expressed in Terms of Probability”. Monthly Weather Review. 78: 1–3.</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>– a list with the target values</p></li>
<li><p><strong>densities</strong>– a list with pyFTS.probabil objectsistic.ProbabilityDistribution</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>float</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.coverage">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">coverage</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#coverage"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.coverage"title="Permalink to this definition">¶</a></dt>
<dd><p>Percent of target values that fall inside forecasted interval</p>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.crps">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">crps</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">densities</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#crps"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.crps"title="Permalink to this definition">¶</a></dt>
<dd><p>Continuous Ranked Probability Score</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>– a list with the target values</p></li>
<li><p><strong>densities</strong>– a list with pyFTS.probabil objectsistic.ProbabilityDistribution</p></li>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">get_distribution_ahead_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">distributions</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#get_distribution_ahead_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.get_distribution_ahead_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Get CRPS statistic and time for a forecasting model</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>model</strong>– FTS model with probabilistic forecasting capability</p></li>
<li><p><strong>kwargs</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the CRPS and execution time</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">get_distribution_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">model</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#get_distribution_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.get_distribution_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Get CRPS statistic and time for a forecasting model</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>model</strong>– FTS model with probabilistic forecasting capability</p></li>
<li><p><strong>kwargs</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the CRPS and execution time</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">get_interval_ahead_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">intervals</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#get_interval_ahead_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.get_interval_ahead_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Condensate all measures for point interval forecasters</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>intervals</strong>– predicted intervals for each datapoint</p></li>
<li><p><strong>kwargs</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the sharpness, resolution, coverage, .05 pinball mean,
.25 pinball mean, .75 pinball mean and .95 pinball mean.</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">get_interval_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">model</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#get_interval_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.get_interval_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Condensate all measures for point interval forecasters</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>model</strong>– FTS model with interval forecasting capability</p></li>
<li><p><strong>kwargs</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the sharpness, resolution, coverage, .05 pinball mean,
.25 pinball mean, .75 pinball mean and .95 pinball mean.</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">get_point_ahead_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#get_point_ahead_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.get_point_ahead_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Condensate all measures for point forecasters</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>model</strong>– FTS model with point forecasting capability</p></li>
<li><p><strong>kwargs</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the RMSE, SMAPE and U Statistic</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">get_point_statistics</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">model</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#get_point_statistics"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.get_point_statistics"title="Permalink to this definition">¶</a></dt>
<dd><p>Condensate all measures for point forecasters</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>model</strong>– FTS model with point forecasting capability</p></li>
<li><p><strong>kwargs</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the RMSE, SMAPE and U Statistic</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">logarithm_score</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">densities</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#logarithm_score"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.logarithm_score"title="Permalink to this definition">¶</a></dt>
<dd><p>Logarithm Score for probabilistic forecasts.
Good IJ (1952). “Rational Decisions.”Journal of the Royal Statistical Society B,14(1),107–114. URLhttps://www.jstor.org/stable/2984087.</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>– a list with the target values</p></li>
<li><p><strong>densities</strong>– a list with pyFTS.probabil objectsistic.ProbabilityDistribution</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>float</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.mape">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">mape</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#mape"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.mape"title="Permalink to this definition">¶</a></dt>
<dd><p>Mean Average Percentual Error</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>–</p></li>
<li><p><strong>forecasts</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.mape_interval">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">mape_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#mape_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.mape_interval"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.pinball">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">pinball</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">tau</span></em>, <emclass="sig-param"><spanclass="n">target</span></em>, <emclass="sig-param"><spanclass="n">forecast</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#pinball"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.pinball"title="Permalink to this definition">¶</a></dt>
<dd><p>Pinball loss function. Measure the distance of forecast to the tau-quantile of the target</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>tau</strong>– quantile value in the range (0,1)</p></li>
<li><p><strong>target</strong>–</p></li>
<li><p><strong>forecast</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>float, distance of forecast to the tau-quantile of the target</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.pinball_mean">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">pinball_mean</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">tau</span></em>, <emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#pinball_mean"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.pinball_mean"title="Permalink to this definition">¶</a></dt>
<dd><p>Mean pinball loss value of the forecast for a given tau-quantile of the targets</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>tau</strong>– quantile value in the range (0,1)</p></li>
<li><p><strong>targets</strong>– list of target values</p></li>
<li><p><strong>forecasts</strong>– list of prediction intervals</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>float, the pinball loss mean for tau quantile</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.resolution">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">resolution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#resolution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.resolution"title="Permalink to this definition">¶</a></dt>
<dd><p>Resolution - Standard deviation of the intervals</p>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.rmse">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">rmse</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#rmse"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.rmse"title="Permalink to this definition">¶</a></dt>
<dd><p>Root Mean Squared Error</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>–</p></li>
<li><p><strong>forecasts</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.rmse_interval">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">rmse_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#rmse_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.rmse_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Root Mean Squared Error</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>–</p></li>
<li><p><strong>forecasts</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.sharpness">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">sharpness</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#sharpness"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.sharpness"title="Permalink to this definition">¶</a></dt>
<dd><p>Sharpness - Mean size of the intervals</p>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.smape">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">smape</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em>, <emclass="sig-param"><spanclass="n">type</span><spanclass="o">=</span><spanclass="default_value">2</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#smape"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.smape"title="Permalink to this definition">¶</a></dt>
<dd><p>Symmetric Mean Average Percentual Error</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>targets</strong>–</p></li>
<li><p><strong>forecasts</strong>–</p></li>
<li><p><strong>type</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p></p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.winkler_mean">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">winkler_mean</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">tau</span></em>, <emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#winkler_mean"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.winkler_mean"title="Permalink to this definition">¶</a></dt>
<dd><p>Mean Winkler score value of the forecast for a given tau-quantile of the targets</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>tau</strong>– quantile value in the range (0,1)</p></li>
<li><p><strong>targets</strong>– list of target values</p></li>
<li><p><strong>forecasts</strong>– list of prediction intervals</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>float, the Winkler score mean for tau quantile</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Measures.winkler_score">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Measures.</code><codeclass="sig-name descname">winkler_score</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">tau</span></em>, <emclass="sig-param"><spanclass="n">target</span></em>, <emclass="sig-param"><spanclass="n">forecast</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Measures.html#winkler_score"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Measures.winkler_score"title="Permalink to this definition">¶</a></dt>
<dd><olclass="upperalpha simple"start="18">
<li><olclass="upperalpha simple"start="12">
<li><p>Winkler, A Decision-Theoretic Approach to Interval Estimation, J. Am. Stat. Assoc. 67 (337) (1972) 187–191. doi:10.2307/2284720.</p></li>
<spanid="pyfts-benchmarks-residualanalysis-module"></span><h2>pyFTS.benchmarks.ResidualAnalysis module<aclass="headerlink"href="#module-pyFTS.benchmarks.ResidualAnalysis"title="Permalink to this headline">¶</a></h2>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.ResidualAnalysis.</code><codeclass="sig-name descname">compare_residuals</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">models</span></em>, <emclass="sig-param"><spanclass="n">alpha</span><spanclass="o">=</span><spanclass="default_value">0.05</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/ResidualAnalysis.html#compare_residuals"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.ResidualAnalysis.compare_residuals"title="Permalink to this definition">¶</a></dt>
<dd><p>Compare residual’s statistics of several models</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– test data</p></li>
<li><p><strong>models</strong>–</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a Pandas dataframe with the Box-Ljung statistic for each model</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.ResidualAnalysis.</code><codeclass="sig-name descname">residuals</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">targets</span></em>, <emclass="sig-param"><spanclass="n">forecasts</span></em>, <emclass="sig-param"><spanclass="n">order</span><spanclass="o">=</span><spanclass="default_value">1</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/ResidualAnalysis.html#residuals"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.ResidualAnalysis.residuals"title="Permalink to this definition">¶</a></dt>
<spanid="pyfts-benchmarks-tests-module"></span><h2>pyFTS.benchmarks.Tests module<aclass="headerlink"href="#module-pyFTS.benchmarks.Tests"title="Permalink to this headline">¶</a></h2>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Tests.BoxLjungStatistic">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Tests.</code><codeclass="sig-name descname">BoxLjungStatistic</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">h</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Tests.html#BoxLjungStatistic"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Tests.BoxLjungStatistic"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Tests.</code><codeclass="sig-name descname">BoxPierceStatistic</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">h</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Tests.html#BoxPierceStatistic"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Tests.BoxPierceStatistic"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Tests.</code><codeclass="sig-name descname">format_experiment_table</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">df</span></em>, <emclass="sig-param"><spanclass="n">exclude</span><spanclass="o">=</span><spanclass="default_value">[]</span></em>, <emclass="sig-param"><spanclass="n">replace</span><spanclass="o">=</span><spanclass="default_value">{}</span></em>, <emclass="sig-param"><spanclass="n">csv</span><spanclass="o">=</span><spanclass="default_value">True</span></em>, <emclass="sig-param"><spanclass="n">std</span><spanclass="o">=</span><spanclass="default_value">False</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Tests.html#format_experiment_table"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Tests.format_experiment_table"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Tests.post_hoc_tests">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Tests.</code><codeclass="sig-name descname">post_hoc_tests</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">post_hoc</span></em>, <emclass="sig-param"><spanclass="n">control_method</span></em>, <emclass="sig-param"><spanclass="n">alpha</span><spanclass="o">=</span><spanclass="default_value">0.05</span></em>, <emclass="sig-param"><spanclass="n">method</span><spanclass="o">=</span><spanclass="default_value">'finner'</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Tests.html#post_hoc_tests"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Tests.post_hoc_tests"title="Permalink to this definition">¶</a></dt>
<dd><p>Finner paired post-hoc test with NSFTS as control method.</p>
<p>$H_0$: There is no significant difference between the means</p>
<p>$H_1$: There is a significant difference between the means</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Tests.</code><codeclass="sig-name descname">test_mean_equality</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">tests</span></em>, <emclass="sig-param"><spanclass="n">alpha</span><spanclass="o">=</span><spanclass="default_value">0.05</span></em>, <emclass="sig-param"><spanclass="n">method</span><spanclass="o">=</span><spanclass="default_value">'friedman'</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Tests.html#test_mean_equality"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Tests.test_mean_equality"title="Permalink to this definition">¶</a></dt>
<dd><p>Test for the equality of the means, with alpha confidence level.</p>
<p>H_0: There’s no significant difference between the means
H_1: There is at least one significant difference between the means</p>
<spanid="pyfts-benchmarks-util-module"></span><h2>pyFTS.benchmarks.Util module<aclass="headerlink"href="#module-pyFTS.benchmarks.Util"title="Permalink to this headline">¶</a></h2>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">analytic_tabular_dataframe</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataframe</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#analytic_tabular_dataframe"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.analytic_tabular_dataframe"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">analytical_data_columns</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">experiments</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#analytical_data_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.analytical_data_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">base_dataframe_columns</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#base_dataframe_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.base_dataframe_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">cast_dataframe_to_synthetic</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">infile</span></em>, <emclass="sig-param"><spanclass="n">outfile</span></em>, <emclass="sig-param"><spanclass="n">experiments</span></em>, <emclass="sig-param"><spanclass="n">type</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#cast_dataframe_to_synthetic"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.cast_dataframe_to_synthetic"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">cast_dataframe_to_synthetic_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">df</span></em>, <emclass="sig-param"><spanclass="n">data_columns</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#cast_dataframe_to_synthetic_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.cast_dataframe_to_synthetic_interval"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">cast_dataframe_to_synthetic_point</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">df</span></em>, <emclass="sig-param"><spanclass="n">data_columns</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#cast_dataframe_to_synthetic_point"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.cast_dataframe_to_synthetic_point"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">cast_dataframe_to_synthetic_probabilistic</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">df</span></em>, <emclass="sig-param"><spanclass="n">data_columns</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#cast_dataframe_to_synthetic_probabilistic"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.cast_dataframe_to_synthetic_probabilistic"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.check_ignore_list">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">check_ignore_list</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">b</span></em>, <emclass="sig-param"><spanclass="n">ignore</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#check_ignore_list"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.check_ignore_list"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.check_replace_list">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">check_replace_list</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">m</span></em>, <emclass="sig-param"><spanclass="n">replace</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#check_replace_list"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.check_replace_list"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">create_benchmark_tables</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#create_benchmark_tables"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.create_benchmark_tables"title="Permalink to this definition">¶</a></dt>
<dd><p>Create a sqlite3 table designed to store benchmark results.</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><p><strong>conn</strong>– a sqlite3 database connection</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.extract_measure">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">extract_measure</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataframe</span></em>, <emclass="sig-param"><spanclass="n">measure</span></em>, <emclass="sig-param"><spanclass="n">data_columns</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#extract_measure"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.extract_measure"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.find_best">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">find_best</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataframe</span></em>, <emclass="sig-param"><spanclass="n">criteria</span></em>, <emclass="sig-param"><spanclass="n">ascending</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#find_best"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.find_best"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">get_dataframe_from_bd</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">file</span></em>, <emclass="sig-param"><spanclass="n">filter</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#get_dataframe_from_bd"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.get_dataframe_from_bd"title="Permalink to this definition">¶</a></dt>
<dd><p>Query the sqlite benchmark database and return a pandas dataframe with the results</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>file</strong>– the url of the benchmark database</p></li>
<li><p><strong>filter</strong>– sql conditions to filter</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>pandas dataframe with the query results</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.insert_benchmark">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">insert_benchmark</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">conn</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#insert_benchmark"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.insert_benchmark"title="Permalink to this definition">¶</a></dt>
<dd><p>Insert benchmark data on database</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><p><strong>data</strong>– a tuple with the benchmark data with format:</p>
</dd>
</dl>
<p>ID: integer incremental primary key
Date: Date/hour of benchmark execution
Dataset: Identify on which dataset the dataset was performed
Tag: a user defined word that indentify a benchmark set
Type: forecasting type (point, interval, distribution)
Model: FTS model
Transformation: The name of data transformation, if one was used
Order: the order of the FTS method
Scheme: UoD partitioning scheme
Partitions: Number of partitions
Size: Number of rules of the FTS model
Steps: prediction horizon, i. e., the number of steps ahead
Measure: accuracy measure
Value: the measure value</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><p><strong>conn</strong>– a sqlite3 database connection</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">interval_dataframe_analytic_columns</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">experiments</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#interval_dataframe_analytic_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.interval_dataframe_analytic_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">interval_dataframe_synthetic_columns</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#interval_dataframe_synthetic_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.interval_dataframe_synthetic_columns"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.open_benchmark_db">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">open_benchmark_db</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">name</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#open_benchmark_db"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.open_benchmark_db"title="Permalink to this definition">¶</a></dt>
<dd><p>Open a connection with a Sqlite database designed to store benchmark results.</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">point_dataframe_analytic_columns</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">experiments</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#point_dataframe_analytic_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.point_dataframe_analytic_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">point_dataframe_synthetic_columns</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#point_dataframe_synthetic_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.point_dataframe_synthetic_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">probabilistic_dataframe_analytic_columns</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">experiments</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#probabilistic_dataframe_analytic_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.probabilistic_dataframe_analytic_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">probabilistic_dataframe_synthetic_columns</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#probabilistic_dataframe_synthetic_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.probabilistic_dataframe_synthetic_columns"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">process_common_data</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">type</span></em>, <emclass="sig-param"><spanclass="n">job</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#process_common_data"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.process_common_data"title="Permalink to this definition">¶</a></dt>
<dd><p>Wraps benchmark information on a tuple for sqlite database</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">process_common_data2</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">dataset</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">type</span></em>, <emclass="sig-param"><spanclass="n">job</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#process_common_data2"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.process_common_data2"title="Permalink to this definition">¶</a></dt>
<dd><p>Wraps benchmark information on a tuple for sqlite database</p>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">save_dataframe_probabilistic</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">experiments</span></em>, <emclass="sig-param"><spanclass="n">file</span></em>, <emclass="sig-param"><spanclass="n">objs</span></em>, <emclass="sig-param"><spanclass="n">crps</span></em>, <emclass="sig-param"><spanclass="n">times</span></em>, <emclass="sig-param"><spanclass="n">save</span></em>, <emclass="sig-param"><spanclass="n">synthetic</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="n">method</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#save_dataframe_probabilistic"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.save_dataframe_probabilistic"title="Permalink to this definition">¶</a></dt>
<dd><p>Save benchmark results for m-step ahead probabilistic forecasters
:param experiments:
:param file:
:param objs:
:param crps_interval:
:param crps_distr:
:param times:
:param times2:
:param save:
:param synthetic:
:return:</p>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.scale">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">scale</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">params</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#scale"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.scale"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.scale_params">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">scale_params</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#scale_params"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.scale_params"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">simple_synthetic_dataframe</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">file</span></em>, <emclass="sig-param"><spanclass="n">tag</span></em>, <emclass="sig-param"><spanclass="n">measure</span></em>, <emclass="sig-param"><spanclass="n">sql</span><spanclass="o">=</span><spanclass="default_value">None</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#simple_synthetic_dataframe"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.simple_synthetic_dataframe"title="Permalink to this definition">¶</a></dt>
<dd><p>Read experiments results from sqlite3 database in ‘file’, make a synthesis of the results
of the metric ‘measure’ with the same ‘tag’, returning a Pandas DataFrame with the mean results.</p>
<li><p><strong>tag</strong>– common tag of the experiments</p></li>
<li><p><strong>measure</strong>– metric to synthetize</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>Pandas DataFrame with the mean results</p>
</dd>
</dl>
</dd></dl>
<dlclass="py function">
<dtid="pyFTS.benchmarks.Util.stats">
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">stats</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">measure</span></em>, <emclass="sig-param"><spanclass="n">data</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#stats"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.stats"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-prename descclassname">pyFTS.benchmarks.Util.</code><codeclass="sig-name descname">tabular_dataframe_columns</code><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/Util.html#tabular_dataframe_columns"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.Util.tabular_dataframe_columns"title="Permalink to this definition">¶</a></dt>
<spanid="pyfts-benchmarks-arima-module"></span><h2>pyFTS.benchmarks.arima module<aclass="headerlink"href="#module-pyFTS.benchmarks.arima"title="Permalink to this headline">¶</a></h2>
<dlclass="py class">
<dtid="pyFTS.benchmarks.arima.ARIMA">
<emclass="property">class </em><codeclass="sig-prename descclassname">pyFTS.benchmarks.arima.</code><codeclass="sig-name descname">ARIMA</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">ar</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.ar"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.ar"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py method">
<dtid="pyFTS.benchmarks.arima.ARIMA.forecast">
<codeclass="sig-name descname">forecast</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.forecast"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.forecast"title="Permalink to this definition">¶</a></dt>
<dd><p>Point forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted values</p>
<codeclass="sig-name descname">forecast_ahead_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.forecast_ahead_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.forecast_ahead_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_ahead_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.forecast_ahead_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.forecast_ahead_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted intervals</p>
<codeclass="sig-name descname">forecast_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.forecast_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.forecast_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with probabilistic.ProbabilityDistribution objects representing the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.forecast_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.forecast_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the prediction intervals</p>
</dd>
</dl>
</dd></dl>
<dlclass="py method">
<dtid="pyFTS.benchmarks.arima.ARIMA.ma">
<codeclass="sig-name descname">ma</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.ma"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.ma"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py method">
<dtid="pyFTS.benchmarks.arima.ARIMA.train">
<codeclass="sig-name descname">train</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/arima.html#ARIMA.train"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.arima.ARIMA.train"title="Permalink to this definition">¶</a></dt>
<dd><p>Method specific parameter fitting</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– training time series data</p></li>
<li><p><strong>kwargs</strong>– Method specific parameters</p></li>
<spanid="pyfts-benchmarks-knn-module"></span><h2>pyFTS.benchmarks.knn module<aclass="headerlink"href="#module-pyFTS.benchmarks.knn"title="Permalink to this headline">¶</a></h2>
<dlclass="py class">
<dtid="pyFTS.benchmarks.knn.KNearestNeighbors">
<emclass="property">class </em><codeclass="sig-prename descclassname">pyFTS.benchmarks.knn.</code><codeclass="sig-name descname">KNearestNeighbors</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">forecast</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.forecast"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.forecast"title="Permalink to this definition">¶</a></dt>
<dd><p>Point forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted values</p>
<codeclass="sig-name descname">forecast_ahead_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.forecast_ahead_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.forecast_ahead_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_ahead_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.forecast_ahead_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.forecast_ahead_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted intervals</p>
<codeclass="sig-name descname">forecast_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.forecast_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.forecast_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with probabilistic.ProbabilityDistribution objects representing the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.forecast_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.forecast_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the prediction intervals</p>
<codeclass="sig-name descname">knn</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">sample</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.knn"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.knn"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">train</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/knn.html#KNearestNeighbors.train"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.knn.KNearestNeighbors.train"title="Permalink to this definition">¶</a></dt>
<dd><p>Method specific parameter fitting</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– training time series data</p></li>
<li><p><strong>kwargs</strong>– Method specific parameters</p></li>
<spanid="pyfts-benchmarks-naive-module"></span><h2>pyFTS.benchmarks.naive module<aclass="headerlink"href="#module-pyFTS.benchmarks.naive"title="Permalink to this headline">¶</a></h2>
<dlclass="py class">
<dtid="pyFTS.benchmarks.naive.Naive">
<emclass="property">class </em><codeclass="sig-prename descclassname">pyFTS.benchmarks.naive.</code><codeclass="sig-name descname">Naive</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/naive.html#Naive"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.naive.Naive"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">forecast</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/naive.html#Naive.forecast"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.naive.Naive.forecast"title="Permalink to this definition">¶</a></dt>
<dd><p>Point forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted values</p>
<spanid="pyfts-benchmarks-quantreg-module"></span><h2>pyFTS.benchmarks.quantreg module<aclass="headerlink"href="#module-pyFTS.benchmarks.quantreg"title="Permalink to this headline">¶</a></h2>
<emclass="property">class </em><codeclass="sig-prename descclassname">pyFTS.benchmarks.quantreg.</code><codeclass="sig-name descname">QuantileRegression</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">forecast</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.forecast"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.forecast"title="Permalink to this definition">¶</a></dt>
<dd><p>Point forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted values</p>
<codeclass="sig-name descname">forecast_ahead_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.forecast_ahead_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.forecast_ahead_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_ahead_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.forecast_ahead_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.forecast_ahead_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted intervals</p>
<codeclass="sig-name descname">forecast_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.forecast_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.forecast_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with probabilistic.ProbabilityDistribution objects representing the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.forecast_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.forecast_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the prediction intervals</p>
<codeclass="sig-name descname">interval_to_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">lo_params</span></em>, <emclass="sig-param"><spanclass="n">up_params</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.interval_to_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.interval_to_interval"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">linearmodel</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">params</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.linearmodel"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.linearmodel"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">point_to_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">lo_params</span></em>, <emclass="sig-param"><spanclass="n">up_params</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.point_to_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.point_to_interval"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">train</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/quantreg.html#QuantileRegression.train"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.quantreg.QuantileRegression.train"title="Permalink to this definition">¶</a></dt>
<dd><p>Method specific parameter fitting</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– training time series data</p></li>
<li><p><strong>kwargs</strong>– Method specific parameters</p></li>
<spanid="pyfts-benchmarks-bsts-module"></span><h2>pyFTS.benchmarks.BSTS module<aclass="headerlink"href="#module-pyFTS.benchmarks.BSTS"title="Permalink to this headline">¶</a></h2>
<dlclass="py class">
<dtid="pyFTS.benchmarks.BSTS.ARIMA">
<emclass="property">class </em><codeclass="sig-prename descclassname">pyFTS.benchmarks.BSTS.</code><codeclass="sig-name descname">ARIMA</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA"title="Permalink to this definition">¶</a></dt>
<codeclass="sig-name descname">forecast</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.forecast"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.forecast"title="Permalink to this definition">¶</a></dt>
<dd><p>Point forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted values</p>
<codeclass="sig-name descname">forecast_ahead</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.forecast_ahead"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.forecast_ahead"title="Permalink to this definition">¶</a></dt>
<dd><p>Point forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast (default: 1)</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted values</p>
<codeclass="sig-name descname">forecast_ahead_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.forecast_ahead_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.forecast_ahead_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_ahead_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">ndata</span></em>, <emclass="sig-param"><spanclass="n">steps</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.forecast_ahead_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.forecast_ahead_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast from 1 to H steps ahead, where H is given by the steps parameter</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>steps</strong>– the number of steps ahead to forecast</p></li>
<li><p><strong>start_at</strong>– in the multi step forecasting, the index of the data where to start forecasting (default: 0)</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the forecasted intervals</p>
<codeclass="sig-name descname">forecast_distribution</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.forecast_distribution"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.forecast_distribution"title="Permalink to this definition">¶</a></dt>
<dd><p>Probabilistic forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with probabilistic.ProbabilityDistribution objects representing the forecasted Probability Distributions</p>
<codeclass="sig-name descname">forecast_interval</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.forecast_interval"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.forecast_interval"title="Permalink to this definition">¶</a></dt>
<dd><p>Interval forecast one step ahead</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– time series data with the minimal length equal to the max_lag of the model</p></li>
<li><p><strong>kwargs</strong>– model specific parameters</p></li>
</ul>
</dd>
<dtclass="field-even">Returns</dt>
<ddclass="field-even"><p>a list with the prediction intervals</p>
</dd>
</dl>
</dd></dl>
<dlclass="py method">
<dtid="pyFTS.benchmarks.BSTS.ARIMA.inference">
<codeclass="sig-name descname">inference</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">steps</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.inference"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.inference"title="Permalink to this definition">¶</a></dt>
<dd></dd></dl>
<dlclass="py method">
<dtid="pyFTS.benchmarks.BSTS.ARIMA.train">
<codeclass="sig-name descname">train</code><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n">data</span></em>, <emclass="sig-param"><spanclass="o">**</span><spanclass="n">kwargs</span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/pyFTS/benchmarks/BSTS.html#ARIMA.train"><spanclass="viewcode-link">[source]</span></a><aclass="headerlink"href="#pyFTS.benchmarks.BSTS.ARIMA.train"title="Permalink to this definition">¶</a></dt>
<dd><p>Method specific parameter fitting</p>
<dlclass="field-list simple">
<dtclass="field-odd">Parameters</dt>
<ddclass="field-odd"><ulclass="simple">
<li><p><strong>data</strong>– training time series data</p></li>
<li><p><strong>kwargs</strong>– Method specific parameters</p></li>
