Documentation update

This commit is contained in:
Petrônio Cândido 2019-09-23 23:16:06 -03:00
parent 9efe7ba453
commit aa4598f79f
20 changed files with 97 additions and 35 deletions

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -25,9 +25,9 @@ Fuzzy Time Series (FTS) are non parametric methods for time series forecasting b
2. **Universe of Discourse Partitioning**: This is the most important step. Here, the range of values of the numerical time series *Y(t)* will be splited in overlapped intervals and for each interval will be created a Fuzzy Set. This step is performed by pyFTS.partition module and its classes (for instance GridPartitioner, EntropyPartitioner, etc). The main parameters are:
- the number of intervals
- which fuzzy membership function (on `pyFTS.common.Membership <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/common/Membership.py>`_)
- partition scheme (`GridPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py>`_, `EntropyPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py>`_, `FCMPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py>`_, `CMeansPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/CMeans.py>`_, `HuarngPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py>`_)
- partition scheme (`GridPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py>`_, `EntropyPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py>`_, `FCMPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py>`_, `HuarngPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py>`_)
Check out the jupyter notebook on `notebooks/Partitioners.ipynb <https://github.com/PYFTS/notebooks/Partitioners.ipynb>`_ for sample codes.
Check out the jupyter notebook on `notebooks/Partitioners.ipynb <https://github.com/PYFTS/notebooks/blob/master/Partitioners.ipynb>`_ for sample codes.
3. **Data Fuzzyfication**: Each data point of the numerical time series *Y(t)* will be translated to a fuzzy representation (usually one or more fuzzy sets), and then a fuzzy time series *F(t)* is created.

View File

@ -656,8 +656,6 @@
<li><a href="pyFTS.models.html#pyFTS.models.ifts.IntervalFTS.forecast_ahead_interval">(pyFTS.models.ifts.IntervalFTS method)</a>
</li>
<li><a href="pyFTS.models.html#pyFTS.models.ifts.WeightedIntervalFTS.forecast_ahead_interval">(pyFTS.models.ifts.WeightedIntervalFTS method)</a>
</li>
<li><a href="pyFTS.models.multivariate.html#pyFTS.models.multivariate.cmvfts.ClusteredMVFTS.forecast_ahead_interval">(pyFTS.models.multivariate.cmvfts.ClusteredMVFTS method)</a>
</li>
<li><a href="pyFTS.models.multivariate.html#pyFTS.models.multivariate.mvfts.MVFTS.forecast_ahead_interval">(pyFTS.models.multivariate.mvfts.MVFTS method)</a>
</li>
@ -694,6 +692,8 @@
<li><a href="pyFTS.models.html#pyFTS.models.pwfts.ProbabilisticWeightedFTS.forecast_distribution">(pyFTS.models.pwfts.ProbabilisticWeightedFTS method)</a>
</li>
</ul></li>
<li><a href="pyFTS.models.html#pyFTS.models.pwfts.ProbabilisticWeightedFTS.forecast_distribution_from_distribution">forecast_distribution_from_distribution() (pyFTS.models.pwfts.ProbabilisticWeightedFTS method)</a>
</li>
<li><a href="pyFTS.benchmarks.html#pyFTS.benchmarks.arima.ARIMA.forecast_interval">forecast_interval() (pyFTS.benchmarks.arima.ARIMA method)</a>
<ul>
@ -739,6 +739,8 @@
</li>
</ul></li>
<li><a href="pyFTS.benchmarks.html#pyFTS.benchmarks.Tests.format_experiment_table">format_experiment_table() (in module pyFTS.benchmarks.Tests)</a>
</li>
<li><a href="pyFTS.probabilistic.html#pyFTS.probabilistic.ProbabilityDistribution.from_point">from_point() (in module pyFTS.probabilistic.ProbabilityDistribution)</a>
</li>
<li><a href="pyFTS.common.html#pyFTS.common.fts.FTS">FTS (class in pyFTS.common.fts)</a>
</li>
@ -1346,12 +1348,12 @@
</ul></li>
<li><a href="pyFTS.common.html#pyFTS.common.fts.FTS.merge">merge() (pyFTS.common.fts.FTS method)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="pyFTS.models.seasonal.html#pyFTS.models.seasonal.common.DateTime.minute">minute (pyFTS.models.seasonal.common.DateTime attribute)</a>
</li>
<li><a href="pyFTS.models.seasonal.html#pyFTS.models.seasonal.common.DateTime.minute_of_day">minute_of_day (pyFTS.models.seasonal.common.DateTime attribute)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="pyFTS.models.seasonal.html#pyFTS.models.seasonal.common.DateTime.minute_of_month">minute_of_month (pyFTS.models.seasonal.common.DateTime attribute)</a>
</li>
<li><a href="pyFTS.models.seasonal.html#pyFTS.models.seasonal.common.DateTime.minute_of_week">minute_of_week (pyFTS.models.seasonal.common.DateTime attribute)</a>
@ -1361,10 +1363,18 @@
<li><a href="pyFTS.models.seasonal.html#pyFTS.models.seasonal.common.DateTime.month">month (pyFTS.models.seasonal.common.DateTime attribute)</a>
</li>
<li><a href="pyFTS.models.seasonal.html#pyFTS.models.seasonal.msfts.MultiSeasonalFTS">MultiSeasonalFTS (class in pyFTS.models.seasonal.msfts)</a>
</li>
<li><a href="pyFTS.benchmarks.html#pyFTS.benchmarks.benchmarks.multivariate_sliding_window_benchmarks2">multivariate_sliding_window_benchmarks2() (in module pyFTS.benchmarks.benchmarks)</a>
</li>
<li><a href="pyFTS.models.multivariate.html#pyFTS.models.multivariate.common.MultivariateFuzzySet">MultivariateFuzzySet (class in pyFTS.models.multivariate.common)</a>
</li>
<li><a href="pyFTS.models.multivariate.html#pyFTS.models.multivariate.partitioner.MultivariatePartitioner">MultivariatePartitioner (class in pyFTS.models.multivariate.partitioner)</a>
</li>
<li><a href="pyFTS.benchmarks.html#pyFTS.benchmarks.benchmarks.mv_run_interval2">mv_run_interval2() (in module pyFTS.benchmarks.benchmarks)</a>
</li>
<li><a href="pyFTS.benchmarks.html#pyFTS.benchmarks.benchmarks.mv_run_point2">mv_run_point2() (in module pyFTS.benchmarks.benchmarks)</a>
</li>
<li><a href="pyFTS.benchmarks.html#pyFTS.benchmarks.benchmarks.mv_run_probabilistic2">mv_run_probabilistic2() (in module pyFTS.benchmarks.benchmarks)</a>
</li>
<li><a href="pyFTS.models.multivariate.html#pyFTS.models.multivariate.mvfts.MVFTS">MVFTS (class in pyFTS.models.multivariate.mvfts)</a>
</li>
@ -1471,6 +1481,8 @@
<li><a href="pyFTS.common.html#pyFTS.common.Util.plot_distribution">plot_distribution() (in module pyFTS.common.Util)</a>
</li>
<li><a href="pyFTS.common.html#pyFTS.common.Util.plot_distribution2">plot_distribution2() (in module pyFTS.common.Util)</a>
</li>
<li><a href="pyFTS.common.html#pyFTS.common.Util.plot_distribution_tiled">plot_distribution_tiled() (in module pyFTS.common.Util)</a>
</li>
<li><a href="pyFTS.common.html#pyFTS.common.Util.plot_interval">plot_interval() (in module pyFTS.common.Util)</a>
</li>

Binary file not shown.

View File

@ -202,6 +202,26 @@
<dd><p>Return all FTS methods for probabilistic forecasting</p>
</dd></dl>
<dl class="function">
<dt id="pyFTS.benchmarks.benchmarks.multivariate_sliding_window_benchmarks2">
<code class="descclassname">pyFTS.benchmarks.benchmarks.</code><code class="descname">multivariate_sliding_window_benchmarks2</code><span class="sig-paren">(</span><em>data</em>, <em>windowsize</em>, <em>train=0.8</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.benchmarks.benchmarks.multivariate_sliding_window_benchmarks2" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="function">
<dt id="pyFTS.benchmarks.benchmarks.mv_run_interval2">
<code class="descclassname">pyFTS.benchmarks.benchmarks.</code><code class="descname">mv_run_interval2</code><span class="sig-paren">(</span><em>mfts</em>, <em>train_data</em>, <em>test_data</em>, <em>window_key=None</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.benchmarks.benchmarks.mv_run_interval2" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="function">
<dt id="pyFTS.benchmarks.benchmarks.mv_run_point2">
<code class="descclassname">pyFTS.benchmarks.benchmarks.</code><code class="descname">mv_run_point2</code><span class="sig-paren">(</span><em>mfts</em>, <em>train_data</em>, <em>test_data</em>, <em>window_key=None</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.benchmarks.benchmarks.mv_run_point2" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="function">
<dt id="pyFTS.benchmarks.benchmarks.mv_run_probabilistic2">
<code class="descclassname">pyFTS.benchmarks.benchmarks.</code><code class="descname">mv_run_probabilistic2</code><span class="sig-paren">(</span><em>mfts</em>, <em>train_data</em>, <em>test_data</em>, <em>window_key=None</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.benchmarks.benchmarks.mv_run_probabilistic2" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="function">
<dt id="pyFTS.benchmarks.benchmarks.pftsExploreOrderAndPartitions">
<code class="descclassname">pyFTS.benchmarks.benchmarks.</code><code class="descname">pftsExploreOrderAndPartitions</code><span class="sig-paren">(</span><em>data</em>, <em>save=False</em>, <em>file=None</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.benchmarks.benchmarks.pftsExploreOrderAndPartitions" title="Permalink to this definition"></a></dt>

View File

@ -1253,7 +1253,7 @@ bisect but with a simpler API and support for key functions.</p>
<dl class="function">
<dt id="pyFTS.common.Util.plot_distribution2">
<code class="descclassname">pyFTS.common.Util.</code><code class="descname">plot_distribution2</code><span class="sig-paren">(</span><em>probabilitydist</em>, <em>data</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.common.Util.plot_distribution2" title="Permalink to this definition"></a></dt>
<dd><p>Plot distributions over the time (x-axis)</p>
<dd><p>Plot distributions in y-axis over the time (x-axis)</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
@ -1273,6 +1273,32 @@ bisect but with a simpler API and support for key functions.</p>
</table>
</dd></dl>
<dl class="function">
<dt id="pyFTS.common.Util.plot_distribution_tiled">
<code class="descclassname">pyFTS.common.Util.</code><code class="descname">plot_distribution_tiled</code><span class="sig-paren">(</span><em>distributions, data=None, rows=5, cols=5, index=None, axis=None, size=[10, 20]</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.common.Util.plot_distribution_tiled" title="Permalink to this definition"></a></dt>
<dd><p>Plot one distribution individually in each axis, with probability in y-axis and UoD on x-axis</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>distributions</strong> </li>
<li><strong>data</strong> </li>
<li><strong>rows</strong> </li>
<li><strong>cols</strong> </li>
<li><strong>index</strong> </li>
<li><strong>axis</strong> </li>
<li><strong>size</strong> </li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last"></p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt id="pyFTS.common.Util.plot_interval">
<code class="descclassname">pyFTS.common.Util.</code><code class="descname">plot_interval</code><span class="sig-paren">(</span><em>axis</em>, <em>intervals</em>, <em>order</em>, <em>label</em>, <em>color='red'</em>, <em>typeonlegend=False</em>, <em>ls='-'</em>, <em>linewidth=1</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.common.Util.plot_interval" title="Permalink to this definition"></a></dt>

View File

@ -115,7 +115,7 @@
</div>
<div class="section" id="module-pyFTS.hyperparam.Util">
<span id="pyfts-hyperparam-util-module"></span><h2>pyFTS.hyperparam.Util module<a class="headerlink" href="#module-pyFTS.hyperparam.Util" title="Permalink to this headline"></a></h2>
<p>Common facilities for hyperparameter tunning</p>
<p>Common facilities for hyperparameter optimization</p>
<dl class="function">
<dt id="pyFTS.hyperparam.Util.create_hyperparam_tables">
<code class="descclassname">pyFTS.hyperparam.Util.</code><code class="descname">create_hyperparam_tables</code><span class="sig-paren">(</span><em>conn</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.hyperparam.Util.create_hyperparam_tables" title="Permalink to this definition"></a></dt>

View File

@ -1101,6 +1101,11 @@ US Dollar to Ringgit Malaysia,” Int. J. Comput. Intell. Appl., vol. 12, no. 1,
</table>
</dd></dl>
<dl class="method">
<dt id="pyFTS.models.pwfts.ProbabilisticWeightedFTS.forecast_distribution_from_distribution">
<code class="descname">forecast_distribution_from_distribution</code><span class="sig-paren">(</span><em>previous_dist</em>, <em>smooth</em>, <em>uod</em>, <em>bins</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.models.pwfts.ProbabilisticWeightedFTS.forecast_distribution_from_distribution" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="method">
<dt id="pyFTS.models.pwfts.ProbabilisticWeightedFTS.forecast_interval">
<code class="descname">forecast_interval</code><span class="sig-paren">(</span><em>ndata</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.models.pwfts.ProbabilisticWeightedFTS.forecast_interval" title="Permalink to this definition"></a></dt>

View File

@ -806,28 +806,6 @@ multivariate fuzzy set base.</p>
</table>
</dd></dl>
<dl class="method">
<dt id="pyFTS.models.multivariate.cmvfts.ClusteredMVFTS.forecast_ahead_interval">
<code class="descname">forecast_ahead_interval</code><span class="sig-paren">(</span><em>data</em>, <em>steps</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.models.multivariate.cmvfts.ClusteredMVFTS.forecast_ahead_interval" title="Permalink to this definition"></a></dt>
<dd><p>Interval forecast n steps ahead</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>data</strong> time series data with the minimal length equal to the max_lag of the model</li>
<li><strong>steps</strong> the number of steps ahead to forecast</li>
<li><strong>start_at</strong> in the multi step forecasting, the index of the data where to start forecasting (default: 0)</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">a list with the forecasted intervals</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="method">
<dt id="pyFTS.models.multivariate.cmvfts.ClusteredMVFTS.forecast_ahead_multivariate">
<code class="descname">forecast_ahead_multivariate</code><span class="sig-paren">(</span><em>data</em>, <em>steps</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.models.multivariate.cmvfts.ClusteredMVFTS.forecast_ahead_multivariate" title="Permalink to this definition"></a></dt>

View File

@ -340,6 +340,27 @@ such that Q(tau) = min( {x | F(x) &gt;= tau })</p>
</dd></dl>
<dl class="function">
<dt id="pyFTS.probabilistic.ProbabilityDistribution.from_point">
<code class="descclassname">pyFTS.probabilistic.ProbabilityDistribution.</code><code class="descname">from_point</code><span class="sig-paren">(</span><em>x</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#pyFTS.probabilistic.ProbabilityDistribution.from_point" title="Permalink to this definition"></a></dt>
<dd><p>Create a probability distribution from a scalar value</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>x</strong> scalar value</li>
<li><strong>kwargs</strong> common parameters of the distribution</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first last">the ProbabilityDistribution object</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
<div class="section" id="module-pyFTS.probabilistic.kde">
<span id="pyfts-probabilistic-kde-module"></span><h2>pyFTS.probabilistic.kde module<a class="headerlink" href="#module-pyFTS.probabilistic.kde" title="Permalink to this headline"></a></h2>

View File

@ -124,9 +124,9 @@
<div><ul class="simple">
<li>the number of intervals</li>
<li>which fuzzy membership function (on <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/common/Membership.py">pyFTS.common.Membership</a>)</li>
<li>partition scheme (<a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py">GridPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py">EntropyPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py">FCMPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/CMeans.py">CMeansPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py">HuarngPartitioner</a>)</li>
<li>partition scheme (<a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py">GridPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py">EntropyPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py">FCMPartitioner</a>, <a class="reference external" href="https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py">HuarngPartitioner</a>)</li>
</ul>
<p>Check out the jupyter notebook on <a class="reference external" href="https://github.com/PYFTS/notebooks/Partitioners.ipynb">notebooks/Partitioners.ipynb</a> for sample codes.</p>
<p>Check out the jupyter notebook on <a class="reference external" href="https://github.com/PYFTS/notebooks/blob/master/Partitioners.ipynb">notebooks/Partitioners.ipynb</a> for sample codes.</p>
</div></blockquote>
<ol class="arabic simple" start="3">
<li><strong>Data Fuzzyfication</strong>: Each data point of the numerical time series <em>Y(t)</em> will be translated to a fuzzy representation (usually one or more fuzzy sets), and then a fuzzy time series <em>F(t)</em> is created.</li>

File diff suppressed because one or more lines are too long

View File

@ -25,9 +25,9 @@ Fuzzy Time Series (FTS) are non parametric methods for time series forecasting b
2. **Universe of Discourse Partitioning**: This is the most important step. Here, the range of values of the numerical time series *Y(t)* will be splited in overlapped intervals and for each interval will be created a Fuzzy Set. This step is performed by pyFTS.partition module and its classes (for instance GridPartitioner, EntropyPartitioner, etc). The main parameters are:
- the number of intervals
- which fuzzy membership function (on `pyFTS.common.Membership <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/common/Membership.py>`_)
- partition scheme (`GridPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py>`_, `EntropyPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py>`_, `FCMPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py>`_, `CMeansPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/CMeans.py>`_, `HuarngPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py>`_)
- partition scheme (`GridPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Grid.py>`_, `EntropyPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Entropy.py>`_, `FCMPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/FCM.py>`_, `HuarngPartitioner <https://github.com/PYFTS/pyFTS/blob/master/pyFTS/partitioners/Huarng.py>`_)
Check out the jupyter notebook on `notebooks/Partitioners.ipynb <https://github.com/PYFTS/notebooks/Partitioners.ipynb>`_ for sample codes.
Check out the jupyter notebook on `notebooks/Partitioners.ipynb <https://github.com/PYFTS/notebooks/blob/master/Partitioners.ipynb>`_ for sample codes.
3. **Data Fuzzyfication**: Each data point of the numerical time series *Y(t)* will be translated to a fuzzy representation (usually one or more fuzzy sets), and then a fuzzy time series *F(t)* is created.