ANL-CEEESA
/
MIPLearn
mirror of https://github.com/ANL-CEEESA/MIPLearn.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Docs: minor fixes

Browse Source
pull/3/head
Alinson S. Xavier 5 years ago
parent c15ec9e2c8
commit 929ff0d9d8
10 changed files with 17 additions and 17 deletions
Show Stats Download Patch File Download Diff File

4
docs/about/index.html
Unescape View File

@ -140,7 +140,7 @@
<li class="first-level active"><a href="#about">About</a></li> <li class="first-level active"><a href="#about">About</a></li>
<li class="second-level"><a href="#authors">Authors</a></li> <li class="second-level"><a href="#authors">Authors</a></li>
<li class="second-level"><a href="#acknowledgements">Acknowledgements</a></li> <li class="second-level"><a href="#acknowledgments">Acknowledgments</a></li>
<li class="second-level"><a href="#references">References</a></li> <li class="second-level"><a href="#references">References</a></li>
@ -156,7 +156,7 @@
<li><strong>Alinson S. Xavier,</strong> Argonne National Laboratory &lt;<a href="&#109;&#97;&#105;&#108;&#116;&#111;&#58;&#97;&#120;&#97;&#118;&#105;&#101;&#114;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;">&#97;&#120;&#97;&#118;&#105;&#101;&#114;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;</a>&gt;</li> <li><strong>Alinson S. Xavier,</strong> Argonne National Laboratory &lt;<a href="&#109;&#97;&#105;&#108;&#116;&#111;&#58;&#97;&#120;&#97;&#118;&#105;&#101;&#114;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;">&#97;&#120;&#97;&#118;&#105;&#101;&#114;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;</a>&gt;</li>
<li><strong>Feng Qiu,</strong> Argonne National Laboratory &lt;<a href="&#109;&#97;&#105;&#108;&#116;&#111;&#58;&#102;&#113;&#105;&#117;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;">&#102;&#113;&#105;&#117;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;</a>&gt;</li> <li><strong>Feng Qiu,</strong> Argonne National Laboratory &lt;<a href="&#109;&#97;&#105;&#108;&#116;&#111;&#58;&#102;&#113;&#105;&#117;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;">&#102;&#113;&#105;&#117;&#64;&#97;&#110;&#108;&#46;&#103;&#111;&#118;</a>&gt;</li>
</ul> </ul>
<h3 id="acknowledgements">Acknowledgements</h3> <h3 id="acknowledgments">Acknowledgments</h3>
<ul> <ul>
<li>Based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357.</li> <li>Based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357.</li>
</ul> </ul>

6
docs/customization/index.html
Unescape View File

@ -142,7 +142,7 @@
<li class="second-level"><a href="#selecting-solver-components">Selecting solver components</a></li> <li class="second-level"><a href="#selecting-solver-components">Selecting solver components</a></li>
<li class="second-level"><a href="#adjusting-component-aggresiveness">Adjusting component aggresiveness</a></li> <li class="second-level"><a href="#adjusting-component-aggressiveness">Adjusting component aggressiveness</a></li>
<li class="second-level"><a href="#evaluating-component-performance">Evaluating component performance</a></li> <li class="second-level"><a href="#evaluating-component-performance">Evaluating component performance</a></li>
@ -189,11 +189,11 @@ solver = LearningSolver()
solver.add(LazyConstraintComponent(...)) solver.add(LazyConstraintComponent(...))
</code></pre> </code></pre>
<h2 id="adjusting-component-aggresiveness">Adjusting component aggresiveness</h2> <h2 id="adjusting-component-aggressiveness">Adjusting component aggressiveness</h2>
<p>The aggressiveness of classification components (such as <code>PrimalSolutionComponent</code> and <code>LazyConstraintComponent</code>) can <p>The aggressiveness of classification components (such as <code>PrimalSolutionComponent</code> and <code>LazyConstraintComponent</code>) can
be adjusted through the <code>threshold</code> constructor argument. Internally, these components ask the ML models how confident be adjusted through the <code>threshold</code> constructor argument. Internally, these components ask the ML models how confident
they are on each prediction (through the <code>predict_proba</code> method in the sklearn API), and only take into account they are on each prediction (through the <code>predict_proba</code> method in the sklearn API), and only take into account
predictions which have probabilities above the threshold. Lowering a component's threshold increases its aggresiveness, predictions which have probabilities above the threshold. Lowering a component's threshold increases its aggressiveness,
while raising a component's threshold makes it more conservative. </p> while raising a component's threshold makes it more conservative. </p>
<p>MIPLearn also includes <code>MinPrecisionThreshold</code>, a dynamic threshold which adjusts itself automatically during training <p>MIPLearn also includes <code>MinPrecisionThreshold</code>, a dynamic threshold which adjusts itself automatically during training
to achieve a minimum desired true positive rate (also known as precision). The example below shows how to initialize to achieve a minimum desired true positive rate (also known as precision). The example below shows how to initialize

8
docs/index.html
Unescape View File

@ -142,7 +142,7 @@
<li class="second-level"><a href="#documentation">Documentation</a></li> <li class="second-level"><a href="#documentation">Documentation</a></li>
<li class="second-level"><a href="#souce-code">Souce Code</a></li> <li class="second-level"><a href="#source-code">Source Code</a></li>
</ul> </ul>
</div></div> </div></div>
@ -172,9 +172,9 @@
<li><a href="benchmark/">Benchmark utilities</a></li> <li><a href="benchmark/">Benchmark utilities</a></li>
<li><a href="problems/">Benchmark problems, challenges and results</a></li> <li><a href="problems/">Benchmark problems, challenges and results</a></li>
<li><a href="customization/">Customizing the solver</a></li> <li><a href="customization/">Customizing the solver</a></li>
<li><a href="about/">License, authors, references and acknowledgements</a></li> <li><a href="about/">License, authors, references and acknowledgments</a></li>
</ul> </ul>
<h3 id="souce-code">Souce Code</h3> <h3 id="source-code">Source Code</h3>
<ul> <ul>
<li><a href="https://github.com/ANL-CEEESA/MIPLearn">https://github.com/ANL-CEEESA/MIPLearn</a></li> <li><a href="https://github.com/ANL-CEEESA/MIPLearn">https://github.com/ANL-CEEESA/MIPLearn</a></li>
</ul></div> </ul></div>
@ -273,5 +273,5 @@
<!-- <!--
MkDocs version : 1.1 MkDocs version : 1.1
Build Date UTC : 2020-05-05 18:38:02 Build Date UTC : 2020-05-05 18:41:02
--> -->

2
docs/search/search_index.json
View File

File diff suppressed because one or more lines are too long

BIN
docs/sitemap.xml.gz
View File

Binary file not shown.

2
docs/usage/index.html
Unescape View File

@ -176,7 +176,7 @@ as follows:</p>
<div class="admonition note"> <div class="admonition note">
<p class="admonition-title">Note</p> <p class="admonition-title">Note</p>
<p>To install MIPLearn in another Python environment, switch to that enviroment before running <code>make install</code>. To install the package in development mode, run <code>make develop</code> instead.</p> <p>To install MIPLearn in another Python environment, switch to that environment before running <code>make install</code>. To install the package in development mode, run <code>make develop</code> instead.</p>
</div> </div>
<h3 id="using-learningsolver">Using <code>LearningSolver</code></h3> <h3 id="using-learningsolver">Using <code>LearningSolver</code></h3>
<p>The main class provided by this package is <code>LearningSolver</code>, a learning-enhanced MIP solver which uses information from previously solved instances to accelerate the solution of new instances. The following example shows its basic usage:</p> <p>The main class provided by this package is <code>LearningSolver</code>, a learning-enhanced MIP solver which uses information from previously solved instances to accelerate the solution of new instances. The following example shows its basic usage:</p>

2
src/docs/about.md
Unescape View File

@ -5,7 +5,7 @@
* **Alinson S. Xavier,** Argonne National Laboratory <<axavier@anl.gov>> * **Alinson S. Xavier,** Argonne National Laboratory <<axavier@anl.gov>>
* **Feng Qiu,** Argonne National Laboratory <<fqiu@anl.gov>> * **Feng Qiu,** Argonne National Laboratory <<fqiu@anl.gov>>
### Acknowledgements ### Acknowledgments
* Based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357. * Based upon work supported by Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science, of the U.S. Department of Energy under Contract No. DE-AC02-06CH11357.

4
src/docs/customization.md
Unescape View File

@ -45,12 +45,12 @@ solver = LearningSolver()
solver.add(LazyConstraintComponent(...)) solver.add(LazyConstraintComponent(...))
``` ```
## Adjusting component aggresiveness ## Adjusting component aggressiveness
The aggressiveness of classification components (such as `PrimalSolutionComponent` and `LazyConstraintComponent`) can The aggressiveness of classification components (such as `PrimalSolutionComponent` and `LazyConstraintComponent`) can
be adjusted through the `threshold` constructor argument. Internally, these components ask the ML models how confident be adjusted through the `threshold` constructor argument. Internally, these components ask the ML models how confident
they are on each prediction (through the `predict_proba` method in the sklearn API), and only take into account they are on each prediction (through the `predict_proba` method in the sklearn API), and only take into account
predictions which have probabilities above the threshold. Lowering a component's threshold increases its aggresiveness, predictions which have probabilities above the threshold. Lowering a component's threshold increases its aggressiveness,
while raising a component's threshold makes it more conservative. while raising a component's threshold makes it more conservative.
MIPLearn also includes `MinPrecisionThreshold`, a dynamic threshold which adjusts itself automatically during training MIPLearn also includes `MinPrecisionThreshold`, a dynamic threshold which adjusts itself automatically during training

4
src/docs/index.md
Unescape View File

@ -20,9 +20,9 @@ The package uses Machine Learning (ML) to automatically identify patterns in pre
* [Benchmark utilities](benchmark.md) * [Benchmark utilities](benchmark.md)
* [Benchmark problems, challenges and results](problems.md) * [Benchmark problems, challenges and results](problems.md)
* [Customizing the solver](customization.md) * [Customizing the solver](customization.md)
* [License, authors, references and acknowledgements](about.md) * [License, authors, references and acknowledgments](about.md)
### Souce Code ### Source Code
* [https://github.com/ANL-CEEESA/MIPLearn](https://github.com/ANL-CEEESA/MIPLearn) * [https://github.com/ANL-CEEESA/MIPLearn](https://github.com/ANL-CEEESA/MIPLearn)

2
src/docs/usage.md
Unescape View File

@ -25,7 +25,7 @@ import miplearn
``` ```
!!! note !!! note
To install MIPLearn in another Python environment, switch to that enviroment before running `make install`. To install the package in development mode, run `make develop` instead. To install MIPLearn in another Python environment, switch to that environment before running `make install`. To install the package in development mode, run `make develop` instead.
### Using `LearningSolver` ### Using `LearningSolver`

Write Preview
Loading…
Cancel
Save