Merge pull request #576 from rhiever/development

0.9 release

.appveyor.yml

@@ -19,9 +19,9 @@ install:
   - conda config --set always_yes yes --set changeps1 no
   - conda update -q conda
   - conda info -a
-  - conda create -q -n test-environment python=%PYTHON_VERSION% numpy scipy scikit-learn nose cython py-xgboost
+  - conda create -q -n test-environment python=%PYTHON_VERSION% numpy scipy scikit-learn nose cython py-xgboost pandas
   - activate test-environment
-  - pip install deap tqdm update_checker pypiwin32
+  - pip install deap tqdm update_checker pypiwin32 stopit
 
 
 test_script:

ci/.travis_install.sh

@@ -33,13 +33,14 @@ conda update --yes conda
 # provided versions
 if [[ "$LATEST" == "true" ]]; then
     conda create -n testenv --yes python=$PYTHON_VERSION pip nose \
-        numpy scipy scikit-learn cython py-xgboost
+        numpy scipy scikit-learn cython py-xgboost pandas
 else
     conda create -n testenv --yes python=$PYTHON_VERSION pip nose \
         numpy=$NUMPY_VERSION scipy=$SCIPY_VERSION \
         scikit-learn=$SKLEARN_VERSION \
 	py-xgboost=$XGBOOST_VERSION \
-	cython
+	cython \
+  pandas
 fi
 
 source activate testenv
@@ -52,6 +53,7 @@ fi
 
 pip install update_checker
 pip install tqdm
+pip install stopit
 
 if [[ "$COVERAGE" == "true" ]]; then
     pip install coverage coveralls
@@ -66,4 +68,6 @@ python -c "import deap; print('deap %s' % deap.__version__)"
 python -c "import xgboost; print('xgboost %s ' % xgboost.__version__)"
 python -c "import update_checker; print('update_checker %s' % update_checker.__version__)"
 python -c "import tqdm; print('tqdm %s' % tqdm.__version__)"
+python -c "import pandas; print('pandas %s' % pandas.__version__)"
+python -c "import stopit; print('stopit %s' % stopit.__version__)"
 python setup.py build_ext --inplace

docs/api/index.html

@@ -101,6 +101,11 @@
     <a class="" href="../support/">Support</a>
 	    </li>
 
+            <li class="toctree-l1">
+
+    <a class="" href="../related/">Related</a>
+	    </li>
+
         </ul>
       </div>
       &nbsp;
@@ -144,7 +149,9 @@ <h1 id="classification">Classification</h1>
                           <strong>subsample</strong>=1.0, <strong>n_jobs</strong>=1,
                           <strong>max_time_mins</strong>=None, <strong>max_eval_time_mins</strong>=5,
                           <strong>random_state</strong>=None, <strong>config_dict</strong>=None,
-                          <strong>warm_start</strong>=False, <strong>verbosity</strong>=0,
+                          <strong>warm_start</strong>=False,
+                          <strong>periodic_checkpoint_folder</strong>=None,
+                          <strong>verbosity</strong>=0,
                           <strong>disable_update_check</strong>=False</em>)</pre>
 
 <div align="right"><a href="https://github.com/rhiever/tpot/blob/master/tpot/base.py">source</a></div>
@@ -266,6 +273,7 @@ <h1 id="classification">Classification</h1>
 <li>Python dictionary, TPOT will use your custom configuration,</li>
 <li>string 'TPOT light', TPOT will use a built-in configuration with only fast models and preprocessors, or</li>
 <li>string 'TPOT MDR', TPOT will use a built-in configuration specialized for genomic studies, or</li>
+<li>string 'TPOT sparse': TPOT will use a configuration dictionary with a one-hot encoder and the operators normally included in TPOT that also support sparse matrices, or</li>
 <li>None, TPOT will use the default TPOTClassifier configuration.</li>
 </ul>
 See the <a href="../using/#built-in-tpot-configurations">built-in configurations</a> section for the list of configurations included with TPOT, and the <a href="../using/#customizing-tpots-operators-and-parameters">custom configuration</a> section for more information and examples of how to create your own TPOT configurations.
@@ -278,6 +286,25 @@ <h1 id="classification">Classification</h1>
 Setting <em>warm_start</em>=True can be useful for running TPOT for a short time on a dataset, checking the results, then resuming the TPOT run from where it left off.
 </blockquote>
 
+<strong>periodic_checkpoint_folder</strong>: path string, optional (default: None)
+<blockquote>
+If supplied, a folder in which TPOT will periodically save the best pipeline so far while optimizing.<br /><br />
+Currently once per generation but not more often than once per 30 seconds.<br /><br />
+Useful in multiple cases:
+<ul>
+<li>Sudden death before TPOT could save optimized pipeline</li>
+<li>Track its progress</li>
+<li>Grab pipelines while it's still optimizing</li>
+</ul>
+</blockquote>
+
+<strong>early_stop</strong>: integer, optional (default: None)
+<blockquote>
+How many generations TPOT checks whether there is no improvement in optimization process.
+<br /><br />
+Ends the optimization process if there is no improvement in the given number of generations.
+</blockquote>
+
 <strong>verbosity</strong>: integer, optional (default=0)
 <blockquote>
 How much information TPOT communicates while it's running.
@@ -555,7 +582,9 @@ <h1 id="regression">Regression</h1>
                          <strong>subsample</strong>=1.0, <strong>n_jobs</strong>=1,
                          <strong>max_time_mins</strong>=None, <strong>max_eval_time_mins</strong>=5,
                          <strong>random_state</strong>=None, <strong>config_dict</strong>=None,
-                         <strong>warm_start</strong>=False, <strong>verbosity</strong>=0,
+                         <strong>warm_start</strong>=False,
+                         <strong>periodic_checkpoint_folder</strong>=None,
+                         <strong>verbosity</strong>=0,
                          <strong>disable_update_check</strong>=False</em>)</pre>
 
 <div align="right"><a href="https://github.com/rhiever/tpot/blob/master/tpot/base.py">source</a></div>
@@ -679,6 +708,7 @@ <h1 id="regression">Regression</h1>
 <li>Python dictionary, TPOT will use your custom configuration,</li>
 <li>string 'TPOT light', TPOT will use a built-in configuration with only fast models and preprocessors, or</li>
 <li>string 'TPOT MDR', TPOT will use a built-in configuration specialized for genomic studies, or</li>
+<li>string 'TPOT sparse': TPOT will use a configuration dictionary with a one-hot encoder and the operators normally included in TPOT that also support sparse matrices, or</li>
 <li>None, TPOT will use the default TPOTRegressor configuration.</li>
 </ul>
 See the <a href="../using/#built-in-tpot-configurations">built-in configurations</a> section for the list of configurations included with TPOT, and the <a href="../using/#customizing-tpots-operators-and-parameters">custom configuration</a> section for more information and examples of how to create your own TPOT configurations.
@@ -691,6 +721,25 @@ <h1 id="regression">Regression</h1>
 Setting <em>warm_start</em>=True can be useful for running TPOT for a short time on a dataset, checking the results, then resuming the TPOT run from where it left off.
 </blockquote>
 
+<strong>periodic_checkpoint_folder</strong>: path string, optional (default: None)
+<blockquote>
+If supplied, a folder in which TPOT will periodically save the best pipeline so far while optimizing.<br /><br />
+Currently once per generation but not more often than once per 30 seconds.<br /><br />
+Useful in multiple cases:
+<ul>
+<li>Sudden death before TPOT could save optimized pipeline</li>
+<li>Track its progress</li>
+<li>Grab pipelines while it's still optimizing</li>
+</ul>
+</blockquote>
+
+<strong>early_stop</strong>: integer, optional (default: None)
+<blockquote>
+How many generations TPOT checks whether there is no improvement in optimization process.
+<br /><br />
+Ends the optimization process if there is no improvement in the given number of generations.
+</blockquote>
+
 <strong>verbosity</strong>: integer, optional (default=0)
 <blockquote>
 How much information TPOT communicates while it's running.

docs/citing/index.html

@@ -95,6 +95,11 @@
     <a class="" href="../support/">Support</a>
 	    </li>
 
+            <li class="toctree-l1">
+
+    <a class="" href="../related/">Related</a>
+	    </li>
+
         </ul>
       </div>
       &nbsp;

docs/contributing/index.html

@@ -110,6 +110,11 @@
     <a class="" href="../support/">Support</a>
 	    </li>
 
+            <li class="toctree-l1">
+
+    <a class="" href="../related/">Related</a>
+	    </li>
+
         </ul>
       </div>
       &nbsp;

docs/examples/index.html

@@ -107,6 +107,11 @@
     <a class="" href="../support/">Support</a>
 	    </li>
 
+            <li class="toctree-l1">
+
+    <a class="" href="../related/">Related</a>
+	    </li>
+
         </ul>
       </div>
       &nbsp;

docs/index.html

@@ -95,6 +95,11 @@
     <a class="" href="support/">Support</a>
 	    </li>
 
+            <li class="toctree-l1">
+
+    <a class="" href="related/">Related</a>
+	    </li>
+
         </ul>
       </div>
       &nbsp;
@@ -205,5 +210,5 @@
 
 <!--
 MkDocs version : 0.16.3
-Build Date UTC : 2017-06-17 14:34:03
+Build Date UTC : 2017-09-27 17:00:29
 -->

docs/installing/index.html

@@ -95,6 +95,11 @@
     <a class="" href="../support/">Support</a>
 	    </li>
 
+            <li class="toctree-l1">
+
+    <a class="" href="../related/">Related</a>
+	    </li>
+
         </ul>
       </div>
       &nbsp;
@@ -150,14 +155,20 @@
 <li>
 <p><a href="https://github.com/tqdm/tqdm">tqdm</a></p>
 </li>
+<li>
+<p><a href="https://github.com/glenfant/stopit">stopit</a></p>
+</li>
+<li>
+<p><a href="http://pandas.pydata.org">pandas</a></p>
+</li>
 </ul>
 <p>Most of the necessary Python packages can be installed via the <a href="https://www.continuum.io/downloads">Anaconda Python distribution</a>, which we strongly recommend that you use. We also strongly recommend that you use of Python 3 over Python 2 if you're given the choice.</p>
-<p>NumPy, SciPy, and scikit-learn can be installed in Anaconda via the command:</p>
-<pre><code class="Shell">conda install numpy scipy scikit-learn
+<p>NumPy, SciPy, scikit-learn and pandas can be installed in Anaconda via the command:</p>
+<pre><code class="Shell">conda install numpy scipy scikit-learn pandas
 </code></pre>
 
-<p>DEAP, update_checker, and tqdm can be installed with <code>pip</code> via the command:</p>
-<pre><code class="Shell">pip install deap update_checker tqdm
+<p>DEAP, update_checker, tqdm and stopit can be installed with <code>pip</code> via the command:</p>
+<pre><code class="Shell">pip install deap update_checker tqdm stopit
 </code></pre>
 
 <p><strong>For the Windows users</strong>, the pywin32 module is required if Python is NOT installed via the <a href="https://www.continuum.io/downloads">Anaconda Python distribution</a> and can be installed with <code>pip</code>:</p>