Merge pull request #153 from perib/documentation

Documentation

Tutorial/1_Estimators_Overview.ipynb

@@ -134,7 +134,7 @@
  "X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(X, y, train_size=0.75, test_size=0.25)\n",
  "\n",
  "\n",
- "est = tpot2.TPOTClassifier(n_jobs=40, max_time_seconds=30, verbose=5, generations=1, population_size=5)\n",
+ "est = tpot2.TPOTClassifier(n_jobs=40, max_time_mins=30, verbose=5, generations=1, population_size=5)\n",
  "est.fit(X_train, y_train)\n",
  "\n",
  "\n",
@@ -815,7 +815,7 @@
  "X, y = sklearn.datasets.load_diabetes(return_X_y=True)\n",
  "X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(X, y, train_size=0.75, test_size=0.25)\n",
  "\n",
- "est = tpot2.tpot_estimator.templates.TPOTRegressor(n_jobs=4, max_time_seconds=30, verbose=2, cv=5)\n",
+ "est = tpot2.tpot_estimator.templates.TPOTRegressor(n_jobs=4, max_time_mins=30, verbose=2, cv=5)\n",
  "est.fit(X_train, y_train)\n",
  "\n",
  "print(scorer(est, X_test, y_test))"
@@ -865,7 +865,7 @@
  " X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(X, y, train_size=0.75, test_size=0.25)\n",
  "\n",
  "\n",
- " est = tpot2.TPOTClassifier(n_jobs=4, max_time_seconds=60, verbose=2)\n",
+ " est = tpot2.TPOTClassifier(n_jobs=4, max_time_mins=60, verbose=2)\n",
  " est.fit(X_train, y_train)\n",
  "\n",
  "\n",
@@ -909,10 +909,10 @@
  " generations : int, default=50\n",
  " Number of generations to run\n",
  " \n",
- " max_time_seconds : float, default=float(\"inf\")\n",
+ " max_time_mins : float, default=float(\"inf\")\n",
  " Maximum time to run the optimization. If none or inf, will run until the end of the generations.\n",
  " \n",
- " max_eval_time_seconds : float, default=60*5\n",
+ " max_eval_time_mins : float, default=60*5\n",
  " Maximum time to evaluate a single individual. If none or inf, there will be no time limit per evaluation.\n",
  "\n",
  " n_jobs : int, default=1\n",
@@ -930,7 +930,7 @@
  " 3. best individual\n",
  " 4. warnings\n",
  " >=5. full warnings trace\n",
- " 6. evaluations progress bar. (Temporary: This used to be 2. Currently, using evaluation progress bar may prevent some instances were we terminate a generation early due to it reaching max_time_seconds in the middle of a generation OR a pipeline failed to be terminated normally and we need to manually terminate it.)\n",
+ " 6. evaluations progress bar. (Temporary: This used to be 2. Currently, using evaluation progress bar may prevent some instances were we terminate a generation early due to it reaching max_time_mins in the middle of a generation OR a pipeline failed to be terminated normally and we need to manually terminate it.)\n",
  " \n"
  ]
  },
@@ -995,8 +995,8 @@
  "\n",
  " classification=True,\n",
  "\n",
- " max_eval_time_seconds=15,\n",
- " max_time_seconds=30,\n",
+ " max_eval_time_mins=15,\n",
+ " max_time_mins=30,\n",
  " verbose=2)\n",
  "\n",
  "\n",
@@ -1303,8 +1303,8 @@
  "\n",
  " classification=True,\n",
  "\n",
- " max_eval_time_seconds=15,\n",
- " max_time_seconds=30,\n",
+ " max_eval_time_mins=15,\n",
+ " max_time_mins=30,\n",
  " verbose=2)\n",
  "\n",
  "\n",

Tutorial/2_Search_Spaces.ipynb

@@ -5228,16 +5228,16 @@
  " /* fitted */\n",
  " background-color: var(--sklearn-color-fitted-level-3);\n",
  "}\n",
- "</style><div id=\"sk-container-id-16\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ "</style><div id=\"sk-container-id-16\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=[&#x27;roc_auc&#x27;], scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.graph.GraphPipeline object at 0x716246e21cf0&gt;,\n",
- " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-22\" type=\"checkbox\" checked><label for=\"sk-estimator-id-22\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-22\" type=\"checkbox\" checked><label for=\"sk-estimator-id-22\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=[&#x27;roc_auc&#x27;], scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.graph.GraphPipeline object at 0x716246e21cf0&gt;,\n",
  " verbose=2)</pre></div> </div></div></div></div>"
  ],
  "text/plain": [
- "TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ "TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=['roc_auc'], scorers_weights=[1],\n",
  " search_space=<tpot2.search_spaces.pipelines.graph.GraphPipeline object at 0x716246e21cf0>,\n",
  " verbose=2)"
@@ -5277,7 +5277,7 @@
  " search_space = graph_search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 2,\n",
  ")\n",
  "\n",
@@ -5739,16 +5739,16 @@
  " /* fitted */\n",
  " background-color: var(--sklearn-color-fitted-level-3);\n",
  "}\n",
- "</style><div id=\"sk-container-id-17\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ "</style><div id=\"sk-container-id-17\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=[&#x27;roc_auc&#x27;], scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.graph.GraphPipeline object at 0x716246e21cf0&gt;,\n",
- " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-23\" type=\"checkbox\" checked><label for=\"sk-estimator-id-23\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-23\" type=\"checkbox\" checked><label for=\"sk-estimator-id-23\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=[&#x27;roc_auc&#x27;], scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.graph.GraphPipeline object at 0x716246e21cf0&gt;,\n",
  " verbose=2)</pre></div> </div></div></div></div>"
  ],
  "text/plain": [
- "TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ "TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=['roc_auc'], scorers_weights=[1],\n",
  " search_space=<tpot2.search_spaces.pipelines.graph.GraphPipeline object at 0x716246e21cf0>,\n",
  " verbose=2)"
@@ -6189,16 +6189,16 @@
  " /* fitted */\n",
  " background-color: var(--sklearn-color-fitted-level-3);\n",
  "}\n",
- "</style><div id=\"sk-container-id-18\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ "</style><div id=\"sk-container-id-18\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=[&#x27;roc_auc&#x27;], scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.sequential.SequentialPipeline object at 0x716238dc50f0&gt;,\n",
- " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-24\" type=\"checkbox\" checked><label for=\"sk-estimator-id-24\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ " verbose=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-24\" type=\"checkbox\" checked><label for=\"sk-estimator-id-24\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=[&#x27;roc_auc&#x27;], scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.sequential.SequentialPipeline object at 0x716238dc50f0&gt;,\n",
  " verbose=2)</pre></div> </div></div></div></div>"
  ],
  "text/plain": [
- "TPOTEstimator(classification=True, generations=5, max_eval_time_seconds=300,\n",
+ "TPOTEstimator(classification=True, generations=5, max_eval_time_mins=300,\n",
  " population_size=10, scorers=['roc_auc'], scorers_weights=[1],\n",
  " search_space=<tpot2.search_spaces.pipelines.sequential.SequentialPipeline object at 0x716238dc50f0>,\n",
  " verbose=2)"
@@ -6257,7 +6257,7 @@
  " search_space = search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 2,\n",
  ")\n",
  "\n",

Tutorial/7_dask_parallelization.ipynb

@@ -150,7 +150,7 @@
  " search_space = graph_search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 3,\n",
  " )\n",
  " \n",
@@ -224,7 +224,7 @@
  " search_space = graph_search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 2,\n",
  " n_jobs=10,\n",
  " memory_limit=\"4GB\"\n",
@@ -346,7 +346,7 @@
  " search_space = graph_search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 2,\n",
  ")\n",
  "\n",
@@ -429,7 +429,7 @@
  " search_space = graph_search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 2,\n",
  " )\n",
  " est.fit(X_train, y_train)\n",
@@ -505,7 +505,7 @@
  " search_space = graph_search_space,\n",
  " population_size= 10,\n",
  " generations = 5,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 2,\n",
  " )\n",
  " est.fit(X_train, y_train)\n",

Tutorial/8_SH_and_early_termination.ipynb

@@ -111,7 +111,7 @@
  " cv = 5,\n",
  " search_space = graph_search_space,\n",
  " generations = 50,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 3,\n",
  "\n",
  "\n",

Tutorial/amltk_search_space_parser_example.ipynb

@@ -1285,18 +1285,18 @@
  " /* fitted */\n",
  " background-color: var(--sklearn-color-fitted-level-3);\n",
  "}\n",
- "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=2, max_eval_time_seconds=300,\n",
+ "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTEstimator(classification=True, generations=2, max_eval_time_mins=300,\n",
  " n_jobs=10, population_size=10, scorers=[&#x27;roc_auc&#x27;],\n",
  " scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.sequential.SequentialPipeline object at 0x7d34ec1efbb0&gt;,\n",
- " verbose=5)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-18\" type=\"checkbox\" checked><label for=\"sk-estimator-id-18\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=2, max_eval_time_seconds=300,\n",
+ " verbose=5)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-18\" type=\"checkbox\" checked><label for=\"sk-estimator-id-18\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;TPOTEstimator<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>TPOTEstimator(classification=True, generations=2, max_eval_time_mins=300,\n",
  " n_jobs=10, population_size=10, scorers=[&#x27;roc_auc&#x27;],\n",
  " scorers_weights=[1],\n",
  " search_space=&lt;tpot2.search_spaces.pipelines.sequential.SequentialPipeline object at 0x7d34ec1efbb0&gt;,\n",
  " verbose=5)</pre></div> </div></div></div></div>"
  ],
  "text/plain": [
- "TPOTEstimator(classification=True, generations=2, max_eval_time_seconds=300,\n",
+ "TPOTEstimator(classification=True, generations=2, max_eval_time_mins=300,\n",
  " n_jobs=10, population_size=10, scorers=['roc_auc'],\n",
  " scorers_weights=[1],\n",
  " search_space=<tpot2.search_spaces.pipelines.sequential.SequentialPipeline object at 0x7d34ec1efbb0>,\n",
@@ -1320,7 +1320,7 @@
  " search_space = tpot_search_space, #converted search space goes here\n",
  " population_size= 10,\n",
  " generations = 2,\n",
- " max_eval_time_seconds = 60*5,\n",
+ " max_eval_time_mins = 60*5,\n",
  " verbose = 5,\n",
  " n_jobs=10,\n",
  ")\n",

setup.py

@@ -41,7 +41,6 @@ def calculate_version():
  'traitlets>=5.8.0',
  'lightgbm>=3.3.3',
  'optuna>=3.0.5',
- 'baikal>=0.4.2',
  'networkx>=3.0',
  'dask>=2024.4.2',
  'distributed>=2024.4.2',

tpot2/builtin_modules/__init__.py

@@ -6,4 +6,11 @@
 from .passthrough import Passthrough, SkipTransformer
 from .imputer import ColumnSimpleImputer
 from .estimatortransformer import EstimatorTransformer
-from .passkbinsdiscretizer import PassKBinsDiscretizer
+from .passkbinsdiscretizer import PassKBinsDiscretizer
+
+try:
+ from .nn import PytorchLRClassifier, PytorchMLPClassifier
+except (ModuleNotFoundError, ImportError):
+ pass
+ # import warnings
+ # warnings.warn("Warning: optional dependency `torch` is not available. - skipping import of NN models.")