Ravin Kohli: Merge pull request #83 from franchuterivera/refactor_dev…

…elopment_docs

refactor_development/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 395ef1b736268e6c59361d91832ecd27
+config: badc6677826ff369d0cd924e63d913f3
 tags: 645f666f9bcd5a90fca523b33c5a78b7

refactor_development/_downloads/08a8d852a0652c3f1a4a72cc129ab783/example_tabular_classification.py

@@ -6,9 +6,16 @@
 The following example shows how to fit a sample classification model
 with AutoPyTorch
 """
+import os
+import tempfile as tmp
 import typing
 import warnings
 
+os.environ['JOBLIB_TEMP_FOLDER'] = tmp.gettempdir()
+os.environ['OMP_NUM_THREADS'] = '1'
+os.environ['OPENBLAS_NUM_THREADS'] = '1'
+os.environ['MKL_NUM_THREADS'] = '1'
+
 warnings.simplefilter(action='ignore', category=UserWarning)
 warnings.simplefilter(action='ignore', category=FutureWarning)
 

refactor_development/_downloads/a39c0378d911b81ecec47ff0a116e6bf/example_image_classification.ipynb

@@ -46,7 +46,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.8.5"
+      "version": "3.8.7"
     }
   },
   "nbformat": 4,

refactor_development/_downloads/c62547d844fd82c936bc377a1da9a504/example_tabular_classification.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import typing\nimport warnings\n\nwarnings.simplefilter(action='ignore', category=UserWarning)\nwarnings.simplefilter(action='ignore', category=FutureWarning)\n\nimport sklearn.datasets\nimport sklearn.model_selection\n\nfrom autoPyTorch.api.tabular_classification import TabularClassificationTask\nfrom autoPyTorch.datasets.tabular_dataset import TabularDataset\nfrom autoPyTorch.utils.hyperparameter_search_space_update import HyperparameterSearchSpaceUpdates\n\n\n# Get the training data for tabular classification\ndef get_data_to_train() -> typing.Tuple[typing.Any, typing.Any, typing.Any, typing.Any]:\n    \"\"\"\n    This function returns a fit dictionary that within itself, contains all\n    the information to fit a pipeline\n    \"\"\"\n\n    # Get the training data for tabular classification\n    # Move to Australian to showcase numerical vs categorical\n    X, y = sklearn.datasets.fetch_openml(data_id=40981, return_X_y=True, as_frame=True)\n    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(\n        X,\n        y,\n        random_state=1,\n    )\n\n    return X_train, X_test, y_train, y_test\n\n\ndef get_search_space_updates():\n    \"\"\"\n    Search space updates to the task can be added using HyperparameterSearchSpaceUpdates\n    Returns:\n        HyperparameterSearchSpaceUpdates\n    \"\"\"\n    updates = HyperparameterSearchSpaceUpdates()\n    updates.append(node_name=\"data_loader\",\n                   hyperparameter=\"batch_size\",\n                   value_range=[16, 512],\n                   default_value=32)\n    updates.append(node_name=\"lr_scheduler\",\n                   hyperparameter=\"CosineAnnealingLR:T_max\",\n                   value_range=[50, 60],\n                   default_value=55)\n    updates.append(node_name='network_backbone',\n                   hyperparameter='ResNetBackbone:dropout',\n                   value_range=[0, 0.5],\n                   default_value=0.2)\n    return updates\n\n\nif __name__ == '__main__':\n    ############################################################################\n    # Data Loading\n    # ============\n    X_train, X_test, y_train, y_test = get_data_to_train()\n    datamanager = TabularDataset(\n        X=X_train, Y=y_train,\n        X_test=X_test, Y_test=y_test)\n\n    ############################################################################\n    # Build and fit a classifier\n    # ==========================\n    api = TabularClassificationTask(\n        delete_tmp_folder_after_terminate=False,\n        search_space_updates=get_search_space_updates()\n    )\n    api.search(\n        dataset=datamanager,\n        optimize_metric='accuracy',\n        total_walltime_limit=500,\n        func_eval_time_limit=150\n    )\n\n    ############################################################################\n    # Print the final ensemble performance\n    # ====================================\n    print(api.run_history, api.trajectory)\n    y_pred = api.predict(X_test)\n    score = api.score(y_pred, y_test)\n    print(score)"
+        "import os\nimport tempfile as tmp\nimport typing\nimport warnings\n\nos.environ['JOBLIB_TEMP_FOLDER'] = tmp.gettempdir()\nos.environ['OMP_NUM_THREADS'] = '1'\nos.environ['OPENBLAS_NUM_THREADS'] = '1'\nos.environ['MKL_NUM_THREADS'] = '1'\n\nwarnings.simplefilter(action='ignore', category=UserWarning)\nwarnings.simplefilter(action='ignore', category=FutureWarning)\n\nimport sklearn.datasets\nimport sklearn.model_selection\n\nfrom autoPyTorch.api.tabular_classification import TabularClassificationTask\nfrom autoPyTorch.datasets.tabular_dataset import TabularDataset\nfrom autoPyTorch.utils.hyperparameter_search_space_update import HyperparameterSearchSpaceUpdates\n\n\n# Get the training data for tabular classification\ndef get_data_to_train() -> typing.Tuple[typing.Any, typing.Any, typing.Any, typing.Any]:\n    \"\"\"\n    This function returns a fit dictionary that within itself, contains all\n    the information to fit a pipeline\n    \"\"\"\n\n    # Get the training data for tabular classification\n    # Move to Australian to showcase numerical vs categorical\n    X, y = sklearn.datasets.fetch_openml(data_id=40981, return_X_y=True, as_frame=True)\n    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(\n        X,\n        y,\n        random_state=1,\n    )\n\n    return X_train, X_test, y_train, y_test\n\n\ndef get_search_space_updates():\n    \"\"\"\n    Search space updates to the task can be added using HyperparameterSearchSpaceUpdates\n    Returns:\n        HyperparameterSearchSpaceUpdates\n    \"\"\"\n    updates = HyperparameterSearchSpaceUpdates()\n    updates.append(node_name=\"data_loader\",\n                   hyperparameter=\"batch_size\",\n                   value_range=[16, 512],\n                   default_value=32)\n    updates.append(node_name=\"lr_scheduler\",\n                   hyperparameter=\"CosineAnnealingLR:T_max\",\n                   value_range=[50, 60],\n                   default_value=55)\n    updates.append(node_name='network_backbone',\n                   hyperparameter='ResNetBackbone:dropout',\n                   value_range=[0, 0.5],\n                   default_value=0.2)\n    return updates\n\n\nif __name__ == '__main__':\n    ############################################################################\n    # Data Loading\n    # ============\n    X_train, X_test, y_train, y_test = get_data_to_train()\n    datamanager = TabularDataset(\n        X=X_train, Y=y_train,\n        X_test=X_test, Y_test=y_test)\n\n    ############################################################################\n    # Build and fit a classifier\n    # ==========================\n    api = TabularClassificationTask(\n        delete_tmp_folder_after_terminate=False,\n        search_space_updates=get_search_space_updates()\n    )\n    api.search(\n        dataset=datamanager,\n        optimize_metric='accuracy',\n        total_walltime_limit=500,\n        func_eval_time_limit=150\n    )\n\n    ############################################################################\n    # Print the final ensemble performance\n    # ====================================\n    print(api.run_history, api.trajectory)\n    y_pred = api.predict(X_test)\n    score = api.score(y_pred, y_test)\n    print(score)"
       ]
     }
   ],
@@ -46,7 +46,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.8.5"
+      "version": "3.8.7"
     }
   },
   "nbformat": 4,

refactor_development/_modules/autoPyTorch/api/base_task.html

@@ -28,7 +28,7 @@
 
   </head><body>
 
-  <a href="https://github.com/automl/auto-sklearn"
+  <a href="https://github.com/automl/Auto-PyTorch"
      class="visible-desktop hidden-xs"><img
     id="gh-banner"
     style="position: absolute; top: 50px; right: 0; border: 0;"
@@ -328,7 +328,7 @@ <h1>Source code for autoPyTorch.api.base_task</h1><div class="highlight"><pre>
 <span class="sd">        then sets them to the current pipeline</span>
 <span class="sd">        configuration.</span>
 <span class="sd">        Args:</span>
-<span class="sd">            **pipeline_config_kwargs: Valid config options include &quot;job_id&quot;,</span>
+<span class="sd">            **pipeline_config_kwargs: Valid config options include &quot;num_run&quot;,</span>
 <span class="sd">            &quot;device&quot;, &quot;budget_type&quot;, &quot;epochs&quot;, &quot;runtime&quot;, &quot;torch_num_threads&quot;,</span>
 <span class="sd">            &quot;early_stopping&quot;, &quot;use_tensorboard_logger&quot;, &quot;use_pynisher&quot;,</span>
 <span class="sd">            &quot;metrics_during_training&quot;</span>
@@ -1035,7 +1035,7 @@ <h1>Source code for autoPyTorch.api.base_task</h1><div class="highlight"><pre>
                                   <span class="s1">&#39;train_indices&#39;</span><span class="p">:</span> <span class="n">dataset</span><span class="o">.</span><span class="n">splits</span><span class="p">[</span><span class="n">split_id</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span>
                                   <span class="s1">&#39;val_indices&#39;</span><span class="p">:</span> <span class="n">dataset</span><span class="o">.</span><span class="n">splits</span><span class="p">[</span><span class="n">split_id</span><span class="p">][</span><span class="mi">1</span><span class="p">],</span>
                                   <span class="s1">&#39;split_id&#39;</span><span class="p">:</span> <span class="n">split_id</span><span class="p">,</span>
-                                  <span class="s1">&#39;job_id&#39;</span><span class="p">:</span> <span class="mi">0</span>
+                                  <span class="s1">&#39;num_run&#39;</span><span class="p">:</span> <span class="mi">0</span>
                                   <span class="p">})</span>
         <span class="n">X</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="p">,</span> <span class="o">**</span><span class="n">budget_config</span><span class="p">})</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">models_</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">models_</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">ensemble_</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
@@ -1108,7 +1108,7 @@ <h1>Source code for autoPyTorch.api.base_task</h1><div class="highlight"><pre>
                                   <span class="s1">&#39;train_indices&#39;</span><span class="p">:</span> <span class="n">dataset</span><span class="o">.</span><span class="n">splits</span><span class="p">[</span><span class="n">split_id</span><span class="p">][</span><span class="mi">0</span><span class="p">],</span>
                                   <span class="s1">&#39;val_indices&#39;</span><span class="p">:</span> <span class="n">dataset</span><span class="o">.</span><span class="n">splits</span><span class="p">[</span><span class="n">split_id</span><span class="p">][</span><span class="mi">1</span><span class="p">],</span>
                                   <span class="s1">&#39;split_id&#39;</span><span class="p">:</span> <span class="n">split_id</span><span class="p">,</span>
-                                  <span class="s1">&#39;job_id&#39;</span><span class="p">:</span> <span class="mi">0</span>
+                                  <span class="s1">&#39;num_run&#39;</span><span class="p">:</span> <span class="mi">0</span>
                                   <span class="p">})</span>
         <span class="n">X</span><span class="o">.</span><span class="n">update</span><span class="p">({</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">pipeline_options</span><span class="p">,</span> <span class="o">**</span><span class="n">budget_config</span><span class="p">})</span>
 

refactor_development/_modules/autoPyTorch/api/tabular_classification.html

@@ -28,7 +28,7 @@
 
   </head><body>
 
-  <a href="https://github.com/automl/auto-sklearn"
+  <a href="https://github.com/automl/Auto-PyTorch"
      class="visible-desktop hidden-xs"><img
     id="gh-banner"
     style="position: absolute; top: 50px; right: 0; border: 0;"

refactor_development/_modules/index.html

@@ -28,7 +28,7 @@
 
   </head><body>
 
-  <a href="https://github.com/automl/auto-sklearn"
+  <a href="https://github.com/automl/Auto-PyTorch"
      class="visible-desktop hidden-xs"><img
     id="gh-banner"
     style="position: absolute; top: 50px; right: 0; border: 0;"