Merge branch 'development' into reg_cocktails

automl · Dec 10, 2021 · 9238a04 · 9238a04
2 parents 33b2223 + 40a3987
commit 9238a04
Showing 1 changed file with 76 additions and 73 deletions.
diff --git a/examples/40_advanced/example_custom_configuration_space.py b/examples/40_advanced/example_custom_configuration_space.py
@@ -5,6 +5,7 @@
 
 The following example shows how adjust the configuration space of
 the search. Currently, there are two changes that can be made to the space:-
+
 1. Adjust individual hyperparameters in the pipeline
 2. Include or exclude components:
     a) include: Dictionary containing components to include. Key is the node
@@ -66,76 +67,78 @@ def get_search_space_updates():
     return updates
 
 
-if __name__ == '__main__':
-
-    ############################################################################
-    # Data Loading
-    # ============
-    X, y = sklearn.datasets.fetch_openml(data_id=40981, return_X_y=True, as_frame=True)
-    X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
-        X,
-        y,
-        random_state=1,
-    )
-
-    ############################################################################
-    # Build and fit a classifier with include components
-    # ==================================================
-    api = TabularClassificationTask(
-        search_space_updates=get_search_space_updates(),
-        include_components={'network_backbone': ['ResNetBackbone'],
-                            'encoder': ['OneHotEncoder']}
-    )
-
-    ############################################################################
-    # Search for an ensemble of machine learning algorithms
-    # =====================================================
-    api.search(
-        X_train=X_train.copy(),
-        y_train=y_train.copy(),
-        X_test=X_test.copy(),
-        y_test=y_test.copy(),
-        optimize_metric='accuracy',
-        total_walltime_limit=300,
-        func_eval_time_limit_secs=50
-    )
-
-    ############################################################################
-    # Print the final ensemble performance
-    # ====================================
-    print(api.run_history, api.trajectory)
-    y_pred = api.predict(X_test)
-    score = api.score(y_pred, y_test)
-    print(score)
-    print(api.show_models())
-
-    ############################################################################
-    # Build and fit a classifier with exclude components
-    # ==================================================
-    api = TabularClassificationTask(
-        search_space_updates=get_search_space_updates(),
-        exclude_components={'network_backbone': ['MLPBackbone'],
-                            'encoder': ['OneHotEncoder']}
-    )
-
-    ############################################################################
-    # Search for an ensemble of machine learning algorithms
-    # =====================================================
-    api.search(
-        X_train=X_train,
-        y_train=y_train,
-        X_test=X_test.copy(),
-        y_test=y_test.copy(),
-        optimize_metric='accuracy',
-        total_walltime_limit=300,
-        func_eval_time_limit_secs=50
-    )
-
-    ############################################################################
-    # Print the final ensemble performance
-    # ====================================
-    print(api.run_history, api.trajectory)
-    y_pred = api.predict(X_test)
-    score = api.score(y_pred, y_test)
-    print(score)
-    print(api.show_models())
+############################################################################
+# Data Loading
+# ============
+X, y = sklearn.datasets.fetch_openml(data_id=40981, return_X_y=True, as_frame=True)
+X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
+    X,
+    y,
+    random_state=1,
+)
+
+############################################################################
+# Build and fit a classifier with include components
+# ==================================================
+api = TabularClassificationTask(
+    search_space_updates=get_search_space_updates(),
+    include_components={'network_backbone': ['MLPBackbone', 'ResNetBackbone'],
+                        'encoder': ['OneHotEncoder']}
+)
+
+############################################################################
+# Search for an ensemble of machine learning algorithms
+# =====================================================
+api.search(
+    X_train=X_train.copy(),
+    y_train=y_train.copy(),
+    X_test=X_test.copy(),
+    y_test=y_test.copy(),
+    optimize_metric='accuracy',
+    total_walltime_limit=150,
+    func_eval_time_limit_secs=30
+)
+
+############################################################################
+# Print the final ensemble performance
+# ====================================
+y_pred = api.predict(X_test)
+score = api.score(y_pred, y_test)
+print(score)
+print(api.show_models())
+
+# Print statistics from search
+print(api.sprint_statistics())
+
+############################################################################
+# Build and fit a classifier with exclude components
+# ==================================================
+api = TabularClassificationTask(
+    search_space_updates=get_search_space_updates(),
+    exclude_components={'network_backbone': ['MLPBackbone'],
+                        'encoder': ['OneHotEncoder']}
+)
+
+############################################################################
+# Search for an ensemble of machine learning algorithms
+# =====================================================
+api.search(
+    X_train=X_train,
+    y_train=y_train,
+    X_test=X_test.copy(),
+    y_test=y_test.copy(),
+    optimize_metric='accuracy',
+    total_walltime_limit=150,
+    func_eval_time_limit_secs=30
+)
+
+############################################################################
+# Print the final ensemble performance
+# ====================================
+y_pred = api.predict(X_test)
+score = api.score(y_pred, y_test)
+print(score)
+print(api.show_models())
+
+# Print statistics from search
+print(api.sprint_statistics())