Adding warnings to all examples switching to a test server (#1061)

* Adding warnings to all examples switching to a test server

* Creating warnings in new text cells

* Fixing a bug

* Debugging doc build failures

* Update openml/config.py

Co-authored-by: Matthias Feurer <feurerm@informatik.uni-freiburg.de>

* Fixing GUI commit bug

* Using a common warning message for docs

* Renaming warning message file

* Editing the non-edited file

Co-authored-by: Matthias Feurer <feurerm@informatik.uni-freiburg.de>

Author: Neeratyoy

doc/test_server_usage_warning.txt

@@ -0,0 +1,3 @@
+This example uploads data. For that reason, this example connects to the test server at test.openml.org.
+This prevents the main server from crowding with example datasets, tasks, runs, and so on.
+The use of this test server can affect behaviour and performance of the OpenML-Python API.

examples/20_basic/introduction_tutorial.py

@@ -53,10 +53,7 @@
 #
 # Alternatively, by running the code below and replacing 'YOURKEY' with your API key,
 # you authenticate for the duration of the python process.
-#
-# .. warning:: This example uploads data. For that reason, this example
-#   connects to the test server instead. This prevents the live server from
-#   crowding with example datasets, tasks, studies, and so on.
+
 
 ############################################################################
 
@@ -65,6 +62,9 @@
 import openml
 from sklearn import neighbors
 
+############################################################################
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
 openml.config.start_using_configuration_for_example()
 
 ############################################################################

examples/20_basic/simple_flows_and_runs_tutorial.py

@@ -10,15 +10,15 @@
 import openml
 from sklearn import ensemble, neighbors
 
+
+############################################################################
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
+openml.config.start_using_configuration_for_example()
+
 ############################################################################
 # Train a machine learning model
 # ==============================
-#
-# .. warning:: This example uploads data. For that reason, this example
-#   connects to the test server at test.openml.org. This prevents the main
-#   server from crowding with example datasets, tasks, runs, and so on.
-
-openml.config.start_using_configuration_for_example()
 
 # NOTE: We are using dataset 20 from the test server: https://test.openml.org/d/20
 dataset = openml.datasets.get_dataset(20)

examples/30_extended/create_upload_tutorial.py

@@ -16,9 +16,8 @@
 from openml.datasets.functions import create_dataset
 
 ############################################################################
-# .. warning:: This example uploads data. For that reason, this example
-#   connects to the test server at test.openml.org. This prevents the main
-#   server from crowding with example datasets, tasks, runs, and so on.
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
 
 openml.config.start_using_configuration_for_example()
 ############################################################################

examples/30_extended/custom_flow_.py

@@ -13,19 +13,18 @@
 and also show how to link runs to the custom flow.
 """
 
-####################################################################################################
-
 # License: BSD 3-Clause
-# .. warning:: This example uploads data. For that reason, this example
-#   connects to the test server at test.openml.org. This prevents the main
-#   server from crowding with example datasets, tasks, runs, and so on.
+
 from collections import OrderedDict
 import numpy as np
 
 import openml
 from openml import OpenMLClassificationTask
 from openml.runs.functions import format_prediction
 
+####################################################################################################
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
 openml.config.start_using_configuration_for_example()
 
 ####################################################################################################

examples/30_extended/datasets_tutorial.py

@@ -114,6 +114,9 @@
 # Edit a created dataset
 # ======================
 # This example uses the test server, to avoid editing a dataset on the main server.
+#
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
 openml.config.start_using_configuration_for_example()
 ############################################################################
 # Edit non-critical fields, allowed for all authorized users:

examples/30_extended/flow_id_tutorial.py

@@ -16,10 +16,14 @@
 import openml
 
 
-# Activating test server
+############################################################################
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
 openml.config.start_using_configuration_for_example()
 
 
+############################################################################
+# Defining a classifier
 clf = sklearn.tree.DecisionTreeClassifier()
 
 ####################################################################################################

examples/30_extended/flows_and_runs_tutorial.py

@@ -10,17 +10,20 @@
 import openml
 from sklearn import compose, ensemble, impute, neighbors, preprocessing, pipeline, tree
 
+
+############################################################################
+# We'll use the test server for the rest of this tutorial.
+#
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
+openml.config.start_using_configuration_for_example()
+
 ############################################################################
 # Train machine learning models
 # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 #
 # Train a scikit-learn model on the data manually.
-#
-# .. warning:: This example uploads data. For that reason, this example
-#   connects to the test server at test.openml.org. This prevents the main
-#   server from crowding with example datasets, tasks, runs, and so on.
 
-openml.config.start_using_configuration_for_example()
 # NOTE: We are using dataset 68 from the test server: https://test.openml.org/d/68
 dataset = openml.datasets.get_dataset(68)
 X, y, categorical_indicator, attribute_names = dataset.get_data(

examples/30_extended/run_setup_tutorial.py

@@ -24,10 +24,6 @@
     2) Download the flow, reinstantiate the model with same hyperparameters,
        and solve the same task again;
     3) We will verify that the obtained results are exactly the same.
-
-.. warning:: This example uploads data. For that reason, this example
-   connects to the test server at test.openml.org. This prevents the main
-   server from crowding with example datasets, tasks, runs, and so on.
 """
 
 # License: BSD 3-Clause
@@ -43,7 +39,9 @@
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.decomposition import TruncatedSVD
 
-
+############################################################################
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
 openml.config.start_using_configuration_for_example()
 
 ###############################################################################

examples/30_extended/study_tutorial.py

@@ -2,9 +2,7 @@
 =================
 Benchmark studies
 =================
-
 How to list, download and upload benchmark studies.
-
 In contrast to `benchmark suites <https://docs.openml.org/benchmark/#benchmarking-suites>`_ which
 hold a list of tasks, studies hold a list of runs. As runs contain all information on flows and
 tasks, all required information about a study can be retrieved.
@@ -20,15 +18,6 @@
 import openml
 
 
-############################################################################
-# .. warning:: This example uploads data. For that reason, this example
-#   connects to the test server at test.openml.org before doing so.
-#   This prevents the crowding of the main server with example datasets,
-#   tasks, runs, and so on.
-#
-############################################################################
-
-
 ############################################################################
 # Listing studies
 # ***************
@@ -66,14 +55,20 @@
 )
 print(evaluations.head())
 
+############################################################################
+# We'll use the test server for the rest of this tutorial.
+#
+# .. warning::
+#    .. include:: ../../test_server_usage_warning.txt
+openml.config.start_using_configuration_for_example()
+
 ############################################################################
 # Uploading studies
 # =================
 #
 # Creating a study is as simple as creating any kind of other OpenML entity.
 # In this examples we'll create a few runs for the OpenML-100 benchmark
 # suite which is available on the OpenML test server.
-openml.config.start_using_configuration_for_example()
 
 # Model to be used
 clf = RandomForestClassifier()