reworking examples a bit based on Pieter's suggestions

Author: mfeurer

examples/create_upload_tutorial.py

@@ -14,8 +14,8 @@
 
 ############################################################################
 # .. 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.
+#   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()
 ############################################################################

examples/datasets_tutorial.py

@@ -9,13 +9,6 @@
 import openml
 import pandas as pd
 
-############################################################################
-# .. 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.
-
-openml.config.start_using_configuration_for_example()
-
 ############################################################################
 # List datasets
 # =============
@@ -50,9 +43,8 @@
 # Download datasets
 # =================
 
-# This is done based on the dataset ID ('did').
-dataset = openml.datasets.get_dataset(68)
-# NOTE: Dataset 68 exists on the test server https://test.openml.org/d/68
+# This is done based on the dataset ID.
+dataset = openml.datasets.get_dataset(1471)
 
 # Print a summary
 print("This is dataset '%s', the target feature is '%s'" %
@@ -91,8 +83,7 @@
 # data file. The dataset object can be used as normal.
 # Whenever you use any functionality that requires the data,
 # such as `get_data`, the data will be downloaded.
-dataset = openml.datasets.get_dataset(68, download_data=False)
-# NOTE: Dataset 68 exists on the test server https://test.openml.org/d/68
+dataset = openml.datasets.get_dataset(1471, download_data=False)
 
 ############################################################################
 # Exercise 2
@@ -108,7 +99,3 @@
     alpha=.8,
     cmap='plasma'
 )
-
-
-############################################################################
-openml.config.stop_using_configuration_for_example()

examples/flows_and_runs_tutorial.py

@@ -14,9 +14,10 @@
 # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 #
 # Train a scikit-learn model on the data manually.
+#
 # .. 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.
+#   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

examples/introduction_tutorial.py

@@ -45,6 +45,7 @@
 #   file must be in the directory ~/.openml/config and exist prior to
 #   importing the openml module.
 # * Run the code below, replacing 'YOURKEY' with your API key.
+#
 # .. 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.
@@ -88,7 +89,7 @@
 run = openml.runs.run_model_on_task(clf, task, avoid_duplicate_runs=False)
 # Publish the experiment on OpenML (optional, requires an API key).
 # For this tutorial, our configuration publishes to the test server
-# as to not pollute the main server.
+# as to not crowd the main server with runs created by examples.
 myrun = run.publish()
 print("kNN on %s: http://test.openml.org/r/%d" % (data.name, myrun.run_id))
 

examples/run_setup_tutorial.py

@@ -26,8 +26,8 @@
     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 instead. This prevents the live server from
-crowding with example datasets, tasks, studies, and so on.
+   connects to the test server at test.openml.org. This prevents the main
+   server from crowding with example datasets, tasks, runs, and so on.
 """
 import logging
 import numpy as np

examples/sklearn/openml_run_example.py

@@ -9,8 +9,8 @@
 
 ############################################################################
 # .. 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.
+#   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()
 ############################################################################

examples/tasks_tutorial.py

@@ -79,7 +79,7 @@
 ############################################################################
 # Furthermore, we can list tasks based on the dataset id:
 
-tasks = openml.tasks.list_tasks(data_id=61)
+tasks = openml.tasks.list_tasks(data_id=1471)
 tasks = pd.DataFrame.from_dict(tasks, orient='index')
 print("First 5 of %s tasks:" % len(tasks))
 pprint(tasks.head())