Skip to content

Commit 4cd2de4

Browse files
author
Github Actions
committed
Matthias Feurer: Merge pull request #1087 from openml/develop
1 parent 06f5b98 commit 4cd2de4

File tree

261 files changed

+6348
-4473
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

261 files changed

+6348
-4473
lines changed

‎main/.buildinfo‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
11
# Sphinx build info version 1
22
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
3-
config: b3932b610db1816b74d9cdc3168b2dca
3+
config: 884c0728f1dea38019eaffe6df15f82c
44
tags: 645f666f9bcd5a90fca523b33c5a78b7

‎main/_downloads/006bd0fc770c8918e54252890f1e023e/study_tutorial.py‎

Lines changed: 7 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -2,9 +2,7 @@
22
=================
33
Benchmark studies
44
=================
5-
65
How to list, download and upload benchmark studies.
7-
86
In contrast to `benchmark suites <https://docs.openml.org/benchmark/#benchmarking-suites>`_ which
97
hold a list of tasks, studies hold a list of runs. As runs contain all information on flows and
108
tasks, all required information about a study can be retrieved.
@@ -20,14 +18,6 @@
2018
import openml
2119

2220

23-
############################################################################
24-
# .. warning:: This example uploads data. For that reason, this example
25-
# connects to the test server at test.openml.org before doing so.
26-
# This prevents the crowding of the main server with example datasets,
27-
# tasks, runs, and so on.
28-
############################################################################
29-
30-
3121
############################################################################
3222
# Listing studies
3323
# ***************
@@ -65,14 +55,20 @@
6555
)
6656
print(evaluations.head())
6757

58+
############################################################################
59+
# We'll use the test server for the rest of this tutorial.
60+
#
61+
# .. warning::
62+
# .. include:: ../../test_server_usage_warning.txt
63+
openml.config.start_using_configuration_for_example()
64+
6865
############################################################################
6966
# Uploading studies
7067
# =================
7168
#
7269
# Creating a study is as simple as creating any kind of other OpenML entity.
7370
# In this examples we'll create a few runs for the OpenML-100 benchmark
7471
# suite which is available on the OpenML test server.
75-
openml.config.start_using_configuration_for_example()
7672

7773
# Model to be used
7874
clf = RandomForestClassifier()

‎main/_downloads/0a5da6cf0947c30e6ebb0b171dfc1b5a/configure_logging.py‎

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -6,8 +6,6 @@
66
Explains openml-python logging, and shows how to configure it.
77
"""
88
##################################################################################
9-
# Logging
10-
# ^^^^^^^
119
# Openml-python uses the `Python logging module <https://docs.python.org/3/library/logging.html>`_
1210
# to provide users with log messages. Each log message is assigned a level of importance, see
1311
# the table in Python's logging tutorial
@@ -16,7 +14,7 @@
1614
# By default, openml-python will print log messages of level `WARNING` and above to console.
1715
# All log messages (including `DEBUG` and `INFO`) are also saved in a file, which can be
1816
# found in your cache directory (see also the
19-
# `introduction tutorial <../20_basic/introduction_tutorial.html>`_).
17+
# :ref:`sphx_glr_examples_20_basic_introduction_tutorial.py`).
2018
# These file logs are automatically deleted if needed, and use at most 2MB of space.
2119
#
2220
# It is possible to configure what log levels to send to console and file.

‎main/_downloads/0d1d1c06933bd6d32bda534cb0aa0e53/create_upload_tutorial.py‎

Lines changed: 9 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -16,9 +16,8 @@
1616
from openml.datasets.functions import create_dataset
1717

1818
############################################################################
19-
# .. warning:: This example uploads data. For that reason, this example
20-
# connects to the test server at test.openml.org. This prevents the main
21-
# server from crowding with example datasets, tasks, runs, and so on.
19+
# .. warning::
20+
# .. include:: ../../test_server_usage_warning.txt
2221

2322
openml.config.start_using_configuration_for_example()
2423
############################################################################
@@ -67,7 +66,7 @@
6766
"Robert Tibshirani (2004) (Least Angle Regression) "
6867
"Annals of Statistics (with discussion), 407-499"
6968
)
70-
paper_url = "http://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf"
69+
paper_url = "https://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf"
7170

7271
############################################################################
7372
# Create the dataset object
@@ -110,7 +109,7 @@
110109
data=data,
111110
# A version label which is provided by the user.
112111
version_label="test",
113-
original_data_url="http://www4.stat.ncsu.edu/~boos/var.select/diabetes.html",
112+
original_data_url="https://www4.stat.ncsu.edu/~boos/var.select/diabetes.html",
114113
paper_url=paper_url,
115114
)
116115

@@ -126,7 +125,7 @@
126125
# OrderedDicts in the case of sparse data.
127126
#
128127
# Weather dataset:
129-
# http://storm.cis.fordham.edu/~gweiss/data-mining/datasets.html
128+
# https://storm.cis.fordham.edu/~gweiss/data-mining/datasets.html
130129

131130
data = [
132131
["sunny", 85, 85, "FALSE", "no"],
@@ -200,8 +199,8 @@
200199
# storing the type of data for each column as well as the attribute names.
201200
# Therefore, when providing a Pandas DataFrame, OpenML can infer this
202201
# information without needing to explicitly provide it when calling the
203-
# function :func:`create_dataset`. In this regard, you only need to pass
204-
# ``'auto'`` to the ``attributes`` parameter.
202+
# function :func:`openml.datasets.create_dataset`. In this regard, you only
203+
# need to pass ``'auto'`` to the ``attributes`` parameter.
205204

206205
df = pd.DataFrame(data, columns=[col_name for col_name, _ in attribute_names])
207206
# enforce the categorical column to have a categorical dtype
@@ -214,8 +213,8 @@
214213
# We enforce the column 'outlook' and 'play' to be a categorical
215214
# dtype while the column 'windy' is kept as a boolean column. 'temperature'
216215
# and 'humidity' are kept as numeric columns. Then, we can
217-
# call :func:`create_dataset` by passing the dataframe and fixing the parameter
218-
# ``attributes`` to ``'auto'``.
216+
# call :func:`openml.datasets.create_dataset` by passing the dataframe and
217+
# fixing the parameter ``attributes`` to ``'auto'``.
219218

220219
weather_dataset = create_dataset(
221220
name="Weather",

‎main/_downloads/1ad3e73844b6bba64db63f52045fc1ae/suites_tutorial.py‎

Lines changed: 8 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
How to list, download and upload benchmark suites.
77
88
If you want to learn more about benchmark suites, check out our
9-
`brief introductory tutorial <../20_basic/simple_suites_tutorial.html>`_ or the
9+
brief introductory tutorial :ref:`sphx_glr_examples_20_basic_simple_suites_tutorial.py` or the
1010
`OpenML benchmark docs <https://docs.openml.org/benchmark/#benchmarking-suites>`_.
1111
"""
1212
############################################################################
@@ -19,13 +19,6 @@
1919

2020
import openml
2121

22-
############################################################################
23-
# .. warning:: This example uploads data. For that reason, this example
24-
# connects to the test server at test.openml.org before doing so.
25-
# This prevents the main server from crowding with example datasets,
26-
# tasks, runs, and so on.
27-
############################################################################
28-
2922

3023
############################################################################
3124
# Listing suites
@@ -65,6 +58,13 @@
6558
tasks = tasks.query("tid in @suite.tasks")
6659
print(tasks.describe().transpose())
6760

61+
############################################################################
62+
# We'll use the test server for the rest of this tutorial.
63+
#
64+
# .. warning::
65+
# .. include:: ../../test_server_usage_warning.txt
66+
openml.config.start_using_configuration_for_example()
67+
6868
############################################################################
6969
# Uploading suites
7070
# ================
@@ -73,8 +73,6 @@
7373
# entity - the only reason why we need so much code in this example is
7474
# because we upload some random data.
7575

76-
openml.config.start_using_configuration_for_example()
77-
7876
# We'll take a random subset of at least ten tasks of all available tasks on
7977
# the test server:
8078
all_tasks = list(openml.tasks.list_tasks().keys())

‎main/_downloads/25a00d3d6385de3b0fbf8dd033ff9db0/simple_suites_tutorial.py‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,6 @@
6262
# Further examples
6363
# ================
6464
#
65-
# * `Advanced benchmarking suites tutorial <../30_extended/suites_tutorial.html>`_
66-
# * `Benchmarking studies tutorial <../30_extended/study_tutorial.html>`_
67-
# * `Using studies to compare linear and non-linear classifiers
68-
# <../40_paper/2018_ida_strang_example.html>`_
65+
# * :ref:`sphx_glr_examples_30_extended_suites_tutorial.py`
66+
# * :ref:`sphx_glr_examples_30_extended_study_tutorial.py`
67+
# * :ref:`sphx_glr_examples_40_paper_2018_ida_strang_example.py`

‎main/_downloads/27f49b0e36fba2fe65360adcf060e098/2015_neurips_feurer_example.ipynb‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
"cell_type": "markdown",
1616
"metadata": {},
1717
"source": [
18-
"\n# Feurer et al. (2015)\n\nA tutorial on how to get the datasets used in the paper introducing *Auto-sklearn* by Feurer et al..\n\nAuto-sklearn website: https://automl.github.io/auto-sklearn/master/\n\n## Publication\n\n| Efficient and Robust Automated Machine Learning\n| Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum and Frank Hutter\n| In *Advances in Neural Information Processing Systems 28*, 2015\n| Available at http://papers.nips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf\n"
18+
"\n# Feurer et al. (2015)\n\nA tutorial on how to get the datasets used in the paper introducing *Auto-sklearn* by Feurer et al..\n\nAuto-sklearn website: https://automl.github.io/auto-sklearn/\n\n## Publication\n\n| Efficient and Robust Automated Machine Learning\n| Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum and Frank Hutter\n| In *Advances in Neural Information Processing Systems 28*, 2015\n| Available at https://papers.nips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf\n"
1919
]
2020
},
2121
{
@@ -89,7 +89,7 @@
8989
"name": "python",
9090
"nbconvert_exporter": "python",
9191
"pygments_lexer": "ipython3",
92-
"version": "3.8.8"
92+
"version": "3.8.10"
9393
}
9494
},
9595
"nbformat": 4,

‎main/_downloads/296bc5731c400ca6e06e54ecb9b84b5c/configure_logging.ipynb‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@
2222
"cell_type": "markdown",
2323
"metadata": {},
2424
"source": [
25-
"## Logging\nOpenml-python uses the `Python logging module <https://docs.python.org/3/library/logging.html>`_\nto provide users with log messages. Each log message is assigned a level of importance, see\nthe table in Python's logging tutorial\n`here <https://docs.python.org/3/howto/logging.html#when-to-use-logging>`_.\n\nBy default, openml-python will print log messages of level `WARNING` and above to console.\nAll log messages (including `DEBUG` and `INFO`) are also saved in a file, which can be\nfound in your cache directory (see also the\n`introduction tutorial <../20_basic/introduction_tutorial.html>`_).\nThese file logs are automatically deleted if needed, and use at most 2MB of space.\n\nIt is possible to configure what log levels to send to console and file.\nWhen downloading a dataset from OpenML, a `DEBUG`-level message is written:\n\n"
25+
"Openml-python uses the `Python logging module <https://docs.python.org/3/library/logging.html>`_\nto provide users with log messages. Each log message is assigned a level of importance, see\nthe table in Python's logging tutorial\n`here <https://docs.python.org/3/howto/logging.html#when-to-use-logging>`_.\n\nBy default, openml-python will print log messages of level `WARNING` and above to console.\nAll log messages (including `DEBUG` and `INFO`) are also saved in a file, which can be\nfound in your cache directory (see also the\n`sphx_glr_examples_20_basic_introduction_tutorial.py`).\nThese file logs are automatically deleted if needed, and use at most 2MB of space.\n\nIt is possible to configure what log levels to send to console and file.\nWhen downloading a dataset from OpenML, a `DEBUG`-level message is written:\n\n"
2626
]
2727
},
2828
{
@@ -53,7 +53,7 @@
5353
"name": "python",
5454
"nbconvert_exporter": "python",
5555
"pygments_lexer": "ipython3",
56-
"version": "3.8.8"
56+
"version": "3.8.10"
5757
}
5858
},
5959
"nbformat": 4,

‎main/_downloads/2fc23bfc18345b110ab68bc5f3939dc8/2018_neurips_perrone_example.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@
1111
| Scalable Hyperparameter Transfer Learning
1212
| Valerio Perrone and Rodolphe Jenatton and Matthias Seeger and Cedric Archambeau
1313
| In *Advances in Neural Information Processing Systems 31*, 2018
14-
| Available at http://papers.nips.cc/paper/7917-scalable-hyperparameter-transfer-learning.pdf
14+
| Available at https://papers.nips.cc/paper/7917-scalable-hyperparameter-transfer-learning.pdf
1515
1616
This example demonstrates how OpenML runs can be used to construct a surrogate model.
1717

‎main/_downloads/4076733b22158deda2a79e57d217b001/2018_kdd_rijn_example.ipynb‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
"cell_type": "markdown",
1616
"metadata": {},
1717
"source": [
18-
"\n# van Rijn and Hutter (2018)\n\nA tutorial on how to reproduce the paper *Hyperparameter Importance Across Datasets*.\n\nThis is a Unix-only tutorial, as the requirements can not be satisfied on a Windows machine (Untested on other\nsystems).\n\n## Publication\n\n| Hyperparameter importance across datasets\n| Jan N. van Rijn and Frank Hutter\n| In *Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining*, 2018\n| Available at https://dl.acm.org/citation.cfm?id=3220058\n"
18+
"\n# van Rijn and Hutter (2018)\n\nA tutorial on how to reproduce the paper *Hyperparameter Importance Across Datasets*.\n\nThis is a Unix-only tutorial, as the requirements can not be satisfied on a Windows machine (Untested on other\nsystems).\n\n## Publication\n\n| Hyperparameter importance across datasets\n| Jan N. van Rijn and Frank Hutter\n| In *Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining*, 2018\n| Available at https://dl.acm.org/doi/10.1145/3219819.3220058\n"
1919
]
2020
},
2121
{
@@ -82,7 +82,7 @@
8282
"name": "python",
8383
"nbconvert_exporter": "python",
8484
"pygments_lexer": "ipython3",
85-
"version": "3.8.8"
85+
"version": "3.8.10"
8686
}
8787
},
8888
"nbformat": 4,

0 commit comments

Comments
 (0)