Lennart Purucker: Minor Documentation Fixes: TaskID for Example Custo…

…m Flow; Comment on Homepage; More documentation for `components` (#1243)
openml · Apr 18, 2023 · bf3f751 · bf3f751
1 parent f819812
commit bf3f751
Show file tree

Hide file tree

Showing 90 changed files with 559 additions and 798 deletions.
diff --git a/develop/.buildinfo b/develop/.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: 977121ba2ad02efffcbb2ee6874bcd8d
+config: 378b865a00dfd372de092b59284a596b
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/develop/_downloads/0a5da6cf0947c30e6ebb0b171dfc1b5a/configure_logging.py b/develop/_downloads/0a5da6cf0947c30e6ebb0b171dfc1b5a/configure_logging.py
@@ -37,8 +37,8 @@
 
 import logging
 
-openml.config.console_log.setLevel(logging.DEBUG)
-openml.config.file_log.setLevel(logging.WARNING)
+openml.config.set_console_log_level(logging.DEBUG)
+openml.config.set_file_log_level(logging.WARNING)
 openml.datasets.get_dataset("iris")
 
 # Now the log level that was previously written to file should also be shown in the console.

diff --git a/develop/_downloads/27f49b0e36fba2fe65360adcf060e098/2015_neurips_feurer_example.ipynb b/develop/_downloads/27f49b0e36fba2fe65360adcf060e098/2015_neurips_feurer_example.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/296bc5731c400ca6e06e54ecb9b84b5c/configure_logging.ipynb b/develop/_downloads/296bc5731c400ca6e06e54ecb9b84b5c/configure_logging.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -33,7 +22,7 @@
       },
       "outputs": [],
       "source": [
-        "# License: BSD 3-Clause\n\nimport openml\n\nopenml.datasets.get_dataset(\"iris\")\n\n# With default configuration, the above example will show no output to console.\n# However, in your cache directory you should find a file named 'openml_python.log',\n# which has a DEBUG message written to it. It should be either like\n# \"[DEBUG] [10:46:19:openml.datasets.dataset] Saved dataset 61: iris to file ...\"\n# or like\n# \"[DEBUG] [10:49:38:openml.datasets.dataset] Data pickle file already exists and is up to date.\"\n# , depending on whether or not you had downloaded iris before.\n# The processed log levels can be configured programmatically:\n\nimport logging\n\nopenml.config.console_log.setLevel(logging.DEBUG)\nopenml.config.file_log.setLevel(logging.WARNING)\nopenml.datasets.get_dataset(\"iris\")\n\n# Now the log level that was previously written to file should also be shown in the console.\n# The message is now no longer written to file as the `file_log` was set to level `WARNING`.\n#\n# It is also possible to specify the desired log levels through the configuration file.\n# This way you will not need to set them on each script separately.\n# Add the  line **verbosity = NUMBER** and/or **file_verbosity = NUMBER** to the config file,\n# where 'NUMBER' should be one of:\n#\n# * 0: `logging.WARNING` and up.\n# * 1: `logging.INFO` and up.\n# * 2: `logging.DEBUG` and up (i.e. all messages)."
+        "# License: BSD 3-Clause\n\nimport openml\n\nopenml.datasets.get_dataset(\"iris\")\n\n# With default configuration, the above example will show no output to console.\n# However, in your cache directory you should find a file named 'openml_python.log',\n# which has a DEBUG message written to it. It should be either like\n# \"[DEBUG] [10:46:19:openml.datasets.dataset] Saved dataset 61: iris to file ...\"\n# or like\n# \"[DEBUG] [10:49:38:openml.datasets.dataset] Data pickle file already exists and is up to date.\"\n# , depending on whether or not you had downloaded iris before.\n# The processed log levels can be configured programmatically:\n\nimport logging\n\nopenml.config.set_console_log_level(logging.DEBUG)\nopenml.config.set_file_log_level(logging.WARNING)\nopenml.datasets.get_dataset(\"iris\")\n\n# Now the log level that was previously written to file should also be shown in the console.\n# The message is now no longer written to file as the `file_log` was set to level `WARNING`.\n#\n# It is also possible to specify the desired log levels through the configuration file.\n# This way you will not need to set them on each script separately.\n# Add the  line **verbosity = NUMBER** and/or **file_verbosity = NUMBER** to the config file,\n# where 'NUMBER' should be one of:\n#\n# * 0: `logging.WARNING` and up.\n# * 1: `logging.INFO` and up.\n# * 2: `logging.DEBUG` and up (i.e. all messages)."
       ]
     }
   ],

diff --git a/develop/_downloads/4076733b22158deda2a79e57d217b001/2018_kdd_rijn_example.ipynb b/develop/_downloads/4076733b22158deda2a79e57d217b001/2018_kdd_rijn_example.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/42ecf9b9ca30a385452934aeb1a420d5/2018_neurips_perrone_example.ipynb b/develop/_downloads/42ecf9b9ca30a385452934aeb1a420d5/2018_neurips_perrone_example.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/4e36450a7c3d3fe8c9f4e71689c8e677/plot_svm_hyperparameters_tutorial.ipynb b/develop/_downloads/4e36450a7c3d3fe8c9f4e71689c8e677/plot_svm_hyperparameters_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/4ff7bd62b4b1b9012f431cd3c21d497d/study_tutorial.ipynb b/develop/_downloads/4ff7bd62b4b1b9012f431cd3c21d497d/study_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/51e951fb65905058a563b0f066ec5771/2018_ida_strang_example.ipynb b/develop/_downloads/51e951fb65905058a563b0f066ec5771/2018_ida_strang_example.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/55fed401604e83ceb83e08221c96c779/fetch_evaluations_tutorial.ipynb b/develop/_downloads/55fed401604e83ceb83e08221c96c779/fetch_evaluations_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/763456abfe22344e6b6aed250579eddb/create_upload_tutorial.ipynb b/develop/_downloads/763456abfe22344e6b6aed250579eddb/create_upload_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/7c9d63c8c818944ac2677942af934da6/task_manual_iteration_tutorial.ipynb b/develop/_downloads/7c9d63c8c818944ac2677942af934da6/task_manual_iteration_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/7da39d2664dd3348316be15a6659e681/suites_tutorial.ipynb b/develop/_downloads/7da39d2664dd3348316be15a6659e681/suites_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/7f02370ea703f89b42bf49582f3a252c/tasks_tutorial.ipynb b/develop/_downloads/7f02370ea703f89b42bf49582f3a252c/tasks_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/80bc340cf8aecda2685552d5dc61a84c/simple_flows_and_runs_tutorial.ipynb b/develop/_downloads/80bc340cf8aecda2685552d5dc61a84c/simple_flows_and_runs_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/8c360a24a862fc5b2df293439dbd1564/custom_flow_.py b/develop/_downloads/8c360a24a862fc5b2df293439dbd1564/custom_flow_.py
@@ -77,6 +77,8 @@
 # you can use the Random Forest Classifier flow as a *subflow*. It allows for
 # all hyperparameters of the Random Classifier Flow to also be specified in your pipeline flow.
 #
+# Note: you can currently only specific one subflow as part of the components.
+#
 # In this example, the auto-sklearn flow is a subflow: the auto-sklearn flow is entirely executed as part of this flow.
 # This allows people to specify auto-sklearn hyperparameters used in this flow.
 # In general, using a subflow is not required.
@@ -87,6 +89,8 @@
 autosklearn_flow = openml.flows.get_flow(9313)  # auto-sklearn 0.5.1
 subflow = dict(
     components=OrderedDict(automl_tool=autosklearn_flow),
+    # If you do not want to reference a subflow, you can use the following:
+    # components=OrderedDict(),
 )
 
 ####################################################################################################
@@ -124,7 +128,7 @@
     OrderedDict([("oml:name", "time"), ("oml:value", 120), ("oml:component", flow_id)]),
 ]
 
-task_id = 1965  # Iris Task
+task_id = 1200  # Iris Task
 task = openml.tasks.get_task(task_id)
 dataset_id = task.get_dataset().dataset_id
 

diff --git a/develop/_downloads/a6bb62e32779272bda5770e2d0102148/flow_id_tutorial.ipynb b/develop/_downloads/a6bb62e32779272bda5770e2d0102148/flow_id_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/b38628dd5a6df6d64efcbd57ac258e5f/fetch_runtimes_tutorial.ipynb b/develop/_downloads/b38628dd5a6df6d64efcbd57ac258e5f/fetch_runtimes_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/b525adc48f286431bee47fbbfc545b21/simple_datasets_tutorial.ipynb b/develop/_downloads/b525adc48f286431bee47fbbfc545b21/simple_datasets_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/bc82bea3a5dd7bdba60b65220891d9e5/examples_python.zip b/develop/_downloads/bc82bea3a5dd7bdba60b65220891d9e5/examples_python.zip
diff --git a/develop/_downloads/c1946bda41ddebec13a9af79c1766ead/simple_suites_tutorial.ipynb b/develop/_downloads/c1946bda41ddebec13a9af79c1766ead/simple_suites_tutorial.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},

diff --git a/develop/_downloads/cd015a0038fe3d4ebe69c12134b7dc35/custom_flow_.ipynb b/develop/_downloads/cd015a0038fe3d4ebe69c12134b7dc35/custom_flow_.ipynb
@@ -1,16 +1,5 @@
 {
   "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "collapsed": false
-      },
-      "outputs": [],
-      "source": [
-        "%matplotlib inline"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -87,7 +76,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "It is possible to build a flow which uses other flows.\nFor example, the Random Forest Classifier is a flow, but you could also construct a flow\nwhich uses a Random Forest Classifier in a ML pipeline. When constructing the pipeline flow,\nyou can use the Random Forest Classifier flow as a *subflow*. It allows for\nall hyperparameters of the Random Classifier Flow to also be specified in your pipeline flow.\n\nIn this example, the auto-sklearn flow is a subflow: the auto-sklearn flow is entirely executed as part of this flow.\nThis allows people to specify auto-sklearn hyperparameters used in this flow.\nIn general, using a subflow is not required.\n\nNote: flow 9313 is not actually the right flow on the test server,\nbut that does not matter for this demonstration.\n\n"
+        "It is possible to build a flow which uses other flows.\nFor example, the Random Forest Classifier is a flow, but you could also construct a flow\nwhich uses a Random Forest Classifier in a ML pipeline. When constructing the pipeline flow,\nyou can use the Random Forest Classifier flow as a *subflow*. It allows for\nall hyperparameters of the Random Classifier Flow to also be specified in your pipeline flow.\n\nNote: you can currently only specific one subflow as part of the components.\n\nIn this example, the auto-sklearn flow is a subflow: the auto-sklearn flow is entirely executed as part of this flow.\nThis allows people to specify auto-sklearn hyperparameters used in this flow.\nIn general, using a subflow is not required.\n\nNote: flow 9313 is not actually the right flow on the test server,\nbut that does not matter for this demonstration.\n\n"
       ]
     },
     {
@@ -98,7 +87,7 @@
       },
       "outputs": [],
       "source": [
-        "autosklearn_flow = openml.flows.get_flow(9313)  # auto-sklearn 0.5.1\nsubflow = dict(\n    components=OrderedDict(automl_tool=autosklearn_flow),\n)"
+        "autosklearn_flow = openml.flows.get_flow(9313)  # auto-sklearn 0.5.1\nsubflow = dict(\n    components=OrderedDict(automl_tool=autosklearn_flow),\n    # If you do not want to reference a subflow, you can use the following:\n    # components=OrderedDict(),\n)"
       ]
     },
     {
@@ -134,7 +123,7 @@
       },
       "outputs": [],
       "source": [
-        "flow_id = autosklearn_amlb_flow.flow_id\n\nparameters = [\n    OrderedDict([(\"oml:name\", \"cores\"), (\"oml:value\", 4), (\"oml:component\", flow_id)]),\n    OrderedDict([(\"oml:name\", \"memory\"), (\"oml:value\", 16), (\"oml:component\", flow_id)]),\n    OrderedDict([(\"oml:name\", \"time\"), (\"oml:value\", 120), (\"oml:component\", flow_id)]),\n]\n\ntask_id = 1965  # Iris Task\ntask = openml.tasks.get_task(task_id)\ndataset_id = task.get_dataset().dataset_id"
+        "flow_id = autosklearn_amlb_flow.flow_id\n\nparameters = [\n    OrderedDict([(\"oml:name\", \"cores\"), (\"oml:value\", 4), (\"oml:component\", flow_id)]),\n    OrderedDict([(\"oml:name\", \"memory\"), (\"oml:value\", 16), (\"oml:component\", flow_id)]),\n    OrderedDict([(\"oml:name\", \"time\"), (\"oml:value\", 120), (\"oml:component\", flow_id)]),\n]\n\ntask_id = 1200  # Iris Task\ntask = openml.tasks.get_task(task_id)\ndataset_id = task.get_dataset().dataset_id"
       ]
     },
     {