Skip to content

Commit

Permalink
Lennart Purucker: Minor Documentation Fixes: TaskID for Example Custo…
Browse files Browse the repository at this point in the history
…m Flow; Comment on Homepage; More documentation for `components` (#1243)
  • Loading branch information
Github Actions committed Apr 18, 2023
1 parent f819812 commit bf3f751
Show file tree
Hide file tree
Showing 90 changed files with 559 additions and 798 deletions.
2 changes: 1 addition & 1 deletion develop/.buildinfo
Original file line number Diff line number Diff line change
@@ -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
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand All @@ -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)."
]
}
],
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Expand All @@ -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(),
)

####################################################################################################
Expand Down Expand Up @@ -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

Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Binary file not shown.
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Original file line number Diff line number Diff line change
@@ -1,16 +1,5 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down Expand Up @@ -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"
]
},
{
Expand All @@ -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)"
]
},
{
Expand Down Expand Up @@ -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"
]
},
{
Expand Down
Loading

0 comments on commit bf3f751

Please sign in to comment.