openml · mfeurer · Jul 26, 2019 · Jul 19, 2019 · Jul 19, 2019 · Jul 23, 2019
diff --git a/LICENSE b/LICENSE
@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2014-2018, Matthias Feurer, Jan van Rijn, Andreas Müller, 
+Copyright (c) 2014-2019, Matthias Feurer, Jan van Rijn, Andreas Müller, 
 Joaquin Vanschoren and others.
 All rights reserved.
 

diff --git a/doc/conf.py b/doc/conf.py
@@ -15,6 +15,7 @@
 import os
 import sys
 import sphinx_bootstrap_theme
+import time
 import openml
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -65,7 +66,7 @@
 # General information about the project.
 project = u'OpenML'
 copyright = (
- u'2014-2019, the OpenML-Python team.'
+ u'2014-{}, the OpenML-Python team.'.format(time.strftime("%Y,%m,%d,%H,%M,%S").split(',')[0])
 )
 
 # The version info for the project you're documenting, acts as replacement for

diff --git a/doc/index.rst b/doc/index.rst
@@ -21,16 +21,12 @@ Example
 .. code:: python
 
  import openml
- from sklearn import preprocessing, tree, pipeline
-
- # Set the OpenML API Key which is required to upload your runs.
- # You can get your own API by signing up to OpenML.org.
- openml.config.apikey = 'ABC'
+ from sklearn import impute, tree, pipeline
 
  # Define a scikit-learn classifier or pipeline
  clf = pipeline.Pipeline(
  steps=[
- ('imputer', preprocessing.Imputer()),
+ ('imputer', impute.SimpleImputer()),
  ('estimator', tree.DecisionTreeClassifier())
  ]
  )
@@ -39,10 +35,13 @@ Example
  task = openml.tasks.get_task(31)
  # Run the scikit-learn model on the task.
  run = openml.runs.run_model_on_task(clf, task)
- # Publish the experiment on OpenML (optional, requires an API key).
+ # Publish the experiment on OpenML (optional, requires an API key.
+ # You can get your own API key by signing up to OpenML.org)
  run.publish()
  print('View the run online: %s/run/%d' % (openml.config.server, run.run_id))
 
+You can find more examples in our `examples gallery <examples/index.html>`_.
+
 ----------------------------
 How to get OpenML for python
 ----------------------------

diff --git a/examples/fetch_evaluations_tutorial.py b/examples/fetch_evaluations_tutorial.py
@@ -20,7 +20,6 @@
 
 ############################################################################
 import openml
-from pprint import pprint
 
 ############################################################################
 # Listing evaluations
@@ -37,7 +36,7 @@
  output_format='dataframe')
 
 # Querying the returned results for precision above 0.98
-pprint(evals[evals.value > 0.98])
+print(evals[evals.value > 0.98])
 
 #############################################################################
 # Viewing a sample task
@@ -47,7 +46,7 @@
 # We will start by displaying a simple *supervised classification* task:
 task_id = 167140 # https://www.openml.org/t/167140
 task = openml.tasks.get_task(task_id)
-pprint(vars(task))
+print(task)
 
 #############################################################################
 # Obtaining all the evaluations for the task
@@ -60,11 +59,11 @@
 evals = openml.evaluations.list_evaluations(function=metric, task=[task_id],
  output_format='dataframe')
 # Displaying the first 10 rows
-pprint(evals.head(n=10))
+print(evals.head(n=10))
 # Sorting the evaluations in decreasing order of the metric chosen
 evals = evals.sort_values(by='value', ascending=False)
 print("\nDisplaying head of sorted dataframe: ")
-pprint(evals.head())
+print(evals.head())
 
 #############################################################################
 # Obtaining CDF of metric for chosen task
@@ -147,4 +146,4 @@ def plot_flow_compare(evaluations, top_n=10, metric='predictive_accuracy'):
 flow_ids = evals.flow_id.unique()[:top_n]
 flow_names = evals.flow_name.unique()[:top_n]
 for i in range(top_n):
-pprint((flow_ids[i], flow_names[i]))
+print((flow_ids[i], flow_names[i]))
diff --git a/examples/flows_and_runs_tutorial.py b/examples/flows_and_runs_tutorial.py
@@ -6,7 +6,6 @@
 """
 
 import openml
-from pprint import pprint
 from sklearn import compose, ensemble, impute, neighbors, preprocessing, pipeline, tree
 
 ############################################################################
@@ -58,7 +57,7 @@
 # Run the flow
 run = openml.runs.run_model_on_task(clf, task)
 
-# pprint(vars(run), depth=2)
+print(run)
 
 ############################################################################
 # Share the run on the OpenML server
@@ -75,17 +74,37 @@
 # We can now also inspect the flow object which was automatically created:
 
 flow = openml.flows.get_flow(run.flow_id)
-pprint(vars(flow), depth=1)
+print(flow)
 
 ############################################################################
 # It also works with pipelines
 # ############################
 #
 # When you need to handle 'dirty' data, build pipelines to model then automatically.
-task = openml.tasks.get_task(115)
+task = openml.tasks.get_task(1)
+features = task.get_dataset().features
+nominal_feature_indices = [
+ i for i in range(len(features))
+ if features[i].name != task.target_name and features[i].data_type == 'nominal'
+]
 pipe = pipeline.Pipeline(steps=[
- ('Imputer', impute.SimpleImputer(strategy='median')),
- ('OneHotEncoder', preprocessing.OneHotEncoder(sparse=False, handle_unknown='ignore')),
+ (
+ 'Preprocessing',
+ compose.ColumnTransformer([
+ ('Nominal', pipeline.Pipeline(
+ [
+ ('Imputer', impute.SimpleImputer(strategy='most_frequent')),
+ (
+ 'Encoder',
+ preprocessing.OneHotEncoder(
+ sparse=False, handle_unknown='ignore',
+ )
+ ),
+ ]),
+ nominal_feature_indices,
+ ),
+ ]),
+ ),
  ('Classifier', ensemble.RandomForestClassifier(n_estimators=10))
 ])
 

diff --git a/examples/introduction_tutorial.py b/examples/introduction_tutorial.py
@@ -1,6 +1,6 @@
 """
 Introduction
-===================
+============
 
 An introduction to OpenML, followed up by a simple example.
 """
@@ -15,6 +15,8 @@
 # * Works seamlessly with scikit-learn and other libraries
 # * Large scale benchmarking, compare to state of the art
 #
+
+############################################################################
 # Installation
 # ^^^^^^^^^^^^
 # Installation is done via ``pip``:
@@ -26,6 +28,8 @@
 # For further information, please check out the installation guide at
 # https://openml.github.io/openml-python/master/contributing.html#installation
 #
+
+############################################################################
 # Authentication
 # ^^^^^^^^^^^^^^
 #
@@ -49,6 +53,7 @@
 # .. 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.
+
 ############################################################################
 import openml
 from sklearn import neighbors

diff --git a/examples/tasks_tutorial.py b/examples/tasks_tutorial.py
@@ -133,7 +133,7 @@
 ############################################################################
 # Properties of the task are stored as member variables:
 
-print(vars(task))
+print(task)
 
 ############################################################################
 # And:

diff --git a/openml/datasets/data_feature.py b/openml/datasets/data_feature.py
@@ -1,18 +1,19 @@
 class OpenMLDataFeature(object):
- """Data Feature (a.k.a. Attribute) object.
+ """
+ Data Feature (a.k.a. Attribute) object.
 
-Parameters
-----------
-index : int
-The index of this feature
-name : str
-Name of the feature
-data_type : str
-can be nominal, numeric, string, date (corresponds to arff)
-nominal_values : list(str)
-list of the possible values, in case of nominal attribute
-number_missing_values : int
-"""
+ Parameters
+ ----------
+ index : int
+ The index of this feature
+ name : str
+ Name of the feature
+ data_type : str
+ can be nominal, numeric, string, date (corresponds to arff)
+ nominal_values : list(str)
+ list of the possible values, in case of nominal attribute
+ number_missing_values : int
+ """
  LEGAL_DATA_TYPES = ['nominal', 'numeric', 'string', 'date']
 
  def __init__(self, index, name, data_type, nominal_values,
@@ -22,8 +23,16 @@ def __init__(self, index, name, data_type, nominal_values,
  if data_type not in self.LEGAL_DATA_TYPES:
  raise ValueError('data type should be in %s, found: %s' %
  (str(self.LEGAL_DATA_TYPES), data_type))
- if nominal_values is not None and type(nominal_values) != list:
- raise ValueError('Nominal_values is of wrong datatype')
+ if data_type == 'nominal':
+ if nominal_values is None:
+ raise TypeError('Dataset features require attribute `nominal_values` for nominal '
+ 'feature type.')
+ elif not isinstance(nominal_values, list):
+ raise TypeError('Argument `nominal_values` is of wrong datatype, should be list, '
+ 'but is {}'.format(type(nominal_values)))
+ else:
+ if nominal_values is not None:
+ raise TypeError('Argument `nominal_values` must be None for non-nominal feature.')
  if type(number_missing_values) != int:
  raise ValueError('number_missing_values is of wrong datatype')
 

diff --git a/openml/datasets/dataset.py b/openml/datasets/dataset.py
@@ -153,7 +153,6 @@ def __init__(self, name, description, format=None,
 
  if features is not None:
  self.features = {}
- # todo add nominal values (currently not in database)
  for idx, xmlfeature in enumerate(features['oml:feature']):
  nr_missing = xmlfeature.get('oml:number_of_missing_values', 0)
  feature = OpenMLDataFeature(int(xmlfeature['oml:index']),

diff --git a/openml/setups/setup.py b/openml/setups/setup.py
@@ -4,14 +4,14 @@
 class OpenMLSetup(object):
  """Setup object (a.k.a. Configuration).
 
-Parameters
-----------
-setup_id : int
-The OpenML setup id
-flow_id : int
-The flow that it is build upon
-parameters : dict
-The setting of the parameters
+ Parameters
+ ----------
+ setup_id : int
+ The OpenML setup id
+ flow_id : int
+ The flow that it is build upon
+ parameters : dict
+ The setting of the parameters
  """
 
  def __init__(self, setup_id, flow_id, parameters):

diff --git a/openml/study/functions.py b/openml/study/functions.py
@@ -182,8 +182,8 @@ def create_study(
  where the runs are the main entity (collection consists of runs and all
  entities (flows, tasks, etc) that are related to these runs)
 
- Parameters:
- -----------
+ Parameters
+ ----------
  alias : str (optional)
  a string ID, unique on server (url-friendly)
  benchmark_suite : int (optional)
@@ -195,8 +195,8 @@ def create_study(
  run_ids : list
  a list of run ids associated with this study
 
- Returns:
- --------
+ Returns
+ -------
  OpenMLStudy
  A local OpenML study object (call publish method to upload to server)
  """
@@ -228,8 +228,8 @@ def create_benchmark_suite(
  Creates an OpenML benchmark suite (collection of entity types, where
  the tasks are the linked entity)
 
- Parameters:
- -----------
+ Parameters
+ ----------
  alias : str (optional)
  a string ID, unique on server (url-friendly)
  name : str
@@ -239,8 +239,8 @@ def create_benchmark_suite(
  task_ids : list
  a list of task ids associated with this study
 
- Returns:
- --------
+ Returns
+ -------
  OpenMLStudy
  A local OpenML study object (call publish method to upload to server)
  """

diff --git a/openml/tasks/functions.py b/openml/tasks/functions.py
@@ -133,14 +133,14 @@ def list_tasks(
 ) -> Union[Dict, pd.DataFrame]:
  """
  Return a number of tasks having the given tag and task_type_id
+
  Parameters
  ----------
  Filter task_type_id is separated from the other filters because
  it is used as task_type_id in the task description, but it is named
  type when used as a filter in list tasks call.
  task_type_id : int, optional
- ID of the task type as detailed
- `here <https://www.openml.org/search?type=task_type>`_.
+ ID of the task type as detailed `here <https://www.openml.org/search?type=task_type>`_.
  - Supervised classification: 1
  - Supervised regression: 2
  - Learning curve: 3
@@ -362,7 +362,7 @@ def get_task(task_id: int, download_data: bool = True) -> OpenMLTask:
  # List of class labels availaible in dataset description
  # Including class labels as part of task meta data handles
  # the case where data download was initially disabled
- if isinstance(task, OpenMLClassificationTask):
+ if isinstance(task, (OpenMLClassificationTask, OpenMLLearningCurveTask)):
  task.class_labels = \
  dataset.retrieve_class_labels(task.target_name)
  # Clustering tasks do not have class labels

diff --git a/openml/testing.py b/openml/testing.py
@@ -73,7 +73,9 @@ def setUp(self, n_levels: int = 1):
  self.static_cache_dir = os.path.join(static_cache_dir, 'files')
 
  if self.static_cache_dir is None:
- raise ValueError('Cannot find test cache dir!')
+ raise ValueError(
+ 'Cannot find test cache dir, expected it to be {}!'.format(static_cache_dir)
+ )
 
  self.cwd = os.getcwd()
  workdir = os.path.dirname(os.path.abspath(__file__))

diff --git a/tests/files/org/openml/test/datasets/-1/features.xml b/tests/files/org/openml/test/datasets/-1/features.xml
@@ -180003,6 +180003,8 @@
  <oml:index>20000</oml:index>
  <oml:name>class</oml:name>
  <oml:data_type>nominal</oml:data_type>
+ <oml:nominal_value>-1</oml:nominal_value>
+ <oml:nominal_value>1</oml:nominal_value>
  <oml:is_target>false</oml:is_target>
  <oml:is_ignore>false</oml:is_ignore>
  <oml:is_row_identifier>false</oml:is_row_identifier>