Merge pull request #355 from amueller/tagging

WIP dataset Tagging

Author: amueller

openml/_api_calls.py

@@ -7,7 +7,8 @@
 import xmltodict
 
 from . import config
-from .exceptions import OpenMLServerError, OpenMLServerException
+from .exceptions import (OpenMLServerError, OpenMLServerException,
+                         OpenMLServerNoResult)
 
 
 def _perform_api_call(call, data=None, file_dictionary=None,
@@ -138,4 +139,6 @@ def _parse_server_exception(response):
     additional = None
     if 'oml:additional_information' in server_exception['oml:error']:
         additional = server_exception['oml:error']['oml:additional_information']
+    if code in [370, 372]:
+        return OpenMLServerNoResult(code, message, additional)
     return OpenMLServerException(code, message, additional)

openml/datasets/dataset.py

@@ -3,7 +3,6 @@
 import logging
 import os
 import six
-import sys
 
 import arff
 
@@ -26,9 +25,9 @@ class OpenMLDataset(object):
 
     Parameters
     ----------
-    name : string
+    name : str
         Name of the dataset
-    description : string
+    description : str
         Description of the dataset
     FIXME : which of these do we actually nee?
     """
@@ -82,7 +81,7 @@ def __init__(self, dataset_id=None, name=None, version=None, description=None,
                 feature = OpenMLDataFeature(int(xmlfeature['oml:index']),
                                             xmlfeature['oml:name'],
                                             xmlfeature['oml:data_type'],
-                                            None, #todo add nominal values (currently not in database)
+                                            None,  # todo add nominal values (currently not in database)
                                             int(xmlfeature.get('oml:number_of_missing_values', 0)))
                 if idx != feature.index:
                     raise ValueError('Data features not provided in right order')
@@ -124,6 +123,28 @@ def __init__(self, dataset_id=None, name=None, version=None, description=None,
                     logger.debug("Saved dataset %d: %s to file %s" %
                                  (self.dataset_id, self.name, self.data_pickle_file))
 
+    def push_tag(self, tag):
+        """Annotates this data set with a tag on the server.
+
+        Parameters
+        ----------
+        tag : str
+            Tag to attach to the dataset.
+        """
+        data = {'data_id': self.dataset_id, 'tag': tag}
+        _perform_api_call("/data/tag", data=data)
+
+    def remove_tag(self, tag):
+        """Removes a tag from this dataset on the server.
+
+        Parameters
+        ----------
+        tag : str
+            Tag to attach to the dataset.
+        """
+        data = {'data_id': self.dataset_id, 'tag': tag}
+        _perform_api_call("/data/untag", data=data)
+
     def __eq__(self, other):
         if type(other) != OpenMLDataset:
             return False
@@ -310,7 +331,6 @@ def retrieve_class_labels(self, target_name='class'):
         else:
             return None
 
-
     def get_features_by_type(self, data_type, exclude=None,
                              exclude_ignore_attributes=True,
                              exclude_row_id_attribute=True):
@@ -372,11 +392,7 @@ def publish(self):
 
         Returns
         -------
-        return_code : int
-            Return code from server
-
-        return_value : string
-            xml return from server
+        self
         """
 
         file_elements = {'description': self._to_xml()}
@@ -396,7 +412,7 @@ def _to_xml(self):
 
         Returns
         -------
-        xml_dataset : string
+        xml_dataset : str
             XML description of the data.
         """
         xml_dataset = ('<oml:data_set_description '

openml/datasets/functions.py

@@ -8,7 +8,7 @@
 import xmltodict
 
 from .dataset import OpenMLDataset
-from ..exceptions import OpenMLCacheException
+from ..exceptions import OpenMLCacheException, OpenMLServerNoResult
 from .. import config
 from .._api_calls import _perform_api_call, _read_url
 
@@ -178,7 +178,10 @@ def list_datasets(offset=None, size=None, tag=None):
 
 def _list_datasets(api_call):
     # TODO add proper error handling here!
-    xml_string = _perform_api_call(api_call)
+    try:
+        xml_string = _perform_api_call(api_call)
+    except OpenMLServerNoResult:
+        return []
     datasets_dict = xmltodict.parse(xml_string, force_list=('oml:dataset',))
 
     # Minimalistic check if the XML is useful

openml/exceptions.py

@@ -11,7 +11,7 @@ class OpenMLServerError(PyOpenMLError):
     def __init__(self, message):
         super(OpenMLServerError, self).__init__(message)
 
-#
+
 class OpenMLServerException(OpenMLServerError):
     """exception for when the result of the server was
        not 200 (e.g., listing call w/o results). """
@@ -22,6 +22,11 @@ def __init__(self, code, message, additional=None):
         super(OpenMLServerException, self).__init__(message)
 
 
+class OpenMLServerNoResult(OpenMLServerException):
+    """exception for when the result of the server is empty. """
+    pass
+
+
 class OpenMLCacheException(PyOpenMLError):
     """Dataset / task etc not found in cache"""
     def __init__(self, message):

tests/test_datasets/test_dataset.py

@@ -1,6 +1,7 @@
 import numpy as np
 from scipy import sparse
 import six
+from time import time
 
 from openml.testing import TestBase
 import openml
@@ -90,6 +91,25 @@ def test_get_data_with_ignore_attributes(self):
         # TODO test multiple ignore attributes!
 
 
+class OpenMLDatasetTestOnTestServer(TestBase):
+    def setUp(self):
+        super(OpenMLDatasetTestOnTestServer, self).setUp()
+        # longley, really small dataset
+        self.dataset = openml.datasets.get_dataset(125)
+
+    def test_tagging(self):
+        tag = "testing_tag_{}_{}".format(self.id(), time())
+        ds_list = openml.datasets.list_datasets(tag=tag)
+        self.assertEqual(len(ds_list), 0)
+        self.dataset.push_tag(tag)
+        ds_list = openml.datasets.list_datasets(tag=tag)
+        self.assertEqual(len(ds_list), 1)
+        self.assertIn(125, ds_list)
+        self.dataset.remove_tag(tag)
+        ds_list = openml.datasets.list_datasets(tag=tag)
+        self.assertEqual(len(ds_list), 0)
+
+
 class OpenMLDatasetTestSparse(TestBase):
     _multiprocess_can_split_ = True
 

tests/test_datasets/test_dataset_functions.py

@@ -1,6 +1,5 @@
 import unittest
 import os
-import os
 import sys
 
 if sys.version_info[0] >= 3: