add tagging for runs, don't error on empty list_runs

Author: amueller

openml/_api_calls.py

@@ -139,6 +139,7 @@ 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]:
+    if code in [370, 372, 512]:
+        # 512 for runs, 370 for datasets (should be 372)
         return OpenMLServerNoResult(code, message, additional)
     return OpenMLServerException(code, message, additional)

openml/runs/functions.py

@@ -14,7 +14,7 @@
 
 import openml
 import openml.utils
-from ..exceptions import PyOpenMLError
+from ..exceptions import PyOpenMLError, OpenMLServerNoResult
 from .. import config
 from ..flows import sklearn_to_flow, get_flow, flow_exists, _check_n_jobs, \
     _copy_server_fields
@@ -862,8 +862,10 @@ def list_runs(offset=None, size=None, id=None, task=None, setup=None,
 
 def _list_runs(api_call):
     """Helper function to parse API calls which are lists of runs"""
-
-    xml_string = _perform_api_call(api_call)
+    try:
+        xml_string = _perform_api_call(api_call)
+    except OpenMLServerNoResult:
+        return []
 
     runs_dict = xmltodict.parse(xml_string, force_list=('oml:run',))
     # Minimalistic check if the XML is useful

openml/runs/run.py

@@ -1,4 +1,4 @@
-from collections import OrderedDict, defaultdict
+from collections import OrderedDict
 import json
 import sys
 import time
@@ -12,6 +12,7 @@
 from .._api_calls import _perform_api_call, _file_id_to_url, _read_url_files
 from ..exceptions import PyOpenMLError
 
+
 class OpenMLRun(object):
     """OpenML Run: result of running a model on an openml dataset.
 
@@ -349,6 +350,28 @@ def extract_parameters(_flow, _flow_dict, component_model,
 
         return parameters
 
+    def push_tag(self, tag):
+        """Annotates this run with a tag on the server.
+
+        Parameters
+        ----------
+        tag : str
+            Tag to attach to the run.
+        """
+        data = {'run_id': self.run_id, 'tag': tag}
+        _perform_api_call("/run/tag", data=data)
+
+    def remove_tag(self, tag):
+        """Removes a tag from this run on the server.
+
+        Parameters
+        ----------
+        tag : str
+            Tag to attach to the run.
+        """
+        data = {'run_id': self.run_id, 'tag': tag}
+        _perform_api_call("/run/untag", data=data)
+
 
 ################################################################################
 # Functions which cannot be in runs/functions due to circular imports

tests/test_runs/test_run.py

@@ -1,43 +1,44 @@
+from time import time
+
 from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
 from sklearn.linear_model import LogisticRegression
 from sklearn.model_selection import RandomizedSearchCV, StratifiedKFold
 
 from openml.testing import TestBase
 from openml.flows.sklearn_converter import sklearn_to_flow
 from openml import OpenMLRun
+import openml
 
 
 class TestRun(TestBase):
-    # Splitting not helpful, these test's don't rely on the server and take less
-    # than 1 seconds
+    # Splitting not helpful, these test's don't rely on the server and take
+    # less than 1 seconds
 
     def test_parse_parameters_flow_not_on_server(self):
 
         model = LogisticRegression()
         flow = sklearn_to_flow(model)
-        self.assertRaisesRegexp(ValueError,
-                                'Flow sklearn.linear_model.logistic.LogisticRegression '
-                                'has no flow_id!',
-                                OpenMLRun._parse_parameters, flow)
+        self.assertRaisesRegexp(
+            ValueError, 'Flow sklearn.linear_model.logistic.LogisticRegression'
+            'has no flow_id!', OpenMLRun._parse_parameters, flow)
 
         model = AdaBoostClassifier(base_estimator=LogisticRegression())
         flow = sklearn_to_flow(model)
         flow.flow_id = 1
-        self.assertRaisesRegexp(ValueError,
-                                'Flow sklearn.linear_model.logistic.LogisticRegression '
-                                'has no flow_id!',
-                                OpenMLRun._parse_parameters, flow)
+        self.assertRaisesRegexp(
+            ValueError, 'Flow sklearn.linear_model.logistic.LogisticRegression'
+            'has no flow_id!', OpenMLRun._parse_parameters, flow)
 
     def test_parse_parameters(self):
 
         model = RandomizedSearchCV(
             estimator=RandomForestClassifier(n_estimators=5),
-            param_distributions={"max_depth": [3, None],
-                                 "max_features": [1, 2, 3, 4],
-                                 "min_samples_split": [2, 3, 4, 5, 6, 7, 8, 9, 10],
-                                 "min_samples_leaf": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
-                                 "bootstrap": [True, False],
-                                 "criterion": ["gini", "entropy"]},
+            param_distributions={
+                "max_depth": [3, None],
+                "max_features": [1, 2, 3, 4],
+                "min_samples_split": [2, 3, 4, 5, 6, 7, 8, 9, 10],
+                "min_samples_leaf": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+                "bootstrap": [True, False], "criterion": ["gini", "entropy"]},
             cv=StratifiedKFold(n_splits=2, random_state=1),
             n_iter=5)
         flow = sklearn_to_flow(model)
@@ -49,3 +50,16 @@ def test_parse_parameters(self):
             if parameter['oml:name'] == 'n_estimators':
                 self.assertEqual(parameter['oml:value'], '5')
                 self.assertEqual(parameter['oml:component'], 2)
+
+    def test_tagging(self):
+        run = openml.runs.get_run(1)
+        tag = "testing_tag_{}_{}".format(self.id(), time())
+        run_list = openml.runs.list_runs(tag=tag)
+        self.assertEqual(len(run_list), 0)
+        run.push_tag(tag)
+        run_list = openml.runs.list_runs(tag=tag)
+        self.assertEqual(len(run_list), 1)
+        self.assertIn(1, run_list)
+        run.remove_tag(tag)
+        run_list = openml.runs.list_runs(tag=tag)
+        self.assertEqual(len(run_list), 0)