parses api errors with correct message

Author: janvanrijn

openml/_api_calls.py

@@ -3,9 +3,10 @@
 import requests
 import arff
 import warnings
+import xmltodict
 
 from . import config
-from .exceptions import OpenMLServerError
+from .exceptions import OpenMLServerError, OpenMLServerException
 
 
 def _perform_api_call(call, data=None, file_dictionary=None,
@@ -80,7 +81,7 @@ def _read_url_files(url, data=None, file_dictionary=None, file_elements=None):
     # 'gzip,deflate'
     response = requests.post(url, data=data, files=file_elements)
     if response.status_code != 200:
-        raise OpenMLServerError(('Status code: %d\n' % response.status_code) + response.text)
+        raise _parse_server_exception(response)
     if 'Content-Encoding' not in response.headers or \
             response.headers['Content-Encoding'] != 'gzip':
         warnings.warn('Received uncompressed content from OpenML for %s.' % url)
@@ -97,8 +98,23 @@ def _read_url(url, data=None):
     response = requests.post(url, data=data)
 
     if response.status_code != 200:
-        raise OpenMLServerError(('Status code: %d\n' % response.status_code) + response.text)
+        raise _parse_server_exception(response)
     if 'Content-Encoding' not in response.headers or \
             response.headers['Content-Encoding'] != 'gzip':
         warnings.warn('Received uncompressed content from OpenML for %s.' % url)
     return response.text
+
+def _parse_server_exception(response):
+    # OpenML has a sopisticated error system
+    # where information about failures is provided. try to parse this
+    try:
+        server_exception = xmltodict.parse(response.text)
+    except:
+        raise OpenMLServerError(('Status code: %d\n' % response.status_code) + response.text)
+
+    code = int(server_exception['oml:error']['oml:code'])
+    message = server_exception['oml:error']['oml:message']
+    additional = None
+    if 'oml:additional_information' in server_exception['oml:error']:
+        additional = server_exception['oml:error']['oml:additional_information']
+    return OpenMLServerException(code, message, additional)

openml/exceptions.py

@@ -2,13 +2,22 @@ class PyOpenMLError(Exception):
     def __init__(self, message):
         super(PyOpenMLError, self).__init__(message)
 
-
+# class for when something is really wrong on the server (result did not parse to dict)
 class OpenMLServerError(PyOpenMLError):
-    """Server didn't respond 200."""
+    """Server didn't respond 200, contains unparsed error."""
     def __init__(self, message):
         message = "OpenML Server error: " + message
         super(OpenMLServerError, self).__init__(message)
 
+# class for when the result of the server was not 200 (e.g., listing call w/o results)
+class OpenMLServerException(OpenMLServerError):
+    """Server didn't respond 200."""
+    def __init__(self, code, message, additional=None):
+        self.code = code
+        self.additional = additional
+        message = "OpenML Server exception: " + message
+        super(OpenMLServerException, self).__init__(message)
+
 
 class OpenMLCacheException(PyOpenMLError):
     """Dataset / task etc not found in cache"""

openml/runs/functions.py

@@ -10,7 +10,7 @@
 from .. import config
 from ..flows import sklearn_to_flow, get_flow
 from ..setups import setup_exists
-from ..exceptions import OpenMLCacheException
+from ..exceptions import OpenMLCacheException, OpenMLServerException
 from ..util import URLError
 from ..tasks.functions import _create_task_from_xml
 from .._api_calls import _perform_api_call
@@ -89,13 +89,19 @@ def _run_exists(task_id, setup_id):
         # openml setups are in range 1-inf
         return False
 
-    result = list_runs(task=[task_id], setup=[setup_id])
-    if len(result) > 0:
-        return set(result.keys())
-    else:
+    try:
+        result = list_runs(task=[task_id], setup=[setup_id])
+        if len(result) > 0:
+            return set(result.keys())
+        else:
+            return False
+    except OpenMLServerException as exception:
+        # error code 512 implies no results. This means the run does not exist yet
+        assert(exception.code == 512)
         return False
 
 
+
 def _prediction_to_row(rep_no, fold_no, row_id, correct_label, predicted_label, predicted_probabilities, class_labels, model_classes_mapping):
     """Complicated util function that turns probability estimates of a classifier for a given instance into the right arff format to upload to openml.
 

openml/testing.py

@@ -45,6 +45,7 @@ def setUp(self):
         self.production_server = openml.config.server
         self.test_server = "https://test.openml.org/api/v1/xml"
         openml.config.server = self.test_server
+        openml.config.avoid_duplicate_runs = False
 
         openml.config.set_cache_directory(self.workdir)