Merge pull request #707 from Labelbox/develop

3.27.1

Author: kkim-labelbox

CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+# Version 3.27.1 (2022-09-16)
+### Changed
+* Removed `client.get_data_rows_for_global_keys` until further notice
+
 # Version 3.27.0 (2022-09-12)
 ### Added
 * Global Keys for data rows

CONTRIB.md

@@ -25,6 +25,14 @@ following packages/modules:
 * Approved PRs are merged to the `develop` branch.
 * The `develop` branch is merged to `master` on each release.
 
+## Commits
+
+Before making a commit, to automatically adhere to our formatting standards,
+install and activate [pre-commit](https://pre-commit.com/)
+
+After the above, running `git commit ...` will attempt to fix formatting. If
+there was formatted needed, you will need to re-add and re-commit before pushing.
+
 ## Testing
 
 Currently, the SDK functionality is tested using integration tests. These tests
@@ -36,7 +44,8 @@ To execute tests you will need to provide an API key for the server you're using
 for testing (staging by default) in the `LABELBOX_TEST_API_KEY` environment
 variable. For more info see [Labelbox API key docs](https://labelbox.helpdocs.io/docs/api/getting-started).
 
-To pass tests, code must be formatted using the following command:
+To pass tests, code must be formatted. If pre-commit was not installed, 
+you will need to use the following command:
 
 ```shell
 yapf tests labelbox -i --verbose --recursive --parallel --style "google"
@@ -54,4 +63,4 @@ Each release should follow the following steps:
 6. This will kick off a Github Actions workflow that will:
   - Build the library in the [standard way](https://packaging.python.org/tutorials/packaging-projects/#generating-distribution-archives)
   - Upload the distribution archives in the [standard way](https://packaging.python.org/tutorials/packaging-projects/#uploading-the-distribution-archives)
-  with credentials for the `labelbox` PyPI user.
+  with credentials for the `labelbox` PyPI user.

docs/source/conf.py

@@ -21,7 +21,7 @@
 copyright = '2021, Labelbox'
 author = 'Labelbox'
 
-release = '3.27.0'
+release = '3.27.1'
 
 # -- General configuration ---------------------------------------------------
 

examples/basics/basics.ipynb

@@ -43,7 +43,7 @@
     "The quick version is basically just\n",
     "1. `!pip install labelbox`\n",
     "2. `export LABELBOX_API_KEY=\"<your_api_key>\"`\n",
-    "* Get this from the UI under (Account -> API -> Create API Key)\n",
+    "* Get this from the UI under (Workspace settings -> API -> Create API Key)\n",
     "* You can also set the api_key below in the notebook.\n",
     "\n",
     "This only works for cloud deployments.\n",

examples/basics/batches.ipynb

@@ -239,7 +239,7 @@
    },
    "outputs": [],
    "source": [
-    "sample = random.sample(data_rows, 5)"
+    "sample = random.sample(data_row_ids, 5)"
    ]
   },
   {

labelbox/__init__.py

@@ -1,5 +1,5 @@
 name = "labelbox"
-__version__ = "3.27.0"
+__version__ = "3.27.1"
 
 from labelbox.client import Client
 from labelbox.schema.project import Project

labelbox/client.py

@@ -1192,45 +1192,3 @@ def _format_failed_rows(rows: List[str],
                     "Timed out waiting for get_data_rows_for_global_keys job to complete."
                 )
             time.sleep(sleep_time)
-
-    def get_data_rows_for_global_keys(
-            self,
-            global_keys: List[str],
-            timeout_seconds=60) -> Dict[str, Union[str, List[Any]]]:
-        """
-        Gets data rows for a list of global keys.
-
-        Args:
-            A list of global keys
-        Returns:
-            Dictionary containing 'status', 'results' and 'errors'.
-
-            'Status' contains the outcome of this job. It can be one of
-            'Success', 'Partial Success', or 'Failure'.
-
-            'Results' contains a list of `DataRow` instances successfully fetchced. It may
-            not necessarily contain all data rows requested.
-
-            'Errors' contains a list of global_keys that could not be fetched, along
-            with the failure reason
-        Examples:
-            >>> job_result = client.get_data_rows_for_global_keys(["key1","key2"])
-            >>> print(job_result['status'])
-            Partial Success
-            >>> print(job_result['results'])
-            [<DataRow ID: cl7tvvybc00icka6ggipyh8tj>, <DataRow ID: cl7tvvyfp00igka6gblrw2idc>]
-            >>> print(job_result['errors'])
-            [{'global_key': 'asdf', 'error': 'Data Row not found'}]
-        """
-        job_result = self.get_data_row_ids_for_global_keys(
-            global_keys, timeout_seconds)
-
-        # Query for data row by data_row_id to ensure we get all fields populated in DataRow instances
-        data_rows = []
-        for data_row_id in job_result['results']:
-            # TODO: Need to optimize this to run over a collection of data_row_ids
-            data_rows.append(self.get_data_row(data_row_id))
-
-        job_result['results'] = data_rows
-
-        return job_result

labelbox/schema/model_run.py

@@ -132,49 +132,83 @@ def upsert_predictions_and_send_to_project(
         project_id: str,
         priority: Optional[int] = 5,
     ) -> 'MEAPredictionImport':  # type: ignore
-        """ Upload predictions and create a batch import to project.
+        """
+        Provides a convenient way to execute the following steps in a single function call:
+            1. Upload predictions to a Model
+            2. Create a batch from data rows that had predictions assocated with them
+            3. Attach the batch to a project
+            4. Add those same predictions to the project as MAL annotations
+
+        Note that partial successes are possible.
+        If it is important that all stages are successful then check the status of each individual task
+        with task.errors. E.g.
+
+        >>>    mea_import_job, batch, mal_import_job = upsert_predictions_and_send_to_project(name, predictions, project_id)
+        >>>    # handle mea import job successfully created (check for job failure or partial failures)
+        >>>    print(mea_import_job.status, mea_import_job.errors)
+        >>>    if batch is None:
+        >>>        # Handle batch creation failure
+        >>>    if mal_import_job is None:
+        >>>        # Handle mal_import_job creation failure
+        >>>    else:
+        >>>        # handle mal import job successfully created (check for job failure or partial failures)
+        >>>        print(mal_import_job.status, mal_import_job.errors)
+
+
         Args:
             name (str): name of the AnnotationImport job as well as the name of the batch import
             predictions (Iterable):
                 iterable of annotation rows
             project_id (str): id of the project to import into
             priority (int): priority of the job
         Returns:
-            (MEAPredictionImport, Batch, MEAToMALPredictionImport)
+            Tuple[MEAPredictionImport, Batch, MEAToMALPredictionImport]
+            If any of these steps fail the return value will be None.
+
         """
         kwargs = dict(client=self.client, model_run_id=self.uid, name=name)
         project = self.client.get_project(project_id)
         import_job = self.add_predictions(name, predictions)
         prediction_statuses = import_job.statuses
-        mea_to_mal_data_rows_set = set([
-            row['dataRow']['id']
-            for row in prediction_statuses
-            if row['status'] == 'SUCCESS'
-        ])
         mea_to_mal_data_rows = list(
-            mea_to_mal_data_rows_set)[:DATAROWS_IMPORT_LIMIT]
-
-        if len(mea_to_mal_data_rows) >= DATAROWS_IMPORT_LIMIT:
+            set([
+                row['dataRow']['id']
+                for row in prediction_statuses
+                if row['status'] == 'SUCCESS'
+            ]))
+
+        if not mea_to_mal_data_rows:
+            # 0 successful model predictions imported
+            return import_job, None, None
 
+        elif len(mea_to_mal_data_rows) >= DATAROWS_IMPORT_LIMIT:
+            mea_to_mal_data_rows = mea_to_mal_data_rows[:DATAROWS_IMPORT_LIMIT]
             logger.warning(
-                f"Got {len(mea_to_mal_data_rows_set)} data rows to import, trimmed down to {DATAROWS_IMPORT_LIMIT} data rows"
+                f"Exeeded max data row limit {len(mea_to_mal_data_rows)}, trimmed down to {DATAROWS_IMPORT_LIMIT} data rows."
             )
-        if len(mea_to_mal_data_rows) == 0:
-            return import_job, None, None
 
         try:
             batch = project.create_batch(name, mea_to_mal_data_rows, priority)
-            try:
-                mal_prediction_import = Entity.MEAToMALPredictionImport.create_for_model_run_data_rows(
-                    data_row_ids=mea_to_mal_data_rows,
-                    project_id=project_id,
-                    **kwargs)
-                return import_job, batch, mal_prediction_import
-            except:
-                return import_job, batch, None
-        except:
+        except Exception as e:
+            logger.warning(f"Failed to create batch. Messsage : {e}.")
+            # Unable to create batch
             return import_job, None, None
 
+        try:
+            mal_prediction_import = Entity.MEAToMALPredictionImport.create_for_model_run_data_rows(
+                data_row_ids=mea_to_mal_data_rows,
+                project_id=project_id,
+                **kwargs)
+            mal_prediction_import.wait_until_done()
+        except Exception as e:
+            logger.warning(
+                f"Failed to create MEA to MAL prediction import. Message : {e}."
+            )
+            # Unable to create mea to mal prediction import
+            return import_job, batch, None
+
+        return import_job, batch, mal_prediction_import
+
     def add_predictions(
         self,
         name: str,

tests/integration/test_global_keys.py

@@ -147,6 +147,8 @@ def test_global_key_with_whitespaces_validation(client, dataset, image_url):
         ['Invalid global key', 'Invalid global key', 'Invalid global key'])
 
 
+@pytest.mark.skip(reason='get_data_rows_for_global_keys not included in '
+                  'the initial release of global_keys')
 def test_get_data_rows_for_global_keys(client, dataset, image_url):
     gk_1 = str(uuid.uuid4())
     gk_2 = str(uuid.uuid4())
@@ -174,6 +176,8 @@ def test_get_data_rows_for_global_keys(client, dataset, image_url):
     assert res['results'] == [dr_1, dr_2]
 
 
+@pytest.mark.skip(reason='get_data_rows_for_global_keys not included in '
+                  'the initial release of global_keys')
 def test_get_data_rows_for_invalid_global_keys(client, dataset, image_url):
     gk_1 = str(uuid.uuid4())
     gk_2 = str(uuid.uuid4())