requested changes

Author: Matt Sokoloff

labelbox/schema/dataset.py

@@ -1,12 +1,14 @@
+import os
 import json
 import logging
+from itertools import islice
 from multiprocessing.dummy import Pool as ThreadPool
-import os
 
 from labelbox.exceptions import InvalidQueryError, ResourceNotFoundError, InvalidAttributeError
 from labelbox.orm.db_object import DbObject, Updateable, Deletable
 from labelbox.orm.model import Entity, Field, Relationship
 
+logger = logging.getLogger(__name__)
 
 class Dataset(DbObject, Updateable, Deletable):
     """ A Dataset is a collection of DataRows.
@@ -185,7 +187,7 @@ def data_rows_for_external_id(self, external_id, limit=10):
 
         data_rows = self.data_rows(where=where)
         # Get at most `limit` data_rows.
-        data_rows = [row for row, _ in zip(data_rows, range(limit))]
+        data_rows = list(islice(data_rows, limit))
 
         if not len(data_rows):
             raise ResourceNotFoundError(DataRow, where)
@@ -209,7 +211,7 @@ def data_row_for_external_id(self, external_id):
         data_rows = self.data_rows_for_external_id(external_id=external_id,
                                                    limit=2)
         if len(data_rows) > 1:
-            logging.warn(
-                f"More than one data_row has the provided external_id : `{external_id}`. Use function data_rows_for_external_id to fetch all"
+            logger.warning(
+                f"More than one data_row has the provided external_id : `%s`. Use function data_rows_for_external_id to fetch all", external_id
             )
         return data_rows[0]

labelbox/schema/project.py

@@ -200,7 +200,7 @@ def upsert_instructions(self, instructions_file: str):
         frontendId = frontend.uid
 
         if frontend.name != "Editor":
-            logger.warn(
+            logger.warning(
                 f"This function has only been tested to work with the Editor front end. Found %s",
                 frontend.name)
 
@@ -325,7 +325,7 @@ def validate_labeling_parameter_overrides(self, data):
             data_row, priority, num_labels = row
             if not isinstance(data_row, DataRow):
                 raise TypeError(
-                    f"Datarow should be be of type DataRow. Found {type(data_row)}. Index: {idx}"
+                    f"data_row should be be of type DataRow. Found {type(data_row)}. Index: {idx}"
                 )
 
             for name, value in [["Priority", priority],
@@ -358,7 +358,7 @@ def set_labeling_parameter_overrides(self, data):
                         - Minimum priority is 1.
                     * Priority is not the queue position.
                         - The position is determined by the relative priority.
-                        - Eg. [(data_row_1, 5,1), (data_row_2, 2,1), (data_row_3, 10,1)] 
+                        - E.g. [(data_row_1, 5,1), (data_row_2, 2,1), (data_row_3, 10,1)] 
                             will be assigned in the following order: [data_row_2, data_row_1, data_row_3]
                     * Datarows with parameter overrides will appear before datarows without overrides.
                     * The priority only effects items in the queue.

tests/integration/test_labeling_parameter_overrides.py

@@ -50,7 +50,7 @@ def test_labeling_parameter_overrides(project, rand_gen):
         data = [(data_rows[12].uid, 1, 3)]
         project.set_labeling_parameter_overrides(data)
     assert str(exc_info.value) == \
-        "Datarow should be be of type DataRow. Found <class 'str'>. Index: 0"
+        "data_row should be be of type DataRow. Found <class 'str'>. Index: 0"
 
     with pytest.raises(ValueError) as exc_info:
         data = [(data_rows[12], 0, 3)]