[QQC-2944] Remove deprecated project.datasets and dataset.projects methods (#1295)

richardsun0713 · web-flow · commit 8392dae2f226 · 2023-12-04T18:02:21.000-08:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,9 @@
 # Changelog
 
+# Version TBD (Date TBD)
+## Removed
+* Project.datasets and Datasets.projects methods as they have been deprecated
+
 # Version 3.57.0 (2023-11-30)
 ## Added
 * Global key support for Project move_data_rows_to_task_queue
diff --git a/examples/basics/basics.ipynb b/examples/basics/basics.ipynb
@@ -315,8 +315,6 @@
     {
       "metadata": {},
       "source": [
-        "# Since the project we created only has batches, we can't query for datasets. \n",
-        "# sample_project_datasets = project.datasets() --> Run if project is in dataset mode\n",
         "sample_project_batches = project.batches()\n",
         "\n",
         "list(sample_project_batches)\n",
diff --git a/examples/basics/datasets.ipynb b/examples/basics/datasets.ipynb
@@ -138,17 +138,6 @@
       "outputs": [],
       "execution_count": null
     },
-    {
-      "metadata": {},
-      "source": [
-        "# Attached projects\n",
-        "print(\"Projects with this dataset attached :\", list(dataset.projects()))\n",
-        "print(\"Dataset name :\", dataset.name)"
-      ],
-      "cell_type": "code",
-      "outputs": [],
-      "execution_count": null
-    },
     {
       "metadata": {},
       "source": [
diff --git a/examples/integrations/detectron2/coco_object.ipynb b/examples/integrations/detectron2/coco_object.ipynb
@@ -550,7 +550,7 @@
         "    client.get_labeling_frontends(where=lb.LabelingFrontend.name == 'editor'))\n",
         "project.setup(editor, labels_mal.get_ontology().asdict())\n",
         "project.enable_model_assisted_labeling()\n",
-        "project.datasets.connect(dataset)"
+        "project.create_batches_from_dataset(\"batch\", dataset.uid)"
       ],
       "cell_type": "code",
       "outputs": [],
@@ -583,4 +583,4 @@
       "execution_count": null
     }
   ]
-}
+}
diff --git a/examples/integrations/detectron2/coco_panoptic.ipynb b/examples/integrations/detectron2/coco_panoptic.ipynb
@@ -1014,7 +1014,7 @@
         "    for future in tqdm(as_completed(futures)):\n",
         "        labels.append(future.result())\n",
         "\n",
-	"labels_mea = lb_types.LabelGenerator(labels)\n",
+        "labels_mea = lb_types.LabelGenerator(labels)\n",
         "labels_mea.add_url_to_masks(signer) \\\n",
         "      .add_url_to_data(signer) "
       ],
@@ -1317,7 +1317,7 @@
         "    client.get_labeling_frontends(where=lb.LabelingFrontend.name == 'editor'))\n",
         "project.setup(editor, labels_mal.get_ontology().asdict())\n",
         "project.enable_model_assisted_labeling()\n",
-        "project.datasets.connect(dataset)\n"
+        "project.create_batches_from_dataset(\"batch\", dataset.uid)"
       ],
       "cell_type": "code",
       "outputs": [],
@@ -1366,4 +1366,4 @@
       "execution_count": null
     }
   ]
-}
+}
diff --git a/examples/integrations/tlt/labelbox_upload.ipynb b/examples/integrations/tlt/labelbox_upload.ipynb
@@ -228,8 +228,8 @@
       "source": [
         "project = client.create_project(name = \"animal_demo_proj\", media_type=lb.MediaType.Image)\n",
         "dataset = client.create_dataset(name = \"animal_demo_ds\")\n",
-        "project.datasets.connect(dataset)\n",
         "dataset.create_data_rows(image_paths)\n",
+        "project.create_batches_from_dataset(\"batch\", dataset.uid)\n",
         "project.enable_model_assisted_labeling()"
       ],
       "cell_type": "code",
@@ -272,7 +272,9 @@
     {
       "metadata": {},
       "source": [
-        "datarows = [dr for dr in list(project.datasets())[0].data_rows()]"
+        "datarows = []\n",
+        "for batch in list(project.batches()):\n",
+        "    datarows.extend(list(batch.export_data_rows()))"
       ],
       "cell_type": "code",
       "outputs": [],
diff --git a/examples/model_diagnostics/custom_metrics_demo.ipynb b/examples/model_diagnostics/custom_metrics_demo.ipynb
@@ -334,7 +334,7 @@
         "\n",
         "dataset = client.create_dataset(name=\"Mapillary Diagnostics Demo\")\n",
         "print(f\"Dataset Created: {dataset.uid}\")\n",
-        "project.datasets.connect(dataset)"
+        "project.create_batches_from_dataset(\"batch\", dataset.uid)"
       ],
       "cell_type": "code",
       "outputs": [],
@@ -580,4 +580,4 @@
       "execution_count": null
     }
   ]
-}
+}
diff --git a/examples/model_diagnostics/model_diagnostics_demo.ipynb b/examples/model_diagnostics/model_diagnostics_demo.ipynb
@@ -345,7 +345,7 @@
         "\n",
         "dataset = client.create_dataset(name=\"Mapillary Diagnostics Demo\")\n",
         "print(f\"Dataset Created: {dataset.uid}\")\n",
-        "project.datasets.connect(dataset)"
+        "project.create_batches_from_dataset(\"batch\", dataset.uid)"
       ],
       "cell_type": "code",
       "outputs": [],
@@ -549,4 +549,4 @@
       "execution_count": null
     }
   ]
-}
+}
diff --git a/labelbox/schema/dataset.py b/labelbox/schema/dataset.py
@@ -44,7 +44,6 @@ class Dataset(DbObject, Updateable, Deletable):
         created_at (datetime)
         row_count (int): The number of rows in the dataset. Fetch the dataset again to update since this is cached.
 
-        projects (Relationship): `ToMany` relationship to Project
         created_by (Relationship): `ToOne` relationship to User
         organization (Relationship): `ToOne` relationship to Organization
 
@@ -56,12 +55,6 @@ class Dataset(DbObject, Updateable, Deletable):
     row_count = Field.Int("row_count")
 
     # Relationships
-    projects = Relationship.ToMany(
-        "Project",
-        True,
-        deprecation_warning=
-        "This method does not return any data for batch-based projects and it will be deprecated on or around November 1, 2023."
-    )
     created_by = Relationship.ToOne("User", False, "created_by")
     organization = Relationship.ToOne("Organization", False)
     iam_integration = Relationship.ToOne("IAMIntegration", False,
diff --git a/labelbox/schema/project.py b/labelbox/schema/project.py
@@ -61,7 +61,6 @@ class Project(DbObject, Updateable, Deletable):
         auto_audit_number_of_labels (int)
         auto_audit_percentage (float)
 
-        datasets (Relationship): `ToMany` relationship to Dataset
         created_by (Relationship): `ToOne` relationship to User
         organization (Relationship): `ToOne` relationship to Organization
         labeling_frontend (Relationship): `ToOne` relationship to LabelingFrontend
@@ -86,12 +85,6 @@ class Project(DbObject, Updateable, Deletable):
     media_type = Field.Enum(MediaType, "media_type", "allowedMediaType")
 
     # Relationships
-    datasets = Relationship.ToMany(
-        "Dataset",
-        True,
-        deprecation_warning=
-        "This method does not return any data for batch-based projects and it will be deprecated on or around November 1, 2023."
-    )
     created_by = Relationship.ToOne("User", False, "created_by")
     organization = Relationship.ToOne("Organization", False)
     labeling_frontend = Relationship.ToOne("LabelingFrontend")
diff --git a/tests/integration/test_client_errors.py b/tests/integration/test_client_errors.py
@@ -77,17 +77,10 @@ def test_network_error(client):
         client.create_project(name="Project name")
 
 
-@pytest.fixture
-def project_for_test_invalid_attribute_error(client):
-    project = client.create_project(name="Project name")
-    yield project
-    project.delete()
-
-
-def test_invalid_attribute_error(client, rand_gen,
-                                 project_for_test_invalid_attribute_error):
-    project = project_for_test_invalid_attribute_error
-
+def test_invalid_attribute_error(
+    client,
+    rand_gen,
+):
     # Creation
     with pytest.raises(labelbox.exceptions.InvalidAttributeError) as excinfo:
         client.create_project(name="Name", invalid_field="Whatever")
@@ -101,18 +94,6 @@ def test_invalid_attribute_error(client, rand_gen,
     assert excinfo.value.db_object_type == Project
     assert excinfo.value.field == "invalid_field"
 
-    # Relationship expansion filtering
-    with pytest.raises(labelbox.exceptions.InvalidAttributeError) as excinfo:
-        project.datasets(where=User.email == "email")
-    assert excinfo.value.db_object_type == Dataset
-    assert excinfo.value.field == {User.email}
-
-    # Relationship order-by
-    with pytest.raises(labelbox.exceptions.InvalidAttributeError) as excinfo:
-        project.datasets(order_by=User.email.asc)
-    assert excinfo.value.db_object_type == Dataset
-    assert excinfo.value.field == {User.email}
-
     # Top-level-fetch
     with pytest.raises(labelbox.exceptions.InvalidAttributeError) as excinfo:
         client.get_projects(where=User.email == "email")
@@ -129,9 +110,9 @@ def get(arg):
         except labelbox.exceptions.ApiLimitError as e:
             return e
 
-    #Rate limited at 1500 + buffer
+    # Rate limited at 1500 + buffer
     n = 1600
-    #max of 30 concurrency before the service becomes unavailable
+    # max of 30 concurrency before the service becomes unavailable
     with Pool(30) as pool:
         start = time.time()
         results = list(pool.imap(get, range(n)), total=n)
diff --git a/tests/integration/test_legacy_project.py b/tests/integration/test_legacy_project.py
@@ -15,11 +15,6 @@ def test_project_dataset(client, rand_gen):
         )
 
 
-def test_legacy_project_dataset_relationships(project, dataset):
-    assert [ds for ds in project.datasets()] == []
-    assert [p for p in dataset.projects()] == []
-
-
 def test_project_auto_audit_parameters(client, rand_gen):
     with pytest.raises(
             ValueError,
diff --git a/tests/integration/test_sorting.py b/tests/integration/test_sorting.py
@@ -1,44 +1,6 @@
 import pytest
 
 from labelbox import Project
-from labelbox.schema.media_type import MediaType
-from labelbox.schema.queue_mode import QueueMode
-
-
-@pytest.mark.xfail(reason="Relationship sorting not implemented correctly "
-                   "on the server-side")
-def test_relationship_sorting(client):
-    a = client.create_project(name="a",
-                              description="b",
-                              queue_mode=QueueMode.Batch,
-                              media_type=MediaType.Image)
-    b = client.create_project(name="b",
-                              description="c",
-                              queue_mode=QueueMode.Batch,
-                              media_type=MediaType.Image)
-    c = client.create_project(name="c",
-                              description="a",
-                              queue_mode=QueueMode.Batch,
-                              media_type=MediaType.Image)
-
-    dataset = client.create_dataset(name="Dataset")
-    a.datasets.connect(dataset)
-    b.datasets.connect(dataset)
-    c.datasets.connect(dataset)
-
-    def get(order_by):
-        where = Project.created_at >= a.created_at
-        return list(dataset.projects(where=where, order_by=order_by))
-
-    assert get(Project.name.asc) == [a, b, c]
-    assert get(Project.name.desc) == [c, b, a]
-    assert get(Project.description.asc) == [c, a, b]
-    assert get(Project.description.desc) == [b, a, c]
-
-    dataset.delete()
-    a.delete()
-    b.delete()
-    c.delete()
 
 
 @pytest.mark.xfail(reason="Sorting not supported on top-level fetches")

Original file line number	Diff line number	Diff line change
`@@ -315,8 +315,6 @@`
`315`	`315`	`{`
`316`	`316`	`"metadata": {},`
`317`	`317`	`"source": [`
`318`		`- "# Since the project we created only has batches, we can't query for datasets. \n",`
`319`		`- "# sample_project_datasets = project.datasets() --> Run if project is in dataset mode\n",`
`320`	`318`	`"sample_project_batches = project.batches()\n",`
`321`	`319`	`"\n",`
`322`	`320`	`"list(sample_project_batches)\n",`
Original file line number	Diff line number	Diff line change
`@@ -550,7 +550,7 @@`
`550`	`550`	`" client.get_labeling_frontends(where=lb.LabelingFrontend.name == 'editor'))\n",`
`551`	`551`	`"project.setup(editor, labels_mal.get_ontology().asdict())\n",`
`552`	`552`	`"project.enable_model_assisted_labeling()\n",`
`553`		`- "project.datasets.connect(dataset)"`
	`553`	`+ "project.create_batches_from_dataset(\"batch\", dataset.uid)"`
`554`	`554`	`],`
`555`	`555`	`"cell_type": "code",`
`556`	`556`	`"outputs": [],`
`@@ -583,4 +583,4 @@`
`583`	`583`	`"execution_count": null`
`584`	`584`	`}`
`585`	`585`	`]`
`586`		`-}`
	`586`	`+}`
Original file line number	Diff line number	Diff line change
`@@ -334,7 +334,7 @@`
`334`	`334`	`"\n",`
`335`	`335`	`"dataset = client.create_dataset(name=\"Mapillary Diagnostics Demo\")\n",`
`336`	`336`	`"print(f\"Dataset Created: {dataset.uid}\")\n",`
`337`		`- "project.datasets.connect(dataset)"`
	`337`	`+ "project.create_batches_from_dataset(\"batch\", dataset.uid)"`
`338`	`338`	`],`
`339`	`339`	`"cell_type": "code",`
`340`	`340`	`"outputs": [],`
`@@ -580,4 +580,4 @@`
`580`	`580`	`"execution_count": null`
`581`	`581`	`}`
`582`	`582`	`]`
`583`		`-}`
	`583`	`+}`
Original file line number	Diff line number	Diff line change
`@@ -345,7 +345,7 @@`
`345`	`345`	`"\n",`
`346`	`346`	`"dataset = client.create_dataset(name=\"Mapillary Diagnostics Demo\")\n",`
`347`	`347`	`"print(f\"Dataset Created: {dataset.uid}\")\n",`
`348`		`- "project.datasets.connect(dataset)"`
	`348`	`+ "project.create_batches_from_dataset(\"batch\", dataset.uid)"`
`349`	`349`	`],`
`350`	`350`	`"cell_type": "code",`
`351`	`351`	`"outputs": [],`
`@@ -549,4 +549,4 @@`
`549`	`549`	`"execution_count": null`
`550`	`550`	`}`
`551`	`551`	`]`
`552`		`-}`
	`552`	`+}`