Merge pull request #821 from Labelbox/develop

3.34.0

Author: msokoloff1

CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+# Version 3.34.0 (2022-12-22)
+### Added
+* Added `get_by_name()` method to MetadataOntology object to access both custom and reserved metadata by name.
+* Added support for adding metadata by name when creating datarows using `DataRowMetadataOntology.bulk_upsert()`.
+* Added support for adding metadata by name when creating datarows using `Dataset.create_data_rows()`, `Dataset.create_data_rows_sync()`, and `Dataset.create_data_row()`.
+* Example notebooks for auto metrics in models
+
+
+### Changed
+* `Dataset.create_data_rows()` max limit of DataRows increased to 150,000
+* Improved error handling for invalid annotation import content
+* String metadata can now be 1024 characters long (from 500)
+
+## Fixed
+* Broken urls in detectron notebook
+
 # Version 3.33.1 (2022-12-14)
 ### Fixed
 * Fixed where batch creation limit was still limiting # of data rows. SDK should now support creating batches with up to 100k data rows

docs/source/conf.py

@@ -21,7 +21,7 @@
 copyright = '2021, Labelbox'
 author = 'Labelbox'
 
-release = '3.33.1'
+release = '3.34.0'
 
 # -- General configuration ---------------------------------------------------
 

examples/README.md

@@ -74,6 +74,16 @@ Learn more about annotation types in the [docs](https://docs.labelbox.com/docs/a
 | Webhooks           | [Github](project_configuration/webhooks.ipynb)   | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Labelbox/labelbox-python/blob/develop/examples/project_configuration/webhooks.ipynb) | [Docs](https://docs.labelbox.com/docs/webhooks) |
 
 
+## [Prediction Upload to a Model Run](prediction_upload)
+
+
+| Notebook                    | Github                            | Google Colab | Learn more |
+| --------------------------- | --------------------------------- | ------------ | ---------- |
+| Image Prediction upload                    | [Github](prediction_upload/image_predictions.ipynb)             | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Labelbox/labelbox-python/blob/develop/examples/prediction_upload/image_predictions.ipynb) |  [Docs](https://docs.labelbox.com/docs/upload-model_predictions) |
+| Text Prediction upload | [Github](prediction_upload/text_predictions.ipynb)               | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Labelbox/labelbox-python/blob/develop/examples/prediction_upload/text_predictions.ipynb) | [Docs](https://docs.labelbox.com/docs/upload-model_predictions) |
+
+------
+
 
 ## [Model Diagnostics](model_diagnostics)
 | Notebook                    | Github                            | Google Colab | Learn more |

examples/annotation_import/conversational.ipynb

@@ -205,7 +205,7 @@
    "outputs": [],
    "source": [
     "# Create Labelbox project\n",
-    "mal_project = client.create_project(name=\"conversational_mal_project\", media_type=MediaType.Document)\n",
+    "mal_project = client.create_project(name=\"conversational_mal_project\", media_type=MediaType.Conversational)\n",
     "\n",
     "# Create one Labelbox dataset\n",
     "dataset = client.create_dataset(name=\"conversational_annotation_import_demo_dataset\")\n",
@@ -220,7 +220,8 @@
     "editor = next(client.get_labeling_frontends(where=LabelingFrontend.name == \"Editor\")) # Unless using a custom editor, do not modify this\n",
     "\n",
     "mal_project.setup(editor, ontology_builder.asdict()) # Connect your ontology and editor to your MAL project\n",
-    "mal_project.datasets.connect(dataset) # Connect your dataset to your MAL project"
+    "\n",
+    "mal_project.create_batch('initial-batch', [data_row]) # Create a batch to start labelling"
    ]
   },
   {

examples/basics/data_row_metadata.ipynb

@@ -39,7 +39,7 @@
       "source": [
         "# Data Row Metadata\n",
         "\n",
-        "Metadata is useful to be better understand data on the platform to help with labeling review, model diagnostics, and data selection. This **should not be confused with attachments**. Attachments provide additional context for labelers but is not searchable within Catalog."
+        "Metadata is useful to better understand data on the platform to help with labeling review, model diagnostics, and data selection. This **should not be confused with attachments**. Attachments provide additional context for labelers but is not searchable within Catalog."
       ]
     },
     {
@@ -261,21 +261,20 @@
       "source": [
         "# Construct a metadata field of string kind\n",
         "tag_metadata_field = DataRowMetadataField(\n",
-        "    schema_id=mdo.reserved_by_name[\"tag\"].uid,  # specify the schema id\n",
+        "    name=\"tag\",  # specify the schema name\n",
         "    value=\"tag_string\", # typed inputs\n",
         ")\n",
         "\n",
         "# Construct an metadata field of datetime kind\n",
         "capture_datetime_field = DataRowMetadataField(\n",
-        "    schema_id=mdo.reserved_by_name[\"captureDateTime\"].uid,  # specify the schema id\n",
+        "    name=\"captureDateTime\",  # specify the schema id\n",
         "    value=datetime.utcnow(), # typed inputs\n",
         ")\n",
         "\n",
         "# Construct a metadata field of Enums options\n",
-        "train_schema = mdo.reserved_by_name[\"split\"][\"train\"]\n",
         "split_metadta_field = DataRowMetadataField(\n",
-        "    schema_id=train_schema.parent,  # specify the schema id\n",
-        "    value=train_schema.uid, # typed inputs\n",
+        "    name=\"split\",  # specify the schema id\n",
+        "    value=\"train\", # typed inputs\n",
         ")"
       ]
     },
@@ -300,20 +299,20 @@
       "source": [
         "# Construct a dictionary of string metadata\n",
         "tag_metadata_field_dict = {\n",
-        "    \"schema_id\": mdo.reserved_by_name[\"tag\"].uid,\n",
+        "    \"name\": \"tag\",\n",
         "    \"value\": \"tag_string\",\n",
         "}\n",
         "\n",
         "# Construct a dictionary of datetime metadata\n",
         "capture_datetime_field_dict = {\n",
-        "    \"schema_id\": mdo.reserved_by_name[\"captureDateTime\"].uid,\n",
+        "    \"name\": \"captureDateTime\",\n",
         "    \"value\": datetime.utcnow(),\n",
         "}\n",
         "\n",
         "# Construct a dictionary of Enums options metadata\n",
         "split_metadta_field_dict = {\n",
-        "    \"schema_id\": mdo.reserved_by_name[\"split\"][\"train\"].parent,\n",
-        "    \"value\": mdo.reserved_by_name[\"split\"][\"train\"].uid,\n",
+        "    \"name\": \"split\",\n",
+        "    \"value\": \"train\",\n",
         "}"
       ]
     },
@@ -491,7 +490,7 @@
       "outputs": [],
       "source": [
         "# Select a dataset to use, or you can just use the 1-image dataset created above. \n",
-        "dataset_id = \"cl3ntfr7j7cmh07bmeqz3gfjt\"\n",
+        "dataset_id = dataset.uid\n",
         "dataset = client.get_dataset(dataset_id)"
       ]
     },
@@ -541,11 +540,11 @@
         "    # assign datarows a split\n",
         "    rnd = random.random()\n",
         "    if rnd < test:\n",
-        "        split = mdo.reserved_by_name[\"split\"][\"test\"]\n",
+        "        split = \"test\"\n",
         "    elif rnd < valid:\n",
-        "        split = mdo.reserved_by_name[\"split\"][\"valid\"]\n",
+        "        split = \"valid\"\n",
         "    else:\n",
-        "        split = mdo.reserved_by_name[\"split\"][\"train\"]\n",
+        "        split = \"train\"\n",
         "\n",
         "    embeddings.append(\n",
         "        list(model(processor(response.content), training=False)[0].numpy()))\n",
@@ -557,12 +556,11 @@
         "            data_row_id=datarow.uid,\n",
         "            fields=[\n",
         "                DataRowMetadataField(\n",
-        "                    schema_id=mdo.reserved_by_name[\"captureDateTime\"].uid,\n",
+        "                    name=\"captureDateTime\",\n",
         "                    value=dt,\n",
         "                ),\n",
-        "                DataRowMetadataField(schema_id=split.parent, value=split.uid),\n",
-        "                DataRowMetadataField(schema_id=mdo.reserved_by_name[\"tag\"].uid,\n",
-        "                                     value=message),\n",
+        "                DataRowMetadataField(name=\"split\", value=split),\n",
+        "                DataRowMetadataField(name=\"tag\", value=message),\n",
         "            ]))"
       ]
     },
@@ -620,7 +618,7 @@
         "for md, embd in zip(uploads, projected):\n",
         "    md.fields.append(\n",
         "        DataRowMetadataField(\n",
-        "            schema_id=mdo.reserved_by_name[\"embedding\"].uid,\n",
+        "            name=\"embedding\",\n",
         "            value=embd.tolist(),  # convert from numpy to list\n",
         "        ),)"
       ]
@@ -801,4 +799,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 5
-}
+}

examples/integrations/detectron2/coco_object.ipynb

@@ -97,7 +97,7 @@
     "                torchvision \\\n",
     "                git+https://github.com/cocodataset/panopticapi.git \\\n",
     "                'git+https://github.com/facebookresearch/detectron2.git'           \n",
-    "!pip install -q \"git+https://github.com/Labelbox/labelbox-python@ms/coco#egg=labelbox[data]\""
+    "!pip install -q \"labelbox[data]\""
    ]
   },
   {
@@ -156,7 +156,7 @@
     ")\n",
     "\n",
     "with open('./coco_utils.py', 'w' ) as file:\n",
-    "    helper = requests.get(\"https://raw.githubusercontent.com/Labelbox/labelbox-python/ms/coco/examples/integrations/detectron2/coco_utils.py\").text\n",
+    "    helper = requests.get(\"https://raw.githubusercontent.com/Labelbox/labelbox-python/develop/examples/integrations/detectron2/coco_utils.py\").text\n",
     "    file.write(helper)\n",
     "from coco_utils import visualize_coco_examples, visualize_object_inferences, partition_coco    \n"
    ]