Merge pull request #568 from Labelbox/jt/al-2326

[AL-2326] Metadata and Media Attributes for common BaseData object

Author: jtsodapop

labelbox/data/annotation_types/data/base_data.py

@@ -1,5 +1,5 @@
 from abc import ABC
-from typing import Optional
+from typing import Optional, Dict, List, Any
 
 from pydantic import BaseModel
 
@@ -11,3 +11,5 @@ class BaseData(BaseModel, ABC):
     """
     external_id: Optional[str] = None
     uid: Optional[str] = None
+    media_attributes: Optional[Dict[str, Any]] = None
+    metadata: Optional[List[Dict[str, Any]]] = None

labelbox/data/serialization/labelbox_v1/label.py

@@ -1,6 +1,6 @@
 from labelbox.data.annotation_types.data.tiled_image import TiledImageData
 from labelbox.utils import camel_case
-from typing import List, Optional, Union
+from typing import List, Optional, Union, Dict, Any
 
 from pydantic import BaseModel, Field
 
@@ -126,6 +126,10 @@ class LBV1Label(BaseModel):
     row_data: str = Field(None, alias="Labeled Data")
     id: Optional[str] = Field(None, alias='ID')
     external_id: Optional[str] = Field(None, alias="External ID")
+    data_row_media_attributes: Optional[Dict[str, Any]] = Field(
+        {}, alias="Media Attributes")
+    data_row_metadata: Optional[List[Dict[str, Any]]] = Field(
+        [], alias="DataRow Metadata")
 
     created_by: Optional[str] = Extra('Created By')
     project_name: Optional[str] = Extra('Project Name')
@@ -167,12 +171,13 @@ def from_common(cls, label: Label):
             label_ = LBV1LabelAnnotationsVideo.from_common(label.annotations)
         else:
             label_ = LBV1LabelAnnotations.from_common(label.annotations)
-
         return LBV1Label(label=label_,
                          id=label.uid,
                          data_row_id=label.data.uid,
                          row_data=label.data.url,
                          external_id=label.data.external_id,
+                         data_row_media_attributes=label.data.media_attributes,
+                         data_row_metadata=label.data.metadata,
                          **label.extra)
 
     def _data_row_to_common(
@@ -181,7 +186,9 @@ def _data_row_to_common(
         data_row_info = {
             'url' if self._is_url() else 'text': self.row_data,
             'external_id': self.external_id,
-            'uid': self.data_row_id
+            'uid': self.data_row_id,
+            'media_attributes': self.data_row_media_attributes,
+            'metadata': self.data_row_metadata
         }
 
         self.media_type = self.media_type or self._infer_media_type()
@@ -238,4 +245,4 @@ def _is_url(self) -> bool:
              "s3://")) or "tileLayerUrl" in self.row_data
 
     class Config:
-        allow_population_by_field_name = True
+        allow_population_by_field_name = True

tests/data/annotation_types/data/test_raster.py

@@ -40,6 +40,14 @@ def test_im_path():
 def test_ref():
     external_id = "external_id"
     uid = "uid"
-    data = ImageData(im_bytes=b'', external_id=external_id, uid=uid)
+    metadata = []
+    media_attributes = {}
+    data = ImageData(im_bytes=b'',
+                     external_id=external_id,
+                     uid=uid,
+                     metadata=metadata,
+                     media_attributes=media_attributes)
     assert data.external_id == external_id
     assert data.uid == uid
+    assert data.media_attributes == media_attributes
+    assert data.metadata == metadata

tests/data/annotation_types/data/test_text.py

@@ -13,7 +13,11 @@ def test_validate_schema():
 
 def test_text():
     text = "hello world"
-    text_data = TextData(text=text)
+    metadata = []
+    media_attributes = {}
+    text_data = TextData(text=text,
+                         metadata=metadata,
+                         media_attributes=media_attributes)
     assert text_data.text == text
 
 
@@ -36,6 +40,14 @@ def test_file(tmpdir):
 def test_ref():
     external_id = "external_id"
     uid = "uid"
-    data = TextData(text="hello world", external_id=external_id, uid=uid)
+    metadata = []
+    media_attributes = {}
+    data = TextData(text="hello world",
+                    external_id=external_id,
+                    uid=uid,
+                    metadata=metadata,
+                    media_attributes=media_attributes)
     assert data.external_id == external_id
     assert data.uid == uid
+    assert data.media_attributes == media_attributes
+    assert data.metadata == metadata

tests/data/annotation_types/data/test_video.py

@@ -58,6 +58,14 @@ def test_ref():
         x: (np.random.random((32, 32, 3)) * 255).astype(np.uint8)
         for x in range(5)
     }
-    data = VideoData(frames=data, external_id=external_id, uid=uid)
+    metadata = []
+    media_attributes = {}
+    data = VideoData(frames=data,
+                     external_id=external_id,
+                     uid=uid,
+                     metadata=metadata,
+                     media_attributes=media_attributes)
     assert data.external_id == external_id
     assert data.uid == uid
+    assert data.media_attributes == media_attributes
+    assert data.metadata == metadata

tests/data/annotation_types/test_metrics.py

@@ -21,7 +21,9 @@ def test_legacy_scalar_metric():
             'im_bytes': None,
             'file_path': None,
             'url': None,
-            'arr': None
+            'arr': None,
+            'media_attributes': None,
+            'metadata': None,
         },
         'annotations': [{
             'value': 10.0,
@@ -70,7 +72,9 @@ def test_custom_scalar_metric(feature_name, subclass_name, aggregation, value):
             'im_bytes': None,
             'file_path': None,
             'url': None,
-            'arr': None
+            'arr': None,
+            'media_attributes': None,
+            'metadata': None,
         },
         'annotations': [{
             'value':
@@ -125,7 +129,9 @@ def test_custom_confusison_matrix_metric(feature_name, subclass_name,
             'im_bytes': None,
             'file_path': None,
             'url': None,
-            'arr': None
+            'arr': None,
+            'media_attributes': None,
+            'metadata': None,
         },
         'annotations': [{
             'value':

tests/data/assets/labelbox_v1/highly_nested_image.json

@@ -1 +1,195 @@
-{"ID": "ckt3hu4aq524s0y9e7i0dbbtg", "DataRow ID": "ckt3h8c7e200j0y6ob2g3629b", "Labeled Data": "https://storage.labelbox.com/ckk4q1vgapsau07324awnsjq2%2Fa8c0d364-b10f-5b49-09a3-151264999cfb-1?Expires=1630706709794&KeyName=labelbox-assets-key-3&Signature=W8RPYzKo1Qs6Qxclapnx4_chhJ8", "Label": {"objects": [{"featureId": "ckt3hu9ux00003h69bzk55eaj", "schemaId": "ckt3h8e8s51li0y7ucy0bgrlz", "color": "#ff0000", "title": "deer", "value": "deer", "polygon": [{"x": 71.832, "y": 62.37}, {"x": 50.636, "y": 90.087}, {"x": 103.625, "y": 94.571}, {"x": 104.033, "y": 59.517}], "instanceURI": "https://api.labelbox.com/masks/feature/ckt3hu9ux00003h69bzk55eaj?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJja2s0cTF2Z3djMHZwMDcwNHhoeDdtNHZrIiwib3JnYW5pemF0aW9uSWQiOiJja2s0cTF2Z2Fwc2F1MDczMjRhd25zanEyIiwiaWF0IjoxNjMwNjI1NjgxLCJleHAiOjE2MzMyMTc2ODF9.hUJ46wdigdN9RdICF8FYzaA7MLbscfjvBeP5O-QhGa8", "classifications": [{"featureId": "ckt3hud1m00023h696pofvwkq", "schemaId": "ckt3hu2yn523g0y9ehzhg5opb", "title": "rrrr", "value": "rrrr", "answer": {"featureId": "ckt3hud1l00013h69xob7gwoh", "schemaId": "ckt3hu302523w0y9e39pub4zp", "title": "rrrrrrrr", "value": "rrrrrrrr"}}]}, {"featureId": "ckt3hullq000c3h69o8iqty8k", "schemaId": "ckt3h8e8s51lm0y7ucl6bgixn", "color": "#0000ff", "title": "deer_eyes", "value": "deer_eyes", "instanceURI": "https://api.labelbox.com/masks/feature/ckt3hullq000c3h69o8iqty8k?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJja2s0cTF2Z3djMHZwMDcwNHhoeDdtNHZrIiwib3JnYW5pemF0aW9uSWQiOiJja2s0cTF2Z2Fwc2F1MDczMjRhd25zanEyIiwiaWF0IjoxNjMwNjI1NjgxLCJleHAiOjE2MzMyMTc2ODF9.hUJ46wdigdN9RdICF8FYzaA7MLbscfjvBeP5O-QhGa8"}, {"featureId": "ckt3hug4600073h692cpxwc2v", "schemaId": "ckt3hu2ya523e0y9eaika5flx", "color": "#00ff00", "title": "deer_nose", "value": "deer_nose", "point": {"x": 73.054, "y": 165.495}, "instanceURI": "https://api.labelbox.com/masks/feature/ckt3hug4600073h692cpxwc2v?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJja2s0cTF2Z3djMHZwMDcwNHhoeDdtNHZrIiwib3JnYW5pemF0aW9uSWQiOiJja2s0cTF2Z2Fwc2F1MDczMjRhd25zanEyIiwiaWF0IjoxNjMwNjI1NjgxLCJleHAiOjE2MzMyMTc2ODF9.hUJ46wdigdN9RdICF8FYzaA7MLbscfjvBeP5O-QhGa8", "classifications": [[{"featureId": "ckt3hui8800093h69swml8uzf", "schemaId": "ckt3hu308523x0y9eclq1g2k8", "title": "description", "value": "description", "answers": [{"featureId": "ckt3hui8800083h69696qdgdf", "schemaId": "ckt3hu31m524b0y9eeiuobmlo", "title": "wet", "value": "wet"}, {"featureId": "ckt3kb8ym00013h69lydpjjkp", "schemaId": "ckt3k5asi26wt0y6o805pf9ve", "title": "dry", "value": "dry"}]}, {"featureId": "ckt3hujza000b3h69jfu850bx", "schemaId": "ckt3hu32x524p0y9ehuzf6wtw", "title": "asdasdsadsa", "value": "asdasdsadsa", "answer": {"featureId": "ckt3hujza000a3h691fbs2iik", "schemaId": "ckt3hu33h524r0y9e5q6j91wt", "title": "aasdsadsada", "value": "aasdsadsada"}}, {"featureId": "ckt3kbapf00033h69aup591oj", "schemaId": "ckt3k5au226x50y6o5wlv9j3g", "title": "anotherone...", "value": "anotherone...", "answer": {"featureId": "ckt3kbape00023h69ohwyr625", "schemaId": "ckt3k5aum26xb0y6o2gxtctze", "title": "weeewrew", "value": "weeewrew"}}]]}], "classifications": [{"featureId": "ckt3huphm000f3h69esv5u6ch", "schemaId": "ckt3h8e8r51lg0y7u2mtz9791", "title": "image_description", "value": "image_description", "answers": [{"featureId": "ckt3huphm000e3h69a18xeme7", "schemaId": "ckt3h8e9m51lo0y7u5v81b3cz", "title": "bright", "value": "bright"}, {"featureId": "ckt3hus0i000h3h69kwde3ilk", "schemaId": "ckt3h8e9m51lq0y7u15ygdlyw", "title": "not_blurry", "value": "not_blurry"}, {"featureId": "ckt3huuhi000k3h69io60j4xq", "schemaId": "ckt3h8e9m51ls0y7u82aj5m3f", "title": "dark", "value": "dark"}]}, {"featureId": "ckt3hvcm4000p3h69vdbc0c23", "schemaId": "ckt3hu2y652300y9e6fkefo42", "title": "a", "value": "a", "answer": {"featureId": "ckt3hvcm4000o3h693oy8exqm", "schemaId": "ckt3hu2z6523l0y9e83yg91zc", "title": "ass", "value": "ass"}}, {"featureId": "ckt3hvdl4000r3h69jqvrrb67", "schemaId": "ckt3hu30w52410y9e485y1vwi", "title": "asdsadsad", "value": "asdsadsad", "answer": [{"featureId": "ckt3hvdl4000q3h69i8afxwv5", "schemaId": "ckt3hu31o524d0y9ehwk4ds2a", "title": "asdasdsa", "value": "asdasdsa"}]}, {"featureId": "ckt3hvfz4000s3h69heqauwmu", "schemaId": "ckt3hu30x52430y9ebixq8f3t", "title": "wee223", "value": "wee223", "answer": "fretre"}, {"featureId": "ckt3hvgkq000u3h69tjsg5rl1", "schemaId": "ckt3hu30x52450y9eaw056vgj", "title": "3223432", "value": "3223432", "answer": {"featureId": "ckt3hvgkq000t3h6928o3rgzf", "schemaId": "ckt3hu31v524j0y9e7x1g2shq", "title": "dddd", "value": "dddd"}}, {"featureId": "ckt3hvife000v3h6980b3ccxa", "schemaId": "ckt3hu2y652320y9e4n1lb9dx", "title": "weeeee", "value": "weeeee", "answer": "5354"}, {"featureId": "ckt3hviho000x3h69xt3npgtb", "schemaId": "ckt3hu2y652340y9e1brp3l1i", "title": "asdsadsa", "value": "asdsadsa", "answer": [{"featureId": "ckt3hviho000w3h690kvv8isp", "schemaId": "ckt3hu2zn523p0y9eel4l4ts9", "title": "asxdsds", "value": "asxdsds"}]}], "relationships": []}, "Created By": "msokoloff@labelbox.com", "Project Name": "test_annotation_types", "Created At": "2021-09-02T22:23:24.000Z", "Updated At": "2021-09-02T23:31:27.707Z", "Seconds to Label": 220.91400000000002, "External ID": null, "Agreement": -1, "Benchmark Agreement": -1, "Benchmark ID": null, "Dataset Name": "label_dataset", "Reviews": [], "View Label": "https://editor.labelbox.com?project=ckt3h8d9z51l10y7uavvf5zcn&label=ckt3hu4aq524s0y9e7i0dbbtg", "Has Open Issues": 0, "Skipped": false,   "Data Split" : null}
+{
+    "ID": "ckt3hu4aq524s0y9e7i0dbbtg",
+    "DataRow ID": "ckt3h8c7e200j0y6ob2g3629b",
+    "DataRow Metadata": [],
+    "Media Attributes": {},
+    "Labeled Data": "https://storage.labelbox.com/ckk4q1vgapsau07324awnsjq2%2Fa8c0d364-b10f-5b49-09a3-151264999cfb-1?Expires=1630706709794&KeyName=labelbox-assets-key-3&Signature=W8RPYzKo1Qs6Qxclapnx4_chhJ8",
+    "Label": {
+        "objects": [{
+            "featureId": "ckt3hu9ux00003h69bzk55eaj",
+            "schemaId": "ckt3h8e8s51li0y7ucy0bgrlz",
+            "color": "#ff0000",
+            "title": "deer",
+            "value": "deer",
+            "polygon": [{
+                "x": 71.832,
+                "y": 62.37
+            }, {
+                "x": 50.636,
+                "y": 90.087
+            }, {
+                "x": 103.625,
+                "y": 94.571
+            }, {
+                "x": 104.033,
+                "y": 59.517
+            }],
+            "instanceURI": "https://api.labelbox.com/masks/feature/ckt3hu9ux00003h69bzk55eaj?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJja2s0cTF2Z3djMHZwMDcwNHhoeDdtNHZrIiwib3JnYW5pemF0aW9uSWQiOiJja2s0cTF2Z2Fwc2F1MDczMjRhd25zanEyIiwiaWF0IjoxNjMwNjI1NjgxLCJleHAiOjE2MzMyMTc2ODF9.hUJ46wdigdN9RdICF8FYzaA7MLbscfjvBeP5O-QhGa8",
+            "classifications": [{
+                "featureId": "ckt3hud1m00023h696pofvwkq",
+                "schemaId": "ckt3hu2yn523g0y9ehzhg5opb",
+                "title": "rrrr",
+                "value": "rrrr",
+                "answer": {
+                    "featureId": "ckt3hud1l00013h69xob7gwoh",
+                    "schemaId": "ckt3hu302523w0y9e39pub4zp",
+                    "title": "rrrrrrrr",
+                    "value": "rrrrrrrr"
+                }
+            }]
+        }, {
+            "featureId": "ckt3hullq000c3h69o8iqty8k",
+            "schemaId": "ckt3h8e8s51lm0y7ucl6bgixn",
+            "color": "#0000ff",
+            "title": "deer_eyes",
+            "value": "deer_eyes",
+            "instanceURI": "https://api.labelbox.com/masks/feature/ckt3hullq000c3h69o8iqty8k?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJja2s0cTF2Z3djMHZwMDcwNHhoeDdtNHZrIiwib3JnYW5pemF0aW9uSWQiOiJja2s0cTF2Z2Fwc2F1MDczMjRhd25zanEyIiwiaWF0IjoxNjMwNjI1NjgxLCJleHAiOjE2MzMyMTc2ODF9.hUJ46wdigdN9RdICF8FYzaA7MLbscfjvBeP5O-QhGa8"
+        }, {
+            "featureId": "ckt3hug4600073h692cpxwc2v",
+            "schemaId": "ckt3hu2ya523e0y9eaika5flx",
+            "color": "#00ff00",
+            "title": "deer_nose",
+            "value": "deer_nose",
+            "point": {
+                "x": 73.054,
+                "y": 165.495
+            },
+            "instanceURI": "https://api.labelbox.com/masks/feature/ckt3hug4600073h692cpxwc2v?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJja2s0cTF2Z3djMHZwMDcwNHhoeDdtNHZrIiwib3JnYW5pemF0aW9uSWQiOiJja2s0cTF2Z2Fwc2F1MDczMjRhd25zanEyIiwiaWF0IjoxNjMwNjI1NjgxLCJleHAiOjE2MzMyMTc2ODF9.hUJ46wdigdN9RdICF8FYzaA7MLbscfjvBeP5O-QhGa8",
+            "classifications": [
+                [{
+                    "featureId": "ckt3hui8800093h69swml8uzf",
+                    "schemaId": "ckt3hu308523x0y9eclq1g2k8",
+                    "title": "description",
+                    "value": "description",
+                    "answers": [{
+                        "featureId": "ckt3hui8800083h69696qdgdf",
+                        "schemaId": "ckt3hu31m524b0y9eeiuobmlo",
+                        "title": "wet",
+                        "value": "wet"
+                    }, {
+                        "featureId": "ckt3kb8ym00013h69lydpjjkp",
+                        "schemaId": "ckt3k5asi26wt0y6o805pf9ve",
+                        "title": "dry",
+                        "value": "dry"
+                    }]
+                }, {
+                    "featureId": "ckt3hujza000b3h69jfu850bx",
+                    "schemaId": "ckt3hu32x524p0y9ehuzf6wtw",
+                    "title": "asdasdsadsa",
+                    "value": "asdasdsadsa",
+                    "answer": {
+                        "featureId": "ckt3hujza000a3h691fbs2iik",
+                        "schemaId": "ckt3hu33h524r0y9e5q6j91wt",
+                        "title": "aasdsadsada",
+                        "value": "aasdsadsada"
+                    }
+                }, {
+                    "featureId": "ckt3kbapf00033h69aup591oj",
+                    "schemaId": "ckt3k5au226x50y6o5wlv9j3g",
+                    "title": "anotherone...",
+                    "value": "anotherone...",
+                    "answer": {
+                        "featureId": "ckt3kbape00023h69ohwyr625",
+                        "schemaId": "ckt3k5aum26xb0y6o2gxtctze",
+                        "title": "weeewrew",
+                        "value": "weeewrew"
+                    }
+                }]
+            ]
+        }],
+        "classifications": [{
+            "featureId": "ckt3huphm000f3h69esv5u6ch",
+            "schemaId": "ckt3h8e8r51lg0y7u2mtz9791",
+            "title": "image_description",
+            "value": "image_description",
+            "answers": [{
+                "featureId": "ckt3huphm000e3h69a18xeme7",
+                "schemaId": "ckt3h8e9m51lo0y7u5v81b3cz",
+                "title": "bright",
+                "value": "bright"
+            }, {
+                "featureId": "ckt3hus0i000h3h69kwde3ilk",
+                "schemaId": "ckt3h8e9m51lq0y7u15ygdlyw",
+                "title": "not_blurry",
+                "value": "not_blurry"
+            }, {
+                "featureId": "ckt3huuhi000k3h69io60j4xq",
+                "schemaId": "ckt3h8e9m51ls0y7u82aj5m3f",
+                "title": "dark",
+                "value": "dark"
+            }]
+        }, {
+            "featureId": "ckt3hvcm4000p3h69vdbc0c23",
+            "schemaId": "ckt3hu2y652300y9e6fkefo42",
+            "title": "a",
+            "value": "a",
+            "answer": {
+                "featureId": "ckt3hvcm4000o3h693oy8exqm",
+                "schemaId": "ckt3hu2z6523l0y9e83yg91zc",
+                "title": "ass",
+                "value": "ass"
+            }
+        }, {
+            "featureId": "ckt3hvdl4000r3h69jqvrrb67",
+            "schemaId": "ckt3hu30w52410y9e485y1vwi",
+            "title": "asdsadsad",
+            "value": "asdsadsad",
+            "answer": [{
+                "featureId": "ckt3hvdl4000q3h69i8afxwv5",
+                "schemaId": "ckt3hu31o524d0y9ehwk4ds2a",
+                "title": "asdasdsa",
+                "value": "asdasdsa"
+            }]
+        }, {
+            "featureId": "ckt3hvfz4000s3h69heqauwmu",
+            "schemaId": "ckt3hu30x52430y9ebixq8f3t",
+            "title": "wee223",
+            "value": "wee223",
+            "answer": "fretre"
+        }, {
+            "featureId": "ckt3hvgkq000u3h69tjsg5rl1",
+            "schemaId": "ckt3hu30x52450y9eaw056vgj",
+            "title": "3223432",
+            "value": "3223432",
+            "answer": {
+                "featureId": "ckt3hvgkq000t3h6928o3rgzf",
+                "schemaId": "ckt3hu31v524j0y9e7x1g2shq",
+                "title": "dddd",
+                "value": "dddd"
+            }
+        }, {
+            "featureId": "ckt3hvife000v3h6980b3ccxa",
+            "schemaId": "ckt3hu2y652320y9e4n1lb9dx",
+            "title": "weeeee",
+            "value": "weeeee",
+            "answer": "5354"
+        }, {
+            "featureId": "ckt3hviho000x3h69xt3npgtb",
+            "schemaId": "ckt3hu2y652340y9e1brp3l1i",
+            "title": "asdsadsa",
+            "value": "asdsadsa",
+            "answer": [{
+                "featureId": "ckt3hviho000w3h690kvv8isp",
+                "schemaId": "ckt3hu2zn523p0y9eel4l4ts9",
+                "title": "asxdsds",
+                "value": "asxdsds"
+            }]
+        }],
+        "relationships": []
+    },
+    "Created By": "msokoloff@labelbox.com",
+    "Project Name": "test_annotation_types",
+    "Created At": "2021-09-02T22:23:24.000Z",
+    "Updated At": "2021-09-02T23:31:27.707Z",
+    "Seconds to Label": 220.91400000000002,
+    "External ID": null,
+    "Agreement": -1,
+    "Benchmark Agreement": -1,
+    "Benchmark ID": null,
+    "Dataset Name": "label_dataset",
+    "Reviews": [],
+    "View Label": "https://editor.labelbox.com?project=ckt3h8d9z51l10y7uavvf5zcn&label=ckt3hu4aq524s0y9e7i0dbbtg",
+    "Has Open Issues": 0,
+    "Skipped": false,
+    "Data Split": null
+}