UUID7 (#1267)

* UUID7

* fixes and hopefully lint

* fix mypy

* fix tests

* lint

* validate new and old uuids

* remove uuid7 requirement

* remove more uuid4

* serialization

* change aliases to base uuid type

* remove ser stuff

* introduce new_id

* fix

* move

requirements.min.txt

@@ -24,6 +24,7 @@ certifi==2024.7.4
 urllib3==1.26.19
 ujson==5.4.0
 deprecation==2.1.0
+uuid6==2024.7.10
 cryptography==43.0.1
 
 openai==1.16.2

setup.py

@@ -74,6 +74,7 @@
         "fsspec>=2024.6.1",
         "ujson>=5.4.0",
         "deprecation>=2.1.0",
+        "uuid6>=2024.7.10",
         "cryptography>=43.0.1",
     ],
     extras_require={

src/evidently/_pydantic_compat.py

@@ -5,7 +5,6 @@
 v = 1 if pydantic.__version__.startswith("1") else 2
 
 if v == 2:
-    from pydantic.v1 import UUID4
     from pydantic.v1 import BaseConfig
     from pydantic.v1 import BaseModel
     from pydantic.v1 import Extra
@@ -31,7 +30,6 @@
         from pydantic.v1.typing import DictStrAny
 
 else:
-    from pydantic import UUID4
     from pydantic import BaseConfig
     from pydantic import BaseModel
     from pydantic import Extra
@@ -58,7 +56,6 @@
 
 
 __all__ = [
-    "UUID4",
     "BaseConfig",
     "BaseModel",
     "Field",

src/evidently/cli/ui.py

@@ -1,25 +1,27 @@
 import os
 from typing import Optional
 
+import uuid6
 from typer import BadParameter
 from typer import Option
 from typer import echo
 
 from evidently.cli.main import app
 
 
-def setup_deterministic_generation_uuid4(seed: int = 8754):
+def setup_deterministic_generation_uuid(seed: int = 8754):
     import uuid
 
     from faker import Faker
 
     Faker.seed(seed)
     fake = Faker()
 
-    def deterministic_uuid4():
+    def deterministic_uuid():
         return fake.uuid4(cast_to=None)
 
-    uuid.uuid4 = deterministic_uuid4
+    uuid.uuid4 = deterministic_uuid
+    uuid6.uuid7 = deterministic_uuid
 
 
 @app.command("ui")
@@ -36,7 +38,7 @@ def ui(
 ):
     """Start Evidently UI service"""
     if os.environ.get("EXPERIMENTAL_DETERMINISTIC_UUID"):
-        setup_deterministic_generation_uuid4()
+        setup_deterministic_generation_uuid()
 
     from evidently.ui.app import run_local
     from evidently.ui.demo_projects import DEMO_PROJECTS

src/evidently/core.py

@@ -1,3 +1,4 @@
+import uuid
 from typing import TYPE_CHECKING
 from typing import Any
 from typing import ClassVar
@@ -12,6 +13,7 @@
 
 import numpy as np
 import pandas as pd
+import uuid6
 from typing_inspect import is_literal_type
 
 from evidently._pydantic_compat import SHAPE_DICT
@@ -273,3 +275,7 @@ def get_field_tags(cls: Type[BaseModel], field_name: str) -> Set[IncludeTags]:
 
 def get_all_fields_tags(cls: Type[BaseResult]) -> Dict[str, Set[IncludeTags]]:
     return {field_name: get_field_tags(cls, field_name) for field_name in cls.__fields__}
+
+
+def new_id() -> uuid.UUID:
+    return uuid6.uuid7()

src/evidently/descriptors/custom_descriptor.py

@@ -1,10 +1,10 @@
-import uuid
 from typing import Callable
 from typing import Union
 
 import pandas as pd
 
 from evidently.core import ColumnType
+from evidently.core import new_id
 from evidently.features.custom_feature import CustomPairColumnFeature
 from evidently.features.custom_feature import CustomSingleColumnFeature
 from evidently.features.generated_features import FeatureDescriptor
@@ -24,7 +24,7 @@ def feature(self, column_name: str) -> GeneratedFeature:
             column_name=column_name,
             display_name=self.display_name,
             feature_type=ColumnType(self.feature_type),
-            name=self.name or getattr(self.func, "__name__", str(uuid.uuid4())),
+            name=self.name or getattr(self.func, "__name__", str(new_id())),
         )
 
 

src/evidently/experimental/report_set.py

@@ -1,19 +1,19 @@
 import datetime
 import os
-import uuid
 from typing import Dict
 from typing import Optional
 
 from evidently._pydantic_compat import ValidationError
 from evidently.suite.base_suite import Snapshot
+from evidently.ui.type_aliases import SnapshotID
 
 
 def load_snapshots(
     path: str,
     date_from: Optional[datetime.datetime] = None,
     date_to: Optional[datetime.datetime] = None,
     skip_errors: bool = False,
-) -> Dict[uuid.UUID, Snapshot]:
+) -> Dict[SnapshotID, Snapshot]:
     result = {}
     for file in os.listdir(path):
         filepath = os.path.join(path, file)

src/evidently/features/custom_feature.py

@@ -1,4 +1,3 @@
-import uuid
 from typing import Callable
 from typing import Tuple
 
@@ -7,6 +6,7 @@
 from evidently import ColumnType
 from evidently._pydantic_compat import Field
 from evidently.base_metric import ColumnName
+from evidently.core import new_id
 from evidently.features.generated_features import FeatureTypeFieldMixin
 from evidently.features.generated_features import GeneratedFeature
 from evidently.pydantic_utils import FingerprintPart
@@ -15,7 +15,7 @@
 
 class CustomFeature(FeatureTypeFieldMixin, GeneratedFeature):
     display_name: str
-    name: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    name: str = Field(default_factory=lambda: str(new_id()))
     func: Callable[[pd.DataFrame, DataDefinition], pd.Series]
     feature_type: ColumnType = ColumnType.Numerical
 
@@ -30,7 +30,7 @@ def _as_column(self) -> "ColumnName":
 class CustomSingleColumnFeature(FeatureTypeFieldMixin, GeneratedFeature):
     display_name: str
     func: Callable[[pd.Series], pd.Series]
-    name: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    name: str = Field(default_factory=lambda: str(new_id()))
     column_name: str
     feature_type: ColumnType = ColumnType.Numerical
 
@@ -52,7 +52,7 @@ def get_fingerprint_parts(self) -> Tuple[FingerprintPart, ...]:
 class CustomPairColumnFeature(FeatureTypeFieldMixin, GeneratedFeature):
     display_name: str
     func: Callable[[pd.Series, pd.Series], pd.Series]
-    name: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    name: str = Field(default_factory=lambda: str(new_id()))
     first_column: str
     second_column: str
     feature_type: ColumnType = ColumnType.Numerical

src/evidently/features/generated_features.py

@@ -1,6 +1,5 @@
 import abc
 import dataclasses
-import uuid
 from typing import Any
 from typing import ClassVar
 from typing import Generic
@@ -9,6 +8,7 @@
 
 import deprecation
 import pandas as pd
+import uuid6
 
 from evidently._pydantic_compat import BaseModel
 from evidently._pydantic_compat import Field
@@ -173,7 +173,7 @@ def _feature_display_name(self):
 
 class DataFeature(GeneratedFeature):
     display_name: str
-    name: str = Field(default_factory=lambda: str(uuid.uuid4()))
+    name: str = Field(default_factory=lambda: str(uuid6.uuid7()))
 
     @abc.abstractmethod
     def generate_data(self, data: pd.DataFrame, data_definition: DataDefinition) -> pd.Series:

src/evidently/features/openai_feature.py

@@ -1,4 +1,3 @@
-import uuid
 from itertools import repeat
 from typing import List
 from typing import Optional
@@ -8,6 +7,7 @@
 
 from evidently.base_metric import ColumnName
 from evidently.core import ColumnType
+from evidently.core import new_id
 from evidently.features.generated_features import FeatureTypeFieldMixin
 from evidently.features.generated_features import GeneratedFeature
 from evidently.utils.data_preprocessing import DataDefinition
@@ -43,7 +43,7 @@ def __init__(
         openai_params: Optional[dict] = None,
         display_name: Optional[str] = None,
     ):
-        self.feature_id = str(uuid.uuid4())
+        self.feature_id = str(new_id())
         self.prompt = prompt
         self.prompt_replace_string = prompt_replace_string
         if context is not None and context_column is not None:

src/evidently/model/widget.py

@@ -2,7 +2,6 @@
 # coding: utf-8
 # pylint: disable=invalid-name
 import dataclasses
-import uuid
 from dataclasses import dataclass
 from dataclasses import field
 from enum import Enum
@@ -12,6 +11,8 @@
 from typing import Optional
 from typing import Union
 
+import uuid6
+
 from evidently.pydantic_utils import EvidentlyBaseModel
 from evidently.pydantic_utils import Fingerprint
 
@@ -66,7 +67,7 @@ class AdditionalGraphInfo:
 class PlotlyGraphInfo:
     data: Any
     layout: Any
-    id: str = dataclasses.field(default_factory=lambda: str(uuid.uuid4()))
+    id: str = dataclasses.field(default_factory=lambda: str(uuid6.uuid7()))
 
 
 class WidgetType(Enum):
@@ -84,7 +85,7 @@ class BaseWidgetInfo:
     type: str
     title: str
     size: int
-    id: str = dataclasses.field(default_factory=lambda: str(uuid.uuid4()))
+    id: str = dataclasses.field(default_factory=lambda: str(uuid6.uuid7()))
     details: str = ""
     alertsPosition: Optional[str] = None
     alertStats: Optional[AlertStats] = None

src/evidently/pydantic_utils.py

@@ -33,21 +33,28 @@
 
 if TYPE_CHECKING:
     from evidently._pydantic_compat import DictStrAny
+
+
 T = TypeVar("T")
 
 
-def pydantic_type_validator(type_: Type[Any]):
+def pydantic_type_validator(type_: Type[Any], prioritize: bool = False):
     def decorator(f):
         from evidently._pydantic_compat import _VALIDATORS
 
         for cls, validators in _VALIDATORS:
             if cls is type_:
-                validators.append(f)
+                if prioritize:
+                    validators.insert(0, f)
+                else:
+                    validators.append(f)
                 return
-
-        _VALIDATORS.append(
-            (type_, [f]),
-        )
+        if prioritize:
+            _VALIDATORS.insert(0, (type_, [f]))
+        else:
+            _VALIDATORS.append(
+                (type_, [f]),
+            )
 
     return decorator
 

src/evidently/renderers/base_renderer.py

@@ -1,5 +1,4 @@
 import dataclasses
-import uuid
 import warnings
 from typing import TYPE_CHECKING
 from typing import Dict
@@ -8,6 +7,7 @@
 from typing import Union
 
 import pandas as pd
+import uuid6
 
 from evidently.model.widget import AdditionalGraphInfo
 from evidently.model.widget import BaseWidgetInfo
@@ -62,7 +62,7 @@ def render_html(self, obj) -> List[BaseWidgetInfo]:
 class DetailsInfo:
     title: str
     info: BaseWidgetInfo
-    id: str = dataclasses.field(default_factory=lambda: str(uuid.uuid4()))
+    id: str = dataclasses.field(default_factory=lambda: str(uuid6.uuid7()))
 
 
 @dataclasses.dataclass

src/evidently/renderers/html_widgets.py

@@ -6,12 +6,12 @@
 from typing import Optional
 from typing import Tuple
 from typing import Union
-from uuid import uuid4
 
 import numpy as np
 import pandas as pd
 from plotly import graph_objs as go
 from plotly.subplots import make_subplots
+from uuid6 import uuid7
 
 from evidently.metric_results import Distribution
 from evidently.metric_results import HistogramData
@@ -140,7 +140,7 @@ def plotly_graph_tabs(*, title: str, figures: List[GraphData], size: WidgetSize
         params={
             "graphs": [
                 {
-                    "id": str(uuid4()),
+                    "id": str(uuid7()),
                     "title": graph.title,
                     "graph": {
                         "data": graph.data,
@@ -339,7 +339,7 @@ def widget_tabs(*, title: str = "", size: WidgetSize = WidgetSize.FULL, tabs: Li
         title=title,
         type=WidgetType.TABS.value,
         size=size.value,
-        tabs=[TabInfo(str(uuid4()), tab.title, tab.widget) for tab in tabs],
+        tabs=[TabInfo(str(uuid7()), tab.title, tab.widget) for tab in tabs],
     )