GH-62: refactor(metadata): Rename ColumnProfile to ColumnInformation

.github/workflows/python-tests.yml

@@ -1,7 +1,20 @@
 name: Python Linting, Formatting, Testing, Coverage
 on:
   pull_request:
-    branches: [main, develop]
+    paths:
+      - 'src/**'
+      - 'tests/**'
+      - '.github/workflows/**'
+      - 'pyproject.toml'
+  push:
+    branches:
+      - main
+      - develop
+    paths:
+      - 'src/**'
+      - 'tests/**'
+      - '.github/workflows/**'
+      - 'pyproject.toml'
 jobs:
   test:
     runs-on: ubuntu-latest

src/getml_io/getml/feature_learning.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from collections.abc import Set as AbstractSet
-from typing import Annotated, ClassVar, Literal
+from typing import Annotated, Literal
 
 from getml.feature_learning.aggregations.types import (
     FastPropAggregations,
@@ -11,12 +11,10 @@
     CrossEntropyLossType,
     SquareLossType,
 )
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
 
-class FastProp(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class FastProp(BaseModel, frozen=True):
     aggregation: AbstractSet[FastPropAggregations]
     delta_t: float
     loss_function: CrossEntropyLossType | SquareLossType | None
@@ -31,9 +29,7 @@ class FastProp(BaseModel):
     type: Literal["fast_prop"] = "fast_prop"
 
 
-class Fastboost(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Fastboost(BaseModel, frozen=True):
     gamma: float
     loss_function: CrossEntropyLossType | SquareLossType | None
     max_depth: int
@@ -48,9 +44,7 @@ class Fastboost(BaseModel):
     type: Literal["fastboost"] = "fastboost"
 
 
-class Multirel(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Multirel(BaseModel, frozen=True):
     aggregation: AbstractSet[MultirelAggregations]
     allow_sets: bool
     delta_t: float
@@ -75,9 +69,7 @@ class Multirel(BaseModel):
     type: Literal["multirel"] = "multirel"
 
 
-class Relboost(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Relboost(BaseModel, frozen=True):
     allow_null_weights: bool
     delta_t: float
     gamma: float
@@ -98,9 +90,7 @@ class Relboost(BaseModel):
     type: Literal["relboost"] = "relboost"
 
 
-class RelMT(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class RelMT(BaseModel, frozen=True):
     allow_avg: bool
     delta_t: float
     gamma: float

src/getml_io/getml/features.py

@@ -1,12 +1,9 @@
 from collections.abc import Mapping
-from typing import ClassVar
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel
 
 
-class Feature(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Feature(BaseModel, frozen=True):
     name: str
     index: int
     target: str

src/getml_io/getml/predictors.py

@@ -1,29 +1,23 @@
 from __future__ import annotations
 
-from typing import Annotated, ClassVar, Literal
+from typing import Annotated, Literal
 
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
 
-class LinearRegression(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class LinearRegression(BaseModel, frozen=True):
     learning_rate: float
     reg_lambda: float
     type: Literal["linear_regression"] = "linear_regression"
 
 
-class LogisticRegression(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class LogisticRegression(BaseModel, frozen=True):
     learning_rate: float
     reg_lambda: float
     type: Literal["logistic_regression"] = "logistic_regression"
 
 
-class ScaleGBMClassifier(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class ScaleGBMClassifier(BaseModel, frozen=True):
     colsample_bylevel: float
     colsample_bytree: float
     early_stopping_rounds: int
@@ -41,9 +35,7 @@ class ScaleGBMClassifier(BaseModel):
     type: Literal["scale_gbm_classifier"] = "scale_gbm_classifier"
 
 
-class ScaleGBMRegressor(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class ScaleGBMRegressor(BaseModel, frozen=True):
     colsample_bylevel: float
     colsample_bytree: float
     early_stopping_rounds: int
@@ -61,9 +53,7 @@ class ScaleGBMRegressor(BaseModel):
     type: Literal["scale_gbm_regressor"] = "scale_gbm_regressor"
 
 
-class XGBoostClassifier(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class XGBoostClassifier(BaseModel, frozen=True):
     booster: str
     colsample_bylevel: float
     colsample_bytree: float
@@ -90,9 +80,7 @@ class XGBoostClassifier(BaseModel):
     type: Literal["xgboost_classifier"] = "xgboost_classifier"
 
 
-class XGBoostRegressor(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class XGBoostRegressor(BaseModel, frozen=True):
     booster: str
     colsample_bylevel: float
     colsample_bytree: float

src/getml_io/getml/preprocessors.py

@@ -1,45 +1,35 @@
 from __future__ import annotations
 
 from collections.abc import Set as AbstractSet
-from typing import Annotated, ClassVar, Literal
+from typing import Annotated, Literal
 
 from getml.feature_learning.aggregations.types import MappingAggregations
-from pydantic import BaseModel, ConfigDict, Field
+from pydantic import BaseModel, Field
 
 
-class CategoryTrimmer(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class CategoryTrimmer(BaseModel, frozen=True):
     max_num_categories: int
     min_freq: int
     type: Literal["category_trimmer"] = "category_trimmer"
 
 
-class EmailDomain(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class EmailDomain(BaseModel, frozen=True):
     type: Literal["email_domain"] = "email_domain"
 
 
-class Imputation(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Imputation(BaseModel, frozen=True):
     add_dummies: bool
     type: Literal["imputation"] = "imputation"
 
 
-class Mapping(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Mapping(BaseModel, frozen=True):
     aggregation: AbstractSet[MappingAggregations]
     min_freq: int
     multithreading: bool
     type: Literal["mapping"] = "mapping"
 
 
-class Seasonal(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Seasonal(BaseModel, frozen=True):
     disable_year: bool
     disable_month: bool
     disable_weekday: bool
@@ -48,18 +38,14 @@ class Seasonal(BaseModel):
     type: Literal["seasonal"] = "seasonal"
 
 
-class Substring(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Substring(BaseModel, frozen=True):
     begin: int
     length: int
     unit: str
     type: Literal["substring"] = "substring"
 
 
-class TextFieldSplitter(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class TextFieldSplitter(BaseModel, frozen=True):
     type: Literal["text_field_splitter"] = "text_field_splitter"
 
 

src/getml_io/getml/project.py

@@ -1,11 +1,10 @@
 import logging
 from collections.abc import Generator
 from contextlib import contextmanager
-from typing import ClassVar
 
 from getml.data import Container
 from getml.pipeline import Pipeline
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel
 
 from getml_io.getml.exception import (
     PipelineNotFoundError,
@@ -25,12 +24,7 @@
 logger: logging.Logger = logging.getLogger(__name__)
 
 
-class Project(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(
-        arbitrary_types_allowed=True,
-        frozen=True,
-    )
-
+class Project(BaseModel, frozen=True, arbitrary_types_allowed=True):
     name: str
     pipeline: Pipeline
     container: Container

src/getml_io/getml/project_information.py

@@ -1,11 +1,7 @@
-from typing import ClassVar
+from pydantic import BaseModel
 
-from pydantic import BaseModel, ConfigDict
-
-
-class ProjectInformation(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
 
+class ProjectInformation(BaseModel, frozen=True):
     project_name: str
     pipeline_id: str
     container_id: str

src/getml_io/getml/roles.py

@@ -2,10 +2,9 @@
 
 from collections.abc import Sequence
 from enum import Enum
-from typing import ClassVar
 
 from getml.data import roles
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel
 
 
 class Role(str, Enum):
@@ -19,9 +18,7 @@ class Role(str, Enum):
     UNUSED_STRING = roles.unused_string
 
 
-class Roles(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class Roles(BaseModel, frozen=True):
     categorical: Sequence[str]
     join_key: Sequence[str]
     numerical: Sequence[str]

src/getml_io/getml/scores.py

@@ -5,20 +5,20 @@
 from pydantic import BaseModel, Field
 
 
-class _Score(BaseModel):
+class _Score(BaseModel, frozen=True):
     date_time: datetime
     set_used: str
     target: str
 
 
-class ClassificationScore(_Score):
+class ClassificationScore(_Score, frozen=True):
     accuracy: float
     auc: float
     cross_entropy: float
     type: Literal["classification"] = "classification"
 
 
-class RegressionScore(_Score):
+class RegressionScore(_Score, frozen=True):
     mae: float
     rmse: float
     rsquared: float

src/getml_io/metadata/container_information.py

@@ -1,18 +1,14 @@
 from __future__ import annotations
 
-from typing import ClassVar
-
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel
 
 from getml_io.metadata.dataframe_information import (
     DataFrameInformation,
     DataFrameInformationByName,
 )
 
 
-class ContainerInformation(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class ContainerInformation(BaseModel, frozen=True):
     id: str
     population: DataFrameInformation | None
     peripheral: DataFrameInformationByName

src/getml_io/metadata/data_model_information.py

@@ -1,15 +1,12 @@
 from __future__ import annotations
 
 from collections.abc import Mapping, Sequence
-from typing import ClassVar
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel
 
 from getml_io.metadata.placeholder_information import PlaceholderInformation
 
 
-class DataModelInformation(BaseModel):
-    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
-
+class DataModelInformation(BaseModel, frozen=True):
     population: PlaceholderInformation
     peripheral: Mapping[str, Sequence[PlaceholderInformation]]