GH-53: refactor: Centralize relative dataframe-information-path and M…

src/getml_io/cli.py

@@ -153,7 +153,7 @@ def deserialize(
         pipeline_id=pipeline,
         container_id=container,
     )
-    message = f"Deserializing {project_information} from {root_storage_directory}"
+    message = f"Deserializing {project_information!r} from {root_storage_directory}"
     # TODO @urfoex: #20: Implement deserialization logic
     raise NotImplementedError(message)
 

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, Literal
+from typing import Annotated, ClassVar, Literal
 
 from getml.feature_learning.aggregations.types import (
     FastPropAggregations,
@@ -11,12 +11,12 @@
     CrossEntropyLossType,
     SquareLossType,
 )
-from pydantic import Field
-from pydantic.dataclasses import dataclass
+from pydantic import BaseModel, ConfigDict, Field
 
 
-@dataclass(frozen=True)
-class FastProp:
+class FastProp(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     aggregation: AbstractSet[FastPropAggregations]
     delta_t: float
     loss_function: CrossEntropyLossType | SquareLossType | None
@@ -31,8 +31,9 @@ class FastProp:
     type: Literal["fast_prop"] = "fast_prop"
 
 
-@dataclass(frozen=True)
-class Fastboost:
+class Fastboost(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     gamma: float
     loss_function: CrossEntropyLossType | SquareLossType | None
     max_depth: int
@@ -47,8 +48,9 @@ class Fastboost:
     type: Literal["fastboost"] = "fastboost"
 
 
-@dataclass(frozen=True)
-class Multirel:
+class Multirel(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     aggregation: AbstractSet[MultirelAggregations]
     allow_sets: bool
     delta_t: float
@@ -73,8 +75,9 @@ class Multirel:
     type: Literal["multirel"] = "multirel"
 
 
-@dataclass(frozen=True)
-class Relboost:
+class Relboost(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     allow_null_weights: bool
     delta_t: float
     gamma: float
@@ -95,8 +98,9 @@ class Relboost:
     type: Literal["relboost"] = "relboost"
 
 
-@dataclass(frozen=True)
-class RelMT:
+class RelMT(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     allow_avg: bool
     delta_t: float
     gamma: float

src/getml_io/getml/predictors.py

@@ -1,27 +1,29 @@
 from __future__ import annotations
 
-from typing import Annotated, Literal
+from typing import Annotated, ClassVar, Literal
 
-from pydantic import Field
-from pydantic.dataclasses import dataclass
+from pydantic import BaseModel, ConfigDict, Field
 
 
-@dataclass(frozen=True)
-class LinearRegression:
+class LinearRegression(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     learning_rate: float
     reg_lambda: float
     type: Literal["linear_regression"] = "linear_regression"
 
 
-@dataclass(frozen=True)
-class LogisticRegression:
+class LogisticRegression(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     learning_rate: float
     reg_lambda: float
     type: Literal["logistic_regression"] = "logistic_regression"
 
 
-@dataclass(frozen=True)
-class ScaleGBMClassifier:
+class ScaleGBMClassifier(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     colsample_bylevel: float
     colsample_bytree: float
     early_stopping_rounds: int
@@ -39,8 +41,9 @@ class ScaleGBMClassifier:
     type: Literal["scale_gbm_classifier"] = "scale_gbm_classifier"
 
 
-@dataclass(frozen=True)
-class ScaleGBMRegressor:
+class ScaleGBMRegressor(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     colsample_bylevel: float
     colsample_bytree: float
     early_stopping_rounds: int
@@ -58,8 +61,9 @@ class ScaleGBMRegressor:
     type: Literal["scale_gbm_regressor"] = "scale_gbm_regressor"
 
 
-@dataclass(frozen=True)
-class XGBoostClassifier:
+class XGBoostClassifier(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     booster: str
     colsample_bylevel: float
     colsample_bytree: float
@@ -86,8 +90,9 @@ class XGBoostClassifier:
     type: Literal["xgboost_classifier"] = "xgboost_classifier"
 
 
-@dataclass(frozen=True)
-class XGBoostRegressor:
+class XGBoostRegressor(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     booster: str
     colsample_bylevel: float
     colsample_bytree: float

src/getml_io/getml/preprocessors.py

@@ -1,41 +1,45 @@
 from __future__ import annotations
 
 from collections.abc import Set as AbstractSet
-from typing import Annotated, Literal
+from typing import Annotated, ClassVar, Literal
 
 from getml.feature_learning.aggregations.types import MappingAggregations
-from pydantic import Field
-from pydantic.dataclasses import dataclass
+from pydantic import BaseModel, ConfigDict, Field
 
 
-@dataclass(frozen=True)
-class CategoryTrimmer:
+class CategoryTrimmer(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     max_num_categories: int
     min_freq: int
     type: Literal["category_trimmer"] = "category_trimmer"
 
 
-@dataclass(frozen=True)
-class EmailDomain:
+class EmailDomain(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     type: Literal["email_domain"] = "email_domain"
 
 
-@dataclass(frozen=True)
-class Imputation:
+class Imputation(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     add_dummies: bool
     type: Literal["imputation"] = "imputation"
 
 
-@dataclass(frozen=True)
-class Mapping:
+class Mapping(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     aggregation: AbstractSet[MappingAggregations]
     min_freq: int
     multithreading: bool
     type: Literal["mapping"] = "mapping"
 
 
-@dataclass(frozen=True)
-class Seasonal:
+class Seasonal(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     disable_year: bool
     disable_month: bool
     disable_weekday: bool
@@ -44,16 +48,18 @@ class Seasonal:
     type: Literal["seasonal"] = "seasonal"
 
 
-@dataclass(frozen=True)
-class Substring:
+class Substring(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     begin: int
     length: int
     unit: str
     type: Literal["substring"] = "substring"
 
 
-@dataclass(frozen=True)
-class TextFieldSplitter:
+class TextFieldSplitter(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     type: Literal["text_field_splitter"] = "text_field_splitter"
 
 

src/getml_io/getml/project.py

@@ -1,10 +1,11 @@
 import logging
 from collections.abc import Generator
 from contextlib import contextmanager
-from dataclasses import dataclass
+from typing import ClassVar
 
 from getml.data import Container
 from getml.pipeline import Pipeline
+from pydantic import BaseModel, ConfigDict
 
 from getml_io.getml.exception import (
     PipelineNotFoundError,
@@ -24,8 +25,12 @@
 logger: logging.Logger = logging.getLogger(__name__)
 
 
-@dataclass
-class Project:
+class Project(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(
+        arbitrary_types_allowed=True,
+        frozen=True,
+    )
+
     name: str
     pipeline: Pipeline
     container: Container

src/getml_io/getml/project_information.py

@@ -1,8 +1,11 @@
-from dataclasses import dataclass
+from typing import ClassVar
 
+from pydantic import BaseModel, ConfigDict
+
+
+class ProjectInformation(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
 
-@dataclass
-class ProjectInformation:
     project_name: str
     pipeline_id: str
     container_id: str

src/getml_io/getml/roles.py

@@ -2,9 +2,10 @@
 
 from collections.abc import Sequence
 from enum import Enum
+from typing import ClassVar
 
 from getml.data import roles
-from pydantic.dataclasses import dataclass
+from pydantic import BaseModel, ConfigDict
 
 
 class Role(str, Enum):
@@ -18,8 +19,9 @@ class Role(str, Enum):
     UNUSED_STRING = roles.unused_string
 
 
-@dataclass(frozen=True)
-class Roles:
+class Roles(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     categorical: Sequence[str]
     join_key: Sequence[str]
     numerical: Sequence[str]

src/getml_io/metadata/container_information.py

@@ -1,62 +1,20 @@
 from __future__ import annotations
 
-from collections.abc import Mapping
-from pathlib import Path
-from typing import Annotated
+from typing import ClassVar
 
-from pydantic import Field, model_serializer
-from pydantic.dataclasses import dataclass
-from typing_extensions import TypedDict
+from pydantic import BaseModel, ConfigDict
 
-from getml_io.metadata.dataframe_information import DataFrameInformation
-from getml_io.metadata.utils import derive_instance_with_relative_path
+from getml_io.metadata.dataframe_information import (
+    DataFrameInformation,
+    DataFrameInformationByName,
+)
 
 
-class ContainerInformationDict(TypedDict):
-    id: str
-    population: DataFrameInformation | None
-    peripheral: Mapping[str, DataFrameInformation]
-    subsets: Mapping[str, DataFrameInformation]
-    deep_copy: bool
+class ContainerInformation(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
 
-
-@dataclass
-class ContainerInformation:
     id: str
     population: DataFrameInformation | None
-    peripheral: Mapping[str, DataFrameInformation]
-    subsets: Mapping[str, DataFrameInformation]
+    peripheral: DataFrameInformationByName
+    subsets: DataFrameInformationByName
     deep_copy: bool
-    path: Annotated[Path, Field(exclude=True)]
-
-    # TODO @urfoex: #53 Adjust relative path already in serialization function
-    @model_serializer()
-    def _serialize_model(
-        self,
-    ) -> ContainerInformationDict:
-        return {
-            "id": self.id,
-            "population": self._create_dataframe_information_with_relative_path(
-                self.population,
-            )
-            if self.population
-            else None,
-            "peripheral": {
-                name: self._create_dataframe_information_with_relative_path(peripheral)
-                for name, peripheral in self.peripheral.items()
-            },
-            "subsets": {
-                name: self._create_dataframe_information_with_relative_path(subset)
-                for name, subset in self.subsets.items()
-            },
-            "deep_copy": self.deep_copy,
-        }
-
-    def _create_dataframe_information_with_relative_path(
-        self,
-        dataframe_information: DataFrameInformation,
-    ) -> DataFrameInformation:
-        return derive_instance_with_relative_path(
-            dataframe_information,
-            self.path,
-        )

src/getml_io/metadata/data_model_information.py

@@ -1,13 +1,15 @@
 from __future__ import annotations
 
 from collections.abc import Mapping, Sequence
+from typing import ClassVar
 
-from pydantic.dataclasses import dataclass
+from pydantic import BaseModel, ConfigDict
 
 from getml_io.metadata.placeholder_information import PlaceholderInformation
 
 
-@dataclass(frozen=True)
-class DataModelInformation:
+class DataModelInformation(BaseModel):
+    model_config: ClassVar[ConfigDict] = ConfigDict(frozen=True)
+
     population: PlaceholderInformation
     peripheral: Mapping[str, Sequence[PlaceholderInformation]]