Source code for arize._generated.api_client.models.dataset

# coding: utf-8

"""
    Arize REST API

    API specification for the backend data server. The API is hosted globally at https://api.arize.com/v2 or in your own environment. 

    The version of the OpenAPI document: 2.0.0
    Generated by OpenAPI Generator (https://openapi-generator.tech)

    Do not edit the class manually.
"""  # noqa: E501


from __future__ import annotations
import pprint
import re  # noqa: F401
import json

from datetime import datetime
from pydantic import BaseModel, ConfigDict, Field, StrictStr
from typing import Any, ClassVar, Dict, List, Optional
from arize._generated.api_client.models.dataset_version import DatasetVersion
from typing import Optional, Set
from typing_extensions import Self



class Dataset(BaseModel):
    """
    A dataset is a structured collection of examples used to test and evaluate LLM applications. Datasets allow you to test models consistently across any real-world scenarios and edge cases, quickly identify regressions, and track measurable improvements. 
    """ # noqa: E501
    id: StrictStr = Field(description="Unique identifier for the dataset")
    name: StrictStr = Field(description="Name of the dataset")
    space_id: StrictStr = Field(description="Unique identifier for the space this dataset belongs to")
    created_at: datetime = Field(description="Timestamp for when the dataset was created")
    updated_at: datetime = Field(description="Timestamp for the last update of the dataset")
    versions: Optional[List[DatasetVersion]] = Field(default=None, description="List of versions associated with this dataset")
    __properties: ClassVar[List[str]] = ["id", "name", "space_id", "created_at", "updated_at", "versions"]

    model_config = ConfigDict(
        populate_by_name=True,
        validate_assignment=True,
        protected_namespaces=(),
    )




    def to_str(self) -> str:
        """Returns the string representation of the model using alias"""
        return pprint.pformat(self.model_dump(by_alias=True))




    def to_json(self) -> str:
        """Returns the JSON representation of the model using alias"""
        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
        return json.dumps(self.to_dict())




    @classmethod
    def from_json(cls, json_str: str) -> Optional[Self]:
        """Create an instance of Dataset from a JSON string"""
        return cls.from_dict(json.loads(json_str))




    def to_dict(self) -> Dict[str, Any]:
        """Return the dictionary representation of the model using alias.

        This has the following differences from calling pydantic's
        `self.model_dump(by_alias=True)`:

        * `None` is only added to the output dict for nullable fields that
          were set at model initialization. Other fields with value `None`
          are ignored.
        """
        excluded_fields: Set[str] = set([
        ])

        _dict = self.model_dump(
            by_alias=True,
            exclude=excluded_fields,
            exclude_none=True,
        )
        # override the default output from pydantic by calling `to_dict()` of each item in versions (list)
        _items = []
        if self.versions:
            for _item_versions in self.versions:
                if _item_versions:
                    _items.append(_item_versions.to_dict())
            _dict['versions'] = _items
        return _dict




    @classmethod
    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
        """Create an instance of Dataset from a dict"""
        if obj is None:
            return None

        if not isinstance(obj, dict):
            return cls.model_validate(obj)

        # raise errors for additional fields in the input
        for _key in obj.keys():
            if _key not in cls.__properties:
                raise ValueError("Error due to additional fields (not defined in Dataset) in the input: " + _key)

        _obj = cls.model_validate({
            "id": obj.get("id"),
            "name": obj.get("name"),
            "space_id": obj.get("space_id"),
            "created_at": obj.get("created_at"),
            "updated_at": obj.get("updated_at"),
            "versions": [DatasetVersion.from_dict(_item) for _item in obj["versions"]] if obj.get("versions") is not None else None
        })
        return _obj