renardeinside

class GitSource(FlexibleModel):
    git_url: str
    git_provider: str
    git_branch: Optional[str]
    git_tag: Optional[str]
    git_commit: Optional[str]

    @root_validator(pre=True)
    def _validate(cls, values):  # noqa
        at_least_one_of(["git_branch", "git_tag", "git_commit"], values)

renardeinside

def mutually_exclusive(fields_names: List[str], values: Dict[str, Any]):
    non_empty_values = [key for key, item in values.items() if item]  # will coalesce both checks for None and []
    _matching_fields = [f for f in fields_names if f in non_empty_values]
    if len(_matching_fields) > 1:
        raise ValueError(
            f"""
            The following fields {_matching_fields} are mutually exclusive.
            Provided payload: {values}
        """,
        )

renardeinside

class BaseNameMixin(BaseModel):
    _only_one_provided = root_validator(pre=True, allow_reuse=True)(
        lambda _, values: at_least_one_by_suffix("_name", values)
    )

renardeinside

class BaseTaskMixin(BaseModel):
    _only_one_provided = root_validator(pre=True, allow_reuse=True)(
        lambda _, values: at_least_one_by_suffix("_task", values)
    )

renardeinside

def at_least_one_by_suffix(suffix: str, values: Dict[str, Any]):
    _matching_fields = [f for f in values if f.endswith(suffix)]
    if not _matching_fields:
        raise ValueError(
            f"""
                At least one field with suffix {suffix} should be provided.
                Provided payload: {values}
            """,
        )
    return values

renardeinside

import requests

resp = requests.get("https://reqres.in/api/users").json()

required_value = [o for o in resp["data"] if o["some_property"] == "something"][0]
nest_prop = required_value.get("some_nested_property")

if nest_prop["something"]:
    do_something()
else:

renardeinside

import requests

resp = requests.get("https://some/api/endpoint").json()
required_value = [o for o in resp if o["some_property"] == "something"]

if required_value["some_other_property"]:
    do_something()
else:
    do_something_else()

renardeinside

# Custom section is used to store configurations that might be repetative.
# Please read YAML documentation for details on how to use substitutions and anchors.
custom:
  basic-cluster-props: &basic-cluster-props
    spark_version: "11.1.x-cpu-ml-scala2.12"

  basic-static-cluster: &basic-static-cluster
    <<: *basic-cluster-props
    instance_pool_name: "f8s-v2-pool"
    driver_instance_pool_name: "f8s-v2-pool"

renardeinside

def test_trainer_trials(
    spark: SparkSession, dataset_fixture: pd.DataFrame, mlflow_local: MlflowInfo
):
    model_data = Provider.get_data(
        dataset_fixture, SourceMetadata(version=0, database="db", table="table")
    )

    def custom_search_space():
        search_space = {
            "classifier": {

renardeinside

class Trainer:
    
    # omitted for readability
    
    def _train_model_and_log_results(
        self, parameters: SearchSpace
    ) -> Tuple[Dict[str, Any], Pipeline]:

        pipeline = Provider.get_pipeline(parameters)
        pipeline.fit(self.data.train.X, self.data.train.y)