Skip to content

Raw Data Definitions

RawDataDefinitions(perfdb)

Class used for handling raw data definitions. Can be accessed via perfdb.rawdata.definitions.

Parameters:

  • perfdb

    (PerfDB) –

    Top level object carrying all functionality and the connection handler.

Source code in echo_postgres/perfdb_root.py
Python
def __init__(self, perfdb: e_pg.PerfDB) -> None:
    """Base class that all subclasses should inherit from.

    Parameters
    ----------
    perfdb : PerfDB
        Top level object carrying all functionality and the connection handler.

    """
    self._perfdb: e_pg.PerfDB = perfdb

get(object_names=None, object_models=None, raw_data_names=None, data_source_types=None, filter_type='and', output_type='DataFrame')

Gets the raw data definitions that match the filters.

The most useful keys/columns returned are:

  • raw_data_id
  • display_name
  • description
  • data_type_name
  • data_source_type_name

Parameters:

  • object_names

    (list[str] | None, default: None ) –

    List of object names to filter the results. If set, will add the models of these objects to the object_models filter. By default None

  • object_models

    (list[str] | None, default: None ) –

    List of object model names to filter the results. By default None

  • raw_data_names

    (str | list[str] | None, default: None ) –

    List of raw data definition names to filter the results. If provided as a string will be treated as regex. By default None

  • data_source_types

    (list[str] | None, default: None ) –

    List of data source type names to filter the results. By default None

  • filter_type

    (Literal['and', 'or'], default: 'and' ) –

    How to treat multiple filters. Can be one of ["and", "or"]. By default "and"

  • output_type

    (Literal['dict', 'DataFrame', 'pl.DataFrame'], default: 'DataFrame' ) –

    Output type of the data. Can be one of ["dict", "DataFrame", "pl.DataFrame"] By default "DataFrame"

Returns:

  • DataFrame –

    If output_type is "DataFrame", returns a pandas DataFrame with the following format: index=MultiIndex["object_model_name", "raw_data_name"], columns=["attribute1", "attribute2", ...]

  • DataFrame –

    If output_type is "pl.DataFrame", returns a Polars DataFrame

  • dict[str, dict[str, dict[str, Any]]] –

    If output_type is "dict", returns a dictionary in the format {object_model: {raw_data_name: {attribute1: value1, attribute2: value2, ...}, ...}, ...}

Source code in echo_postgres/rawdata_definitions.py
Python
@validate_call
def get(
    self,
    object_names: list[str] | None = None,
    object_models: list[str] | None = None,
    raw_data_names: str | list[str] | None = None,
    data_source_types: list[str] | None = None,
    filter_type: Literal["and", "or"] = "and",
    output_type: Literal["dict", "DataFrame", "pl.DataFrame"] = "DataFrame",
) -> pd.DataFrame | pl.DataFrame | dict[str, dict[str, dict[str, Any]]]:
    """Gets the raw data definitions that match the filters.

    The most useful keys/columns returned are:

    - raw_data_id
    - display_name
    - description
    - data_type_name
    - data_source_type_name

    Parameters
    ----------
    object_names : list[str] | None, optional
        List of object names to filter the results. If set, will add the models of these objects to the object_models filter.
        By default None
    object_models : list[str] | None, optional
        List of object model names to filter the results.
        By default None
    raw_data_names : str | list[str] | None, optional
        List of raw data definition names to filter the results. If provided as a string will be treated as regex.
        By default None
    data_source_types : list[str] | None, optional
        List of data source type names to filter the results.
        By default None
    filter_type : Literal["and", "or"], optional
        How to treat multiple filters. Can be one of ["and", "or"].
        By default "and"
    output_type : Literal["dict", "DataFrame", "pl.DataFrame"], optional
        Output type of the data. Can be one of ["dict", "DataFrame", "pl.DataFrame"]
        By default "DataFrame"

    Returns
    -------
    pd.DataFrame
        If output_type is "DataFrame", returns a pandas DataFrame with the following format: index=MultiIndex["object_model_name", "raw_data_name"], columns=["attribute1", "attribute2", ...]
    pl.DataFrame
        If output_type is "pl.DataFrame", returns a Polars DataFrame
    dict[str, dict[str, dict[str, Any]]]
        If output_type is "dict", returns a dictionary in the format {object_model: {raw_data_name: {attribute1: value1, attribute2: value2, ...}, ...}, ...}
    """
    # checking inputs
    where = self._check_get_args(
        object_names=object_names,
        object_models=object_models,
        raw_data_names=raw_data_names,
        data_source_types=data_source_types,
        filter_type=filter_type,
    )

    if filter_type not in ["and", "or"]:
        raise ValueError(f"filter_type must be one of ['and', 'or'], not {filter_type}")
    # getting the definitions
    query = [
        sql.SQL("SELECT * FROM performance.v_raw_data_def "),
    ]
    if where:
        query.append(where)
    query.append(sql.SQL(" ORDER BY object_model_name, name"))

    query = sql.Composed(query)

    df = self._perfdb.conn.read_to_polars(query)

    # renaming and dropping unnecessary columns before conversion
    df = df.rename({"id": "raw_data_id", "name": "raw_data_name"})
    if "object_model_id" in df.columns:
        df = df.drop("object_model_id")

    return convert_output(
        df,
        output_type,
        index_col=["object_model_name", "raw_data_name"],
        nest_by_index=True,
    )

get_ids(object_names=None, object_models=None, raw_data_names=None, data_source_types=None, filter_type='and')

Gets the IDs of the raw data definitions that match the filters.

Parameters:

  • object_names

    (list[str] | None, default: None ) –

    List of object names to filter the results. If set, will add the models of these objects to the object_models filter. By default None

  • object_models

    (list[str] | None, default: None ) –

    List of object model names to filter the results. By default None

  • raw_data_names

    (str | list[str] | None, default: None ) –

    List of raw data definition names to filter the results. If provided as a string will be treated as regex. By default None

  • data_source_types

    (list[str] | None, default: None ) –

    List of data source type names to filter the results. By default None

  • filter_type

    (Literal['and', 'or'], default: 'and' ) –

    How to treat multiple filters. Can be one of ["and", "or"]. By default "and"

Returns:

  • dict[str, dict[str, int]] –

    Dict in the format {object_model: {raw_data_name: raw_data_id, ...}, ...}

Source code in echo_postgres/rawdata_definitions.py
Python
@validate_call
def get_ids(
    self,
    object_names: list[str] | None = None,
    object_models: list[str] | None = None,
    raw_data_names: str | list[str] | None = None,
    data_source_types: list[str] | None = None,
    filter_type: Literal["and", "or"] = "and",
) -> dict[str, dict[str, int]]:
    """Gets the IDs of the raw data definitions that match the filters.

    Parameters
    ----------
    object_names : list[str] | None, optional
        List of object names to filter the results. If set, will add the models of these objects to the object_models filter.
        By default None
    object_models : list[str] | None, optional
        List of object model names to filter the results.
        By default None
    raw_data_names : str | list[str] | None, optional
        List of raw data definition names to filter the results. If provided as a string will be treated as regex.
        By default None
    data_source_types : list[str] | None, optional
        List of data source type names to filter the results.
        By default None
    filter_type : Literal["and", "or"], optional
        How to treat multiple filters. Can be one of ["and", "or"].
        By default "and"

    Returns
    -------
    dict[str, dict[str, int]]
        Dict in the format {object_model: {raw_data_name: raw_data_id, ...}, ...}
    """
    # checking inputs
    where = self._check_get_args(
        object_names=object_names,
        object_models=object_models,
        raw_data_names=raw_data_names,
        data_source_types=data_source_types,
        filter_type=filter_type,
    )

    if filter_type not in ["and", "or"]:
        raise ValueError(f"filter_type must be one of ['and', 'or'], not {filter_type}")

    # getting the definitions
    query = [
        sql.SQL("SELECT object_model_name, name, id FROM performance.v_raw_data_def "),
    ]
    if where:
        query.append(where)
    query.append(sql.SQL(" ORDER BY object_model_name, name"))

    query = sql.Composed(query)

    df = self._perfdb.conn.read_to_polars(query)

    # converting to dictionary
    result = {}
    for row in df.iter_rows(named=True):
        obj_model = row["object_model_name"]
        raw_data_name = row["name"]
        rawdata_id = row["id"]
        result.setdefault(obj_model, {})[raw_data_name] = rawdata_id

    return result