Component Instances - History

ComponentInstancesHistory(perfdb)

Class used for handling component instances history. Can be accessed via perfdb.components.instances.history.

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, component_ids=None, component_serial_numbers=None, component_models=None, component_manufacturers=None, component_types=None, locations=None, period=None, filter_type='and', get_attributes=False, output_type='DataFrame')

Gets components instances history (including dates when they were installed and removed).

The most useful keys/columns returned are:

• object_id
• object_name
• component_type_id
• component_type_name
• manufacturer_id
• manufacturer_name
• component_model_id
• component_model_name
• location_id
• location_name
• component_instance_id
• serial_number
• start_date
• end_date
• duration

Parameters:

• object_names

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

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

• component_ids

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

  List of component ids to filter the results. By default None.

• component_serial_numbers

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

  List of component serial numbers to filter the results. By default None.

• component_models

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

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

• component_manufacturers

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

  List of component manufacturer names to filter the results. By default None.

• component_types

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

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

• locations

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

  List of locations to filter the results. By default None.

• period

  (DateTimeRange | None, default: None ) –

  Period to filter the results. If the period when the component is installed on the turbine overlaps this it will be retrieved. By default None.

• filter_type

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

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

• get_attributes

  (bool, default: False ) –

  If True, will also get the attributes of the component models.

• 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:

• list[dict[str, Any]] –

  List with the component instances. Each element is a dictionary with the keys being the column names.

• DataFrame –

  In case output_type is "DataFrame", returns a pandas DataFrame with the component instances.

• DataFrame –

  In case output_type is "pl.DataFrame", returns a Polars DataFrame

Source code in echo_postgres/component_instances_history.py

Python

@validate_call
def get(
    self,
    object_names: list[str] | None = None,
    component_ids: list[int] | None = None,
    component_serial_numbers: list[str] | None = None,
    component_models: list[str] | None = None,
    component_manufacturers: list[str] | None = None,
    component_types: list[str] | None = None,
    locations: list[str] | None = None,
    period: DateTimeRange | None = None,
    filter_type: Literal["and", "or"] = "and",
    get_attributes: bool = False,
    output_type: Literal["dict", "DataFrame", "pl.DataFrame"] = "DataFrame",
) -> list[dict[str, Any]] | pd.DataFrame | pl.DataFrame:
    """Gets components instances history (including dates when they were installed and removed).

    The most useful keys/columns returned are:

    - object_id
    - object_name
    - component_type_id
    - component_type_name
    - manufacturer_id
    - manufacturer_name
    - component_model_id
    - component_model_name
    - location_id
    - location_name
    - component_instance_id
    - serial_number
    - start_date
    - end_date
    - duration

    Parameters
    ----------
    object_names : list[str] | None, optional
        List of object names to filter the results. By default None.
    component_ids : list[int] | None, optional
        List of component ids to filter the results. By default None.
    component_serial_numbers : list[str] | None, optional
        List of component serial numbers to filter the results. By default None.
    component_models : list[str] | None, optional
        List of component model names to filter the results. By default None.
    component_manufacturers : list[str] | None, optional
        List of component manufacturer names to filter the results. By default None.
    component_types : list[str] | None, optional
        List of component type names to filter the results. By default None.
    locations : list[str] | None, optional
        List of locations to filter the results. By default None.
    period : DateTimeRange | None, optional
        Period to filter the results. If the period when the component is installed on the turbine overlaps this it will be retrieved. By default None.
    filter_type : Literal["and", "or"], optional
        How to treat multiple filters. Can be one of ["and", "or"]. By default "and".
    get_attributes : bool, optional
        If True, will also get the attributes of the component models.
    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
    -------
    list[dict[str, Any]]
        List with the component instances. Each element is a dictionary with the keys being the column names.
    pd.DataFrame
        In case output_type is "DataFrame", returns a pandas DataFrame with the component instances.
    pl.DataFrame
        In case output_type is "pl.DataFrame", returns a Polars DataFrame
    """
    where = self._check_get_args(
        object_names=object_names,
        component_ids=component_ids,
        component_serial_numbers=component_serial_numbers,
        component_models=component_models,
        component_manufacturers=component_manufacturers,
        component_types=component_types,
        locations=locations,
        period=period,
        filter_type=filter_type,
    )

    query = [
        sql.SQL(
            "SELECT object_id, object_name, component_type_id, component_type_name, manufacturer_id, manufacturer_name, component_model_id, component_model_name, location_id, location_name, component_instance_id, serial_number, start_date, end_date, EXTRACT(EPOCH FROM duration)::FLOAT AS duration FROM performance.v_component_instance_history ",
        ),
        where,
        sql.SQL(" ORDER BY object_name, start_date"),
    ]
    query = sql.Composed(query)

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

    # casting duration to pl.Duration("ms")
    df = df.with_columns(
        (pl.col("duration") * 1_000).cast(pl.Int64).cast(pl.Duration("ms")).alias("duration"),
    )

    # getting attributes
    if get_attributes:
        # names of the component models
        got_component_instances = df["component_instance_id"].to_list()
        attrs: pl.DataFrame = self._perfdb.components.instances.attributes.get(
            component_ids=got_component_instances,
            output_type="pl.DataFrame",
            values_only=True,
        )
        # pivot the attributes
        attrs = attrs.pivot(index="component_instance_id", on="attribute_name", values="attribute_value")
        # merging the attributes with the component models
        df = df.join(attrs, on="component_instance_id", how="left")

    return convert_output(df, output_type, orient="records")