data.datasets.electrical_neighbours.insert_generators_sq()

Complexity

Conditions

8

Size

Total Lines	128
Code Lines	60

Duplication

Lines	11
Ratio	8.59 %

Importance

Changes

0

"""The central module containing all code dealing with electrical neighbours
def insert_generators_sq(scn_name="status2019"):
    """
    Insert generators for foreign countries based on ENTSO-E data

    Parameters
    ----------
    gen_sq : pandas dataframe
        df with all the foreign generators produced by the function
        entsoe_historic_generation_capacities
    scn_name : str
        The default is "status2019".

    Returns
    -------
    None.

    """
    if "status" in scn_name:
        year = int(scn_name.split("status")[-1])
        year_start_end = {
            "year_start": f"{year}0101",
            "year_end": f"{year+1}0101",
        }
    else:
        raise ValueError("No valid scenario name!")

    df_gen_sq, not_retrieved = entsoe_historic_generation_capacities(
        **year_start_end
    )

    if not_retrieved:

This code seems to be duplicated in your project.

        logger.warning("Generation data from entsoe could not be retrieved.")
        # check for generation backup from former runs
        file_path = Path(
            "./", "entsoe_data", f"gen_entsoe_{scn_name}.csv"
        ).resolve()
        if os.path.isfile(file_path):
            df_gen_sq, not_retrieved = fill_by_backup_data_from_former_runs(
                df_gen_sq, file_path, not_retrieved
            )
        save_entsoe_data(df_gen_sq, file_path=file_path)

    if not_retrieved:
        logger.warning(
            f"Backup data of 2019 is used instead for {not_retrieved}"
        )
        df_gen_sq_backup = pd.read_csv(
            "data_bundle_egon_data/entsoe/gen_entsoe.csv", index_col="Index"
        )
        df_gen_sq = pd.concat(
            [df_gen_sq, df_gen_sq_backup.loc[not_retrieved]], axis=1
        )

    targets = config.datasets()["electrical_neighbours"]["targets"]
    # Delete existing data
    db.execute_sql(
        f"""
        DELETE FROM
        {targets['generators']['schema']}.{targets['generators']['table']}
        WHERE bus IN (
            SELECT bus_id FROM
            {targets['buses']['schema']}.{targets['buses']['table']}
            WHERE country != 'DE'
            AND scn_name = '{scn_name}')
        AND scn_name = '{scn_name}'
        AND carrier != 'CH4'
        """
    )

    db.execute_sql(
        f"""
        DELETE FROM
        {targets['generators_timeseries']['schema']}.
        {targets['generators_timeseries']['table']}
        WHERE generator_id NOT IN (
            SELECT generator_id FROM
            {targets['generators']['schema']}.{targets['generators']['table']}
        )
        AND scn_name = '{scn_name}'
        """
    )
    entsoe_to_bus = entsoe_to_bus_etrago(scn_name)
    carrier_entsoe = map_carriers_entsoe()
    df_gen_sq = df_gen_sq.groupby(axis=1, by=carrier_entsoe).sum()

    # Filter generators modeled as storage and geothermal
    df_gen_sq = df_gen_sq.loc[
        :, ~df_gen_sq.columns.isin(["Hydro Pumped Storage", "geo_thermal"])
    ]

    list_gen_sq = pd.DataFrame(
        dtype=int, columns=["carrier", "country", "capacity"]
    )
    for carrier in df_gen_sq.columns:
        gen_carry = df_gen_sq[carrier]
        for country, cap in gen_carry.items():
            gen = pd.DataFrame(
                {"carrier": carrier, "country": country, "capacity": cap},
                index=[1],
            )
            # print(gen)
            list_gen_sq = pd.concat([list_gen_sq, gen], ignore_index=True)

    list_gen_sq = list_gen_sq[list_gen_sq.capacity > 0]
    list_gen_sq["scenario"] = scn_name

    # Add marginal costs
    list_gen_sq = add_marginal_costs(list_gen_sq)

    # Find foreign bus to assign the generator
    list_gen_sq["bus"] = list_gen_sq.country.map(entsoe_to_bus)

    # insert generators data
    session = sessionmaker(bind=db.engine())()
    for i, row in list_gen_sq.iterrows():
        entry = etrago.EgonPfHvGenerator(
            scn_name=row.scenario,
            generator_id=int(db.next_etrago_id("generator")),
            bus=row.bus,
            carrier=row.carrier,
            p_nom=row.capacity,
            marginal_cost=row.marginal_cost,
        )

        session.add(entry)
        session.commit()

    renewable_timeseries_pypsaeur(scn_name)