data.datasets.ch4_prod - Code Metrics - Inspection of "Biogas generators for eGon100RE" - openego/eGon-data - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — dev (#931)

unknown

created 2023-03-31 09:01 UTC

data.datasets.ch4_prod A

↳ Parent: Project

Complexity

Total Complexity

Size/Duplication

Total Lines	413
Duplicated Lines	0 %

Importance

Changes

Metric	Value
wmc	13
eloc	171
dl	0
loc	413
rs	10
c	0
b	0
f	0

5 Functions

Rating	Name	Size	Complexity
B	load_NG_generators()	107	4
B	load_biogas_generators()	106	3
A	import_gas_generators()	99	3
A	download_biogas_data()	20	1
A	insert_ch4_generators()	13	1

1 Method

Rating	Name	Duplication	Size	Complexity
A	CH4Production.__init__()	0	6	1

# -*- coding: utf-8 -*-
"""
The central module containing code dealing with importing CH4 production data for eGon2035.

For eGon2035, the gas produced in Germany can be natural gas or biogas.
The source productions are geolocalised potentials described as PyPSA
generators. These generators are not extendable and their overall
production over the year is limited directly in eTraGo by values from
the Netzentwicklungsplan Gas 2020–2030 (36 TWh natural gas and 10 TWh
biogas), also stored in the table
:py:class:`scenario.egon_scenario_parameters <egon.data.datasets.scenario_parameters.EgonScenario>`.

"""
from pathlib import Path
from urllib.request import urlretrieve
import ast

import geopandas as gpd
import numpy as np
import pandas as pd

from egon.data import config, db
from egon.data.config import settings
from egon.data.datasets import Dataset
from egon.data.datasets.scenario_parameters import get_sector_parameters


class CH4Production(Dataset):
    """
    Insert the CH4 productions into the database for eGon2035

    Insert the CH4 productions into the database for eGon2035 by using
    the function :py:func:`import_gas_generators`.

    *Dependencies*
      * :py:class:`GasAreaseGon2035 <egon.data.datasets.gas_areas.GasAreaseGon2035>`
      * :py:class:`GasNodesAndPipes <egon.data.datasets.gas_grid.GasNodesAndPipes>`

    *Resulting tables*
      * :py:class:`grid.egon_etrago_generator <egon.data.datasets.etrago_setup.EgonPfHvGenerator>` is extended

    """

    #:
    name: str = "CH4Production"
    #:

    version: str = "0.0.8"

    def __init__(self, dependencies):
        super().__init__(
            name=self.name,
            version=self.version,
            dependencies=dependencies,
            tasks=(download_biogas_data, insert_ch4_generators),
        )


def load_NG_generators(scn_name="eGon2035"):
    """
    Define the fossil CH4 production units in Germany

    This function reads from the SciGRID_gas dataset the fossil CH4
    production units in Germany, adjuts and returns them.
    Natural gas production reference: SciGRID_gas dataset (datasets/gas_data/data/IGGIELGN_Production.csv
    downloaded in :func:`download_SciGRID_gas_data <egon.data.datasets.gas_grid.download_SciGRID_gas_data>`).
    For more information on these data, refer to the
    `SciGRID_gas IGGIELGN documentation <https://zenodo.org/record/4767098>`_.

    Parameters
    ----------
    scn_name : str
        Name of the scenario.

    Returns
    -------
    CH4_generators_list : pandas.DataFrame
        Dataframe containing the natural gas production units in Germany

    """
    # read carrier information from scnario parameter data
    scn_params = get_sector_parameters("gas", scn_name)

    target_file = (
        Path(".")
        / "datasets"
        / "gas_data"
        / "data"
        / "IGGIELGN_Productions.csv"
    )

    NG_generators_list = pd.read_csv(
        target_file,
        delimiter=";",
        decimal=".",
        usecols=["lat", "long", "country_code", "param"],
    )

    NG_generators_list = NG_generators_list[
        NG_generators_list["country_code"].str.match("DE")
    ]

    # Cut data to federal state if in testmode
    NUTS1 = []
    for index, row in NG_generators_list.iterrows():
        param = ast.literal_eval(row["param"])
        NUTS1.append(param["nuts_id_1"])
    NG_generators_list = NG_generators_list.assign(NUTS1=NUTS1)

    boundary = settings()["egon-data"]["--dataset-boundary"]
    if boundary != "Everything":
        map_states = {
            "Baden-Württemberg": "DE1",
            "Nordrhein-Westfalen": "DEA",
            "Hessen": "DE7",
            "Brandenburg": "DE4",
            "Bremen": "DE5",
            "Rheinland-Pfalz": "DEB",
            "Sachsen-Anhalt": "DEE",
            "Schleswig-Holstein": "DEF",
            "Mecklenburg-Vorpommern": "DE8",
            "Thüringen": "DEG",
            "Niedersachsen": "DE9",
            "Sachsen": "DED",
            "Hamburg": "DE6",
            "Saarland": "DEC",
            "Berlin": "DE3",
            "Bayern": "DE2",
        }

        NG_generators_list = NG_generators_list[
            NG_generators_list["NUTS1"].isin([map_states[boundary], np.nan])
        ]

    NG_generators_list = NG_generators_list.rename(
        columns={"lat": "y", "long": "x"}
    )
    NG_generators_list = gpd.GeoDataFrame(
        NG_generators_list,
        geometry=gpd.points_from_xy(
            NG_generators_list["x"], NG_generators_list["y"]
        ),
    )
    NG_generators_list = NG_generators_list.rename(
        columns={"geometry": "geom"}
    ).set_geometry("geom", crs=4326)

    # Insert p_nom
    p_nom = []
    for index, row in NG_generators_list.iterrows():
        param = ast.literal_eval(row["param"])
        p_nom.append(param["max_supply_M_m3_per_d"])

    conversion_factor = 437.5  # MCM/day to MWh/h
    NG_generators_list["p_nom"] = [i * conversion_factor for i in p_nom]

    # Add missing columns
    NG_generators_list["marginal_cost"] = scn_params["marginal_cost"]["CH4"]

    # Remove useless columns
    NG_generators_list = NG_generators_list.drop(
        columns=["x", "y", "param", "country_code", "NUTS1"]
    )

    return NG_generators_list


def download_biogas_data():
    """Download the biogas production units data in Germany

    Parameters
    ----------
    None

    Returns
    -------
    None

    """
    basename = "Biogaspartner_Einspeiseatlas_Deutschland_2021.xlsx"
    url = (
        "https://www.biogaspartner.de/fileadmin/Biogaspartner/Dokumente/Einspeiseatlas/"
        + basename
    )
    target_file = Path(".") / "datasets" / "gas_data" / basename

    urlretrieve(url, target_file)


def load_biogas_generators(scn_name):
    """
    Define the biogas production units in Germany

    This function download the Biogaspartner Einspeiseatlas into
    (datasets/gas_data/Biogaspartner_Einspeiseatlas_Deutschland_2021.xlsx),
    reads the biogas production units in Germany data, adjuts and
    returns them.
    For more information on these data refer, to the
    `Einspeiseatlas website <https://www.biogaspartner.de/einspeiseatlas/>`_.

    Parameters
    ----------
    scn_name : str
        Name of the scenario

    Returns
    -------
    CH4_generators_list : pandas.DataFrame
        Dataframe containing the biogas production units in Germany

    """
    # read carrier information from scnario parameter data
    scn_params = get_sector_parameters("gas", scn_name)

    basename = "Biogaspartner_Einspeiseatlas_Deutschland_2021.xlsx"
    target_file = Path(".") / "datasets" / "gas_data" / basename

    # Read-in data from csv-file
    biogas_generators_list = pd.read_excel(
        target_file,
        usecols=["Koordinaten", "Einspeisung Biomethan [(N*m^3)/h)]"],
    )

    x = []
    y = []
    for index, row in biogas_generators_list.iterrows():
        coordinates = row["Koordinaten"].split(",")
        y.append(coordinates[0])
        x.append(coordinates[1])
    biogas_generators_list["x"] = x
    biogas_generators_list["y"] = y

    biogas_generators_list = gpd.GeoDataFrame(
        biogas_generators_list,
        geometry=gpd.points_from_xy(
            biogas_generators_list["x"], biogas_generators_list["y"]
        ),
    )
    biogas_generators_list = biogas_generators_list.rename(
        columns={"geometry": "geom"}
    ).set_geometry("geom", crs=4326)

    # Connect to local database
    engine = db.engine()

    # Cut data to federal state if in testmode
    boundary = settings()["egon-data"]["--dataset-boundary"]
    if boundary != "Everything":
        db.execute_sql(
            """
              DROP TABLE IF EXISTS grid.egon_biogas_generator CASCADE;
            """
        )
        biogas_generators_list.to_postgis(
            "egon_biogas_generator",
            engine,
            schema="grid",
            index=False,
            if_exists="replace",
        )

        sql = """SELECT *
            FROM grid.egon_biogas_generator, boundaries.vg250_sta_union as vg
            WHERE ST_Transform(vg.geometry,4326) && egon_biogas_generator.geom
            AND ST_Contains(ST_Transform(vg.geometry,4326), egon_biogas_generator.geom)"""

        biogas_generators_list = gpd.GeoDataFrame.from_postgis(
            sql, con=engine, geom_col="geom", crs=4326
        )
        biogas_generators_list = biogas_generators_list.drop(
            columns=["id", "bez", "area_ha", "geometry"]
        )
        db.execute_sql(
            """
              DROP TABLE IF EXISTS grid.egon_biogas_generator CASCADE;
            """
        )

    # Insert p_nom
    conversion_factor = 0.01083  # m^3/h to MWh/h
    biogas_generators_list["p_nom"] = [
        i * conversion_factor
        for i in biogas_generators_list["Einspeisung Biomethan [(N*m^3)/h)]"]
    ]

    # Add missing columns
    biogas_generators_list["marginal_cost"] = scn_params["marginal_cost"][
        "biogas"
    ]

    # Remove useless columns
    biogas_generators_list = biogas_generators_list.drop(
        columns=["x", "y", "Koordinaten", "Einspeisung Biomethan [(N*m^3)/h)]"]
    )
    return biogas_generators_list


def import_gas_generators(scn_name):
    """
    Insert list of gas production units into the database

    To insert the gas production units into the database, the following
    steps are followed:

      * cleaning of the database table grid.egon_etrago_generator of the
        CH4 generators of the specific scenario (eGon2035),
      * call of the functions :py:func:`load_NG_generators` and
        :py:func:`load_biogas_generators` that respectively return
        dataframes containing the natural- an bio-gas production units
        in Germany,
      * attribution of the bus_id to which each generator is connected
        (call the function :func:`assign_gas_bus_id <egon.data.db.assign_gas_bus_id>`
        from :py:mod:`egon.data.db <egon.data.db>`),
      * aggregation of the CH4 productions with same properties at the
        same bus. The properties that should be the same in order that
        different generators are aggregated are:
          * scenario
          * carrier
          * marginal cost: this parameter differentiates the natural gas
            generators from the biogas generators,
      * addition of the missing columns: scn_name, carrier and
        generator_id,
      * insertion of the generators into the database.

    Parameters
    ----------
    scn_name : str
        Name of the scenario.

    Returns
    -------
    None

    """
    carrier = "CH4"

    # Connect to local database
    engine = db.engine()

    # Select source and target from dataset configuration
    source = config.datasets()["gas_prod"]["source"]
    target = config.datasets()["gas_prod"]["target"]

    # Clean table
    db.execute_sql(
        f"""
        DELETE FROM {target['stores']['schema']}.{target['stores']['table']}
        WHERE "carrier" = '{carrier}' AND
        scn_name = '{scn_name}' AND bus not IN (
            SELECT bus_id FROM {source['buses']['schema']}.{source['buses']['table']}
            WHERE scn_name = '{scn_name}' AND country != 'DE'
        );
        """
    )

    if scn_name == "eGon2035":
        CH4_generators_list = pd.concat(
            [load_NG_generators(scn_name), load_biogas_generators(scn_name)]
        )

    elif scn_name == "eGon100RE":
        CH4_generators_list = load_biogas_generators(scn_name)

    # Add missing columns
    c = {"scn_name": scn_name, "carrier": carrier}
    CH4_generators_list = CH4_generators_list.assign(**c)


    # Match to associated CH4 bus
    CH4_generators_list = db.assign_gas_bus_id(
        CH4_generators_list, scn_name, carrier
    )

    # Remove useless columns
    CH4_generators_list = CH4_generators_list.drop(columns=["geom", "bus_id"])

    # Aggregate ch4 productions with same properties at the same bus
    CH4_generators_list = (
        CH4_generators_list.groupby(
            ["bus", "carrier", "scn_name", "marginal_cost"]
        )
        .agg({"p_nom": "sum"})
        .reset_index(drop=False)
    )

    new_id = db.next_etrago_id("generator")
    CH4_generators_list["generator_id"] = range(
        new_id, new_id + len(CH4_generators_list)
    )

    # Insert data to db
    CH4_generators_list.to_sql(
        target["stores"]["table"],
        engine,
        schema=target["stores"]["schema"],
        index=False,
        if_exists="append",
    )


def insert_ch4_generators():
    """Insert gas production units in database for both scenarios

    Parameters
    ----------
    None

    Returns
    -------
    None
    """
    import_gas_generators("eGon2035")
    import_gas_generators("eGon100RE")


1			# -- coding: utf-8 --
2			"""
3			The central module containing code dealing with importing CH4 production data for eGon2035.
4
5			For eGon2035, the gas produced in Germany can be natural gas or biogas.
6			The source productions are geolocalised potentials described as PyPSA
7			generators. These generators are not extendable and their overall
8			production over the year is limited directly in eTraGo by values from
9			the Netzentwicklungsplan Gas 2020–2030 (36 TWh natural gas and 10 TWh
10			biogas), also stored in the table
11			:py:class:`scenario.egon_scenario_parameters <egon.data.datasets.scenario_parameters.EgonScenario>`.
12
13			"""
14			from pathlib import Path
15			from urllib.request import urlretrieve
16			import ast
17
18			import geopandas as gpd
19			import numpy as np
20			import pandas as pd
21
22			from egon.data import config, db
23			from egon.data.config import settings
24			from egon.data.datasets import Dataset
25			from egon.data.datasets.scenario_parameters import get_sector_parameters
26
27
28			class CH4Production(Dataset):
29			"""
30			Insert the CH4 productions into the database for eGon2035
31
32			Insert the CH4 productions into the database for eGon2035 by using
33			the function :py:func:`import_gas_generators`.
34
35			Dependencies
36			* :py:class:`GasAreaseGon2035 <egon.data.datasets.gas_areas.GasAreaseGon2035>`
37			* :py:class:`GasNodesAndPipes <egon.data.datasets.gas_grid.GasNodesAndPipes>`
38
39			Resulting tables
40			* :py:class:`grid.egon_etrago_generator <egon.data.datasets.etrago_setup.EgonPfHvGenerator>` is extended
41
42			"""
43
44			#:
45			name: str = "CH4Production"
46			#:
47
48			version: str = "0.0.8"
49
50			def __init__(self, dependencies):
51			super().__init__(
52			name=self.name,
53			version=self.version,
54			dependencies=dependencies,
55			tasks=(download_biogas_data, insert_ch4_generators),
56			)
57
58
59			def load_NG_generators(scn_name="eGon2035"):
60			"""
61			Define the fossil CH4 production units in Germany
62
63			This function reads from the SciGRID_gas dataset the fossil CH4
64			production units in Germany, adjuts and returns them.
65			Natural gas production reference: SciGRID_gas dataset (datasets/gas_data/data/IGGIELGN_Production.csv
66			downloaded in :func:`download_SciGRID_gas_data <egon.data.datasets.gas_grid.download_SciGRID_gas_data>`).
67			For more information on these data, refer to the
68			`SciGRID_gas IGGIELGN documentation <https://zenodo.org/record/4767098>`_.
69
70			Parameters
71			----------
72			scn_name : str
73			Name of the scenario.
74
75			Returns
76			-------
77			CH4_generators_list : pandas.DataFrame
78			Dataframe containing the natural gas production units in Germany
79
80			"""
81			# read carrier information from scnario parameter data
82			scn_params = get_sector_parameters("gas", scn_name)
83
84			target_file = (
85			Path(".")
86			/ "datasets"
87			/ "gas_data"
88			/ "data"
89			/ "IGGIELGN_Productions.csv"
90			)
91
92			NG_generators_list = pd.read_csv(
93			target_file,
94			delimiter=";",
95			decimal=".",
96			usecols=["lat", "long", "country_code", "param"],
97			)
98
99			NG_generators_list = NG_generators_list[
100			NG_generators_list["country_code"].str.match("DE")
101			]
102
103			# Cut data to federal state if in testmode
104			NUTS1 = []
105			for index, row in NG_generators_list.iterrows():
106			param = ast.literal_eval(row["param"])
107			NUTS1.append(param["nuts_id_1"])
108			NG_generators_list = NG_generators_list.assign(NUTS1=NUTS1)
109
110			boundary = settings()["egon-data"]["--dataset-boundary"]
111			if boundary != "Everything":
112			map_states = {
113			"Baden-Württemberg": "DE1",
114			"Nordrhein-Westfalen": "DEA",
115			"Hessen": "DE7",
116			"Brandenburg": "DE4",
117			"Bremen": "DE5",
118			"Rheinland-Pfalz": "DEB",
119			"Sachsen-Anhalt": "DEE",
120			"Schleswig-Holstein": "DEF",
121			"Mecklenburg-Vorpommern": "DE8",
122			"Thüringen": "DEG",
123			"Niedersachsen": "DE9",
124			"Sachsen": "DED",
125			"Hamburg": "DE6",
126			"Saarland": "DEC",
127			"Berlin": "DE3",
128			"Bayern": "DE2",
129			}
130
131			NG_generators_list = NG_generators_list[
132			NG_generators_list["NUTS1"].isin([map_states[boundary], np.nan])
133			]
134
135			NG_generators_list = NG_generators_list.rename(
136			columns={"lat": "y", "long": "x"}
137			)
138			NG_generators_list = gpd.GeoDataFrame(
139			NG_generators_list,
140			geometry=gpd.points_from_xy(
141			NG_generators_list["x"], NG_generators_list["y"]
142			),
143			)
144			NG_generators_list = NG_generators_list.rename(
145			columns={"geometry": "geom"}
146			).set_geometry("geom", crs=4326)
147
148			# Insert p_nom
149			p_nom = []
150			for index, row in NG_generators_list.iterrows():
151			param = ast.literal_eval(row["param"])
152			p_nom.append(param["max_supply_M_m3_per_d"])
153
154			conversion_factor = 437.5 # MCM/day to MWh/h
155			NG_generators_list["p_nom"] = [i * conversion_factor for i in p_nom]
156
157			# Add missing columns
158			NG_generators_list["marginal_cost"] = scn_params["marginal_cost"]["CH4"]
159
160			# Remove useless columns
161			NG_generators_list = NG_generators_list.drop(
162			columns=["x", "y", "param", "country_code", "NUTS1"]
163			)
164
165			return NG_generators_list
166
167
168			def download_biogas_data():
169			"""Download the biogas production units data in Germany
170
171			Parameters
172			----------
173			None
174
175			Returns
176			-------
177			None
178
179			"""
180			basename = "Biogaspartner_Einspeiseatlas_Deutschland_2021.xlsx"
181			url = (
182			"https://www.biogaspartner.de/fileadmin/Biogaspartner/Dokumente/Einspeiseatlas/"
183			+ basename
184			)
185			target_file = Path(".") / "datasets" / "gas_data" / basename
186
187			urlretrieve(url, target_file)
188
189
190			def load_biogas_generators(scn_name):
191			"""
192			Define the biogas production units in Germany
193
194			This function download the Biogaspartner Einspeiseatlas into
195			(datasets/gas_data/Biogaspartner_Einspeiseatlas_Deutschland_2021.xlsx),
196			reads the biogas production units in Germany data, adjuts and
197			returns them.
198			For more information on these data refer, to the
199			`Einspeiseatlas website <https://www.biogaspartner.de/einspeiseatlas/>`_.
200
201			Parameters
202			----------
203			scn_name : str
204			Name of the scenario
205
206			Returns
207			-------
208			CH4_generators_list : pandas.DataFrame
209			Dataframe containing the biogas production units in Germany
210
211			"""
212			# read carrier information from scnario parameter data
213			scn_params = get_sector_parameters("gas", scn_name)
214
215			basename = "Biogaspartner_Einspeiseatlas_Deutschland_2021.xlsx"
216			target_file = Path(".") / "datasets" / "gas_data" / basename
217
218			# Read-in data from csv-file
219			biogas_generators_list = pd.read_excel(
220			target_file,
221			usecols=["Koordinaten", "Einspeisung Biomethan [(N*m^3)/h)]"],
222			)
223
224			x = []
225			y = []
226			for index, row in biogas_generators_list.iterrows():
227			coordinates = row["Koordinaten"].split(",")
228			y.append(coordinates[0])
229			x.append(coordinates[1])
230			biogas_generators_list["x"] = x
231			biogas_generators_list["y"] = y
232
233			biogas_generators_list = gpd.GeoDataFrame(
234			biogas_generators_list,
235			geometry=gpd.points_from_xy(
236			biogas_generators_list["x"], biogas_generators_list["y"]
237			),
238			)
239			biogas_generators_list = biogas_generators_list.rename(
240			columns={"geometry": "geom"}
241			).set_geometry("geom", crs=4326)
242
243			# Connect to local database
244			engine = db.engine()
245
246			# Cut data to federal state if in testmode
247			boundary = settings()["egon-data"]["--dataset-boundary"]
248			if boundary != "Everything":
249			db.execute_sql(
250			"""
251			DROP TABLE IF EXISTS grid.egon_biogas_generator CASCADE;
252			"""
253			)
254			biogas_generators_list.to_postgis(
255			"egon_biogas_generator",
256			engine,
257			schema="grid",
258			index=False,
259			if_exists="replace",
260			)
261
262			sql = """SELECT *
263			FROM grid.egon_biogas_generator, boundaries.vg250_sta_union as vg
264			WHERE ST_Transform(vg.geometry,4326) && egon_biogas_generator.geom
265			AND ST_Contains(ST_Transform(vg.geometry,4326), egon_biogas_generator.geom)"""
266
267			biogas_generators_list = gpd.GeoDataFrame.from_postgis(
268			sql, con=engine, geom_col="geom", crs=4326
269			)
270			biogas_generators_list = biogas_generators_list.drop(
271			columns=["id", "bez", "area_ha", "geometry"]
272			)
273			db.execute_sql(
274			"""
275			DROP TABLE IF EXISTS grid.egon_biogas_generator CASCADE;
276			"""
277			)
278
279			# Insert p_nom
280			conversion_factor = 0.01083 # m^3/h to MWh/h
281			biogas_generators_list["p_nom"] = [
282			i * conversion_factor
283			for i in biogas_generators_list["Einspeisung Biomethan [(N*m^3)/h)]"]
284			]
285
286			# Add missing columns
287			biogas_generators_list["marginal_cost"] = scn_params["marginal_cost"][
288			"biogas"
289			]
290
291			# Remove useless columns
292			biogas_generators_list = biogas_generators_list.drop(
293			columns=["x", "y", "Koordinaten", "Einspeisung Biomethan [(N*m^3)/h)]"]
294			)
295			return biogas_generators_list
296
297
298			def import_gas_generators(scn_name):
299			"""
300			Insert list of gas production units into the database
301
302			To insert the gas production units into the database, the following
303			steps are followed:
304
305			* cleaning of the database table grid.egon_etrago_generator of the
306			CH4 generators of the specific scenario (eGon2035),
307			* call of the functions :py:func:`load_NG_generators` and
308			:py:func:`load_biogas_generators` that respectively return
309			dataframes containing the natural- an bio-gas production units
310			in Germany,
311			* attribution of the bus_id to which each generator is connected
312			(call the function :func:`assign_gas_bus_id <egon.data.db.assign_gas_bus_id>`
313			from :py:mod:`egon.data.db <egon.data.db>`),
314			* aggregation of the CH4 productions with same properties at the
315			same bus. The properties that should be the same in order that
316			different generators are aggregated are:
317			* scenario
318			* carrier
319			* marginal cost: this parameter differentiates the natural gas
320			generators from the biogas generators,
321			* addition of the missing columns: scn_name, carrier and
322			generator_id,
323			* insertion of the generators into the database.
324
325			Parameters
326			----------
327			scn_name : str
328			Name of the scenario.
329
330			Returns
331			-------
332			None
333
334			"""
335			carrier = "CH4"
336
337			# Connect to local database
338			engine = db.engine()
339
340			# Select source and target from dataset configuration
341			source = config.datasets()["gas_prod"]["source"]
342			target = config.datasets()["gas_prod"]["target"]
343
344			# Clean table
345			db.execute_sql(
346			f"""
347			DELETE FROM {target['stores']['schema']}.{target['stores']['table']}
348			WHERE "carrier" = '{carrier}' AND
349			scn_name = '{scn_name}' AND bus not IN (
350			SELECT bus_id FROM {source['buses']['schema']}.{source['buses']['table']}
351			WHERE scn_name = '{scn_name}' AND country != 'DE'
352			);
353			"""
354			)
355
356			if scn_name == "eGon2035":
357			CH4_generators_list = pd.concat(
358			[load_NG_generators(scn_name), load_biogas_generators(scn_name)]
359			)
360
361			elif scn_name == "eGon100RE":
362			CH4_generators_list = load_biogas_generators(scn_name)
363
364			# Add missing columns
365			c = {"scn_name": scn_name, "carrier": carrier}
366			CH4_generators_list = CH4_generators_list.assign(**c)
			0 ignored issues – show introduced 2022-09-12 14:50 UTC by Report Bug Copy Issue Report The variable `CH4_generators_list` does not seem to be defined for all execution paths. Loading history...
367
368			# Match to associated CH4 bus
369			CH4_generators_list = db.assign_gas_bus_id(
370			CH4_generators_list, scn_name, carrier
371			)
372
373			# Remove useless columns
374			CH4_generators_list = CH4_generators_list.drop(columns=["geom", "bus_id"])
375
376			# Aggregate ch4 productions with same properties at the same bus
377			CH4_generators_list = (
378			CH4_generators_list.groupby(
379			["bus", "carrier", "scn_name", "marginal_cost"]
380			)
381			.agg({"p_nom": "sum"})
382			.reset_index(drop=False)
383			)
384
385			new_id = db.next_etrago_id("generator")
386			CH4_generators_list["generator_id"] = range(
387			new_id, new_id + len(CH4_generators_list)
388			)
389
390			# Insert data to db
391			CH4_generators_list.to_sql(
392			target["stores"]["table"],
393			engine,
394			schema=target["stores"]["schema"],
395			index=False,
396			if_exists="append",
397			)
398
399
400			def insert_ch4_generators():
401			"""Insert gas production units in database for both scenarios
402
403			Parameters
404			----------
405			None
406
407			Returns
408			-------
409			None
410			"""
411			import_gas_generators("eGon2035")
412			import_gas_generators("eGon100RE")
413

openego / eGon-data

Pull Request — dev (#931)

data.datasets.ch4_prod A

Complexity

Size/Duplication

Importance

5 Functions

1 Method

Duplication Side-by-Side

Filter issues like