shrecc 0.0.4__tar.gz → 0.0.5.dev2__tar.gz

{shrecc-0.0.4 → shrecc-0.0.5.dev2}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright © 2025 Luxembourg Institute of Science and Technology
+Copyright © 2024,2025,2026 Luxembourg Institute of Science and Technology
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{shrecc-0.0.4/shrecc.egg-info → shrecc-0.0.5.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: shrecc
-Version: 0.0.4
+Version: 0.0.5.dev2
 Summary: SHRECC: Smooth Hourly Resolution Electricity Consumption Calculation
 Author-email: Sabina Bednářová <sabina.bednarova@list.lu>
 Maintainer-email: Sabina Bednářová <sabina.bednarova@list.lu>

{shrecc-0.0.4 → shrecc-0.0.5.dev2}/shrecc/__init__.py

@@ -16,4 +16,4 @@ from .database import create_database, filt_cutoff
 from .download import get_data
 from .treatment import data_processing
 
-__version__ = "0.0.4"
+__version__ = "0.0.5.dev2"

{shrecc-0.0.4 → shrecc-0.0.5.dev2}/shrecc/database.py

@@ -1,9 +1,10 @@
-# Copyright © 2024 Luxembourg Institute of Science and Technology
+# Copyright © 2024,2025,2026 Luxembourg Institute of Science and Technology
 # Licensed under the MIT License (see LICENSE file for details).
 # Authors: [Sabina Bednářová, Thomas Gibon]
 
 from datetime import datetime
 from importlib.resources import files
+from packaging.version import parse as vparse
 from pathlib import Path
 import re
 
@@ -14,10 +15,12 @@ from bw2data.query import Filter, Query
 
 from shrecc.treatment import load_from_pickle, save_to_pickle
 
+UNUSED_SOURCE = "Import balance (physical)"
+
 
 def filt_cutoff(
     countries,
-    times=0,
+    times=[],
     general_range=0,
     refined_range=0,
     freq=0,
@@ -56,8 +59,9 @@ def filt_cutoff(
 
     if general_range:
         year = datetime.strptime(general_range[0], "%Y-%m-%d %H:%M:%S").year
-    elif times:
-        year = datetime.strptime(times[0], "%Y-%m-%d %H:%M:%S").year
+    elif len(times):
+        times = pd.to_datetime(times)
+        year = times[0].year
     else:
         raise ValueError("Either `times` or `general_range` must be provided")
 
@@ -67,7 +71,9 @@ def filt_cutoff(
     dataframe = dataframe.droplevel("source", axis=1)
     dataframe = filter_by_countries(dataframe, countries)
 
-    if times:
+    if len(times):
+        # For backwards compatibility and making sure datetime is used in the filtering
+        times = pd.to_datetime(times)
         dataframe = filter_by_times(dataframe, times)
     if general_range:
         dataframe = filter_by_range(dataframe, general_range, refined_range, freq)
@@ -142,11 +148,13 @@ def prepare_consumption_data(Z_cons):
         pd.DataFrame: The prepared consumption data, with the trade data removed and indices swapped.
     """
     Z_cons = Z_cons.sort_index()
+
     if "trade" in Z_cons.index.get_level_values("source"):
         Z_cons_to_multiply = Z_cons.drop("trade", axis=0).copy()
     else:
         Z_cons_to_multiply = Z_cons.copy()
     Z_cons_to_multiply.index.names = ["source", "geography_mix"]
+
     return Z_cons_to_multiply.swaplevel()
 
 
@@ -390,11 +398,13 @@ def map_known_inputs(eidb_name, dataframe_filt):
         # Only UK seems concerned but consider using a dictionary
         if loc == "UK":
             loc = "GB"
+
         # For ecoinvent > 3.10, the activity names have changed
         # They now use a country code, instead of a full name
         # We deal with them here:
         def repl(match):
             return f"from {country_to_code[match.group(1)]}"
+
         if any(v in eidb_name for v in ("3.11", "3.12")):
             pattern = re.compile(r"from (Germany|France)")
             name = pattern.sub(repl, name)
@@ -497,15 +507,36 @@ def create_activity_dict(dataframe_filt, known_inputs, known_inputs_network, db_
             country = col
             name = f"Electricity mix in {country}"
         code = f"electricity {i}"
+        bd_version = bd.__version__
+        if not isinstance(bd_version, str):
+            bd_version = ".".join(map(str, bd_version))
+        BW2 = vparse(bd_version) < vparse("4")
+        if BW2:
+            act_type = "process"
+            prod_exchange_type = "production"
+        else:
+            act_type = bd.labels.process_node_default
+            prod_exchange_type = bd.labels.production_edge_default
         act = {
             "name": name,
             "unit": "kWh",
             "code": code,
             "location": str(country),
             "reference product": "Electricity mix",
-            "type": "process",
+            "type": act_type,
             "exchanges": [],
         }
+        # Add the production exchange
+        act["exchanges"].append(
+            {
+                "input": (db_name, code),
+                "name": name,
+                "location": str(country),
+                "unit": "kWh",
+                "amount": 1,
+                "type": prod_exchange_type,
+            }
+        )
         for idx in dataframe_filt.index:
             source, exch_name, prod, unit = idx
             if float(dataframe_filt.loc[idx, col]) != 0:

{shrecc-0.0.4 → shrecc-0.0.5.dev2}/shrecc/download.py

@@ -75,6 +75,7 @@ def get_prod(start, end, country, cumul=False, rolling=False):
 def get_trade(start, end, country):
     """
     Downloads trade data from the Energy Charts API. Gets called from `get_data()`.
+    Uses the "cbpf" endpoint of the API.
 
     Args:
         start (int): Start of the download period (output of `year_to_unix()`) in unix seconds.
@@ -295,6 +296,7 @@ def cleaning_data(data, data_dir):
     scale_dict = {"production mix": 1, "trade": 1000, "load": 1}
 
     for country in data.keys():
+        print(f"Processing country: {country}")
         data_clean[country.upper()] = {}
         for k, v in data[country].items():
             if type(v) is pd.DataFrame:  # axis = 1 will soon be depreciated

{shrecc-0.0.4 → shrecc-0.0.5.dev2}/shrecc/treatment.py

@@ -1,4 +1,4 @@
-# Copyright © 2024 Luxembourg Institute of Science and Technology
+# Copyright © 2024,2025,2026 Luxembourg Institute of Science and Technology
 # Licensed under the MIT License (see LICENSE file for details).
 # Authors: [Sabina Bednářová, Thomas Gibon]
 

{shrecc-0.0.4 → shrecc-0.0.5.dev2/shrecc.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: shrecc
-Version: 0.0.4
+Version: 0.0.5.dev2
 Summary: SHRECC: Smooth Hourly Resolution Electricity Consumption Calculation
 Author-email: Sabina Bednářová <sabina.bednarova@list.lu>
 Maintainer-email: Sabina Bednářová <sabina.bednarova@list.lu>

{shrecc-0.0.4 → shrecc-0.0.5.dev2}/tests/test_database.py

@@ -1,6 +1,8 @@
 import pytest
 import pandas as pd
+import bw2data as bd
 import numpy as np
+from packaging.version import parse as vparse
 from pytest import approx
 from unittest.mock import patch, MagicMock
 import types
@@ -913,11 +915,55 @@ def test_filter_by_times_no_matching_times():
     assert result.shape[1] == 0
 
 
+@pytest.mark.parametrize(
+    "times_input",
+    [
+        pytest.param(
+            ["2023-06-01 08:00:00", "2023-06-01 10:00:00"],
+            id="list_of_strings",
+        ),
+        pytest.param(
+            pd.to_datetime(["2023-06-01 08:00:00", "2023-06-01 10:00:00"]),
+            id="datetime_index",
+        ),
+    ],
+)
+def test_filter_by_times_accepts_strings_and_datetimeindex(times_input):
+    """filter_by_times should accept either a list of strings or a pd.DatetimeIndex
+    and produce the same filtered DataFrame, regardless of whether the columns'
+    `time` level is stored as strings or as datetime objects.
+    """
+    time_values = pd.to_datetime(
+        [
+            "2023-06-01 08:00:00",
+            "2023-06-01 09:00:00",
+            "2023-06-01 10:00:00",
+            "2023-06-01 11:00:00",
+        ]
+    )
+    countries = ["FR", "DE", "IT", "FR"]
+    columns = pd.MultiIndex.from_arrays(
+        [time_values, countries], names=["time", "country"]
+    )
+    index = pd.MultiIndex.from_tuples(
+        [("FR", "tech1", "electricity, high voltage", "kWh")],
+        names=["geography", "activityName", "prod", "unit"],
+    )
+    df = pd.DataFrame([[1, 2, 3, 4]], index=index, columns=columns)
+
+    result = filter_by_times(df, times_input)
+
+    expected_times = pd.to_datetime(["2023-06-01 08:00:00", "2023-06-01 10:00:00"])
+    assert isinstance(result, pd.DataFrame)
+    assert result.shape == (1, 2)
+    assert set(result.columns.get_level_values("time")) == set(expected_times)
+    assert list(result.values.flatten()) == [1, 3]
+
+
 # ────────────────────────────────────────────────────────────────
 # Tests for: filter_by_range() — requires multiple sub-tests
 # ────────────────────────────────────────────────────────────────
 def test_filter_by_range_basic():
-
     time_range = pd.date_range(
         start="2023-06-01 00:00:00", end="2023-08-31 23:00:00", freq="h"
     )
@@ -1185,7 +1231,6 @@ def dummy_dataframe_for_filt_cutoff():
 def test_filt_cutoff_filtering_by_times(
     mock_df_tech_mapping, dummy_dataframe_for_filt_cutoff
 ):
-
     df = dummy_dataframe_for_filt_cutoff
     mock_df_tech_mapping.return_value = df
 
@@ -1222,7 +1267,6 @@ def test_filt_cutoff_filtering_by_times(
 def test_filt_cutoff_filtering_by_range(
     mock_df_tech_mapping, dummy_dataframe_for_filt_cutoff
 ):
-
     df = dummy_dataframe_for_filt_cutoff
     mock_df_tech_mapping.return_value = df
 
@@ -1338,7 +1382,6 @@ def test_setup_database_handles_multiple_calls(monkeypatch):
 # Tests for: tech_mapping() — requires multiple sub-tests
 # ──────────────────────────────────────────────────────────
 def test_get_network_activities_basic():
-
     eidb_name = "ecoinvent-3.8-cutoff"
     result = get_network_activities(eidb_name)
     assert isinstance(result, list)
@@ -1377,7 +1420,6 @@ def test_get_network_activities_basic():
 
 
 def test_get_network_activities_311():
-
     eidb_name = "ecoinvent-3.11-cutoff"
     result = get_network_activities(eidb_name)
     assert isinstance(result, list)
@@ -1388,7 +1430,6 @@ def test_get_network_activities_311():
 
 
 def test_get_network_activities_other_versions():
-
     # Should not match "3.11" if not present
     for eidb_name in ["ecoinvent 3.7", "ei3.8.1", "eco3.9", ""]:
         result = get_network_activities(eidb_name)
@@ -1671,9 +1712,19 @@ def test_create_activity_dict_basic(
         (db_name, "electricity 1"),
     }
     # Check structure of activity dict
+    bd_version = bd.__version__
+    if not isinstance(bd_version, str):
+        bd_version = ".".join(map(str, bd_version))
+    BW2 = vparse(bd_version) < vparse("4")
+    if BW2:
+        act_type = "process"
+        prod_exchange_type = "production"
+    else:
+        act_type = bd.labels.process_node_default
+        prod_exchange_type = bd.labels.production_edge_default
     for act in activities.values():
         assert act["unit"] == "kWh"
-        assert act["type"] == "process"
+        assert act["type"] == act_type
         assert isinstance(act["exchanges"], list)
         # Should have at least one exchange (the technology)
         assert any(e["type"] == "technosphere" for e in act["exchanges"])
@@ -1686,7 +1737,9 @@ def test_create_activity_dict_basic(
     # Check that the correct technology exchange is present for each activity
     # act0 is for ("2023-06-01 08:00:00", "FR")
     act0 = activities[(db_name, "electricity 0")]
-    inputs0 = [e["input"] for e in act0["exchanges"]]
+    inputs0 = [
+        e["input"] for e in act0["exchanges"] if e["type"] != prod_exchange_type
+    ]
     assert set(inputs0) == {
         "fr_hydro_ei",
         "net_trans_subsea",
@@ -1703,7 +1756,7 @@ def test_create_activity_dict_basic(
     assert tech_ex1[0]["amount"] == 5.5  # specific network
     # act1 is for ("2023-06-01 09:00:00", "DE")
     act1 = activities[(db_name, "electricity 1")]
-    inputs1 = [e["input"] for e in act1["exchanges"]]
+    inputs1 = [e["input"] for e in act1["exchanges"] if e["type"] != prod_exchange_type]
     assert set(inputs1) == {"de_wind_ei", "net_dist_lv", "net_trans_mv"}
     assert "net_trans_subsea" not in inputs1
     assert "net_trans_ch" not in inputs1
@@ -1716,6 +1769,14 @@ def test_create_activity_dict_basic(
 def test_create_activity_dict_no_network_exchanges(
     mock_get_network_activities, sample_dataframe_filt, known_inputs_fixture
 ):
+    bd_version = bd.__version__
+    if not isinstance(bd_version, str):
+        bd_version = ".".join(map(str, bd_version))
+    BW2 = vparse(bd_version) < vparse("4")
+    if BW2:
+        prod_exchange_type = "production"
+    else:
+        prod_exchange_type = bd.labels.production_edge_default
     # No known_inputs_network, so only technology exchanges
     mock_get_network_activities.return_value = []
     db_name = "test_db"
@@ -1727,8 +1788,11 @@ def test_create_activity_dict_no_network_exchanges(
     )
     for act in activities.values():
         # Only technology exchanges should be present
+        technospere_exchanges = [
+            e for e in act["exchanges"] if e["type"] != prod_exchange_type
+        ]
         assert all(
-            e["input"] in known_inputs_fixture.values() for e in act["exchanges"]
+            e["input"] in known_inputs_fixture.values() for e in technospere_exchanges
         )