Fix some issues related to mapping.

conda/meta.yaml

@@ -20,7 +20,7 @@ requirements:
   run:
     - numpy
     - pandas
-    - bw2io==0.8.7
+    - bw2io >=0.8.7, != 0.8.8
     - bw2data
     - wurst
     - xarray

docs/extract.rst

@@ -112,7 +112,9 @@ indicate the database name in `source_db` and its version in `source_version`:
             ],
         source_db="ecoinvent 3.7 cutoff", # <-- this is NEW.
         source_version="3.7.1", # <-- this is NEW
-        key='xxxxxxxxxxxxxxxxxxxxxxxxx'
+        key='xxxxxxxxxxxxxxxxxxxxxxxxx',
+        use_multiprocessing=True, # True by default, set to False if multiprocessing is causing troubles
+        keep_uncertainty_data=False # False by default, set to True if you want to keep ecoinvent's uncertainty data
     )
 
 Note that a cache of the database will be created the first time and

docs/introduction.rst

@@ -74,9 +74,7 @@ Provided a decryption key (ask the maintainers_), the following IAM scenarios ar
 
 CarbonBrief_ wrote a good article explaining the meaning of the SSP/RCP system.
 
-Additionally, we provided a summary of the main characteristics of each scenario in a spreadsheet_.
-
-.. _spreadsheet: https://github.com/polca/premise/raw/master/docs/scenario_report_2023-05-02.xlsx
+Additionally, we provided a summary of the main characteristics of each scenario `here <https://premisedash-6f5a0259c487.herokuapp.com/>`_.
 
 
 .. _CarbonBrief: https://www.carbonbrief.org/explainer-how-shared-socioeconomic-pathways-explore-future-climate-change

docs/load.rst

@@ -162,9 +162,12 @@ This is done as follows:
     ndb.write_db_to_datapackage()
 
 This creates a zip file that contains the all the data necessary for
-other users to replicate teh databases, provided they have access
+other users to replicate the databases, provided they have access
 to the source database locally.
 
-See the library ``unfold`` for more information on data packages
-for sharing LCA databases.
+See the library <``unfold`` https://github.com/polca/unfold/tree/main>_ for more information on data packages
+for sharing LCA databases. ``unfold`` can read these data packages and create
+brightway2 databases (or superstructure databases) from them.
+``unfold`` can also fold premise databases registered in your brightway2 project
+into data packages, to be shared with and recreated by others.
 

examples/examples.ipynb

@@ -1030,7 +1030,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.12"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

premise/__init__.py

@@ -1,5 +1,5 @@
 __all__ = ("NewDatabase", "clear_cache", "get_regions_definition")
-__version__ = (1, 7, 0)
+__version__ = (1, 7, 1)
 
 from pathlib import Path
 

premise/activity_maps.py

@@ -3,6 +3,7 @@
 mapping between ``premise`` and ``ecoinvent`` terminology.
 """
 
+import sys
 from collections import defaultdict
 from pathlib import Path
 from typing import List, Union
@@ -23,11 +24,12 @@
 )
 
 
-def get_mapping(filepath: Path, var: str) -> dict:
+def get_mapping(filepath: Path, var: str, model: str = None) -> dict:
     """
     Loa a YAML file and return a dictionary given a variable.
     :param filepath: YAML file path
     :param var: variable to return the dictionary for.
+    :param model: if provided, only return the dictionary for this model.
     :return: a dictionary
     """
 
@@ -37,7 +39,11 @@ def get_mapping(filepath: Path, var: str) -> dict:
     mapping = {}
     for key, val in techs.items():
         if var in val:
-            mapping[key] = val[var]
+            if model is None:
+                mapping[key] = val[var]
+            else:
+                if model in val.get("iam_aliases", {}):
+                    mapping[key] = val[var]
 
     return mapping
 
@@ -114,12 +120,13 @@ class InventorySet:
     These functions return the result of applying :func:`act_fltr` to the filter dictionaries.
     """
 
-    def __init__(self, database: List[dict], version: str = None) -> None:
+    def __init__(self, database: List[dict], version: str = None, model: str = None) -> None:
         self.database = database
         self.version = version
+        self.model = model
 
         self.powerplant_filters = get_mapping(
-            filepath=POWERPLANT_TECHS, var="ecoinvent_aliases"
+            filepath=POWERPLANT_TECHS, var="ecoinvent_aliases", model=self.model
         )
 
         self.powerplant_fuels_filters = get_mapping(
@@ -253,4 +260,13 @@ def generate_sets_from_filters(self, filtr: dict, database=None) -> dict:
             tech: act_fltr(database, fltr.get("fltr"), fltr.get("mask"))
             for tech, fltr in filtr.items()
         }
-        return {tech: {act["name"] for act in actlst} for tech, actlst in techs.items()}
+
+        mapping = {tech: {act["name"] for act in actlst} for tech, actlst in techs.items()}
+
+        # check if all keys have values
+        # if not, print warning
+        for key, val in mapping.items():
+            if not val:
+                print(f"Warning: No activities found for {key} -- revise mapping.")
+
+        return mapping

premise/data/additional_inventories/migration_map.csv

@@ -616,4 +616,10 @@ from;to;name_from;ref_prod_from;location_from;name_to;ref_prod_to;location_to
 36;39;transmission network construction, electricity, high voltage;transmission network, long-distance;CH;transmission network construction, electricity, high voltage;transmission network, electricity, high voltage;CH
 37;39;transmission network construction, electricity, high voltage;transmission network, long-distance;CH;transmission network construction, electricity, high voltage;transmission network, electricity, high voltage;CH
 38;39;transmission network construction, electricity, high voltage;transmission network, long-distance;CH;transmission network construction, electricity, high voltage;transmission network, electricity, high voltage;CH
-39;38;market for battery cell, Li-ion, LFP;battery cell, Li-ion, LFP;GLO;market for battery cell, Li-ion;battery cell, Li-ion;GLO
+39;38;market for battery cell, Li-ion, LFP;battery cell, Li-ion, LFP;GLO;market for battery cell, Li-ion;battery cell, Li-ion;GLO
+39;37;market for battery cell, Li-ion, LFP;battery cell, Li-ion, LFP;GLO;market for battery cell, Li-ion;battery cell, Li-ion;GLO
+39;37;heat pump production, heat and power co-generation unit, 160kW electrical;heat pump, heat and power co-generation unit, 160kW electrical;RoW;heat pump production, for heat and power co-generation unit, 160kW electrical;heat pump, for heat and power co-generation unit, 160kW electrical;RoW
+39;37;heat pump production, heat and power co-generation unit, 160kW electrical;heat pump, heat and power co-generation unit, 160kW electrical;RER;heat pump production, for heat and power co-generation unit, 160kW electrical;heat pump, for heat and power co-generation unit, 160kW electrical;RER
+38;37;heat pump production, heat and power co-generation unit, 160kW electrical;heat pump, heat and power co-generation unit, 160kW electrical;RoW;heat pump production, for heat and power co-generation unit, 160kW electrical;heat pump, for heat and power co-generation unit, 160kW electrical;RoW
+38;37;heat pump production, heat and power co-generation unit, 160kW electrical;heat pump, heat and power co-generation unit, 160kW electrical;RER;heat pump production, for heat and power co-generation unit, 160kW electrical;heat pump, for heat and power co-generation unit, 160kW electrical;RER
+39;37;market for battery cell, Li-ion, NMC811;battery cell, Li-ion, NMC811;GLO;market for battery cell, Li-ion;battery cell, Li-ion;GLO

premise/data_collection.py

@@ -8,7 +8,7 @@
 import csv
 import os
 from functools import lru_cache
-from io import StringIO
+from io import BytesIO, StringIO
 from itertools import chain
 from pathlib import Path
 from typing import Dict, List, Union
@@ -717,6 +717,13 @@ def __get_iam_data(
 
         dataframe = dataframe.rename(columns={"variable": "variables"})
 
+        # make a list of headers that are integer
+
+        headers = [x for x in dataframe.columns if isinstance(x, int)]
+
+        # convert the values in these columns to numeric
+        dataframe[headers] = dataframe[headers].apply(pd.to_numeric, errors="coerce")
+
         array = (
             dataframe.melt(
                 id_vars=["region", "variables", "unit"],
@@ -1087,9 +1094,11 @@ def get_external_data(self, datapackages):
             data[i] = {}
 
             resource = dp.get_resource("scenario_data")
-            scenario_data = resource.read()
-            scenario_headers = resource.headers
-            df = pd.DataFrame(scenario_data, columns=scenario_headers)
+            # getting scenario data in binary format
+            scenario_data = resource.raw_read()
+            df = pd.read_csv(BytesIO(scenario_data), encoding="latin1")
+            # set headers from first row
+            df.columns = resource.headers
 
             resource = dp.get_resource("config")
             config_file = yaml.safe_load(resource.raw_read())