Merge remote-tracking branch 'origin/main' into major

# Conflicts:
#	activity_browser/actions/exchange/exchange_formula_remove.py
#	activity_browser/actions/exchange/exchange_modify.py
#	activity_browser/bwutils/montecarlo.py
#	activity_browser/layouts/panels/right.py
#	activity_browser/logger.py
#	activity_browser/ui/tables/models/activity.py
#	activity_browser/ui/web/navigator.py

Author: mrvisscher

activity_browser/actions/exchange/exchange_formula_remove.py

@@ -1,5 +1,7 @@
 from typing import Any, List
 
+from bw2data.parameters import ParameterizedExchange
+
 from activity_browser.actions.base import ABAction, exception_dialogs
 from activity_browser.ui.icons import qicons
 
@@ -16,9 +18,10 @@ class ExchangeFormulaRemove(ABAction):
     @exception_dialogs
     def run(exchanges: List[Any]):
         for exchange in exchanges:
-            try:
-                del exchange["formula"]
-                exchange.save()
-            except KeyError:
-                # formula not in the exchange
-                continue
+            if "formula" not in exchange:
+                return
+
+            del exchange["formula"]
+            exchange.save()
+
+            ParameterizedExchange.delete().where(ParameterizedExchange.exchange == exchange._document.id).execute()

activity_browser/actions/exchange/exchange_modify.py

@@ -10,6 +10,7 @@
 from activity_browser.ui.icons import qicons
 
 from ..parameter.parameter_new_automatic import ParameterNewAutomatic
+from .exchange_formula_remove import ExchangeFormulaRemove
 
 log = getLogger(__name__)
 
@@ -25,8 +26,14 @@ class ExchangeModify(ABAction):
     @classmethod
     @exception_dialogs
     def run(cls, exchange: ExchangeProxyBase, data: dict):
+        # remove the formula if it is an empty string
+        if "formula" in exchange and data.get("formula") == "":
+            del data["formula"]
+            ExchangeFormulaRemove.run([exchange])
+
         for key, value in data.items():
             exchange[key] = value
+
         exchange.save()
 
         if "formula" in data:

activity_browser/docs/wiki/LCA-Results.md

@@ -18,6 +18,9 @@ Activity Browser has three contribution analysis approaches available to assess
 `Elementary Flow (EF) Contributions`, `Process contributions` and `First Tier (FT) Contributions`.
 
 Before we discuss the different approaches, we introduce a small example for the production of _'steel'_:
+These approaches are extensively discussed independent of Activity Browser by 
+[van der Meide et al. (2025)](https://doi.org/10.31219/osf.io/sfgj6_v1) 
+if you want to learn more.
 
 ![steel production example](./assets/steel_production_example.svg)
 
@@ -33,7 +36,8 @@ The amounts we use are:
 <b>Note:</b> These numbers are used for ease of understanding, not for realism.
 </sup>
 
-To produce 1 kg of steel, we get a climate change impact of 1.6 kg CO2 eq with the _'IPCC 2021'_ impact category.
+To produce 1 kg of steel, we get a climate change impact of 1.6 kg CO<sub>2</sub> eq. with the 
+_'IPCC 2021 GWP 100'_ impact category.
 In the way Brightway (and thus Activity Browser) calculate results, a _contribution matrix_ is calculated with 
 all impacts _from_ all EFs and all activities. 
 For the system and functional unit above, this would be:
@@ -46,15 +50,15 @@ For the system and functional unit above, this would be:
 The _contribution matrix_ show the dis-aggregated results for each individual biosphere flow for each activity.
 
 #### Elementary Flow (EF) contributions
-If we take sum the _rows_ to one row, we get the EF contributions 
+If we take the sum the _rows_ to one column, we get the EF contributions 
 (the contribution of all CO<sub>2</sub> and CH<sub>4</sub> impacts together).
 
 In the case above, the EF contributions are:
 - CO<sub>2</sub>: 1.5404... (96.3%)
 - CH<sub>4</sub>: 0.0596... (3.7%)
 
 #### Process contributions
-If we take the sum of the _columns_ to one column, we get the process contributions
+If we take the sum of the _columns_ to one row, we get the process contributions
 (the contribution of all coal, electricity and steel production impacts together).
 
 In the case above, the process contributions are:
@@ -115,9 +119,19 @@ in the next sections.
 ![contributions cutoff](./assets/contribution_manipulation.png)
 
 #### Cut-off
-You can manually change the `Cut-off type` of the results in two ways, `Relative` or `Top #`.
-- The `Relative` mode shows contributions _from_ entities of _x_% or higher.
+You can manually change the `Cut-off type` of the results in three ways:
+- The `Minimum %` mode shows contributions _from_ entities of at least _x_% or higher.
+  - For example: If the cut-off is set to 5% for process contribtions, then all contributions of at least 5% are shown.  
+- The `Cumulative %` mode shows contributions that cumulatively contribute at least _x_%.
+  - For example: If the cut-off is set to 80% for process contributions, then the first _n_ processes (sorted highest 
+  to lowest) that count up to 80% are shown.
 - The `Top #` mode shows contributions from the _x_ entities that contribute the most (as absolute).
+  - For example: If the cut-off is set to 5, then the first 5 processes (sorted highest 
+  to lowest) will be shown.
+
+The cut-off is applied per item (e.g. per reference flow or impact category, see [compare](#compare)) below).
+This means that if you want to see the top 5 contributors, you will only see the top 5 per item, even if a contributor would 
+also be present for another item. 
 
 You can adjust the `Cut-off level` to change how many results you see.
 
@@ -147,22 +161,22 @@ You can disable one of them if you want to focus on the other.
 
 #### Relative and Absolute
 You can choose between `Relative` and `Absolute` results.
-The `Relative` results will sum to 100% (the total `Range` or `Score`), 
+The `Relative` results will sum to 100% (the total `Score` or `Range`), 
 the `Absolute` results will sum to the impact score.
-For `Relative`, you can choose what you use as the 100% reference, the `Range` or the `Score`.
+For `Relative`, you can choose what you use as the 100% reference, the `Score` or the `Range`.
 
-#### Range and Score
-The `Range`/`Score` determines what you use as the _total_ to which the contributions are counted. 
-- For `Range`, this is the full _range_ of results
-  - For example, if all your negative results together have a score of -2 and all your positive results together have a 
-    score of 10, the _range_ is 12 (-2 * -1 + 10).
-  - An entity with a contribution of 4 would have a relative contribution of 4/12 = 33.3...%. 
+#### Score and Range
+The `Score`/`Range` determines what you use as the _total_ to which the contributions are counted. 
 - For `Score`, this is the total score (sum) of the results
   - For example, if all your negative results together have a score of -2 and all your positive results together have a 
     score of 10, the _score_ is 8 (-2 + 10).
   - An entity with a contribution of 4 would have a relative contribution of 4/8 = 50%.
+- For `Range`, this is the full _range_ of results
+  - For example, if all your negative results together have a score of -2 and all your positive results together have a 
+    score of 10, the _range_ is 12 (-2 * -1 + 10).
+  - An entity with a contribution of 4 would have a relative contribution of 4/12 = 33.3...%. 
 
-The `Range` or `Score` setting are only relevant when your results contain both positive and negative contributions.
+The `Score` or `Range` setting are only relevant when your results contain both positive and negative contributions.
 
 ### Positive and negative numbers in contribution results
 It can happen in LCA that you get both positive and negative numbers in your contribution results.
@@ -179,9 +193,11 @@ Below is a simple example (with unrealistic values) to demonstrate this:
 ## Sankey
 The `Sankey` tab shows results from [graph traversal](https://docs.brightway.dev/projects/graphtools/en/latest/index.html).
 Graph traversal calculates results step-by-step for _nodes_ (activites) in the _graph_ (supply chain/product system).
+This is explained in detail by 
+[van der Meide et al. (2025)](https://doi.org/10.31219/osf.io/sfgj6_v1) (path contributions).
 
 ### Sankey configuration
-In the `Sankey` tab, you can configure, you can set the 
+In the `Sankey` tab, you can set the 
 Reference flow, Impact category and Scenario (only available in scenario LCA, see [scenarios](#scenarios)) to be shown.
 you can also set a `cutoff` and `calculation depth` setting.
 

activity_browser/docs/wiki/assets/ca_positive_negative_example.png

@@ -1539,7 +1539,10 @@ def data_to_df(self, all_data: List[list], compare: str) -> pd.DataFrame:
 
             all_data[i] = item, data, col_name
 
-        self.unit = get_unit(self.parent.method_dict[self.combobox_menu.method.currentText()], self.relative)
+        if compare == "Impact Categories":
+            self.unit = get_unit(method=False, relative=self.relative)
+        else:
+            self.unit = get_unit(self.parent.method_dict[self.combobox_menu.method.currentText()], self.relative)
 
         # convert to dict format to feed into dataframe
         for key in unique_keys:

activity_browser/docs/wiki/assets/contribution_manipulation.png

@@ -43,7 +43,7 @@ def __init__(self):
         log_file_location = self.filepath
 
         # create the logfile and write the headers
-        with open(self.filepath, "a", encoding="utf-8") as log_file:
+        with open(self.filepath, "a", encoding='utf-8') as log_file:
             log_file.write(";".join(self.headers) + "\n")
 
     def emit(self, record: logging.LogRecord):
@@ -52,7 +52,7 @@ def emit(self, record: logging.LogRecord):
         message = self.format(record)
 
         # append to the logfile
-        with open(self.filepath, "a", encoding="utf-8") as log_file:
+        with open(self.filepath, "a", encoding='utf-8') as log_file:
             log_file.write(message)
 
             # if there's exception info, write the exception traceback to the file as well
@@ -136,7 +136,7 @@ def emit(self, record: logging.LogRecord):
         message = self.format_log(record)
 
         # append to the logfile
-        with open(self.filepath, "a") as log_file:
+        with open(self.filepath, "a", encoding='utf-8') as log_file:
             log_file.write(message)
 
             # if there's exception info, write the exception traceback to the file as well

activity_browser/layouts/pages/lca_results/LCA_results.py

@@ -12,19 +12,22 @@ def sort_array(self, data: np.array, limit: float = 25, limit_type: str = "numbe
         See PR above on why we overwrite this function.
         """
         if not total:
-            abs_total_flag = True
             total = np.abs(data).sum()
-        else:
-            abs_total_flag = False
 
         if total == 0 and limit_type == "cum_percent":
-            raise ValueError("Cumulative percentage cannot be calculated to a total of 0, use a different limit type or total")
+            raise ValueError(
+                "Cumulative percentage cannot be calculated to a total of 0, use a different limit type or total")
 
         if limit_type not in ("number", "percent", "cum_percent"):
             raise ValueError(f"limit_type must be either 'number', 'percent' or 'cum_percent' not '{limit_type}'.")
-        if limit_type  in ("percent", "cum_percent"):
+        if limit_type in ("percent", "cum_percent"):
             if not 0 < limit <= 1:
                 raise ValueError("Percentage limits > 0 and <= 1.")
+        if limit_type == "number":
+            if not int(limit) == limit:
+                raise ValueError("Number limit must a whole number.")
+            if not 0 < limit:
+                raise ValueError("Number limit must be < 0.")
 
         results = np.hstack(
             (data.reshape((-1, 1)), np.arange(data.shape[0]).reshape((-1, 1)))
@@ -38,30 +41,10 @@ def sort_array(self, data: np.array, limit: float = 25, limit_type: str = "numbe
             limit = (np.abs(data) >= (abs(total) * limit))
             results = results[limit, :]
             return results[np.argsort(np.abs(results[:, 0]))[::-1]]
-        elif limit_type == "cum_percent" and abs_total_flag:
+        elif limit_type == "cum_percent":
             # if we would apply this on the 'correct' order, this would stop just before the limit,
             # we want to be on or the first step over the limit.
             results = results[np.argsort(np.abs(data))]  # sort low to high impact
             cumsum = np.cumsum(np.abs(results[:, 0])) / abs(total)
             limit = (cumsum >= (1 - limit))  # find items under limit
             return results[limit, :][::-1]  # drop items under limit and set correct order
-        elif limit_type == "cum_percent" and not abs_total_flag:
-            # iterate over positive and negative values until limit is achieved or surpassed.
-            results = results[np.argsort(np.abs(data))][::-1]
-            pos_neg = [  # split into positive and negative sections
-                results[results[:, 0] > 0],
-                results[results[:, 0] < 0],
-            ]
-            # iterate over positive and negative sections
-            for i, arr in enumerate(pos_neg):
-                c = 0
-                # iterate over array until we have equalled or surpassed limit
-                for j, row in enumerate(arr):
-                    c += abs(row[0] / total)
-                    if c >= limit:
-                        break
-                arr = arr[:min(j + 1, len(arr)), :]
-                pos_neg[i] = arr
-
-            results = np.concatenate(pos_neg)  # rebuild into 1 array
-            return results[np.argsort(np.abs(results[:, 0]))][::-1]  # sort values

activity_browser/logger.py

@@ -10,9 +10,10 @@
 from qtpy.QtCore import Slot
 
 from activity_browser import signals
-from bw2data import Database, get_activity
+from bw2data import Database, get_activity, databases, Edge
+from bw2data.backends import ExchangeDataset, ActivityDataset
 
-from ...bwutils.commontasks import identify_activity_type
+from ...bwutils.commontasks import identify_activity_type, get_activity_name
 from .base import BaseGraph, BaseNavigatorWidget
 
 log = getLogger(__name__)
@@ -60,6 +61,9 @@ class GraphNavigatorWidget(BaseNavigatorWidget):
 
     def __init__(self, parent=None, key=None):
         super().__init__(parent, css_file="navigator.css")
+        self.setObjectName(get_activity_name(get_activity(key), str_length=30))
+        self.key = key
+        self.tab = parent
 
         self.graph = Graph()
 
@@ -113,6 +117,17 @@ def connect_signals(self):
             self.update_graph_settings
         )
         self.checkbox_flip_negative_edges.stateChanged.connect(self.reload_graph)
+        databases.metadata_changed.connect(self.sync_graph)
+
+    def sync_graph(self):
+        """Sync the graph with the current project."""
+        self.graph.update(delete_unstacked=False)
+        self.send_json()
+        try:
+            self.setObjectName(get_activity_name(get_activity(self.key), str_length=30))
+        except ActivityDataset.DoesNotExist:
+            log.debug("Graph activity no longer exists. Closing tab.")
+            self.tab.close_tab_by_tab_name(self.tab.get_tab_name(self))
 
     def construct_layout(self) -> None:
         """Layout of Graph Navigator"""
@@ -251,9 +266,24 @@ def __init__(self):
         self.flip_negative_edges = False  # show true flow direction of edges (e.g. for ecoinvent treatment activities, or substitutions)
 
     def update(self, delete_unstacked: bool = True) -> None:
+        self.update_datasets()
         super().update(delete_unstacked)
         self.json_data = self.get_json_data()
 
+    def update_datasets(self):
+        """Update the activities in the graph."""
+        try:
+            self.nodes = [get_activity(act.key) for act in self.nodes]
+            self.edges = [Edge(document=ExchangeDataset.get_by_id(exc._document.id)) for exc in self.edges]
+        except (ActivityDataset.DoesNotExist, ExchangeDataset.DoesNotExist):
+            try:
+                get_activity(self.central_activity.key)  # test whether the activity still exists
+                self.new_graph(self.central_activity.key)  # if so, create a new graph
+            except ActivityDataset.DoesNotExist:
+                log.warning("Graph activity no longer exists.")
+                self.nodes = []
+                self.edges = []
+
     def store_previous(self) -> None:
         self.stack.append((deepcopy(self.nodes), deepcopy(self.edges)))